doc: change to diverse and inclusive language
Subsystems (3)
RFC 1/1 doc: change to diverse and inclusive language
For diversity reasons, the DPDK should take every effort to eliminate master and slave terminology. The actual code change is just syntax, but it has bigger impacts.
Lets announce this now and do it in the next API changing release.
--- doc/guides/rel_notes/deprecation.rst | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+)
doc/guides/rel_notes/deprecation.rst +27 -0
@@ -138,3 +138,30 @@ Deprecation Notices driver probe scheme. The legacy virtio support will be available through the existing VFIO/UIO based kernel driver scheme. More details at https://patches.dpdk.org/patch/69351/ + +* eal: To be more inclusive in choice of naming, the DPDK project + will follow established diversity guidelines. + The code base will be changed to replace references to sexist + and offensive terms used in function, documentation and variable + names. This change will be progressive across several releases. + + The immediate impact to the API/ABI is that references to + master and slave related to DPDK lcore will be changed to + primary and secondary. + + For example: ``rte_get_master_lcore()`` will be renamed + to ``rte_get_primary_lcore()``. For the 20.11, release + both names will be present and the old function will be + marked with the deprecated tag. + + The macros related to primary and secondary lcore will also + be change: ``RTE_LCORE_FOREACH_SLAVE`` will be replaced + with ``RTE_LCORE_FOREACH_SECONDARY``. + + Drivers and source not governed by API/ABI policy will change + as soon as practical. + + This change aligns DPDK with the MIT diversity guidelines: + https://www.cs.cmu.edu/~mjw/Language/NonSexist/vuw.non-sexist-language-guidelines.txt + and follows precedent of other open source projects: Django, Gnome, + ISC, Python, Rust
Signature · 1 line
2.26.2
RFC 1/1 replace master/slave with primary/secondary
I have a full patch that replaces the master/slave lcore naming (widely used in DPDK) with a better primary/secondary naming.
For now this is just a trial balloon to see what the impact would look like. The change mostly automated so likely that things are broken.
It is hard to break a change like this down, and still keep git bisection clean.
It keeps rte_master_lcore_id and RTE_FOREACH_SLAVE as deprecated items so that user code can still be built but they will be motivated to change.
Here is a sample of what it would look like:
lib/librte_eal/include/rte_launch.h +28 -28
@@ -32,12 +32,12 @@ typedef int (lcore_function_t)(void *);/** * Launch a function on another lcore. * -* To be executed on the MASTER lcore only. +* To be executed on the PRIMARY lcore only. * -* Sends a message to a slave lcore (identified by the slave_id) that +* Sends a message to a secondary lcore (identified by the id) that * is in the WAIT state (this is true after the first call to * rte_eal_init()). This can be checked by first calling -* rte_eal_wait_lcore(slave_id). +* rte_eal_wait_lcore(id). * * When the remote lcore receives the message, it switches to * the RUNNING state, then calls the function f with argument arg. Once the
@@ -45,7 +45,7 @@ typedef int (lcore_function_t)(void *);* the return value of f is stored in a local variable to be read using * rte_eal_wait_lcore(). * -* The MASTER lcore returns as soon as the message is sent and knows +* The PRIMARY lcore returns as soon as the message is sent and knows * nothing about the completion of f. * * Note: This function is not designed to offer optimum
@@ -56,37 +56,37 @@ typedef int (lcore_function_t)(void *);* The function to be called. * @param arg * The argument for the function. -* @param slave_id +* @param id * The identifier of the lcore on which the function should be executed. * @return * - 0: Success. Execution of function f started on the remote lcore. * - (-EBUSY): The remote lcore is not in a WAIT state. */ -int rte_eal_remote_launch (lcore_function_t *f,void *arg,unsigned slave_id); +int rte_eal_remote_launch (lcore_function_t *f,void *arg,unsigned id);/** -* This enum indicates whether the master core must execute the handler +* This enum indicates whether the primary core must execute the handler * launched on all logical cores. */ -enum rte_rmt_call_master_t { -SKIP_MASTER =0 ,/**< lcore handler not executed by master core. */ -CALL_MASTER ,/**< lcore handler executed by master core. */ +enum rte_rmt_call_primary_t { +SKIP_PRIMARY =0 ,/**< lcore handler not executed by primary core. */ +CALL_PRIMARY ,/**< lcore handler executed by primary core. */ };/** * Launch a function on all lcores. * -* Check that each SLAVE lcore is in a WAIT state, then call +* Check that each secondary lcore is in a WAIT state, then call * rte_eal_remote_launch() for each lcore. * * @param f * The function to be called. * @param arg * The argument for the function. -* @param call_master -* If call_master set to SKIP_MASTER, the MASTER lcore does not call -* the function. If call_master is set to CALL_MASTER, the function -* is also called on master before returning. In any case, the master +* @param call_primary +* If call_primary set to SKIP_PRIMARY, the PRIMARY lcore does not call +* the function. If call_primary is set to CALL_PRIMARY, the function +* is also called on primary before returning. In any case, the primary * lcore returns as soon as it finished its job and knows nothing * about the completion of f on the other lcores. * @return
@@ -95,49 +95,49 @@ enum rte_rmt_call_master_t {* case, no message is sent to any of the lcores. */ int rte_eal_mp_remote_launch (lcore_function_t *f,void *arg, -enum rte_rmt_call_master_t call_master); +enum rte_rmt_call_primary_t call_primary);/** -* Get the state of the lcore identified by slave_id. +* Get the state of the lcore identified by id. * -* To be executed on the MASTER lcore only. +* To be executed on the PRIMARY lcore only. * -* @param slave_id +* @param id * The identifier of the lcore. * @return * The state of the lcore. */ -enum rte_lcore_state_t rte_eal_get_lcore_state (unsigned slave_id); +enum rte_lcore_state_t rte_eal_get_lcore_state (unsigned id);/** * Wait until an lcore finishes its job. * -* To be executed on the MASTER lcore only. +* To be executed on the PRIMARY lcore only. * -* If the slave lcore identified by the slave_id is in a FINISHED state, +* If the lcore identified by the id is in a FINISHED state, * switch to the WAIT state. If the lcore is in RUNNING state, wait until * the lcore finishes its job and moves to the FINISHED state. * -* @param slave_id +* @param id * The identifier of the lcore. * @return -* - 0: If the lcore identified by the slave_id is in a WAIT state. +* - 0: If the lcore identified by the id is in a WAIT state. * - The value that was returned by the previous remote launch -* function call if the lcore identified by the slave_id was in a +* function call if the lcore identified by the id was in a * FINISHED or RUNNING state. In this case, it changes the state * of the lcore to WAIT. */ -int rte_eal_wait_lcore (unsigned slave_id); +int rte_eal_wait_lcore (unsigned id);/** * Wait until all lcores finish their jobs. * -* To be executed on the MASTER lcore only. Issue an +* To be executed on the PRIMARY lcore only. Issue an * rte_eal_wait_lcore() for every lcore. The return values are * ignored. * * After a call to rte_eal_mp_wait_lcore(), the caller can assume -* that all slave lcores are in a WAIT state. +* that all secondary lcores are in a WAIT state. */ void rte_eal_mp_wait_lcore (void );
lib/librte_eal/include/rte_lcore.h +24 -8
@@ -54,13 +54,21 @@ rte_lcore_id(void) }/** -* Get the id of the master lcore +* Get the id of the primary lcore * * @return -* the id of the master lcore +* the id of the primary lcore */ -unsigned int rte_get_master_lcore (void ); +unsigned int rte_get_primary_lcore (void ); +/** +* Deprecated API to get the id of the primary lcore +* +* @return +* the id of the primary lcore +*/ +unsigned int rte_get_master_lcore(void) __rte_deprecated; +/** * Return the number of execution units (lcores) on the system. *
@@ -179,15 +187,15 @@ int rte_lcore_is_enabled(unsigned int lcore_id);* * @param i * The current lcore (reference). -* @param skip_master -* If true, do not return the ID of the master lcore. +* @param skip_primary +* If true, do not return the ID of the primary lcore. * @param wrap * If true, go back to 0 when RTE_MAX_LCORE is reached; otherwise, * return RTE_MAX_LCORE. * @return * The next lcore_id or RTE_MAX_LCORE if not found. */ -unsigned int rte_get_next_lcore (unsigned int i,int skip_master,int wrap); +unsigned int rte_get_next_lcore (unsigned int i,int skip_primary,int wrap);/** * Macro to browse all running lcores.
@@ -198,13 +206,21 @@ unsigned int rte_get_next_lcore(unsigned int i, int skip_master, int wrap); i = rte_get_next_lcore(i, 0, 0))/** -* Macro to browse all running lcores except the master lcore. +* Macro to browse all running lcores except the primary lcore. */ -#define RTE_LCORE_FOREACH_SLAVE (i) \ +#define RTE_LCORE_FOREACH_SECONDARY (i) \ for (i = rte_get_next_lcore(-1, 1, 0); \ i<RTE_MAX_LCORE; \ i = rte_get_next_lcore(i, 1, 0)) +/** +* Backword compatiablity +*/ +#define RTE_LCORE_FOREACH_SLAVE (x) \ + _Pragma("GCC warning \"'RTE_LCORE_FOREACH_SLAVE' macro is deprecated\"") \ + RTE_LCORE_FOREACH_SECONDARY(x) + +/** * Set core affinity of the current thread. * Support both EAL and non-EAL thread and update TLS.
lib/librte_eal/linux/eal.c +8 -8
@@ -879,7 +879,7 @@ eal_check_mem_on_local_socket(void) {int socket_id; - socket_id =rte_lcore_to_socket_id (rte_config.master_lcore); + socket_id =rte_lcore_to_socket_id (rte_config.primary_lcore);if (rte_memseg_list_walk (check_socket, &socket_id) ==0 )RTE_LOG (WARNING ,EAL ,"WARNING: Master core has no memory on local socket!\n" );
@@ -1205,23 +1205,23 @@ rte_eal_init(int argc, char **argv)eal_check_mem_on_local_socket (); -eal_thread_init_master (rte_config.master_lcore); +eal_thread_init_primary (rte_config.primary_lcore); ret =eal_thread_dump_affinity (cpuset,sizeof (cpuset));RTE_LOG (DEBUG ,EAL ,"Master lcore %u is ready (tid=%zx;cpuset=[%s%s])\n" , - rte_config.master_lcore, (uintptr_t )thread_id, cpuset, + rte_config.primary_lcore, (uintptr_t )thread_id, cpuset, ret ==0 ?"" :"..." ); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_SECONDARY (i) {/* -* create communication pipes between master thread +* create communication pipes between primary thread * and children */ -if (pipe (lcore_config[i].pipe_master2slave) <0 ) +if (pipe (lcore_config[i].pipe_primary2secondary) <0 )rte_panic ("Cannot create pipe\n" ); -if (pipe (lcore_config[i].pipe_slave2master) <0 ) +if (pipe (lcore_config[i].pipe_secondary2primary) <0 )rte_panic ("Cannot create pipe\n" ); lcore_config[i].state =WAIT ;
@@ -1234,7 +1234,7 @@ rte_eal_init(int argc, char **argv)/* Set thread_name for aid in debugging. */ snprintf (thread_name,sizeof (thread_name), -"lcore-slave-%d" , i); +"lcore-secondary-%d" , i); ret =rte_thread_setname (lcore_config[i].thread_id, thread_name);if (ret !=0 )
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 7 lines · Stephen Hemminger
I have a full patch that replaces the master/slave lcore naming (widely used in DPDK) with a better primary/secondary naming.
For now this is just a trial balloon to see what the impact would look like. The change mostly automated so likely that things are broken.
Quoted 9 lines
It is hard to break a change like this down, and still keep git bisection clean.
It keeps
rte_master_lcore_idandRTE_FOREACH_SLAVEas deprecated items so that user code can still be built but they will be motivated to change.Here is a sample of what it would look like:
I think PRIMARY is a poor choice to describe the control thread. PRIMARY is often used to designate the active element currently doing the work. SECONDARY threads are also active threads doing equal dataplane work.
Another issue I see with primary / secondary is the ambiguity with multi-process in DPDK. Doc readers could get confused about where a primary / secondary thread is executed.
I think we could use instead DPDK-specific terminology. The lcore organization is a little specific, with an lcore that does most init work and spawns the others, but then runs the application like all others.
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Leader / worker?
Signature · 1 line
Gaëtan
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 27 lines · Stephen Hemminger
Quoted 7 lines
I have a full patch that replaces the master/slave lcore naming (widely used in DPDK) with a better primary/secondary naming.
For now this is just a trial balloon to see what the impact would look like. The change mostly automated so likely that things are broken.
Quoted 9 lines
It is hard to break a change like this down, and still keep git bisection clean.
It keeps
rte_master_lcore_idandRTE_FOREACH_SLAVEas deprecated items so that user code can still be built but they will be motivated to change.Here is a sample of what it would look like:
I think PRIMARY is a poor choice to describe the control thread. PRIMARY is often used to designate the active element currently doing the work. SECONDARY threads are also active threads doing equal dataplane work.
Another issue I see with primary / secondary is the ambiguity with multi-process in DPDK. Doc readers could get confused about where a primary / secondary thread is executed.
Quoted 9 lines
I think we could use instead DPDK-specific terminology. The lcore organization is a little specific, with an lcore that does most init work and spawns the others, but then runs the application like all others.
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Leader / worker?
I personally doubt such changes are needed at all.
Code churn will be massive for both DPDK itself and related user projects. With no real gain in return, from my perspective.
Konstantin
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 6 lines · Konstantin
Quoted 6 lines
organization is a little specific, with an lcore that does most init work and spawns the others, but then runs the application like all others.
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Quoted 8 lines
Quoted 2 lines
Leader / worker?
I personally doubt such changes are needed at all.
Code churn will be massive for both DPDK itself and related user projects. With no real gain in return, from my perspective.
Konstantin
Your concern is valid but the issue does need to be addressed. If now when? This is as a good a time as any to do it.
Increasing diversity and inclusion is an overarching goal of many organizations include my employer(Microsoft), the parent organization of DPDK(LF) and my values.
Following values is more important than minor replacement of text in API.
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 22 lines · Stephen Hemminger
Quoted 6 lines · Konstantin
Quoted 6 lines
organization is a little specific, with an lcore that does most init work and spawns the others, but then runs the application like all others.
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Quoted 8 lines
Quoted 2 lines
Leader / worker?
I personally doubt such changes are needed at all.
Code churn will be massive for both DPDK itself and related user projects. With no real gain in return, from my perspective.
Konstantin
Quoted 8 lines
Your concern is valid but the issue does need to be addressed. If now when? This is as a good a time as any to do it.
Increasing diversity and inclusion is an overarching goal of many organizations include my employer(Microsoft), the parent organization of DPDK(LF) and my values.
Following values is more important than minor replacement of text in API.
I feel like Konstantin is correct here.
If we were using these terms for humans or groups of humans, then I would agree they should be changed. We need to take into account the context of the reference to these words. I agree some words should never be used in any context, but these terms are very reasonable in the context of DPDK and networking.
If everyone wants to accept the code churn (and it will effect a large number of applications, plus back porting will be more difficult IMO), then we can do it.
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 20 lines · Keith
Quoted 20 lines
Quoted 4 lines
Quoted 4 lines
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Quoted 8 lines
Quoted 2 lines
Leader / worker?
I personally doubt such changes are needed at all.
Code churn will be massive for both DPDK itself and related user projects. With no real gain in return, from my perspective.
KonstantinYour concern is valid but the issue does need to be addressed. If now when? This is as a good a time as any to do it.
Increasing diversity and inclusion is an overarching goal of many organizations include my employer(Microsoft), the parent organization of DPDK(LF) and my values.
Quoted 5 lines
Quoted 1 line
Following values is more important than minor replacement of text in API.
I feel like Konstantin is correct here.
If we were using these terms for humans or groups of humans, then I would agree they should be changed. We need to take into account the context of the reference to these words. I agree some words should never be used in any context, but these terms are very reasonable in the context of DPDK and networking.
Have to disagree, the words matter. This has been discussed many times. Please look at the footnotes from the Gnome post
[0] - <https://www.cs.cmu.edu/~mjw/Language/NonSexist/vuw.non-sexist-language-guidelines.txt>, <https://twitter.com/justkelly_ok/status/933011085594066944>
[1] - <https://github.com/django/django/pull/2692>
[2] - <https://bugs.python.org/issue34605>
[3] - <https://github.com/rust-lang-deprecated/rust-buildbot/issues/2>, <https://github.com/rust-community/foss-events-planner/issues/58>
[4] - <https://twitter.com/ISCdotORG/status/942815837299253248>
[5] - <https://gitlab.gnome.org/GNOME/geary/issues/324>
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 39 lines · Stephen Hemminger
Quoted 20 lines · Keith
Quoted 20 lines
Quoted 4 lines
Quoted 4 lines
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Quoted 8 lines
Quoted 2 lines
Leader / worker?
I personally doubt such changes are needed at all.
Code churn will be massive for both DPDK itself and related user projects. With no real gain in return, from my perspective.
KonstantinYour concern is valid but the issue does need to be addressed. If now when? This is as a good a time as any to do it.
Increasing diversity and inclusion is an overarching goal of many organizations include my employer(Microsoft), the parent organization of DPDK(LF) and my values.
Quoted 5 lines
Quoted 1 line
Following values is more important than minor replacement of text in API.
I feel like Konstantin is correct here.
If we were using these terms for humans or groups of humans, then I would agree they should be changed. We need to take into account the context of the reference to these words. I agree some words should never be used in any context, but these terms are very reasonable in the context of DPDK and networking.
Have to disagree, the words matter. This has been discussed many times. Please look at the footnotes from the Gnome post
[0] - <https://www.cs.cmu.edu/~mjw/Language/NonSexist/vuw.non-sexist-language-guidelines.txt>, <https://twitter.com/justkelly_ok/status/933011085594066944>
Quoted 7 lines
[1] - <https://github.com/django/django/pull/2692>
[2] - <https://bugs.python.org/issue34605>[3] - <https://github.com/rust-lang-deprecated/rust-buildbot/issues/2>, <https://github.com/rust-community/foss-events-planner/issues/58>
[4] - <https://twitter.com/ISCdotORG/status/942815837299253248>
[5] - <https://gitlab.gnome.org/GNOME/geary/issues/324>
You chopped off my last sentence in your reply.
"If everyone wants to accept the code churn (and it will effect a large number of applications, plus back porting will be more difficult IMO), then we can do it."
So to be clear, I am not opposed to making this change, but wanted to point out the technical impacts of this change to DPDK as a whole.
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 42 lines · Keith
Quoted 42 lines · Stephen Hemminger
Quoted 20 lines · Keith
Quoted 20 lines
Quoted 4 lines
Quoted 4 lines
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Quoted 8 lines
Quoted 2 lines
Leader / worker?
I personally doubt such changes are needed at all.
Code churn will be massive for both DPDK itself and related user projects. With no real gain in return, from my perspective.
KonstantinYour concern is valid but the issue does need to be addressed. If now when? This is as a good a time as any to do it.
Increasing diversity and inclusion is an overarching goal of many organizations include my employer(Microsoft), the parent organization of DPDK(LF) and my values.
Quoted 5 lines
Quoted 1 line
Following values is more important than minor replacement of text in API.
I feel like Konstantin is correct here.
If we were using these terms for humans or groups of humans, then I would agree they should be changed. We need to take into account the context of the reference to these words. I agree some words should never be used in any context, but these terms are very reasonable in the context of DPDK and networking.
Have to disagree, the words matter. This has been discussed many times. Please look at the footnotes from the Gnome post
[0] - <https://www.cs.cmu.edu/~mjw/Language/NonSexist/vuw.non-sexist-language-guidelines.txt>, <https://twitter.com/justkelly_ok/status/933011085594066944>
[1] - <https://github.com/django/django/pull/2692>
[2] - <https://bugs.python.org/issue34605>[3] - <https://github.com/rust-lang-deprecated/rust-buildbot/issues/2>, <https://github.com/rust-community/foss-events-planner/issues/58>
Quoted 8 lines
Quoted 2 lines
[4] - <https://twitter.com/ISCdotORG/status/942815837299253248>
[5] - <https://gitlab.gnome.org/GNOME/geary/issues/324>You chopped off my last sentence in your reply.
"If everyone wants to accept the code churn (and it will effect a large number of applications, plus back porting will be more difficult IMO), then we can do it."
So to be clear, I am not opposed to making this change, but wanted to point out the technical impacts of this change to DPDK as a whole.
Thanks, my editing was not intended to be a way to stifling your response. How many applications try to support multiple DPDK major versions at once?
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 54 lines · Stephen Hemminger
Quoted 47 lines · Keith
Quoted 37 lines · Stephen Hemminger
Quoted 20 lines · Keith
Quoted 20 lines
Quoted 4 lines
Quoted 4 lines
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Quoted 8 lines
Quoted 2 lines
Leader / worker?
I personally doubt such changes are needed at all.
Code churn will be massive for both DPDK itself and related user projects. With no real gain in return, from my perspective.
KonstantinYour concern is valid but the issue does need to be addressed. If now when? This is as a good a time as any to do it.
Increasing diversity and inclusion is an overarching goal of many organizations include my employer(Microsoft), the parent organization of DPDK(LF) and my values.
Quoted 5 lines
Quoted 1 line
Following values is more important than minor replacement of text in API.
I feel like Konstantin is correct here.
If we were using these terms for humans or groups of humans, then I would agree they should be changed. We need to take into account the context of the reference to these words. I agree some words should never be used in any context, but these terms are very reasonable in the context of DPDK and networking.
Have to disagree, the words matter. This has been discussed many times. Please look at the footnotes from the Gnome post
[0] - <https://www.cs.cmu.edu/~mjw/Language/NonSexist/vuw.non-sexist-language-guidelines.txt>, <https://twitter.com/justkelly_ok/status/933011085594066944>
Quoted 7 lines
[1] - <https://github.com/django/django/pull/2692>
[2] - <https://bugs.python.org/issue34605>[3] - <https://github.com/rust-lang-deprecated/rust-buildbot/issues/2>, <https://github.com/rust-community/foss-events-planner/issues/58>
[4] - <https://twitter.com/ISCdotORG/status/942815837299253248>
[5] - <https://gitlab.gnome.org/GNOME/geary/issues/324>You chopped off my last sentence in your reply.
Quoted 8 lines
Quoted 3 lines
"If everyone wants to accept the code churn (and it will effect a large number of applications, plus back porting will be more difficult IMO), then we can do it."
So to be clear, I am not opposed to making this change, but wanted to point out the technical impacts of this change to DPDK as a whole.
Thanks, my editing was not intended to be a way to stifling your response. How many applications try to support multiple DPDK major versions at once?
NP, I understand it was not intended, but wanted to make sure it was not lost.
In Pktgen I try to support back to 18.11 release and some have asked for 18.04, one asked for 16.04 :-) I most likely do not do it very well, but I try given the limited time I have.
The big churn happened in 19.05 I think when all of the APIs and defines changed. It took me a few days to create a compat file to support backward compatibility .
I try to tell everyone I only support the latest release of DPDK and latest release of Pktgen, but that does not fly very well for some customers.
I would hope we can make this change and create methods to allow for supporting backward compatibility without every application having to create the compatibility support themselves.
Let me know how I can help,
Thanks
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
In reply to Gaëtan RivetQuoted 26 lines · Gaëtan Rivet
Quoted 7 lines · Stephen Hemminger
I have a full patch that replaces the master/slave lcore naming (widely used in DPDK) with a better primary/secondary naming.
For now this is just a trial balloon to see what the impact would look like. The change mostly automated so likely that things are broken.
Quoted 9 lines
It is hard to break a change like this down, and still keep git bisection clean.
It keeps
rte_master_lcore_idandRTE_FOREACH_SLAVEas deprecated items so that user code can still be built but they will be motivated to change.Here is a sample of what it would look like:
I think PRIMARY is a poor choice to describe the control thread. PRIMARY is often used to designate the active element currently doing the work. SECONDARY threads are also active threads doing equal dataplane work.
Another issue I see with primary / secondary is the ambiguity with multi-process in DPDK. Doc readers could get confused about where a primary / secondary thread is executed.
Quoted 9 lines
I think we could use instead DPDK-specific terminology. The lcore organization is a little specific, with an lcore that does most init work and spawns the others, but then runs the application like all others.
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Leader / worker?
No sure I like the term "Leader" for a thread, but "worker" is an ok name. How about "init thread" and "worker threads"?
/Bruce
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
Quoted 34 lines · Bruce Richardson
Quoted 33 lines · Gaëtan Rivet
Quoted 7 lines · Stephen Hemminger
I have a full patch that replaces the master/slave lcore naming (widely used in DPDK) with a better primary/secondary naming.
For now this is just a trial balloon to see what the impact would look like. The change mostly automated so likely that things are broken.
Quoted 9 lines
It is hard to break a change like this down, and still keep git bisection clean.
It keeps
rte_master_lcore_idandRTE_FOREACH_SLAVEas deprecated items so that user code can still be built but they will be motivated to change.Here is a sample of what it would look like:
I think PRIMARY is a poor choice to describe the control thread. PRIMARY is often used to designate the active element currently doing the work. SECONDARY threads are also active threads doing equal dataplane work.
Another issue I see with primary / secondary is the ambiguity with multi-process in DPDK. Doc readers could get confused about where a primary / secondary thread is executed.
I think we could use instead DPDK-specific terminology. The lcore organization is a little specific, with an lcore that does most init work and spawns the others, but then runs the application like all others.
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Quoted 6 lines
Quoted 2 lines
Leader / worker?
No sure I like the term "Leader" for a thread, but "worker" is an ok name. How about "init thread" and "worker threads"?
/Bruce
Init was actually my first idea :) . I thought leader could be more palatable in some documentation, but after some tests I think init thread could work better after all.
I was thinking init / spawned threads first, but worker is ok.
Signature · 1 line
Gaëtan
Re: [dpdk-dev] [RFC] replace master/slave with primary/secondary
In reply to Gaëtan RivetQuoted 26 lines · On Fri, 5 Jun 2020 12:43:00 +0200 Gaëtan Rivet <[email protected]> wrote:
Quoted 7 lines · Stephen Hemminger
I have a full patch that replaces the master/slave lcore naming (widely used in DPDK) with a better primary/secondary naming.
For now this is just a trial balloon to see what the impact would look like. The change mostly automated so likely that things are broken.
Quoted 9 lines
It is hard to break a change like this down, and still keep git bisection clean.
It keeps
rte_master_lcore_idandRTE_FOREACH_SLAVEas deprecated items so that user code can still be built but they will be motivated to change.Here is a sample of what it would look like:
I think PRIMARY is a poor choice to describe the control thread. PRIMARY is often used to designate the active element currently doing the work. SECONDARY threads are also active threads doing equal dataplane work.
Another issue I see with primary / secondary is the ambiguity with multi-process in DPDK. Doc readers could get confused about where a primary / secondary thread is executed.
Quoted 9 lines
I think we could use instead DPDK-specific terminology. The lcore organization is a little specific, with an lcore that does most init work and spawns the others, but then runs the application like all others.
I'd propose instead leader lcore - there is this idea that the leader is still a member of the team and will participate in the work.
Leader / worker?
Looking at Django the chose leader/follower.
Other alternatives are:
agency/operative
hive/drone
primary/handler
conductor/doer
captain/conscript
schemer/patsies
primary/replica
Quoted 35 lines · Stephen Hemminger
For diversity reasons, the DPDK should take every effort to eliminate master and slave terminology. The actual code change is just syntax, but it has bigger impacts.
Lets announce this now and do it in the next API changing release.
--- doc/guides/rel_notes/deprecation.rst | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+)doc/guides/rel_notes/deprecation.rst +17
-0@@ -138,3 +138,30 @@ Deprecation Notices driver probe scheme. The legacy virtio support will be available through the existing VFIO/UIO based kernel driver scheme. More details at https://patches.dpdk.org/patch/69351/ + +* eal: To be more inclusive in choice of naming, the DPDK project + will follow established diversity guidelines. + The code base will be changed to replace references to sexist + and offensive terms used in function, documentation and variable + names. This change will be progressive across several releases. + + The immediate impact to the API/ABI is that references to + master and slave related to DPDK lcore will be changed to + primary and secondary. + + For example: ``rte_get_master_lcore()`` will be renamed + to ``rte_get_primary_lcore()``. For the 20.11, release + both names will be present and the old function will be + marked with the deprecated tag. + + The macros related to primary and secondary lcore will also
doc/guides/rel_notes/deprecation.rst Deprecation Notices · line 167
Quoted 10 lines
doc/guides/rel_notes/deprecation.rst +10
-0+ be change: ``RTE_LCORE_FOREACH_SLAVE`` will be replaced + with ``RTE_LCORE_FOREACH_SECONDARY``. + + Drivers and source not governed by API/ABI policy will change + as soon as practical. + + This change aligns DPDK with the MIT diversity guidelines: + https://www.cs.cmu.edu/~mjw/Language/NonSexist/vuw.non-sexist-language-guidelines.txt + and follows precedent of other open source projects: Django, Gnome, + ISC, Python, Rust
Thanks for doing this!
Signature · 2 lines
Kind regards, Luca Boccassi
Bruce Richardson
Acked-byQuoted 40 lines · Luca Boccassi
Quoted 39 lines · Stephen Hemminger
For diversity reasons, the DPDK should take every effort to eliminate master and slave terminology. The actual code change is just syntax, but it has bigger impacts.
Lets announce this now and do it in the next API changing release.
--- doc/guides/rel_notes/deprecation.rst | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+)doc/guides/rel_notes/deprecation.rst +21
-0@@ -138,3 +138,30 @@ Deprecation Notices driver probe scheme. The legacy virtio support will be available through the existing VFIO/UIO based kernel driver scheme. More details at https://patches.dpdk.org/patch/69351/ + +* eal: To be more inclusive in choice of naming, the DPDK project + will follow established diversity guidelines. + The code base will be changed to replace references to sexist + and offensive terms used in function, documentation and variable + names. This change will be progressive across several releases. + + The immediate impact to the API/ABI is that references to + master and slave related to DPDK lcore will be changed to + primary and secondary. + + For example: ``rte_get_master_lcore()`` will be renamed + to ``rte_get_primary_lcore()``. For the 20.11, release + both names will be present and the old function will be + marked with the deprecated tag. + + The macros related to primary and secondary lcore will also + be change: ``RTE_LCORE_FOREACH_SLAVE`` will be replaced + with ``RTE_LCORE_FOREACH_SECONDARY``. + + Drivers and source not governed by API/ABI policy will change
Quoted 9 lines
doc/guides/rel_notes/deprecation.rst Deprecation Notices · line 167
Quoted 6 lines
doc/guides/rel_notes/deprecation.rst +6
-0+ as soon as practical. + + This change aligns DPDK with the MIT diversity guidelines: + https://www.cs.cmu.edu/~mjw/Language/NonSexist/vuw.non-sexist-language-guidelines.txt + and follows precedent of other open source projects: Django, Gnome, + ISC, Python, RustAcked-by Luca Boccassi <[email protected]>
Quoted 7 lines · Stephen Hemminger
For diversity reasons, the DPDK should take every effort to eliminate master and slave terminology. The actual code change is just syntax, but it has bigger impacts.
Lets announce this now and do it in the next API changing release.
---
Okay.
Usually, I am resistant to API/ABI changes - but actually in this case, I think we can do this even *now* without breaking the ABI (IIUC, we can use alias to keep around the old 'functions' - even structures shouldn't have any change). The API, we can carry over the existing stuff, and flag it in documentation as deprecated.
Quoted 38 lines
doc/guides/rel_notes/deprecation.rst | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+)doc/guides/rel_notes/deprecation.rst +27
-0@@ -138,3 +138,30 @@ Deprecation Notices driver probe scheme. The legacy virtio support will be available through the existing VFIO/UIO based kernel driver scheme. More details at https://patches.dpdk.org/patch/69351/ + +* eal: To be more inclusive in choice of naming, the DPDK project + will follow established diversity guidelines. + The code base will be changed to replace references to sexist + and offensive terms used in function, documentation and variable + names. This change will be progressive across several releases. + + The immediate impact to the API/ABI is that references to + master and slave related to DPDK lcore will be changed to + primary and secondary. + + For example: ``rte_get_master_lcore()`` will be renamed + to ``rte_get_primary_lcore()``. For the 20.11, release + both names will be present and the old function will be + marked with the deprecated tag. + + The macros related to primary and secondary lcore will also + be change: ``RTE_LCORE_FOREACH_SLAVE`` will be replaced + with ``RTE_LCORE_FOREACH_SECONDARY``. + + Drivers and source not governed by API/ABI policy will change + as soon as practical. + + This change aligns DPDK with the MIT diversity guidelines: + https://www.cs.cmu.edu/~mjw/Language/NonSexist/vuw.non-sexist-language-guidelines.txt + and follows precedent of other open source projects: Django, Gnome, + ISC, Python, Rust
v2 cover Change references to master/slave to
In reply to Stephen HemmingerThis set of patches changes the API and conventions around referring to DPDK lcores. The first patch changes rte_get_master_lcore_id and related calls. The rest fix the DPDK to use the new naming.
The last patch marks the old names as deprecated.
My preferred option would be to do the rest of the patches now, and hold the last one until 20.11
Buried in the documentation set are a couple of patches where we were using incorrect naming around primary/secondary process.
This will could/should be flagged as an API policy violation since new API is jumping the queue of EXPERIMENTAL. But we can vote on the exception.
Stephen Hemminger (26):
eal: rename terms used for DPDK lcores
kni: fix reference to master/slave process
bbdev: rename master to initial lcore
librte_power: change reference to rte_master_lcore
drivers: replace master/slave terminolgy examples/distrutor: rename master to initial examples/bond: replace references to master lcore examples/ethtool-app: replace references to slave with worker examples/ip_pipeline: replace references to master_lcore examples/qos_{meter/sched}: replace references to master lcore examples/l3fwd: replace references to master lcore examples/l2fwd: replace references to master lcore examples/multi_process: replace references to master lcore examples/performance-thread: replace reference to master lcore examples/ptpclient: replace references to master lcore examples/ipcsec-secgw: replace references to master lcore
examples: replace reference to master lcore app/test-pmd: change references to master/slave
test-eventdev: replace references to slave with worker lcores app/test: repalce refernces to master/slave
doc: fix incorrect reference to master process
doc: update references to master/slave lcore in samples
doc: replace master lcore terminology
app/pdump: replace references to master/slave lcore app/test-XXX: replace reference to master/slave
eal: mark old naming as deprecated
app/pdump/main.c | 2 +- app/test-acl/main.c | 2 +- app/test-bbdev/test_bbdev_perf.c | 16 +-- app/test-compress-perf/main.c | 8 +- app/test-crypto-perf/main.c | 14 +-- app/test-eventdev/evt_options.c | 2 +- app/test-eventdev/test_order_common.c | 12 +- app/test-eventdev/test_perf_common.c | 16 +-- app/test-eventdev/test_pipeline_common.c | 8 +- app/test-pipeline/main.c | 4 +- app/test-pmd/config.c | 4 +- app/test-pmd/parameters.c | 2 +- app/test-pmd/softnicfwd.c | 2 +- app/test-pmd/testpmd.c | 4 +- app/test-sad/main.c | 4 +- app/test/autotest_test_funcs.py | 2 +- app/test/test.c | 2 +- app/test/test_atomic.c | 26 ++--- app/test/test_barrier.c | 2 +- app/test/test_cryptodev.c | 16 +-- app/test/test_distributor.c | 8 +- app/test/test_distributor_perf.c | 10 +- app/test/test_eal_flags.c | 32 +++--- app/test/test_efd.c | 2 +- app/test/test_efd_perf.c | 2 +- app/test/test_func_reentrancy.c | 20 ++-- app/test/test_hash_multiwriter.c | 4 +- app/test/test_hash_readwrite.c | 38 +++---- app/test/test_kni.c | 16 +-- app/test/test_malloc.c | 12 +- app/test/test_mbuf.c | 36 +++--- app/test/test_mcslock.c | 28 ++--- app/test/test_mempool_perf.c | 10 +- app/test/test_mp_secondary.c | 2 +- app/test/test_pdump.c | 2 +- app/test/test_per_lcore.c | 14 +-- app/test/test_pmd_perf.c | 20 ++-- app/test/test_rcu_qsbr.c | 2 +- app/test/test_rcu_qsbr_perf.c | 2 +- app/test/test_ring_perf.c | 14 +-- app/test/test_ring_stress_impl.h | 10 +- app/test/test_rwlock.c | 28 ++--- app/test/test_service_cores.c | 10 +- app/test/test_spinlock.c | 34 +++--- app/test/test_stack.c | 2 +- app/test/test_stack_perf.c | 6 +- app/test/test_ticketlock.c | 36 +++--- app/test/test_timer.c | 106 +++++++++--------- app/test/test_timer_racecond.c | 27 ++--- app/test/test_timer_secondary.c | 2 +- app/test/test_trace_perf.c | 4 +- doc/guides/howto/debug_troubleshoot.rst | 2 +- doc/guides/linux_gsg/eal_args.include.rst | 4 +- doc/guides/nics/bnxt.rst | 2 +- .../thread_safety_dpdk_functions.rst | 4 +- doc/guides/sample_app_ug/hello_world.rst | 4 +- doc/guides/sample_app_ug/ioat.rst | 2 +- doc/guides/sample_app_ug/l3_forward_graph.rst | 6 +- doc/guides/sample_app_ug/multi_process.rst | 4 +- .../sample_app_ug/performance_thread.rst | 2 +- doc/guides/sample_app_ug/qos_scheduler.rst | 2 +- doc/guides/sample_app_ug/timer.rst | 6 +- drivers/bus/dpaa/dpaa_bus.c | 2 +- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 6 +- drivers/net/bnxt/bnxt_ring.c | 4 +- drivers/net/qede/base/bcm_osal.c | 4 +- drivers/net/softnic/rte_eth_softnic_thread.c | 4 +- examples/bbdev_app/main.c | 14 +-- examples/bond/main.c | 8 +- examples/distributor/main.c | 10 +- examples/ethtool/ethtool-app/main.c | 10 +- examples/eventdev_pipeline/main.c | 2 +- examples/flow_classify/flow_classify.c | 2 +- examples/helloworld/main.c | 6 +- examples/ioat/ioatfwd.c | 6 +- examples/ip_fragmentation/main.c | 4 +- examples/ip_pipeline/main.c | 2 +- examples/ip_pipeline/thread.c | 16 +-- examples/ip_reassembly/main.c | 4 +- examples/ipsec-secgw/event_helper.c | 6 +- examples/ipsec-secgw/ipsec-secgw.c | 4 +- examples/ipv4_multicast/main.c | 4 +- examples/kni/main.c | 7 +- examples/l2fwd-cat/l2fwd-cat.c | 2 +- examples/l2fwd-crypto/main.c | 8 +- examples/l2fwd-event/l2fwd_event_generic.c | 2 +- .../l2fwd-event/l2fwd_event_internal_port.c | 2 +- examples/l2fwd-event/l2fwd_poll.c | 2 +- examples/l2fwd-event/main.c | 2 +- examples/l2fwd-jobstats/main.c | 4 +- examples/l2fwd-keepalive/main.c | 6 +- examples/l2fwd/main.c | 8 +- examples/l3fwd-acl/main.c | 4 +- examples/l3fwd-graph/main.c | 14 +-- examples/l3fwd-power/main.c | 20 ++-- examples/l3fwd/main.c | 2 +- examples/link_status_interrupt/main.c | 8 +- .../client_server_mp/mp_server/main.c | 10 +- examples/multi_process/simple_mp/main.c | 6 +- examples/multi_process/symmetric_mp/main.c | 2 +- examples/ntb/ntb_fwd.c | 14 +-- examples/packet_ordering/main.c | 22 ++-- .../performance-thread/l3fwd-thread/main.c | 12 +- .../performance-thread/pthread_shim/main.c | 4 +- examples/ptpclient/ptpclient.c | 2 +- examples/qos_meter/main.c | 4 +- examples/qos_sched/args.c | 22 ++-- examples/qos_sched/cmdline.c | 2 +- examples/qos_sched/main.c | 2 +- examples/rxtx_callbacks/main.c | 2 +- examples/server_node_efd/server/main.c | 10 +- examples/skeleton/basicfwd.c | 2 +- examples/tep_termination/main.c | 12 +- examples/timer/main.c | 8 +- examples/vhost/main.c | 10 +- examples/vmdq/main.c | 4 +- examples/vmdq_dcb/main.c | 6 +- lib/librte_eal/common/eal_common_launch.c | 36 +++--- lib/librte_eal/common/eal_common_lcore.c | 11 +- lib/librte_eal/common/eal_common_options.c | 62 +++++----- lib/librte_eal/common/eal_options.h | 4 +- lib/librte_eal/common/eal_private.h | 6 +- lib/librte_eal/common/eal_thread.h | 6 +- lib/librte_eal/common/rte_random.c | 2 +- lib/librte_eal/common/rte_service.c | 2 +- lib/librte_eal/freebsd/eal.c | 24 ++-- lib/librte_eal/freebsd/eal_thread.c | 24 ++-- lib/librte_eal/include/rte_eal.h | 4 +- lib/librte_eal/include/rte_eal_trace.h | 4 +- lib/librte_eal/include/rte_launch.h | 62 +++++----- lib/librte_eal/include/rte_lcore.h | 31 +++-- lib/librte_eal/linux/eal.c | 24 ++-- lib/librte_eal/linux/eal_memory.c | 20 ++-- lib/librte_eal/linux/eal_thread.c | 24 ++-- lib/librte_eal/rte_eal_version.map | 1 + lib/librte_eal/windows/eal.c | 14 +-- lib/librte_eal/windows/eal_thread.c | 22 ++-- lib/librte_kni/rte_kni.h | 2 +- lib/librte_power/rte_power_empty_poll.c | 2 +- 139 files changed, 753 insertions(+), 724 deletions(-)
Signature · 1 line
2.26.2
RFC v2 1/26 eal: rename terms used for DPDK lcores
Replace the old use of master/slave lcore with more inclusive name of initial/secondary lcore. The old visible API will stay for now.
Change master2slave to new init2worker and vice-versa.
This patch breaks the expected practice for new API's. The new rte_get_initial_lcore() will not go through the standard experimental API phase; there is no functional difference from the previous name.
--- lib/librte_eal/common/eal_common_launch.c | 36 ++++++------- lib/librte_eal/common/eal_common_lcore.c | 11 ++-- lib/librte_eal/common/eal_common_options.c | 62 +++++++++++----------- lib/librte_eal/common/eal_options.h | 4 +- lib/librte_eal/common/eal_private.h | 6 +-- lib/librte_eal/common/eal_thread.h | 6 +-- lib/librte_eal/common/rte_random.c | 2 +- lib/librte_eal/common/rte_service.c | 2 +- lib/librte_eal/freebsd/eal.c | 24 ++++----- lib/librte_eal/freebsd/eal_thread.c | 24 ++++----- lib/librte_eal/include/rte_eal.h | 4 +- lib/librte_eal/include/rte_eal_trace.h | 4 +- lib/librte_eal/include/rte_launch.h | 62 ++++++++++++---------- lib/librte_eal/include/rte_lcore.h | 29 +++++++--- lib/librte_eal/linux/eal.c | 24 ++++----- lib/librte_eal/linux/eal_memory.c | 20 +++---- lib/librte_eal/linux/eal_thread.c | 24 ++++----- lib/librte_eal/rte_eal_version.map | 1 + lib/librte_eal/windows/eal.c | 14 ++--- lib/librte_eal/windows/eal_thread.c | 22 ++++---- 20 files changed, 204 insertions(+), 177 deletions(-)
lib/librte_eal/common/eal_common_launch.c +18 -18
@@ -21,55 +21,55 @@* Wait until a lcore finished its job. */ int -rte_eal_wait_lcore (unsigned slave_id) +rte_eal_wait_lcore (unsigned worker_id) { -if (lcore_config[slave_id].state ==WAIT ) +if (lcore_config[worker_id].state ==WAIT )return 0 ; -while (lcore_config[slave_id].state !=WAIT && - lcore_config[slave_id].state !=FINISHED ) +while (lcore_config[worker_id].state !=WAIT && + lcore_config[worker_id].state !=FINISHED )rte_pause ();rte_rmb ();/* we are in finished state, go to wait state */ - lcore_config[slave_id].state =WAIT ; -return lcore_config[slave_id].ret; + lcore_config[worker_id].state =WAIT ; +return lcore_config[worker_id].ret; }/* -* Check that every SLAVE lcores are in WAIT state, then call -* rte_eal_remote_launch() for all of them. If call_master is true -* (set to CALL_MASTER), also call the function on the master lcore. +* Check that every WORKER lcores are in WAIT state, then call +* rte_eal_remote_launch() for all of them. If call_initial is true +* (set to CALL_INITIAL), also call the function on the initial lcore. */ int rte_eal_mp_remote_launch (int (*f)(void *),void *arg, -enum rte_rmt_call_master_t call_master) +enum rte_rmt_call_initial_t call_initial) {int lcore_id; -int master =rte_get_master_lcore (); +int initial =rte_get_initial_lcore ();/* check state of lcores */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_config[lcore_id].state !=WAIT )return -EBUSY ; }/* send messages to cores */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (f, arg, lcore_id); } -if (call_master ==CALL_MASTER ) { - lcore_config[master].ret =f (arg); - lcore_config[master].state =FINISHED ; +if (call_initial ==CALL_INITIAL ) { + lcore_config[initial].ret =f (arg); + lcore_config[initial].state =FINISHED ; }return 0 ; }/* -* Return the state of the lcore identified by slave_id. +* Return the state of the lcore identified by worker_id. */ enum rte_lcore_state_t rte_eal_get_lcore_state (unsigned lcore_id)
@@ -86,7 +86,7 @@ rte_eal_mp_wait_lcore(void) {unsigned lcore_id; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_wait_lcore (lcore_id); } }
lib/librte_eal/common/eal_common_lcore.c +8 -3
@@ -16,9 +16,14 @@#include "eal_private.h" #include "eal_thread.h" +unsigned int rte_get_initial_lcore (void ) +{ +return rte_eal_get_configuration ()->initial_lcore; +} +unsigned int rte_get_master_lcore (void ) { -return rte_eal_get_configuration ()->master_lcore; +return rte_eal_get_configuration ()->initial_lcore; }unsigned int rte_lcore_count (void )
@@ -72,7 +77,7 @@ int rte_lcore_is_enabled(unsigned int lcore_id)return cfg->lcore_role[lcore_id] ==ROLE_RTE ; } -unsigned int rte_get_next_lcore (unsigned int i,int skip_master,int wrap) +unsigned int rte_get_next_lcore (unsigned int i,int skip_initial,int wrap) { i++;if (wrap)
@@ -80,7 +85,7 @@ unsigned int rte_get_next_lcore(unsigned int i, int skip_master, int wrap)while (i <RTE_MAX_LCORE ) {if (!rte_lcore_is_enabled (i) || - (skip_master && (i ==rte_get_master_lcore ()))) { + (skip_initial && (i ==rte_get_initial_lcore ()))) { i++;if (wrap) i %=RTE_MAX_LCORE ;
lib/librte_eal/common/eal_common_options.c +31 -31
140 lines not on this page · raw message
lib/librte_eal/common/eal_options.h +2 -2
@@ -43,8 +43,8 @@ enum {OPT_TRACE_BUF_SIZE_NUM , #define OPT_TRACE_MODE "trace-mode"OPT_TRACE_MODE_NUM , -#define OPT_MASTER_LCORE "master-lcore" -OPT_MASTER_LCORE_NUM , +#define OPT_INITIAL_LCORE "initial-lcore" +OPT_INITIAL_LCORE_NUM , #define OPT_MBUF_POOL_OPS_NAME "mbuf-pool-ops-name"OPT_MBUF_POOL_OPS_NAME_NUM , #define OPT_PROC_TYPE "proc-type"
lib/librte_eal/common/eal_private.h +3 -3
@@ -17,8 +17,8 @@*/ struct lcore_config {pthread_t thread_id;/**< pthread identifier */ -int pipe_master2slave[2 ];/**< communication pipe with master */ -int pipe_slave2master[2 ];/**< communication pipe with master */ +int pipe_init2worker[2 ];/**< communication pipe with initial core */ +int pipe_worker2init[2 ];/**< communication pipe with initial core */ lcore_function_t *volatile f;/**< function to call */ void *volatile arg;/**< argument of function */
@@ -39,7 +39,7 @@ extern struct lcore_config lcore_config[RTE_MAX_LCORE];* The global RTE configuration structure. */ struct rte_config { -uint32_t master_lcore;/**< Id of the master lcore */ +uint32_t initial_lcore;/**< Id of the initial lcore */ uint32_t lcore_count;/**< Number of available logical cores. */ uint32_t numa_node_count;/**< Number of detected NUMA nodes. */ uint32_t numa_nodes[RTE_MAX_NUMA_NODES ];/**< List of detected NUMA nodes. */
lib/librte_eal/common/eal_thread.h +3 -3
@@ -16,12 +16,12 @@ __rte_noreturn void *eal_thread_loop(void *arg);/** -* Init per-lcore info for master thread +* Init per-lcore info for initial thread * * @param lcore_id -* identifier of master lcore +* identifier of initial lcore */ -void eal_thread_init_master (unsigned lcore_id); +void eal_thread_set_initial_lcore (unsigned lcore_id);/** * Get the NUMA socket id from cpu id.
lib/librte_eal/common/rte_random.c +1 -1
@@ -122,7 +122,7 @@ struct rte_rand_state *__rte_rand_get_state(void) lcore_id =rte_lcore_id ();if (unlikely (lcore_id ==LCORE_ID_ANY )) - lcore_id =rte_get_master_lcore (); + lcore_id =rte_get_initial_lcore ();return &rand_states[lcore_id]; }
lib/librte_eal/common/rte_service.c +1 -1
@@ -106,7 +106,7 @@ rte_service_init(void)struct rte_config *cfg =rte_eal_get_configuration ();for (i =0 ; i <RTE_MAX_LCORE ; i++) {if (lcore_config[i].core_role ==ROLE_SERVICE ) { -if ((unsigned int )i == cfg->master_lcore) +if ((unsigned int )i == cfg->initial_lcore)continue ;rte_service_lcore_add (i); count++;
lib/librte_eal/freebsd/eal.c +12 -12
@@ -650,10 +650,10 @@ eal_check_mem_on_local_socket(void) {int socket_id; - socket_id =rte_lcore_to_socket_id (rte_config.master_lcore); + socket_id =rte_lcore_to_socket_id (rte_config.initial_lcore);if (rte_memseg_list_walk (check_socket, &socket_id) ==0 ) -RTE_LOG (WARNING ,EAL ,"WARNING: Master core has no memory on local socket!\n" ); +RTE_LOG (WARNING ,EAL ,"WARNING: Initial core has no memory on local socket!\n" ); }
@@ -877,23 +877,23 @@ rte_eal_init(int argc, char **argv)eal_check_mem_on_local_socket (); -eal_thread_init_master (rte_config.master_lcore); +eal_thread_set_initial_lcore (rte_config.initial_lcore); ret =eal_thread_dump_affinity (cpuset,sizeof (cpuset)); -RTE_LOG (DEBUG ,EAL ,"Master lcore %u is ready (tid=%p;cpuset=[%s%s])\n" , - rte_config.master_lcore, thread_id, cpuset, +RTE_LOG (DEBUG ,EAL ,"Initial lcore %u is ready (tid=%p;cpuset=[%s%s])\n" , + rte_config.initial_lcore, thread_id, cpuset, ret ==0 ?"" :"..." ); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {/* -* create communication pipes between master thread +* create communication pipes between initial thread * and children */ -if (pipe (lcore_config[i].pipe_master2slave) <0 ) +if (pipe (lcore_config[i].pipe_init2worker) <0 )rte_panic ("Cannot create pipe\n" ); -if (pipe (lcore_config[i].pipe_slave2master) <0 ) +if (pipe (lcore_config[i].pipe_worker2init) <0 )rte_panic ("Cannot create pipe\n" ); lcore_config[i].state =WAIT ;
@@ -906,15 +906,15 @@ rte_eal_init(int argc, char **argv)/* Set thread_name for aid in debugging. */ snprintf (thread_name,sizeof (thread_name), -"lcore-slave-%d" , i); +"lcore-work-%d" , i);rte_thread_setname (lcore_config[i].thread_id, thread_name); }/* -* Launch a dummy function on all slave lcores, so that master lcore +* Launch a dummy function on all worker lcores, so that initial lcore * knows they are all ready when this function returns. */ -rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_INITIAL );rte_eal_mp_wait_lcore ();/* initialize services so vdevs register service during bus_probe. */
lib/librte_eal/freebsd/eal_thread.c +12 -12
@@ -30,24 +30,24 @@ RTE_DEFINE_PER_LCORE(unsigned, _socket_id) = (unsigned)SOCKET_ID_ANY;RTE_DEFINE_PER_LCORE (rte_cpuset_t, _cpuset);/* -* Send a message to a slave lcore identified by slave_id to call a +* Send a message to a worker lcore identified by worker_id to call a * function f with argument arg. Once the execution is done, the * remote lcore switch in FINISHED state. */ int -rte_eal_remote_launch (int (*f)(void *),void *arg,unsigned slave_id) +rte_eal_remote_launch (int (*f)(void *),void *arg,unsigned worker_id) {int n;char c =0 ; -int m2s = lcore_config[slave_id].pipe_master2slave[1 ]; -int s2m = lcore_config[slave_id].pipe_slave2master[0 ]; +int m2s = lcore_config[worker_id].pipe_init2worker[1 ]; +int s2m = lcore_config[worker_id].pipe_worker2init[0 ];int rc = -EBUSY ; -if (lcore_config[slave_id].state !=WAIT ) +if (lcore_config[worker_id].state !=WAIT ) goto finish; - lcore_config[slave_id].f = f; - lcore_config[slave_id].arg = arg; + lcore_config[worker_id].f = f; + lcore_config[worker_id].arg = arg;/* send message */ n =0 ;
@@ -66,7 +66,7 @@ rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned slave_id) rc =0 ; finish: -rte_eal_trace_thread_remote_launch (f, arg, slave_id, rc); +rte_eal_trace_thread_remote_launch (f, arg, worker_id, rc);return rc; }
@@ -83,7 +83,7 @@ eal_thread_set_affinity(void)return rte_thread_set_affinity (&lcore_config[lcore_id].cpuset); } -void eal_thread_init_master (unsigned lcore_id) +void eal_thread_set_initial_lcore (unsigned lcore_id) {/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -107,15 +107,15 @@ eal_thread_loop(__rte_unused void *arg) thread_id =pthread_self ();/* retrieve our lcore_id from the configuration structure */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (thread_id == lcore_config[lcore_id].thread_id)break ; }if (lcore_id ==RTE_MAX_LCORE )rte_panic ("cannot retrieve lcore id\n" ); - m2s = lcore_config[lcore_id].pipe_master2slave[0 ]; - s2m = lcore_config[lcore_id].pipe_slave2master[1 ]; + m2s = lcore_config[lcore_id].pipe_init2worker[0 ]; + s2m = lcore_config[lcore_id].pipe_worker2init[1 ];/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
lib/librte_eal/include/rte_eal.h +2 -2
@@ -73,11 +73,11 @@ int rte_eal_iopl_init(void);/** * Initialize the Environment Abstraction Layer (EAL). * -* This function is to be executed on the MASTER lcore only, as soon +* This function is to be executed on the initial lcore only, as soon * as possible in the application's main() function. * * The function finishes the initialization process before main() is called. -* It puts the SLAVE lcores in the WAIT state. +* It puts the worker lcores in the WAIT state. * * When the multi-partition feature is supported, depending on the * configuration (if CONFIG_RTE_EAL_MAIN_PARTITION is disabled), this
lib/librte_eal/include/rte_eal_trace.h +2 -2
@@ -210,10 +210,10 @@ RTE_TRACE_POINT(RTE_TRACE_POINT ( rte_eal_trace_thread_remote_launch, RTE_TRACE_POINT_ARGS(int (*f)(void *), void *arg, - unsigned int slave_id, int rc), + unsigned int worker_id, int rc), rte_trace_point_emit_ptr(f);rte_trace_point_emit_ptr (arg); -rte_trace_point_emit_u32 (slave_id); +rte_trace_point_emit_u32 (worker_id);rte_trace_point_emit_int (rc); ) RTE_TRACE_POINT(
lib/librte_eal/include/rte_launch.h +34 -28
139 lines not on this page · raw message
lib/librte_eal/include/rte_lcore.h +22 -7
@@ -54,10 +54,18 @@ rte_lcore_id(void) }/** -* Get the id of the master lcore +* Get the id of the initial lcore * * @return -* the id of the master lcore +* the id of the initial lcore +*/ +unsigned int rte_get_initial_lcore (void ); + +/** +* Deprecated API to get the id of the initial lcore +* +* @return +* the id of the initial lcore */ unsigned int rte_get_master_lcore (void );
@@ -179,15 +187,15 @@ int rte_lcore_is_enabled(unsigned int lcore_id);* * @param i * The current lcore (reference). -* @param skip_master -* If true, do not return the ID of the master lcore. +* @param skip_initial +* If true, do not return the ID of the initial lcore. * @param wrap * If true, go back to 0 when RTE_MAX_LCORE is reached; otherwise, * return RTE_MAX_LCORE. * @return * The next lcore_id or RTE_MAX_LCORE if not found. */ -unsigned int rte_get_next_lcore (unsigned int i,int skip_master,int wrap); +unsigned int rte_get_next_lcore (unsigned int i,int skip_initial,int wrap);/** * Macro to browse all running lcores.
@@ -198,13 +206,20 @@ unsigned int rte_get_next_lcore(unsigned int i, int skip_master, int wrap); i = rte_get_next_lcore(i, 0, 0))/** -* Macro to browse all running lcores except the master lcore. +* Macro to browse all running lcores except the initial lcore. */ -#define RTE_LCORE_FOREACH_SLAVE (i) \ +#define RTE_LCORE_FOREACH_WORKER (i) \ for (i = rte_get_next_lcore(-1, 1, 0); \ i<RTE_MAX_LCORE; \ i = rte_get_next_lcore(i, 1, 0)) +/** +* Backward compatibility +*/ +#define RTE_LCORE_FOREACH_SLAVE (x) \ + RTE_LCORE_FOREACH_WORKER(x) + +/** * Set core affinity of the current thread. * Support both EAL and non-EAL thread and update TLS.
lib/librte_eal/linux/eal.c +12 -12
@@ -879,10 +879,10 @@ eal_check_mem_on_local_socket(void) {int socket_id; - socket_id =rte_lcore_to_socket_id (rte_config.master_lcore); + socket_id =rte_lcore_to_socket_id (rte_config.initial_lcore);if (rte_memseg_list_walk (check_socket, &socket_id) ==0 ) -RTE_LOG (WARNING ,EAL ,"WARNING: Master core has no memory on local socket!\n" ); +RTE_LOG (WARNING ,EAL ,"WARNING: Initial core has no memory on local socket!\n" ); } static int
@@ -1205,23 +1205,23 @@ rte_eal_init(int argc, char **argv)eal_check_mem_on_local_socket (); -eal_thread_init_master (rte_config.master_lcore); +eal_thread_set_initial_lcore (rte_config.initial_lcore); ret =eal_thread_dump_affinity (cpuset,sizeof (cpuset)); -RTE_LOG (DEBUG ,EAL ,"Master lcore %u is ready (tid=%zx;cpuset=[%s%s])\n" , - rte_config.master_lcore, (uintptr_t )thread_id, cpuset, +RTE_LOG (DEBUG ,EAL ,"Initial lcore %u is ready (tid=%zx;cpuset=[%s%s])\n" , + rte_config.initial_lcore, (uintptr_t )thread_id, cpuset, ret ==0 ?"" :"..." ); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {/* -* create communication pipes between master thread +* create communication pipes between initial thread * and children */ -if (pipe (lcore_config[i].pipe_master2slave) <0 ) +if (pipe (lcore_config[i].pipe_init2worker) <0 )rte_panic ("Cannot create pipe\n" ); -if (pipe (lcore_config[i].pipe_slave2master) <0 ) +if (pipe (lcore_config[i].pipe_worker2init) <0 )rte_panic ("Cannot create pipe\n" ); lcore_config[i].state =WAIT ;
@@ -1234,7 +1234,7 @@ rte_eal_init(int argc, char **argv)/* Set thread_name for aid in debugging. */ snprintf (thread_name,sizeof (thread_name), -"lcore-slave-%d" , i); +"lcore-work-%d" , i); ret =rte_thread_setname (lcore_config[i].thread_id, thread_name);if (ret !=0 )
@@ -1243,10 +1243,10 @@ rte_eal_init(int argc, char **argv) }/* -* Launch a dummy function on all slave lcores, so that master lcore +* Launch a dummy function on all worker lcores, so that initial lcore * knows they are all ready when this function returns. */ -rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_INITIAL );rte_eal_mp_wait_lcore ();/* initialize services so vdevs register service during bus_probe. */
lib/librte_eal/linux/eal_memory.c +10 -10
@@ -1168,19 +1168,19 @@ calc_num_pages_per_socket(uint64_t * memory, total_size -= default_size; }#else -/* in 32-bit mode, allocate all of the memory only on master +/* in 32-bit mode, allocate all of the memory only on initial * lcore socket */ total_size = internal_config.memory;for (socket =0 ; socket <RTE_MAX_NUMA_NODES && total_size !=0 ; socket++) {struct rte_config *cfg =rte_eal_get_configuration (); -unsigned int master_lcore_socket; +unsigned int initial_lcore_socket; - master_lcore_socket = -rte_lcore_to_socket_id (cfg->master_lcore); + initial_lcore_socket = +rte_lcore_to_socket_id (cfg->initial_lcore); -if (master_lcore_socket != socket) +if (initial_lcore_socket != socket)continue ;/* Update sizes */
@@ -2100,7 +2100,7 @@ memseg_primary_init_32(void)/* the allocation logic is a little bit convoluted, but here's how it * works, in a nutshell: * - if user hasn't specified on which sockets to allocate memory via -* --socket-mem, we allocate all of our memory on master core socket. +* --socket-mem, we allocate all of our memory on initial core socket. * - if user has specified sockets to allocate memory on, there may be * some "unused" memory left (e.g. if user has specified --socket-mem * such that not all memory adds up to 2 gigabytes), so add it to all
@@ -2114,7 +2114,7 @@ memseg_primary_init_32(void)for (i =0 ; i <rte_socket_count (); i++) {int hp_sizes = (int ) internal_config.num_hugepage_sizes;uint64_t max_socket_mem, cur_socket_mem; -unsigned int master_lcore_socket; +unsigned int initial_lcore_socket;struct rte_config *cfg =rte_eal_get_configuration ();bool skip;
@@ -2130,10 +2130,10 @@ memseg_primary_init_32(void) skip = active_sockets !=0 && internal_config.socket_mem[socket_id] ==0 ;/* ...or if we didn't specifically request memory on *any* -* socket, and this is not master lcore +* socket, and this is not initial lcore */ - master_lcore_socket =rte_lcore_to_socket_id (cfg->master_lcore); - skip |= active_sockets ==0 && socket_id != master_lcore_socket; + initial_lcore_socket =rte_lcore_to_socket_id (cfg->initial_lcore); + skip |= active_sockets ==0 && socket_id != initial_lcore_socket;if (skip) { RTE_LOG(DEBUG, EAL, "Will not preallocate memory on socket %u\n",
lib/librte_eal/linux/eal_thread.c +12 -12
@@ -30,24 +30,24 @@ RTE_DEFINE_PER_LCORE(unsigned, _socket_id) = (unsigned)SOCKET_ID_ANY;RTE_DEFINE_PER_LCORE (rte_cpuset_t, _cpuset);/* -* Send a message to a slave lcore identified by slave_id to call a +* Send a message to a worker lcore identified by worker_id to call a * function f with argument arg. Once the execution is done, the * remote lcore switch in FINISHED state. */ int -rte_eal_remote_launch (int (*f)(void *),void *arg,unsigned slave_id) +rte_eal_remote_launch (int (*f)(void *),void *arg,unsigned worker_id) {int n;char c =0 ; -int m2s = lcore_config[slave_id].pipe_master2slave[1 ]; -int s2m = lcore_config[slave_id].pipe_slave2master[0 ]; +int m2s = lcore_config[worker_id].pipe_init2worker[1 ]; +int s2m = lcore_config[worker_id].pipe_worker2init[0 ];int rc = -EBUSY ; -if (lcore_config[slave_id].state !=WAIT ) +if (lcore_config[worker_id].state !=WAIT ) goto finish; - lcore_config[slave_id].f = f; - lcore_config[slave_id].arg = arg; + lcore_config[worker_id].f = f; + lcore_config[worker_id].arg = arg;/* send message */ n =0 ;
@@ -66,7 +66,7 @@ rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned slave_id) rc =0 ; finish: -rte_eal_trace_thread_remote_launch (f, arg, slave_id, rc); +rte_eal_trace_thread_remote_launch (f, arg, worker_id, rc);return rc; }
@@ -83,7 +83,7 @@ eal_thread_set_affinity(void)return rte_thread_set_affinity (&lcore_config[lcore_id].cpuset); } -void eal_thread_init_master (unsigned lcore_id) +void eal_thread_set_initial_lcore (unsigned lcore_id) {/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -107,15 +107,15 @@ eal_thread_loop(__rte_unused void *arg) thread_id =pthread_self ();/* retrieve our lcore_id from the configuration structure */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (thread_id == lcore_config[lcore_id].thread_id)break ; }if (lcore_id ==RTE_MAX_LCORE )rte_panic ("cannot retrieve lcore id\n" ); - m2s = lcore_config[lcore_id].pipe_master2slave[0 ]; - s2m = lcore_config[lcore_id].pipe_slave2master[1 ]; + m2s = lcore_config[lcore_id].pipe_init2worker[0 ]; + s2m = lcore_config[lcore_id].pipe_worker2init[1 ];/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
lib/librte_eal/rte_eal_version.map +1 -0
@@ -79,6 +79,7 @@ DPDK_20.0 { rte_hexdump; rte_hypervisor_get; rte_hypervisor_get_name; + rte_init_lcore_id; rte_intr_allow_others; rte_intr_callback_register; rte_intr_callback_unregister;
lib/librte_eal/windows/eal.c +7 -7
@@ -244,18 +244,18 @@ rte_eal_init(int argc, char **argv)if (fctret <0 )exit (1 ); -eal_thread_init_master (rte_config.master_lcore); +eal_thread_set_initial_lcore (rte_config.initial_lcore); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {/* -* create communication pipes between master thread +* create communication pipes between initial thread * and children */ -if (_pipe (lcore_config[i].pipe_master2slave, +if (_pipe (lcore_config[i].pipe_init2worker,sizeof (char ), _O_BINARY) <0 )rte_panic ("Cannot create pipe\n" ); -if (_pipe (lcore_config[i].pipe_slave2master, +if (_pipe (lcore_config[i].pipe_worker2init,sizeof (char ), _O_BINARY) <0 )rte_panic ("Cannot create pipe\n" );
@@ -267,10 +267,10 @@ rte_eal_init(int argc, char **argv) }/* -* Launch a dummy function on all slave lcores, so that master lcore +* Launch a dummy function on all worker lcores, so that initial lcore * knows they are all ready when this function returns. */ -rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_INITIAL );rte_eal_mp_wait_lcore ();return fctret; }
lib/librte_eal/windows/eal_thread.c +11 -11
@@ -21,23 +21,23 @@ RTE_DEFINE_PER_LCORE(unsigned int, _socket_id) = (unsigned int)SOCKET_ID_ANY;RTE_DEFINE_PER_LCORE (rte_cpuset_t, _cpuset);/* -* Send a message to a slave lcore identified by slave_id to call a +* Send a message to a worker lcore identified by worker_id to call a * function f with argument arg. Once the execution is done, the * remote lcore switch in FINISHED state. */ int -rte_eal_remote_launch (lcore_function_t *f,void *arg,unsigned int slave_id) +rte_eal_remote_launch (lcore_function_t *f,void *arg,unsigned int worker_id) {int n;char c =0 ; -int m2s = lcore_config[slave_id].pipe_master2slave[1 ]; -int s2m = lcore_config[slave_id].pipe_slave2master[0 ]; +int m2s = lcore_config[worker_id].pipe_init2worker[1 ]; +int s2m = lcore_config[worker_id].pipe_worker2init[0 ]; -if (lcore_config[slave_id].state !=WAIT ) +if (lcore_config[worker_id].state !=WAIT )return -EBUSY ; - lcore_config[slave_id].f = f; - lcore_config[slave_id].arg = arg; + lcore_config[worker_id].f = f; + lcore_config[worker_id].arg = arg;/* send message */ n =0 ;
@@ -58,7 +58,7 @@ rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned int slave_id) }void -eal_thread_init_master (unsigned int lcore_id) +eal_thread_set_initial_lcore (unsigned int lcore_id) {/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -84,15 +84,15 @@ eal_thread_loop(void *arg __rte_unused) thread_id =eal_thread_self ();/* retrieve our lcore_id from the configuration structure */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (thread_id == lcore_config[lcore_id].thread_id)break ; }if (lcore_id ==RTE_MAX_LCORE )rte_panic ("cannot retrieve lcore id\n" ); - m2s = lcore_config[lcore_id].pipe_master2slave[0 ]; - s2m = lcore_config[lcore_id].pipe_slave2master[1 ]; + m2s = lcore_config[lcore_id].pipe_init2worker[0 ]; + s2m = lcore_config[lcore_id].pipe_worker2init[1 ];/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
Signature · 1 line
2.26.2
Re: [dpdk-dev] [RFC v2 01/26] eal: rename terms used for DPDK lcores
Quoted 6 lines · Stephen Hemminger
Replace the old use of master/slave lcore with more inclusive name of initial/secondary lcore. The old visible API will stay for now.
Change master2slave to new init2worker and vice-versa.
Quoted 7 lines
This patch breaks the expected practice for new API's. The new
rte_get_initial_lcore()will not go through the standard experimental API phase; there is no functional difference from the previous name.Signed-off-by Stephen Hemminger <[email protected]>---
This patch needs some rebasing as some of the memory functions have moved from eal_memory.c to eal_common_dynmem.c, and the windows code has been updated too.
Any further versions of this set can probably have the "RFC" label removed too, as the consensus very much seems to be in favour of this change - it's just a matter of getting the implementation in.
One further comment below.
/Bruce
Quoted 22 lines
lib/librte_eal/common/eal_common_launch.c | 36 ++++++------- lib/librte_eal/common/eal_common_lcore.c | 11 ++-- lib/librte_eal/common/eal_common_options.c | 62 +++++++++++----------- lib/librte_eal/common/eal_options.h | 4 +- lib/librte_eal/common/eal_private.h | 6 +-- lib/librte_eal/common/eal_thread.h | 6 +-- lib/librte_eal/common/rte_random.c | 2 +- lib/librte_eal/common/rte_service.c | 2 +- lib/librte_eal/freebsd/eal.c | 24 ++++----- lib/librte_eal/freebsd/eal_thread.c | 24 ++++----- lib/librte_eal/include/rte_eal.h | 4 +- lib/librte_eal/include/rte_eal_trace.h | 4 +- lib/librte_eal/include/rte_launch.h | 62 ++++++++++++---------- lib/librte_eal/include/rte_lcore.h | 29 +++++++--- lib/librte_eal/linux/eal.c | 24 ++++----- lib/librte_eal/linux/eal_memory.c | 20 +++---- lib/librte_eal/linux/eal_thread.c | 24 ++++----- lib/librte_eal/rte_eal_version.map | 1 + lib/librte_eal/windows/eal.c | 14 ++--- lib/librte_eal/windows/eal_thread.c | 22 ++++---- 20 files changed, 204 insertions(+), 177 deletions(-)
<snip>
lib/librte_eal/freebsd/eal_thread.c RTE_DEFINE_PER_LCORE(unsigned, _socket_id) = (unsigned)SOCKET_ID_ANY; · line 44
Quoted 12 lines
int
lib/librte_eal/freebsd/eal_thread.c +3
-3-rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned slave_id) +rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned worker_id) {int n;char c =0 ; -int m2s = lcore_config[slave_id].pipe_master2slave[1 ]; -int s2m = lcore_config[slave_id].pipe_slave2master[0 ]; +int m2s = lcore_config[worker_id].pipe_init2worker[1 ]; +int s2m = lcore_config[worker_id].pipe_worker2init[0 ];int rc = -EBUSY ;
For completeness sake, these variable names, which appear in multiple places should be renamed too, m2s -> i2w, s2m -> w2i.
RFC v2 2/26 kni: fix reference to master/slave process
In reply to Stephen HemmingerIn DPDK, the correct terms for process are primary/secondary. This is bugfix, not a change in terms for new release.
--- lib/librte_kni/rte_kni.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
lib/librte_kni/rte_kni.h +1 -1
@@ -212,7 +212,7 @@ const char *rte_kni_get_name(const struct rte_kni *kni);/** * Register KNI request handling for a specified port,and it can -* be called by master process or slave process. +* be called by primary process or secondary process. * * @param kni * pointer to struct rte_kni.
Signature · 1 line
2.26.2
RFC v2 3/26 bbdev: rename master to initial lcore
In reply to Stephen HemmingerConform to new API.
--- examples/bbdev_app/main.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)
examples/bbdev_app/main.c +7 -7
@@ -1040,7 +1040,7 @@ main(int argc, char **argv)struct stats_lcore_params stats_lcore;struct rte_ring *enc_to_dec_ring;bool stats_thread_started = false; -unsigned int master_lcore_id =rte_get_master_lcore (); +unsigned int initial_lcore_id =rte_get_initial_lcore ();rte_atomic16_init (&global_exit_flag);
@@ -1143,9 +1143,9 @@ main(int argc, char **argv) stats_lcore.app_params = &app_params; stats_lcore.lconf = lcore_conf; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_conf[lcore_id].core_type !=0 ) -/* launch per-lcore processing loop on slave lcores */ +/* launch per-lcore processing loop on worker lcores */ rte_eal_remote_launch (processing_loop, &lcore_conf[lcore_id], lcore_id);else if (!stats_thread_started) {
@@ -1157,15 +1157,15 @@ main(int argc, char **argv) }if (!stats_thread_started && - lcore_conf[master_lcore_id].core_type !=0 ) + lcore_conf[initial_lcore_id].core_type !=0 )rte_exit (EXIT_FAILURE ,"Not enough lcores to run the statistics printing loop!" ); -else if (lcore_conf[master_lcore_id].core_type !=0 ) -processing_loop (&lcore_conf[master_lcore_id]); +else if (lcore_conf[initial_lcore_id].core_type !=0 ) +processing_loop (&lcore_conf[initial_lcore_id]);else if (!stats_thread_started)stats_loop (&stats_lcore); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { ret |=rte_eal_wait_lcore (lcore_id); }
Signature · 1 line
2.26.2
RFC v2 4/26 librte_power: change reference to rte_master_lcore
In reply to Stephen HemmingerNew API name is rte_get_initial_lcore()
--- lib/librte_power/rte_power_empty_poll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
lib/librte_power/rte_power_empty_poll.c +1 -1
@@ -452,7 +452,7 @@ rte_power_empty_poll_stat_init(struct ep_params **eptr, uint8_t *freq_tlb,if (get_freq_index (LOW ) > total_avail_freqs[i])return -1 ; -if (rte_get_master_lcore () != i) { +if (rte_get_initial_lcore () != i) { w->wrk_stats[i].lcore_id = i;set_policy (&w->wrk_stats[i], policy); }
Signature · 1 line
2.26.2
RFC v2 5/26 drivers: replace master/slave terminolgy
In reply to Stephen HemmingerReplace rte_get_master_lcore() with rte_get_initial_lcore(). Replace RTE_LCORE_FOREACH_SLAVE with RTE_LCORE_FOREACH_WORKER
--- drivers/bus/dpaa/dpaa_bus.c | 2 +- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 6 +++--- drivers/net/bnxt/bnxt_ring.c | 4 ++-- drivers/net/qede/base/bcm_osal.c | 4 ++-- drivers/net/softnic/rte_eth_softnic_thread.c | 4 ++-- 5 files changed, 10 insertions(+), 10 deletions(-)
drivers/bus/dpaa/dpaa_bus.c +1 -1
@@ -260,7 +260,7 @@ int rte_dpaa_portal_init(void *arg)BUS_INIT_FUNC_TRACE ();if ((size_t )arg ==1 || lcore ==LCORE_ID_ANY ) - lcore =rte_get_master_lcore (); + lcore =rte_get_initial_lcore ();else if (lcore >=RTE_MAX_LCORE )return -1 ;
drivers/bus/fslmc/portal/dpaa2_hw_dpio.c +3 -3
@@ -195,7 +195,7 @@ dpaa2_configure_stashing(struct dpaa2_dpio_dev *dpio_dev, int lcoreid)/* Set the Stashing Destination */ if (lcoreid <0 ) { - lcoreid =rte_get_master_lcore (); + lcoreid =rte_get_initial_lcore ();if (lcoreid <0 ) {DPAA2_BUS_ERR ("Getting CPU Index failed" );return -1 ;
@@ -259,7 +259,7 @@ dpaa2_affine_qbman_swp(void)uint64_t tid =syscall (SYS_gettid);if (lcore_id ==LCORE_ID_ANY ) - lcore_id =rte_get_master_lcore (); + lcore_id =rte_get_initial_lcore ();/* if the core id is not supported */ else if (lcore_id >=RTE_MAX_LCORE )return -1 ;
@@ -307,7 +307,7 @@ dpaa2_affine_qbman_ethrx_swp(void)uint64_t tid =syscall (SYS_gettid);if (lcore_id ==LCORE_ID_ANY ) - lcore_id =rte_get_master_lcore (); + lcore_id =rte_get_initial_lcore ();/* if the core id is not supported */ else if (lcore_id >=RTE_MAX_LCORE )return -1 ;
drivers/net/bnxt/bnxt_ring.c +2 -2
@@ -429,7 +429,7 @@ int bnxt_alloc_rxtx_nq_ring(struct bnxt *bp)if (!BNXT_HAS_NQ (bp) || bp->rxtx_nq_ring)return 0 ; - socket_id =rte_lcore_to_socket_id (rte_get_master_lcore ()); + socket_id =rte_lcore_to_socket_id (rte_get_initial_lcore ()); nqr = rte_zmalloc_socket("nqr", sizeof(struct bnxt_cp_ring_info),
@@ -819,7 +819,7 @@ int bnxt_alloc_async_ring_struct(struct bnxt *bp)if (BNXT_NUM_ASYNC_CPR (bp) ==0 )return 0 ; - socket_id =rte_lcore_to_socket_id (rte_get_master_lcore ()); + socket_id =rte_lcore_to_socket_id (rte_get_initial_lcore ()); cpr = rte_zmalloc_socket("cpr", sizeof(struct bnxt_cp_ring_info),
drivers/net/qede/base/bcm_osal.c +2 -2
@@ -132,7 +132,7 @@ void *osal_dma_alloc_coherent(struct ecore_dev *p_dev,snprintf (mz_name,sizeof (mz_name),"%lx" , (unsigned long )rte_get_timer_cycles ());if (core_id == (unsigned int )LCORE_ID_ANY ) - core_id =rte_get_master_lcore (); + core_id =rte_get_initial_lcore (); socket_id =rte_lcore_to_socket_id (core_id); mz =rte_memzone_reserve_aligned (mz_name, size, socket_id,RTE_MEMZONE_IOVA_CONTIG ,RTE_CACHE_LINE_SIZE );
@@ -171,7 +171,7 @@ void *osal_dma_alloc_coherent_aligned(struct ecore_dev *p_dev,snprintf (mz_name,sizeof (mz_name),"%lx" , (unsigned long )rte_get_timer_cycles ());if (core_id == (unsigned int )LCORE_ID_ANY ) - core_id =rte_get_master_lcore (); + core_id =rte_get_initial_lcore (); socket_id =rte_lcore_to_socket_id (core_id); mz =rte_memzone_reserve_aligned (mz_name, size, socket_id,RTE_MEMZONE_IOVA_CONTIG , align);
drivers/net/softnic/rte_eth_softnic_thread.c +2 -2
@@ -25,7 +25,7 @@ softnic_thread_free(struct pmd_internals *softnic) {uint32_t i; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {struct softnic_thread *t = &softnic->thread[i];/* MSGQs */
@@ -99,7 +99,7 @@ softnic_thread_init(struct pmd_internals *softnic)static inline int thread_is_valid (struct pmd_internals *softnic,uint32_t thread_id) { -if (thread_id ==rte_get_master_lcore ()) +if (thread_id ==rte_get_initial_lcore ())return 0 ;/* FALSE */ if (softnic->params.sc &&rte_lcore_has_role (thread_id,ROLE_SERVICE ))
Signature · 1 line
2.26.2
RFC v2 6/26 examples/distrutor: rename master to initial
In reply to Stephen HemmingerConform to new API
--- examples/distributor/main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
examples/distributor/main.c +5 -5
@@ -612,7 +612,7 @@ static intinit_power_library (void) {int ret =0 , lcore_id; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {/* init power management library */ ret =rte_power_init (lcore_id);if (ret) {
@@ -808,7 +808,7 @@ main(int argc, char *argv[])* available, the higher frequency cores will go to the * distributor first, then rx, then tx. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_power_get_capabilities (lcore_id, &lcore_cap);
@@ -841,7 +841,7 @@ main(int argc, char *argv[])* after the high performing core assignment above, pre-assign * them here. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_id == (unsigned int )distr_core_id || lcore_id == (unsigned int )rx_core_id || lcore_id == (unsigned int )tx_core_id)
@@ -872,7 +872,7 @@ main(int argc, char *argv[])* Kick off all the worker threads first, avoiding the pre-assigned * lcore_ids for tx, rx and distributor workloads. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_id == (unsigned int )distr_core_id || lcore_id == (unsigned int )rx_core_id || lcore_id == (unsigned int )tx_core_id)
@@ -925,7 +925,7 @@ main(int argc, char *argv[])usleep (1000 ); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
Signature · 1 line
2.26.2
RFC v2 7/26 examples/bond: replace references to master lcore
In reply to Stephen HemmingerChange the references to master lcore.
For now, leave refernces to slave for bonding since that is part of the API not addressed yet.
--- examples/bond/main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
examples/bond/main.c +4 -4
@@ -590,7 +590,7 @@ static void cmd_start_parsed(__rte_unused void *parsed_result,return ; } -/* start lcore main on core != master_core - ARP response thread */ +/* start lcore main on core != initial_core - ARP response thread */ slave_core_id =rte_get_next_lcore (rte_lcore_id (),1 ,0 );if ((slave_core_id >=RTE_MAX_LCORE ) || (slave_core_id ==0 ))return ;
@@ -802,7 +802,7 @@ cmdline_parse_ctx_t main_ctx[] = { NULL, }; -/* prompt function, called from main on MASTER lcore */ +/* prompt function, called from main on initial lcore */ static void prompt(__rte_unused void *arg1) {struct cmdline *cl;
@@ -852,12 +852,12 @@ main(int argc, char *argv[])rte_spinlock_init (&global_flag_stru_p->lock);/* check state of lcores */ -RTE_LCORE_FOREACH_SLAVE (slave_core_id) { +RTE_LCORE_FOREACH_WORKER (slave_core_id) {if (rte_eal_get_lcore_state (slave_core_id) !=WAIT )return -EBUSY ; } -/* start lcore main on core != master_core - ARP response thread */ +/* start lcore main on core != initial_core - ARP response thread */ slave_core_id =rte_get_next_lcore (rte_lcore_id (),1 ,0 );if ((slave_core_id >=RTE_MAX_LCORE ) || (slave_core_id ==0 ))return -EPERM ;
Signature · 1 line
2.26.2
RFC v2 8/26 examples/ethtool-app: replace references to slave with worker
In reply to Stephen HemmingerConforms to new API naming conventions.
--- examples/ethtool/ethtool-app/main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
examples/ethtool/ethtool-app/main.c +5 -5
@@ -176,7 +176,7 @@ static void process_frame(struct app_port *ptr_port,rte_ether_addr_copy (&ptr_port->mac_addr, &ptr_mac_hdr->s_addr); } -static int slave_main(__rte_unused void *ptr_data) +static int worker_main(__rte_unused void *ptr_data) {struct app_port *ptr_port;struct rte_mbuf *ptr_frame;
@@ -284,16 +284,16 @@ int main(int argc, char **argv) app_cfg.cnt_ports = cnt_ports;if (rte_lcore_count () <2 ) -rte_exit (EXIT_FAILURE ,"No available slave core!\n" ); -/* Assume there is an available slave.. */ +rte_exit (EXIT_FAILURE ,"No available worker core!\n" ); +/* Assume there is an available worker.. */ id_core =rte_lcore_id (); id_core =rte_get_next_lcore (id_core,1 ,1 ); -rte_eal_remote_launch (slave_main,NULL , id_core); +rte_eal_remote_launch (worker_main,NULL , id_core);ethapp_main (); app_cfg.exit_now =1 ; -RTE_LCORE_FOREACH_SLAVE (id_core) { +RTE_LCORE_FOREACH_WORKER (id_core) {if (rte_eal_wait_lcore (id_core) <0 )return -1 ; }
Signature · 1 line
2.26.2
RFC v2 9/26 examples/ip_pipeline: replace references to master_lcore
In reply to Stephen HemmingerUse initial lcore instead of primary lcore
--- examples/ip_pipeline/main.c | 2 +- examples/ip_pipeline/thread.c | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-)
examples/ip_pipeline/main.c +1 -1
@@ -250,7 +250,7 @@ main(int argc, char **argv)rte_eal_mp_remote_launch ( thread_main,NULL , -SKIP_MASTER ); +SKIP_INITIAL );/* Script */ if (app.script_name)
examples/ip_pipeline/thread.c +8 -8
@@ -32,7 +32,7 @@#endif /** -* Master thead: data plane thread context +* Initial thread: data plane thread context */ struct thread {struct rte_ring *msgq_req;
@@ -78,7 +78,7 @@ struct thread_data {static struct thread_data thread_data[RTE_MAX_LCORE ];/** -* Master thread: data plane thread init +* Initial thread: data plane thread init */ static void thread_free (void )
@@ -105,7 +105,7 @@ thread_init(void) {uint32_t i; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {char name[NAME_MAX ];struct rte_ring *msgq_req, *msgq_rsp;struct thread *t = &thread[i];
@@ -137,7 +137,7 @@ thread_init(void)return -1 ; } -/* Master thread records */ +/* Initial thread records */ t->msgq_req = msgq_req; t->msgq_rsp = msgq_rsp; t->enabled =1 ;
@@ -179,7 +179,7 @@ pipeline_is_running(struct pipeline *p) }/** -* Master thread & data plane threads: message passing +* Initial thread & data plane threads: message passing */ enum thread_req_type {THREAD_REQ_PIPELINE_ENABLE =0 ,
@@ -213,7 +213,7 @@ struct thread_msg_rsp { };/** -* Master thread +* Initial thread */ static struct thread_msg_req *thread_msg_alloc (void )
@@ -556,7 +556,7 @@ thread_msg_handle(struct thread_data *t) }/** -* Master thread & data plane threads: message passing +* Initial thread & data plane threads: message passing */ enum pipeline_req_type {/* Port IN */
@@ -730,7 +730,7 @@ struct pipeline_msg_rsp { };/** -* Master thread +* Initial thread */ static struct pipeline_msg_req *pipeline_msg_alloc (void )
Signature · 1 line
2.26.2
RFC v2 10/26 examples/qos_{meter/sched}: replace references to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- examples/qos_meter/main.c | 4 ++-- examples/qos_sched/args.c | 22 +++++++++++----------- examples/qos_sched/cmdline.c | 2 +- examples/qos_sched/main.c | 2 +- 4 files changed, 15 insertions(+), 15 deletions(-)
examples/qos_meter/main.c +2 -2
@@ -457,8 +457,8 @@ main(int argc, char **argv)rte_exit (EXIT_FAILURE ,"Invalid configure flow table\n" );/* Launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/qos_sched/args.c +11 -11
@@ -22,7 +22,7 @@#define MAX_OPT_VALUES 8#define SYS_CPU_DIR "/sys/devices/system/cpu/cpu%u/topology/" -static uint32_t app_master_core =1 ; +static uint32_t app_initial_core =1 ;static uint32_t app_numa_mask;static uint64_t app_used_core_mask =0 ;static uint64_t app_used_port_mask =0 ;
@@ -40,7 +40,7 @@ static const char usage[] =" \n" "Application optional parameters: \n" " --i : run in interactive mode (default value is %u) \n" -" --mst I : master core index (default value is %u) \n" +" --mst I : initial core index (default value is %u) \n" " --rsz \"A, B, C\" : Ring sizes \n" " A = Size (in number of buffer descriptors) of each of the NIC RX \n" " rings read by the I/O RX lcores (default value is %u) \n"
@@ -72,7 +72,7 @@ static const char usage[] =static void app_usage (const char *prgname) { - printf(usage, prgname, APP_INTERACTIVE_DEFAULT, app_master_core, + printf(usage, prgname, APP_INTERACTIVE_DEFAULT, app_initial_core, APP_RX_DESC_DEFAULT, APP_RING_SIZE, APP_TX_DESC_DEFAULT, MAX_PKT_RX_BURST, PKT_ENQUEUE, PKT_DEQUEUE, MAX_PKT_TX_BURST, NB_MBUF,
@@ -98,7 +98,7 @@ app_eal_core_mask(void) cm |= (1ULL << i); } - cm |= (1ULL <<rte_get_master_lcore ()); + cm |= (1ULL <<rte_get_initial_lcore ());return cm; }
@@ -353,7 +353,7 @@ app_parse_args(int argc, char **argv)break ; }if (str_is (optname,"mst" )) { - app_master_core = (uint32_t )atoi (optarg); + app_initial_core = (uint32_t )atoi (optarg);break ; }if (str_is (optname,"rsz" )) {
@@ -408,18 +408,18 @@ app_parse_args(int argc, char **argv) } } -/* check master core index validity */ -for (i =0 ; i <= app_master_core; i++) { -if (app_used_core_mask & (1u << app_master_core)) { -RTE_LOG (ERR ,APP ,"Master core index is not configured properly\n" ); +/* check initial core index validity */ +for (i =0 ; i <= app_initial_core; i++) { +if (app_used_core_mask & (1u << app_initial_core)) { +RTE_LOG (ERR ,APP ,"Initial core index is not configured properly\n" );app_usage (prgname);return -1 ; } } - app_used_core_mask |=1u << app_master_core; + app_used_core_mask |=1u << app_initial_core;if ((app_used_core_mask !=app_eal_core_mask ()) || - (app_master_core !=rte_get_master_lcore ())) { + (app_initial_core !=rte_get_initial_lcore ())) {RTE_LOG (ERR ,APP ,"EAL core mask not configured properly, must be %" PRIx64" instead of %" PRIx64"\n" , app_used_core_mask,app_eal_core_mask ());return -1 ;
examples/qos_sched/cmdline.c +1 -1
@@ -599,7 +599,7 @@ cmdline_parse_ctx_t main_ctx[] = { NULL, }; -/* prompt function, called from main on MASTER lcore */ +/* prompt function, called from main on initial lcore */ void prompt (void ) {
examples/qos_sched/main.c +1 -1
@@ -204,7 +204,7 @@ main(int argc, char **argv)return -1 ;/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (app_main_loop,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (app_main_loop,NULL ,SKIP_INITIAL );if (interactive) {sleep (1 );
Signature · 1 line
2.26.2
RFC v2 11/26 examples/l3fwd: replace references to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- examples/l3fwd-acl/main.c | 4 ++-- examples/l3fwd-graph/main.c | 14 +++++++------- examples/l3fwd-power/main.c | 20 ++++++++++---------- examples/l3fwd/main.c | 2 +- 4 files changed, 20 insertions(+), 20 deletions(-)
examples/l3fwd-acl/main.c +2 -2
@@ -2110,8 +2110,8 @@ main(int argc, char **argv)check_all_ports_link_status (enabled_port_mask);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l3fwd-graph/main.c +7 -7
@@ -167,8 +167,8 @@ check_lcore_params(void)return -1 ; } -if (lcore ==rte_get_master_lcore ()) { -printf ("Error: lcore %u is master lcore\n" , lcore); +if (lcore ==rte_get_initial_lcore ()) { +printf ("Error: lcore %u is initial lcore\n" , lcore);return -1 ; } socketid =rte_lcore_to_socket_id (lcore);
@@ -1099,16 +1099,16 @@ main(int argc, char **argv) route_str, i); } -/* Launch per-lcore init on every slave lcore */ -rte_eal_mp_remote_launch (graph_main_loop,NULL ,SKIP_MASTER ); +/* Launch per-lcore init on every worker lcore */ +rte_eal_mp_remote_launch (graph_main_loop,NULL ,SKIP_INITIAL ); -/* Accumulate and print stats on master until exit */ +/* Accumulate and print stats on initial until exit */ if (rte_graph_has_stats_feature ())print_stats (); -/* Wait for slave cores to exit */ +/* Wait for worker cores to exit */ ret =0 ; - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + RTE_LCORE_FOREACH_WORKER(lcore_id) { ret = rte_eal_wait_lcore(lcore_id); /* Destroy graph */ if (ret < 0 || rte_graph_destroy(
examples/l3fwd-power/main.c +10 -10
@@ -1351,7 +1351,7 @@ check_lcore_params(void) "off\n", lcore, socketid); }if (app_mode ==APP_MODE_TELEMETRY && lcore ==rte_lcore_id ()) { -printf ("cannot enable master core %d in config for telemetry mode\n" , +printf ("cannot enable initial core %d in config for telemetry mode\n" ,rte_lcore_id ());return -1 ; }
@@ -2089,7 +2089,7 @@ get_current_stat_values(uint64_t *values)uint64_t app_eps =0 , app_fps =0 , app_br =0 ;uint64_t count =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { qconf = &lcore_conf[lcore_id];if (qconf->n_rx_queue ==0 )continue ;
@@ -2181,10 +2181,10 @@ launch_timer(unsigned int lcore_id)RTE_SET_USED (lcore_id); -if (rte_get_master_lcore () != lcore_id) { -rte_panic ("timer on lcore:%d which is not master core:%d\n" , +if (rte_get_initial_lcore () != lcore_id) { +rte_panic ("timer on lcore:%d which is not initial core:%d\n" , lcore_id, -rte_get_master_lcore ()); +rte_get_initial_lcore ()); }RTE_LOG (INFO ,POWER ,"Bring up the Timer\n" );
@@ -2515,11 +2515,11 @@ main(int argc, char **argv)/* launch per-lcore init on every lcore */ if (app_mode ==APP_MODE_LEGACY ) { -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); }else if (app_mode ==APP_MODE_EMPTY_POLL ) { empty_poll_stop = false;rte_eal_mp_remote_launch (main_empty_poll_loop,NULL , -SKIP_MASTER ); +SKIP_INITIAL ); }else {unsigned int i;
@@ -2535,7 +2535,7 @@ main(int argc, char **argv)else rte_exit (EXIT_FAILURE ,"failed to register metrics names" ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_spinlock_init (&stats[lcore_id].telemetry_lock); }rte_timer_init (&telemetry_timer);
@@ -2543,13 +2543,13 @@ main(int argc, char **argv) handle_app_stats, "Returns global power stats. Parameters: None");rte_eal_mp_remote_launch (main_telemetry_loop,NULL , -SKIP_MASTER ); +SKIP_INITIAL ); }if (app_mode ==APP_MODE_EMPTY_POLL || app_mode ==APP_MODE_TELEMETRY )launch_timer (rte_lcore_id ()); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l3fwd/main.c +1 -1
@@ -1278,7 +1278,7 @@ main(int argc, char **argv) ret =0 ;/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (l3fwd_lkp.main_loop,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (l3fwd_lkp.main_loop,NULL ,CALL_INITIAL );if (evt_rsrc->enabled) {for (i =0 ; i < evt_rsrc->rx_adptr.nb_rx_adptr; i++) rte_event_eth_rx_adapter_stop(
Signature · 1 line
2.26.2
RFC v2 12/26 examples/l2fwd: replace references to master lcore
In reply to Stephen HemmingerUse term initial lcore instead.
--- examples/l2fwd-cat/l2fwd-cat.c | 2 +- examples/l2fwd-crypto/main.c | 8 ++++---- examples/l2fwd-event/l2fwd_event_generic.c | 2 +- examples/l2fwd-event/l2fwd_event_internal_port.c | 2 +- examples/l2fwd-event/l2fwd_poll.c | 2 +- examples/l2fwd-event/main.c | 2 +- examples/l2fwd-jobstats/main.c | 4 ++-- examples/l2fwd-keepalive/main.c | 6 +++--- examples/l2fwd/main.c | 8 ++++---- 9 files changed, 18 insertions(+), 18 deletions(-)
examples/l2fwd-cat/l2fwd-cat.c +1 -1
@@ -198,7 +198,7 @@ main(int argc, char *argv[])if (rte_lcore_count () >1 )printf ("\nWARNING: Too many lcores enabled. Only 1 used.\n" ); -/* Call lcore_main on the master core only. */ +/* Call lcore_main on the initial core only. */ lcore_main ();return 0 ;
examples/l2fwd-crypto/main.c +4 -4
@@ -872,8 +872,8 @@ l2fwd_main_loop(struct l2fwd_crypto_options *options)if (unlikely (timer_tsc >= (uint64_t )timer_period)) { -/* do this only on master core */ -if (lcore_id ==rte_get_master_lcore () +/* do this only on initial core */ +if (lcore_id ==rte_get_initial_lcore () && options->refresh_period) {print_stats (); timer_tsc =0 ;
@@ -2800,8 +2800,8 @@ main(int argc, char **argv)/* launch per-lcore init on every lcore */ rte_eal_mp_remote_launch (l2fwd_launch_one_lcore, (void *)&options, -CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l2fwd-event/l2fwd_event_generic.c +1 -1
@@ -72,7 +72,7 @@ l2fwd_event_device_setup_generic(struct l2fwd_resources *rsrc) event_d_conf.nb_event_port_enqueue_depth = dev_info.max_event_port_enqueue_depth; -/* Ignore Master core and service cores. */ +/* Ignore initial core and service cores. */ num_workers =rte_lcore_count () -1 -rte_service_lcore_count ();if (dev_info.max_event_ports < num_workers) num_workers = dev_info.max_event_ports;
examples/l2fwd-event/l2fwd_event_internal_port.c +1 -1
@@ -71,7 +71,7 @@ l2fwd_event_device_setup_internal_port(struct l2fwd_resources *rsrc) event_d_conf.nb_event_port_enqueue_depth = dev_info.max_event_port_enqueue_depth; -/* Ignore Master core. */ +/* Ignore initial core. */ num_workers =rte_lcore_count () -1 ;if (dev_info.max_event_ports < num_workers) num_workers = dev_info.max_event_ports;
examples/l2fwd-event/l2fwd_poll.c +1 -1
@@ -116,7 +116,7 @@ l2fwd_poll_lcore_config(struct l2fwd_resources *rsrc)/* get the lcore_id for this port */ while (rte_lcore_is_enabled (rx_lcore_id) ==0 || - rx_lcore_id ==rte_get_master_lcore () || + rx_lcore_id ==rte_get_initial_lcore () || poll_rsrc->lcore_queue_conf[rx_lcore_id].n_rx_port == rsrc->rx_queue_per_lcore) { rx_lcore_id++;
examples/l2fwd-event/main.c +1 -1
@@ -671,7 +671,7 @@ main(int argc, char **argv)/* launch per-lcore init on every lcore */ rte_eal_mp_remote_launch (l2fwd_launch_one_lcore, rsrc, -SKIP_MASTER ); +SKIP_INITIAL );l2fwd_event_print_stats (rsrc);if (rsrc->event_mode) { struct l2fwd_event_resources *evt_rsrc =
examples/l2fwd-jobstats/main.c +2 -2
@@ -1019,8 +1019,8 @@ main(int argc, char **argv)RTE_LOG (INFO ,L2FWD ,"Stats display disabled\n" );/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (l2fwd_launch_one_lcore,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (l2fwd_launch_one_lcore,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l2fwd-keepalive/main.c +3 -3
@@ -790,8 +790,8 @@ main(int argc, char **argv) ) != 0 )rte_exit (EXIT_FAILURE ,"Stats setup failure.\n" ); } -/* launch per-lcore init on every slave lcore */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +/* launch per-lcore init on every worker lcore */ +RTE_LCORE_FOREACH_WORKER (lcore_id) {struct lcore_queue_conf *qconf = &lcore_queue_conf[lcore_id];if (qconf->n_rx_port ==0 )
@@ -814,7 +814,7 @@ main(int argc, char **argv)rte_delay_ms (5 ); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l2fwd/main.c +4 -4
@@ -248,8 +248,8 @@ l2fwd_main_loop(void)/* if timer has reached its timeout */ if (unlikely (timer_tsc >= timer_period)) { -/* do this only on master core */ -if (lcore_id ==rte_get_master_lcore ()) { +/* do this only on initial core */ +if (lcore_id ==rte_get_initial_lcore ()) {print_stats ();/* reset the timer */ timer_tsc =0 ;
@@ -754,8 +754,8 @@ main(int argc, char **argv) ret =0 ;/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (l2fwd_launch_one_lcore,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (l2fwd_launch_one_lcore,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 ) { ret =-1 ;break ;
Signature · 1 line
2.26.2
RFC v2 13/26 examples/multi_process: replace references to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- .../multi_process/client_server_mp/mp_server/main.c | 10 +++++----- examples/multi_process/simple_mp/main.c | 6 +++--- examples/multi_process/symmetric_mp/main.c | 2 +- 3 files changed, 9 insertions(+), 9 deletions(-)
examples/multi_process/client_server_mp/mp_server/main.c +5 -5
@@ -84,7 +84,7 @@ get_printable_mac_addr(uint16_t port)/* * This function displays the recorded statistics for each port * and for each client. It uses ANSI terminal codes to clear -* screen when called. It is called from a single non-master +* screen when called. It is called from a single worker * thread in the server process, when the process is run with more * than one lcore enabled. */
@@ -146,7 +146,7 @@ do_stats_display(void) }/* -* The function called from each non-master lcore used by the process. +* The function called from each worker lcore used by the process. * The test_and_set function is used to randomly pick a single lcore on which * the code to display the statistics will run. Otherwise, the code just * repeatedly sleeps.
@@ -244,7 +244,7 @@ process_packets(uint32_t port_num __rte_unused, }/* -* Function called by the master lcore of the DPDK process. +* Function called by the initial lcore of the DPDK process. */ static void do_packet_forwarding (void )
@@ -297,8 +297,8 @@ main(int argc, char *argv[])/* clear statistics */ clear_stats (); -/* put all other cores to sleep bar master */ -rte_eal_mp_remote_launch (sleep_lcore,NULL ,SKIP_MASTER ); +/* put all other cores to sleep execpt inital core */ +rte_eal_mp_remote_launch (sleep_lcore,NULL ,SKIP_INITIAL );do_packet_forwarding ();return 0 ;
examples/multi_process/simple_mp/main.c +3 -3
@@ -108,12 +108,12 @@ main(int argc, char **argv)RTE_LOG (INFO ,APP ,"Finished Process Init.\n" ); -/* call lcore_recv() on every slave lcore */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +/* call lcore_recv() on every worker lcore */ +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (lcore_recv,NULL , lcore_id); } -/* call cmd prompt on master lcore */ +/* call cmd prompt on initial lcore */ struct cmdline *cl =cmdline_stdin_new (simple_mp_ctx,"\nsimple_mp > " );if (cl ==NULL )rte_exit (EXIT_FAILURE ,"Cannot create cmdline instance\n" );
examples/multi_process/symmetric_mp/main.c +1 -1
@@ -473,7 +473,7 @@ main(int argc, char **argv)RTE_LOG (INFO ,APP ,"Finished Process Init.\n" ); -rte_eal_mp_remote_launch (lcore_main,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (lcore_main,NULL ,CALL_INITIAL );return 0 ; }
Signature · 1 line
2.26.2
RFC v2 14/26 examples/performance-thread: replace reference to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- examples/performance-thread/l3fwd-thread/main.c | 12 ++++++------ examples/performance-thread/pthread_shim/main.c | 4 ++-- 2 files changed, 8 insertions(+), 8 deletions(-)
examples/performance-thread/l3fwd-thread/main.c +6 -6
@@ -2211,7 +2211,7 @@ lthread_rx(void *dummy)/* * Start scheduler with initial lthread on lcore * -* This lthread loop spawns all rx and tx lthreads on master lcore +* This lthread loop spawns all rx and tx lthreads on intial lcore */ static void *
@@ -2265,7 +2265,7 @@ lthread_spawner(__rte_unused void *arg)* (main_lthread_master). */ static int -lthread_master_spawner(__rte_unused void *arg) { +lthread_initial_spawner(__rte_unused void *arg) {struct lthread *lt;int lcore_id =rte_lcore_id ();
@@ -3765,14 +3765,14 @@ main(int argc, char **argv)#endif lthread_num_schedulers_set (nb_lcores); -rte_eal_mp_remote_launch (sched_spawner,NULL ,SKIP_MASTER ); -lthread_master_spawner (NULL ); +rte_eal_mp_remote_launch (sched_spawner,NULL ,SKIP_INITIAL ); +lthread_initial_spawner (NULL ); }else {printf ("Starting P-Threading Model\n" );/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (pthread_run,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (pthread_run,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/performance-thread/pthread_shim/main.c +2 -2
@@ -252,10 +252,10 @@ int main(int argc, char **argv)lthread_num_schedulers_set (num_sched);/* launch all threads */ -rte_eal_mp_remote_launch (lthread_scheduler, (void *)NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (lthread_scheduler, (void *)NULL ,CALL_INITIAL );/* wait for threads to stop */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_wait_lcore (lcore_id); }return 0 ;
Signature · 1 line
2.26.2
RFC v2 15/26 examples/ptpclient: replace references to master lcore
In reply to Stephen HemmingerReplace master lcore with initial lcore.
This API still has issue with use of term master clock.
--- examples/ptpclient/ptpclient.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
examples/ptpclient/ptpclient.c +1 -1
@@ -785,7 +785,7 @@ main(int argc, char *argv[])if (rte_lcore_count () >1 )printf ("\nWARNING: Too many lcores enabled. Only 1 used.\n" ); -/* Call lcore_main on the master core only. */ +/* Call lcore_main on the initial core only. */ lcore_main ();return 0 ;
Signature · 1 line
2.26.2
RFC v2 16/26 examples/ipcsec-secgw: replace references to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- examples/ipsec-secgw/event_helper.c | 6 +++--- examples/ipsec-secgw/ipsec-secgw.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-)
examples/ipsec-secgw/event_helper.c +3 -3
@@ -1461,16 +1461,16 @@ eh_conf_init(void)/* Set two cores as eth cores for Rx & Tx */ -/* Use first core other than master core as Rx core */ +/* Use first core other than initial core as Rx core */ eth_core_id =rte_get_next_lcore (0 ,/* curr core */ -1 ,/* skip master core */ +1 ,/* skip initial core */ 0 /* wrap */ );rte_bitmap_set (em_conf->eth_core_mask, eth_core_id);/* Use next core as Tx core */ eth_core_id =rte_get_next_lcore (eth_core_id,/* curr core */ -1 ,/* skip master core */ +1 ,/* skip initial core */ 0 /* wrap */ );rte_bitmap_set (em_conf->eth_core_mask, eth_core_id);
examples/ipsec-secgw/ipsec-secgw.c +2 -2
@@ -2917,8 +2917,8 @@ main(int32_t argc, char **argv)check_all_ports_link_status (enabled_port_mask);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (ipsec_launch_one_lcore, eh_conf,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (ipsec_launch_one_lcore, eh_conf,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
Signature · 1 line
2.26.2
RFC v2 17/26 examples: replace reference to master lcore
In reply to Stephen HemmingerSmall changes in several examples to replace master_lcore with initial_lcore across multiple small examples.
--- examples/eventdev_pipeline/main.c | 2 +- examples/flow_classify/flow_classify.c | 2 +- examples/helloworld/main.c | 6 +++--- examples/ioat/ioatfwd.c | 6 +++--- examples/ip_fragmentation/main.c | 4 ++-- examples/ip_reassembly/main.c | 4 ++-- examples/ipv4_multicast/main.c | 4 ++-- examples/kni/main.c | 7 +++---- examples/link_status_interrupt/main.c | 8 ++++---- examples/ntb/ntb_fwd.c | 14 +++++++------- examples/packet_ordering/main.c | 22 +++++++++++----------- examples/rxtx_callbacks/main.c | 2 +- examples/server_node_efd/server/main.c | 10 +++++----- examples/skeleton/basicfwd.c | 2 +- examples/tep_termination/main.c | 12 ++++++------ examples/timer/main.c | 8 ++++---- examples/vhost/main.c | 10 +++++----- examples/vmdq/main.c | 4 ++-- examples/vmdq_dcb/main.c | 6 +++--- 19 files changed, 66 insertions(+), 67 deletions(-)
examples/eventdev_pipeline/main.c +1 -1
@@ -395,7 +395,7 @@ main(int argc, char **argv) }int worker_idx =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_id >=MAX_NUM_CORE )break ;
examples/flow_classify/flow_classify.c +1 -1
@@ -850,7 +850,7 @@ main(int argc, char *argv[])rte_exit (EXIT_FAILURE ,"Failed to add rules\n" ); } -/* Call lcore_main on the master core only. */ +/* Call lcore_main on the initial core only. */ lcore_main (cls_app);return 0 ;
examples/helloworld/main.c +3 -3
@@ -34,12 +34,12 @@ main(int argc, char **argv)if (ret <0 )rte_panic ("Cannot init EAL\n" ); -/* call lcore_hello() on every slave lcore */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +/* call lcore_hello() on every worker lcore */ +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (lcore_hello,NULL , lcore_id); } -/* call it on master lcore too */ +/* call it on initial lcore too */ lcore_hello (NULL );rte_eal_mp_wait_lcore ();
examples/ioat/ioatfwd.c +3 -3
@@ -518,7 +518,7 @@ tx_main_loop(void)ioat_tx_port (&cfg.ports[i]); } -/* Main rx and tx loop if only one slave lcore available */ +/* Main rx and tx loop if only one worker lcore available */ static void rxtx_main_loop (void ) {
@@ -982,7 +982,7 @@ main(int argc, char **argv) cfg.nb_lcores =rte_lcore_count () -1 ;if (cfg.nb_lcores <1 )rte_exit (EXIT_FAILURE , -"There should be at least one slave lcore.\n" ); +"There should be at least one worker lcore.\n" );if (copy_mode ==COPY_MODE_IOAT_NUM )assign_rawdevs ();
@@ -990,7 +990,7 @@ main(int argc, char **argv)assign_rings ();start_forwarding_cores (); -/* master core prints stats while other cores forward */ +/* initial core prints stats while other cores forward */ print_stats (argv[0 ]);/* force_quit is true when we get here */
examples/ip_fragmentation/main.c +2 -2
@@ -1072,8 +1072,8 @@ main(int argc, char **argv)check_all_ports_link_status (enabled_port_mask);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/ip_reassembly/main.c +2 -2
@@ -1201,8 +1201,8 @@ main(int argc, char **argv)signal (SIGINT , signal_handler);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/ipv4_multicast/main.c +2 -2
@@ -801,8 +801,8 @@ main(int argc, char **argv)rte_exit (EXIT_FAILURE ,"Cannot build the multicast hash\n" );/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/kni/main.c +3 -4
@@ -954,8 +954,7 @@ kni_alloc(uint16_t port_id) conf.mbuf_size =MAX_PACKET_SZ ;/* * The first KNI device associated to a port -* is the master, for multiple kernel thread -* environment. +* is special, for multiple kernel thread environment. */ if (i ==0 ) {struct rte_kni_ops ops;
@@ -1103,8 +1102,8 @@ main(int argc, char** argv) "Could not create link status thread!\n");/* Launch per-lcore function on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (i) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (i) {if (rte_eal_wait_lcore (i) <0 )return -1 ; }
examples/link_status_interrupt/main.c +4 -4
@@ -253,8 +253,8 @@ lsi_main_loop(void)/* if timer has reached its timeout */ if (unlikely (timer_tsc >= (uint64_t ) timer_period)) { -/* do this only on master core */ -if (lcore_id ==rte_get_master_lcore ()) { +/* do this only on initial core */ +if (lcore_id ==rte_get_initial_lcore ()) {print_stats ();/* reset the timer */ timer_tsc =0 ;
@@ -733,8 +733,8 @@ main(int argc, char **argv)check_all_ports_link_status (nb_ports, lsi_enabled_port_mask);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (lsi_launch_one_lcore,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (lsi_launch_one_lcore,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/ntb/ntb_fwd.c +7 -7
@@ -162,7 +162,7 @@ cmd_quit_parsed(__rte_unused void *parsed_result,uint32_t lcore_id;/* Stop transmission first. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (!conf->nb_stream)
@@ -668,7 +668,7 @@ assign_stream_to_lcores(void)uint8_t lcore_num, nb_extra; lcore_num =rte_lcore_count (); -/* Exclude master core */ +/* Exclude initial core */ lcore_num--; nb_streams = (fwd_mode ==IOFWD ) ? num_queues *2 : num_queues;
@@ -678,7 +678,7 @@ assign_stream_to_lcores(void) sm_id =0 ; i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (i < nb_extra) {
@@ -697,7 +697,7 @@ assign_stream_to_lcores(void) }/* Print packet forwading config. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (!conf->nb_stream)
@@ -765,7 +765,7 @@ start_pkt_fwd(void)assign_stream_to_lcores (); in_test =1 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (!conf->nb_stream)
@@ -826,7 +826,7 @@ cmd_stop_parsed(__rte_unused void *parsed_result,struct ntb_fwd_lcore_conf *conf;uint32_t lcore_id; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (!conf->nb_stream)
@@ -1074,7 +1074,7 @@ cmdline_parse_ctx_t main_ctx[] = { NULL, }; -/* prompt function, called from main on MASTER lcore */ +/* prompt function, called from main on initial lcore */ static void prompt (void ) {
examples/packet_ordering/main.c +11 -11
@@ -348,10 +348,10 @@ print_stats(void) {uint16_t i;struct rte_eth_stats eth_stats; -unsigned int lcore_id, last_lcore_id, master_lcore_id, end_w_lcore_id; +unsigned int lcore_id, last_lcore_id, initial_lcore_id, end_w_lcore_id; last_lcore_id =get_last_lcore_id (); - master_lcore_id =rte_get_master_lcore (); + initial_lcore_id =rte_get_initial_lcore (); end_w_lcore_id =get_previous_lcore_id (last_lcore_id);printf ("\nRX thread stats:\n" );
@@ -363,7 +363,7 @@ print_stats(void)for (lcore_id =0 ; lcore_id <= end_w_lcore_id; lcore_id++) {if (insight_worker &&rte_lcore_is_enabled (lcore_id) - && lcore_id != master_lcore_id) { + && lcore_id != initial_lcore_id) {printf ("\nWorker thread stats on core [%u]:\n" , lcore_id); printf(" - Pkts deqd from workers ring: %"PRIu64"\n",
@@ -661,7 +661,7 @@ main(int argc, char **argv) {int ret;unsigned nb_ports; -unsigned int lcore_id, last_lcore_id, master_lcore_id; +unsigned int lcore_id, last_lcore_id, initial_lcore_id;uint16_t port_id;uint16_t nb_ports_available;struct worker_thread_args worker_args = {NULL ,NULL };
@@ -748,32 +748,32 @@ main(int argc, char **argv) } last_lcore_id =get_last_lcore_id (); - master_lcore_id =rte_get_master_lcore (); + initial_lcore_id =rte_get_initial_lcore (); worker_args.ring_in = rx_to_workers; worker_args.ring_out = workers_to_tx; -/* Start worker_thread() on all the available slave cores but the last 1 */ +/* Start worker_thread() on all the available worker cores but the last 1 */ for (lcore_id =0 ; lcore_id <=get_previous_lcore_id (last_lcore_id); lcore_id++) -if (rte_lcore_is_enabled (lcore_id) && lcore_id != master_lcore_id) +if (rte_lcore_is_enabled (lcore_id) && lcore_id != initial_lcore_id)rte_eal_remote_launch (worker_thread, (void *)&worker_args, lcore_id);if (disable_reorder) { -/* Start tx_thread() on the last slave core */ +/* Start tx_thread() on the last worker core */ rte_eal_remote_launch ((lcore_function_t *)tx_thread, workers_to_tx, last_lcore_id); }else { send_args.ring_in = workers_to_tx; -/* Start send_thread() on the last slave core */ +/* Start send_thread() on the last worker core */ rte_eal_remote_launch ((lcore_function_t *)send_thread, (void *)&send_args, last_lcore_id); } -/* Start rx_thread() on the master core */ +/* Start rx_thread() on the initial core */ rx_thread (rx_to_workers); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/rxtx_callbacks/main.c +1 -1
@@ -302,7 +302,7 @@ main(int argc, char *argv[])printf ("\nWARNING: Too much enabled lcores - " "App uses only 1 lcore\n" ); -/* call lcore_main on master core only */ +/* call lcore_main on initial core only */ lcore_main ();return 0 ; }
examples/server_node_efd/server/main.c +5 -5
@@ -95,7 +95,7 @@ get_printable_mac_addr(uint16_t port)/* * This function displays the recorded statistics for each port * and for each node. It uses ANSI terminal codes to clear -* screen when called. It is called from a single non-master +* screen when called. It is called from a single worker * thread in the server process, when the process is run with more * than one lcore enabled. */
@@ -168,7 +168,7 @@ do_stats_display(void) }/* -* The function called from each non-master lcore used by the process. +* The function called from each worker lcore used by the process. * The test_and_set function is used to randomly pick a single lcore on which * the code to display the statistics will run. Otherwise, the code just * repeatedly sleeps.
@@ -290,7 +290,7 @@ process_packets(uint32_t port_num __rte_unused, struct rte_mbuf *pkts[], }/* -* Function called by the master lcore of the DPDK process. +* Function called by the initial lcore of the DPDK process. */ static void do_packet_forwarding (void )
@@ -330,8 +330,8 @@ main(int argc, char *argv[])/* clear statistics */ clear_stats (); -/* put all other cores to sleep bar master */ -rte_eal_mp_remote_launch (sleep_lcore,NULL ,SKIP_MASTER ); +/* put all other cores to sleep */ +rte_eal_mp_remote_launch (sleep_lcore,NULL ,SKIP_INITIAL );do_packet_forwarding ();return 0 ;
examples/skeleton/basicfwd.c +1 -1
@@ -202,7 +202,7 @@ main(int argc, char *argv[])if (rte_lcore_count () >1 )printf ("\nWARNING: Too many lcores enabled. Only 1 used.\n" ); -/* Call lcore_main on the master core only. */ +/* Call lcore_main on the initial core only. */ lcore_main ();return 0 ;
examples/tep_termination/main.c +6 -6
@@ -838,7 +838,7 @@ init_data_ll(void) {int lcore; -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) { lcore_info[lcore].lcore_ll =malloc (sizeof (struct lcore_ll_info ));if (lcore_info[lcore].lcore_ll ==NULL ) {
@@ -930,7 +930,7 @@ destroy_device(int vid)rm_data_ll_entry (&ll_root_used, ll_main_dev_cur, ll_main_dev_last);/* Set the dev_removal_flag on each lcore. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) { lcore_info[lcore].lcore_ll->dev_removal_flag =REQUEST_DEV_REMOVAL ; }
@@ -941,7 +941,7 @@ destroy_device(int vid)* the device removed from the linked lists and that the devices * are no longer in use. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) {while (lcore_info[lcore].lcore_ll->dev_removal_flag !=ACK_DEV_REMOVAL )rte_pause ();
@@ -1001,7 +1001,7 @@ new_device(int vid) vdev->remove =0 ;/* Find a suitable lcore to add the device. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) {if (lcore_info[lcore].lcore_ll->device_num < device_num_min) { device_num_min = lcore_info[lcore].lcore_ll->device_num; core_add = lcore;
@@ -1205,7 +1205,7 @@ main(int argc, char *argv[]) }/* Launch all data cores. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (switch_worker, mbuf_pool, lcore_id); }
@@ -1229,7 +1229,7 @@ main(int argc, char *argv[]) "failed to start vhost driver.\n"); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) +RTE_LCORE_FOREACH_WORKER (lcore_id)rte_eal_wait_lcore (lcore_id);return 0 ;
examples/timer/main.c +4 -4
@@ -100,7 +100,7 @@ main(int argc, char **argv)rte_timer_init (&timer0);rte_timer_init (&timer1); -/* load timer0, every second, on master lcore, reloaded automatically */ +/* load timer0, every second, on initial lcore, reloaded automatically */ hz =rte_get_timer_hz (); lcore_id =rte_lcore_id ();rte_timer_reset (&timer0, hz,PERIODICAL , lcore_id, timer0_cb,NULL );
@@ -109,12 +109,12 @@ main(int argc, char **argv) lcore_id =rte_get_next_lcore (lcore_id,0 ,1 );rte_timer_reset (&timer1, hz/3 ,SINGLE , lcore_id, timer1_cb,NULL ); -/* call lcore_mainloop() on every slave lcore */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +/* call lcore_mainloop() on every worker lcore */ +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (lcore_mainloop,NULL , lcore_id); } -/* call it on master lcore too */ +/* call it on initial lcore too */ (void )lcore_mainloop (NULL );return 0 ;
examples/vhost/main.c +5 -5
@@ -1205,7 +1205,7 @@ destroy_device(int vid)/* Set the dev_removal_flag on each lcore. */ -RTE_LCORE_FOREACH_SLAVE (lcore) +RTE_LCORE_FOREACH_WORKER (lcore) lcore_info[lcore].dev_removal_flag = REQUEST_DEV_REMOVAL;/*
@@ -1213,7 +1213,7 @@ destroy_device(int vid)* we can be sure that they can no longer access the device removed * from the linked lists and that the devices are no longer in use. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) {while (lcore_info[lcore].dev_removal_flag !=ACK_DEV_REMOVAL )rte_pause (); }
@@ -1258,7 +1258,7 @@ new_device(int vid) vdev->remove =0 ;/* Find a suitable lcore to add the device. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) {if (lcore_info[lcore].device_num < device_num_min) { device_num_min = lcore_info[lcore].device_num; core_add = lcore;
@@ -1505,7 +1505,7 @@ main(int argc, char *argv[]) }/* Launch all data cores. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) +RTE_LCORE_FOREACH_WORKER (lcore_id)rte_eal_remote_launch (switch_worker, NULL, lcore_id);if (client_mode)
@@ -1566,7 +1566,7 @@ main(int argc, char *argv[]) } } -RTE_LCORE_FOREACH_SLAVE (lcore_id) +RTE_LCORE_FOREACH_WORKER (lcore_id)rte_eal_wait_lcore (lcore_id);return 0 ;
examples/vmdq/main.c +2 -2
@@ -656,8 +656,8 @@ main(int argc, char *argv[]) }/* call lcore_main() on every lcore */ -rte_eal_mp_remote_launch (lcore_main,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (lcore_main,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/vmdq_dcb/main.c +3 -3
@@ -702,12 +702,12 @@ main(int argc, char *argv[])rte_exit (EXIT_FAILURE ,"Cannot initialize network ports\n" ); } -/* call lcore_main() on every slave lcore */ +/* call lcore_main() on every worker lcore */ i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (lcore_main, (void *)i++, lcore_id); } -/* call on master too */ +/* call on initial too */ (void )lcore_main ((void *)i);return 0 ;
Signature · 1 line
2.26.2
RFC v2 18/26 app/test-pmd: change references to master/slave
In reply to Stephen HemmingerUse new API and naming convention
--- app/test-pmd/config.c | 4 ++-- app/test-pmd/parameters.c | 2 +- app/test-pmd/softnicfwd.c | 2 +- app/test-pmd/testpmd.c | 4 ++-- 4 files changed, 6 insertions(+), 6 deletions(-)
app/test-pmd/config.c +2 -2
@@ -2647,9 +2647,9 @@ set_fwd_lcores_list(unsigned int *lcorelist, unsigned int nb_lc)printf ("lcore %u not enabled\n" , lcore_cpuid);return -1 ; } -if (lcore_cpuid ==rte_get_master_lcore ()) { +if (lcore_cpuid ==rte_get_initial_lcore ()) {printf ("lcore %u cannot be masked on for running " -"packet forwarding, which is the master lcore " +"packet forwarding, which is the initial lcore " "and reserved for command line parsing only\n" , lcore_cpuid);return -1 ;
app/test-pmd/parameters.c +1 -1
@@ -88,7 +88,7 @@ usage(char* progname)printf (" --nb-ports=N: set the number of forwarding ports " "(1 <= N <= %d).\n" , nb_ports);printf (" --coremask=COREMASK: hexadecimal bitmask of cores running " -"the packet forwarding test. The master lcore is reserved for " +"the packet forwarding test. The initial lcore is reserved for " "command line parsing only, and cannot be masked on for " "packet forwarding.\n" ); printf(" --portmask=PORTMASK: hexadecimal bitmask of ports used "
app/test-pmd/softnicfwd.c +1 -1
@@ -654,7 +654,7 @@ softnic_fwd_begin(portid_t pi)if (!rte_lcore_is_enabled (lcore))continue ; -if (lcore ==rte_get_master_lcore ()) +if (lcore ==rte_get_initial_lcore ())continue ;if (fwd_core_present ==0 ) {
app/test-pmd/testpmd.c +2 -2
@@ -83,7 +83,7 @@uint16_t verbose_level =0 ;/**< Silent by default. */ int testpmd_logtype;/**< Log type for testpmd logs */ -/* use master core for command line ? */ +/* use initial core for command line ? */ uint8_t interactive =0 ;uint8_t auto_start =0 ;uint8_t tx_first;
@@ -552,7 +552,7 @@ set_default_fwd_lcores_config(void) } socket_ids[num_sockets++] = sock_num; } -if (i ==rte_get_master_lcore ()) +if (i ==rte_get_initial_lcore ())continue ; fwd_lcores_cpuids[nb_lc++] = i; }
Signature · 1 line
2.26.2
RFC v2 19/26 test-eventdev: replace references to slave with worker lcores
In reply to Stephen HemmingerUse new API terminolgy
--- app/test-eventdev/evt_options.c | 2 +- app/test-eventdev/test_order_common.c | 12 ++++++------ app/test-eventdev/test_perf_common.c | 16 ++++++++-------- app/test-eventdev/test_pipeline_common.c | 8 ++++---- 4 files changed, 19 insertions(+), 19 deletions(-)
app/test-eventdev/evt_options.c +1 -1
@@ -438,7 +438,7 @@ evt_options_dump(struct evt_options *opt)evt_dump ("verbose_level" ,"%d" , opt->verbose_level);evt_dump ("socket_id" ,"%d" , opt->socket_id);evt_dump ("pool_sz" ,"%d" , opt->pool_sz); -evt_dump ("master lcore" ,"%d" ,rte_get_master_lcore ()); +evt_dump ("initial lcore" ,"%d" ,rte_get_initial_lcore ());evt_dump ("nb_pkts" ,"%" PRIu64, opt->nb_pkts);evt_dump ("nb_timers" ,"%" PRIu64, opt->nb_timers);evt_dump_begin ("available lcores" );
app/test-eventdev/test_order_common.c +6 -6
@@ -74,15 +74,15 @@ order_opt_check(struct evt_options *opt)return -1 ; } -/* 1 producer + N workers + 1 master */ +/* 1 producer + N workers + 1 initial lcore */ if (rte_lcore_count () <3 ) {evt_err ("test need minimum 3 lcores" );return -1 ; }/* Validate worker lcores */ -if (evt_lcores_has_overlap (opt->wlcores,rte_get_master_lcore ())) { -evt_err ("worker lcores overlaps with master lcore" ); +if (evt_lcores_has_overlap (opt->wlcores,rte_get_initial_lcore ())) { +evt_err ("worker lcores overlaps with initial lcore" );return -1 ; }
@@ -117,8 +117,8 @@ order_opt_check(struct evt_options *opt) }/* Validate producer lcore */ -if (plcore == (int )rte_get_master_lcore ()) { -evt_err ("producer lcore and master lcore should be different" ); +if (plcore == (int )rte_get_initial_lcore ()) { +evt_err ("producer lcore and initial lcore should be different" );return -1 ; }if (!rte_lcore_is_enabled (plcore)) {
@@ -245,7 +245,7 @@ order_launch_lcores(struct evt_test *test, struct evt_options *opt,int wkr_idx =0 ;/* launch workers */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (!(opt->wlcores[lcore_id]))continue ;
app/test-eventdev/test_perf_common.c +8 -8
@@ -254,7 +254,7 @@ perf_launch_lcores(struct evt_test *test, struct evt_options *opt,int port_idx =0 ;/* launch workers */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (!(opt->wlcores[lcore_id]))continue ;
@@ -268,7 +268,7 @@ perf_launch_lcores(struct evt_test *test, struct evt_options *opt, }/* launch producers */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (!(opt->plcores[lcore_id]))continue ;
@@ -541,8 +541,8 @@ perf_opt_check(struct evt_options *opt, uint64_t nb_queues) {unsigned int lcores; -/* N producer + N worker + 1 master when producer cores are used -* Else N worker + 1 master when Rx adapter is used +/* N producer + N worker + 1 initial lcore when producer cores are used +* Else N worker + 1 initial lcore when Rx adapter is used */ lcores = opt->prod_type ==EVT_PROD_TYPE_SYNT ?3 :2 ;
@@ -552,8 +552,8 @@ perf_opt_check(struct evt_options *opt, uint64_t nb_queues) }/* Validate worker lcores */ -if (evt_lcores_has_overlap (opt->wlcores,rte_get_master_lcore ())) { -evt_err ("worker lcores overlaps with master lcore" ); +if (evt_lcores_has_overlap (opt->wlcores,rte_get_initial_lcore ())) { +evt_err ("worker lcores overlaps with initial lcore" );return -1 ; }if (evt_lcores_has_overlap_multi (opt->wlcores, opt->plcores)) {
@@ -573,8 +573,8 @@ perf_opt_check(struct evt_options *opt, uint64_t nb_queues) opt->prod_type == EVT_PROD_TYPE_EVENT_TIMER_ADPTR) {/* Validate producer lcores */ if (evt_lcores_has_overlap (opt->plcores, -rte_get_master_lcore ())) { -evt_err ("producer lcores overlaps with master lcore" ); +rte_get_initial_lcore ())) { +evt_err ("producer lcores overlaps with initial lcore" );return -1 ; }if (evt_has_disabled_lcore (opt->plcores)) {
app/test-eventdev/test_pipeline_common.c +4 -4
@@ -60,7 +60,7 @@ pipeline_launch_lcores(struct evt_test *test, struct evt_options *opt,int port_idx =0 ;/* launch workers */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (!(opt->wlcores[lcore_id]))continue ;
@@ -107,7 +107,7 @@ pipeline_opt_check(struct evt_options *opt, uint64_t nb_queues) {unsigned int lcores;/* -* N worker + 1 master +* N worker + 1 initial lcore */ lcores =2 ;
@@ -129,8 +129,8 @@ pipeline_opt_check(struct evt_options *opt, uint64_t nb_queues) }/* Validate worker lcores */ -if (evt_lcores_has_overlap (opt->wlcores,rte_get_master_lcore ())) { -evt_err ("worker lcores overlaps with master lcore" ); +if (evt_lcores_has_overlap (opt->wlcores,rte_get_initial_lcore ())) { +evt_err ("worker lcores overlaps with initial lcore" );return -1 ; }if (evt_has_disabled_lcore (opt->wlcores)) {
Signature · 1 line
2.26.2
RFC v2 20/26 app/test: repalce refernces to master/slave
In reply to Stephen HemmingerUse initial and worker when referring to lcores
--- app/test/autotest_test_funcs.py | 2 +- app/test/test.c | 2 +- app/test/test_atomic.c | 26 ++++---- app/test/test_barrier.c | 2 +- app/test/test_cryptodev.c | 16 ++--- app/test/test_distributor.c | 8 +-- app/test/test_distributor_perf.c | 10 +-- app/test/test_eal_flags.c | 32 +++++----- app/test/test_efd.c | 2 +- app/test/test_efd_perf.c | 2 +- app/test/test_func_reentrancy.c | 20 +++--- app/test/test_hash_multiwriter.c | 4 +- app/test/test_hash_readwrite.c | 38 +++++------ app/test/test_kni.c | 16 ++--- app/test/test_malloc.c | 12 ++-- app/test/test_mbuf.c | 36 +++++------ app/test/test_mcslock.c | 28 ++++---- app/test/test_mempool_perf.c | 10 +-- app/test/test_mp_secondary.c | 2 +- app/test/test_pdump.c | 2 +- app/test/test_per_lcore.c | 14 ++-- app/test/test_pmd_perf.c | 20 +++--- app/test/test_rcu_qsbr.c | 2 +- app/test/test_rcu_qsbr_perf.c | 2 +- app/test/test_ring_perf.c | 14 ++-- app/test/test_ring_stress_impl.h | 10 +-- app/test/test_rwlock.c | 28 ++++---- app/test/test_service_cores.c | 10 +-- app/test/test_spinlock.c | 34 +++++----- app/test/test_stack.c | 2 +- app/test/test_stack_perf.c | 6 +- app/test/test_ticketlock.c | 36 +++++------ app/test/test_timer.c | 106 +++++++++++++++---------------- app/test/test_timer_racecond.c | 27 ++++---- app/test/test_timer_secondary.c | 2 +- app/test/test_trace_perf.c | 4 +- 36 files changed, 294 insertions(+), 293 deletions(-)
app/test/autotest_test_funcs.py +1 -1
@@ -102,7 +102,7 @@ def rwlock_autotest(child, test_name): index = child.expect(["Test OK", "Test Failed", "Hello from core ([0-9]*) !", - "Global write lock taken on master " + "Global write lock taken on initial lcore " "core ([0-9]*)", pexpect.TIMEOUT], timeout=10) # ok
app/test/test.c +1 -1
@@ -58,7 +58,7 @@ do_recursive_call(void)#endif #endif { "test_missing_c_flag", no_action }, - { "test_master_lcore_flag", no_action }, + { "test_initial_lcore_flag", no_action }, { "test_invalid_n_flag", no_action }, { "test_no_hpet_flag", no_action }, { "test_whitelist_flag", no_action },
app/test/test_atomic.c +13 -13
@@ -456,7 +456,7 @@ test_atomic(void)printf ("usual inc/dec/add/sub functions\n" ); -rte_eal_mp_remote_launch (test_atomic_usual,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_usual,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_set (&synchro,0 );
@@ -482,7 +482,7 @@ test_atomic(void)rte_atomic32_set (&a32,0 );rte_atomic16_set (&a16,0 );rte_atomic64_set (&count,0 ); -rte_eal_mp_remote_launch (test_atomic_tas,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_tas,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_set (&synchro,0 );
@@ -499,7 +499,7 @@ test_atomic(void)rte_atomic16_set (&a16,0 );rte_atomic64_set (&count,0 );rte_eal_mp_remote_launch (test_atomic_addsub_and_return,NULL , -SKIP_MASTER ); +SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_set (&synchro,0 );
@@ -510,8 +510,8 @@ test_atomic(void) }/* -* Set a64, a32 and a16 with the same value of minus "number of slave -* lcores", launch all slave lcores to atomically increase by one and +* Set a64, a32 and a16 with the same value of minus "number of worker +* lcores", launch all worker lcores to atomically increase by one and * test them respectively. * Each lcore should have only one chance to increase a64 by one and * then check if it is equal to 0, but there should be only one lcore
@@ -519,7 +519,7 @@ test_atomic(void)* Then a variable of "count", initialized to zero, is increased by * one if a64, a32 or a16 is 0 after being increased and tested * atomically. -* We can check if "count" is finally equal to 3 to see if all slave +* We can check if "count" is finally equal to 3 to see if all worker * lcores performed "atomic inc and test" right. */ printf ("inc and test\n" );
@@ -533,7 +533,7 @@ test_atomic(void)rte_atomic64_set (&a64, (int64_t )(1 - (int64_t )rte_lcore_count ()));rte_atomic32_set (&a32, (int32_t )(1 - (int32_t )rte_lcore_count ()));rte_atomic16_set (&a16, (int16_t )(1 - (int16_t )rte_lcore_count ())); -rte_eal_mp_remote_launch (test_atomic_inc_and_test,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_inc_and_test,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_clear (&synchro);
@@ -544,7 +544,7 @@ test_atomic(void) }/* -* Same as above, but this time we set the values to "number of slave +* Same as above, but this time we set the values to "number of worker * lcores", and decrement instead of increment. */ printf ("dec and test\n" );
@@ -555,7 +555,7 @@ test_atomic(void)rte_atomic64_set (&a64, (int64_t )(rte_lcore_count () -1 ));rte_atomic32_set (&a32, (int32_t )(rte_lcore_count () -1 ));rte_atomic16_set (&a16, (int16_t )(rte_lcore_count () -1 )); -rte_eal_mp_remote_launch (test_atomic_dec_and_test,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_dec_and_test,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_clear (&synchro);
@@ -569,10 +569,10 @@ test_atomic(void)/* * This case tests the functionality of rte_atomic128_cmp_exchange * API. It calls rte_atomic128_cmp_exchange with four kinds of memory -* models successively on each slave core. Once each 128-bit atomic +* models successively on each worker core. Once each 128-bit atomic * compare and swap operation is successful, it updates the global * 128-bit counter by 2 for the first 64-bit and 1 for the second -* 64-bit. Each slave core iterates this test N times. +* 64-bit. Each worker core iterates this test N times. * At the end of test, verify whether the first 64-bits of the 128-bit * counter and the second 64bits is differ by the total iterations. If * it is, the test passes.
@@ -585,7 +585,7 @@ test_atomic(void) count128.val[1 ] =0 ;rte_eal_mp_remote_launch (test_atomic128_cmp_exchange,NULL , -SKIP_MASTER ); +SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_clear (&synchro);
@@ -619,7 +619,7 @@ test_atomic(void) token64 = ((uint64_t )get_crc8 (&t.u8[0 ],sizeof (token64) -1 ) <<56 ) | (t.u64 &0x00ffffffffffffff ); -rte_eal_mp_remote_launch (test_atomic_exchange,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_exchange,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_clear (&synchro);
app/test/test_barrier.c +1 -1
@@ -236,7 +236,7 @@ plock_test(uint64_t iter, enum plock_use_type utype)/* test phase - start and wait for completion on each active lcore */ -rte_eal_mp_remote_launch (plock_test1_lcore, lpt,CALL_MASTER ); +rte_eal_mp_remote_launch (plock_test1_lcore, lpt,CALL_INITIAL );rte_eal_mp_wait_lcore ();/* validation phase - make sure that shared and local data match */
app/test/test_cryptodev.c +8 -8
@@ -474,29 +474,29 @@ testsuite_setup(void)char vdev_args[VDEV_ARGS_SIZE ] = {"" };char temp_str[VDEV_ARGS_SIZE ] = {"mode=multi-core," "ordering=enable,name=cryptodev_test_scheduler,corelist=" }; -uint16_t slave_core_count =0 ; +uint16_t worker_core_count =0 ;uint16_t socket_id =0 ;if (gbl_driver_id ==rte_cryptodev_driver_id_get (RTE_STR (CRYPTODEV_NAME_SCHEDULER_PMD ))) { -/* Identify the Slave Cores -* Use 2 slave cores for the device args +/* Identify the Worker Cores +* Use 2 worker cores for the device args */ -RTE_LCORE_FOREACH_SLAVE (i) { -if (slave_core_count >1 ) +RTE_LCORE_FOREACH_WORKER (i) { +if (worker_core_count >1 )break ;snprintf (vdev_args,sizeof (vdev_args),"%s%d" , temp_str, i);strcpy (temp_str, vdev_args);strlcat (temp_str,";" ,sizeof (temp_str)); - slave_core_count++; + worker_core_count++; socket_id =rte_lcore_to_socket_id (i); } -if (slave_core_count !=2 ) { +if (worker_core_count !=2 ) {RTE_LOG (ERR ,USER1 ,"Cryptodev scheduler test require at least " -"two slave cores to run. " +"two worker cores to run. " "Please use the correct coremask.\n" );return TEST_FAILED ; }
app/test/test_distributor.c +4 -4
@@ -654,13 +654,13 @@ test_distributor(void) sizeof(worker_params.name));rte_eal_mp_remote_launch (handle_work, - &worker_params,SKIP_MASTER ); + &worker_params,SKIP_INITIAL );if (sanity_test (&worker_params, p) <0 ) goto err;quit_workers (&worker_params, p);rte_eal_mp_remote_launch (handle_work_with_free_mbufs, - &worker_params,SKIP_MASTER ); + &worker_params,SKIP_INITIAL );if (sanity_test_with_mbuf_alloc (&worker_params, p) <0 ) goto err;quit_workers (&worker_params, p);
@@ -668,7 +668,7 @@ test_distributor(void)if (rte_lcore_count () >2 ) {rte_eal_mp_remote_launch (handle_work_for_shutdown_test, &worker_params, -SKIP_MASTER ); +SKIP_INITIAL );if (sanity_test_with_worker_shutdown (&worker_params, p) <0 ) goto err;
@@ -676,7 +676,7 @@ test_distributor(void)rte_eal_mp_remote_launch (handle_work_for_shutdown_test, &worker_params, -SKIP_MASTER ); +SKIP_INITIAL );if (test_flush_with_worker_shutdown (&worker_params, p) <0 ) goto err;
app/test/test_distributor_perf.c +5 -5
@@ -54,10 +54,10 @@ time_cache_line_switch(void)/* allocate a full cache line for data, we use only first byte of it */ uint64_t data[RTE_CACHE_LINE_SIZE *3 /sizeof (uint64_t )]; -unsigned i, slaveid =rte_get_next_lcore (rte_lcore_id (),0 ,0 ); +unsigned i, workerid =rte_get_next_lcore (rte_lcore_id (),0 ,0 );volatile uint64_t *pdata = &data[0 ]; *pdata =1 ; -rte_eal_remote_launch ((lcore_function_t *)flip_bit, &data[0 ], slaveid); +rte_eal_remote_launch ((lcore_function_t *)flip_bit, &data[0 ], workerid);while (*pdata)rte_pause ();
@@ -72,7 +72,7 @@ time_cache_line_switch(void)while (*pdata)rte_pause (); *pdata =2 ; -rte_eal_wait_lcore (slaveid); +rte_eal_wait_lcore (workerid);printf ("==== Cache line switch test ===\n" );printf ("Time for %u iterations = %" PRIu64" ticks\n" , (1 <<ITER_POWER_CL ), end_time-start_time);
@@ -251,13 +251,13 @@ test_distributor_perf(void) }printf ("=== Performance test of distributor (single mode) ===\n" ); -rte_eal_mp_remote_launch (handle_work, ds,SKIP_MASTER ); +rte_eal_mp_remote_launch (handle_work, ds,SKIP_INITIAL );if (perf_test (ds, p) <0 )return -1 ;quit_workers (ds, p);printf ("=== Performance test of distributor (burst mode) ===\n" ); -rte_eal_mp_remote_launch (handle_work, db,SKIP_MASTER ); +rte_eal_mp_remote_launch (handle_work, db,SKIP_INITIAL );if (perf_test (db, p) <0 )return -1 ;quit_workers (db, p);
app/test/test_eal_flags.c +16 -16
@@ -596,10 +596,10 @@ test_missing_c_flag(void) }/* -* Test --master-lcore option with matching coremask +* Test --initial-lcore option with matching coremask */ static int -test_master_lcore_flag (void ) +test_initial_lcore_flag (void ) {#ifdef RTE_EXEC_ENV_FREEBSD /* BSD target doesn't support prefixes at this point */
@@ -616,34 +616,34 @@ test_master_lcore_flag(void)if (!rte_lcore_is_enabled (0 ) || !rte_lcore_is_enabled (1 ))return TEST_SKIPPED ; -/* --master-lcore flag but no value */ +/* --initial-lcore flag but no value */ const char *argv1[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" }; -/* --master-lcore flag with invalid value */ +"-c" ,"3" ,"--initial-lcore" }; +/* --initial-lcore flag with invalid value */ const char *argv2[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" ,"-1" }; +"-c" ,"3" ,"--initial-lcore" ,"-1" };const char *argv3[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" ,"X" }; -/* master lcore not in coremask */ +"-c" ,"3" ,"--initial-lcore" ,"X" }; +/* initial lcore not in coremask */ const char *argv4[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" ,"2" }; +"-c" ,"3" ,"--initial-lcore" ,"2" };/* valid value */ const char *argv5[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" ,"1" }; +"-c" ,"3" ,"--initial-lcore" ,"1" };/* valid value set before coremask */ const char *argv6[] = { prgname, prefix, mp_flag, -"--master-lcore" ,"1" ,"-c" ,"3" }; +"--initial-lcore" ,"1" ,"-c" ,"3" };if (launch_proc (argv1) ==0 ||launch_proc (argv2) ==0 ||launch_proc (argv3) ==0 ||launch_proc (argv4) ==0 ) { -printf ("Error - process ran without error with wrong --master-lcore\n" ); +printf ("Error - process ran without error with wrong --initial-lcore\n" );return -1 ; }if (launch_proc (argv5) !=0 ||launch_proc (argv6) !=0 ) { -printf ("Error - process did not run ok with valid --master-lcore\n" ); +printf ("Error - process did not run ok with valid --initial-lcore\n" );return -1 ; }return 0 ;
@@ -1465,9 +1465,9 @@ test_eal_flags(void)return ret; } - ret =test_master_lcore_flag (); + ret =test_initial_lcore_flag ();if (ret <0 ) { -printf ("Error in test_master_lcore_flag()\n" ); +printf ("Error in test_initial_lcore_flag()\n" );return ret; }
@@ -1539,7 +1539,7 @@ REGISTER_TEST_COMMAND(eal_flags_autotest, test_eal_flags);/* subtests used in meson for CI */ REGISTER_TEST_COMMAND (eal_flags_c_opt_autotest, test_missing_c_flag); -REGISTER_TEST_COMMAND (eal_flags_master_opt_autotest, test_master_lcore_flag); +REGISTER_TEST_COMMAND (eal_flags_master_opt_autotest, test_initial_lcore_flag);REGISTER_TEST_COMMAND (eal_flags_n_opt_autotest, test_invalid_n_flag);REGISTER_TEST_COMMAND (eal_flags_hpet_autotest, test_no_hpet_flag);REGISTER_TEST_COMMAND (eal_flags_no_huge_autotest, test_no_huge_flag);
app/test/test_efd.c +1 -1
@@ -100,7 +100,7 @@ static inline uint8_t efd_get_all_sockets_bitmask(void) {uint8_t all_cpu_sockets_bitmask =0 ;unsigned int i; -unsigned int next_lcore =rte_get_master_lcore (); +unsigned int next_lcore =rte_get_initial_lcore ();const int val_true =1 , val_false =0 ;for (i =0 ; i <rte_lcore_count (); i++) { all_cpu_sockets_bitmask |=1 <<rte_lcore_to_socket_id (next_lcore);
app/test/test_efd_perf.c +1 -1
@@ -33,7 +33,7 @@ static inline uint8_t efd_get_all_sockets_bitmask(void) {uint8_t all_cpu_sockets_bitmask =0 ;unsigned int i; -unsigned int next_lcore =rte_get_master_lcore (); +unsigned int next_lcore =rte_get_initial_lcore ();const int val_true =1 , val_false =0 ;for (i =0 ; i <rte_lcore_count (); i++) { all_cpu_sockets_bitmask |=1 <<rte_lcore_to_socket_id (next_lcore);
app/test/test_func_reentrancy.c +10 -10
@@ -57,8 +57,8 @@ typedef void (*case_clean_t)(unsigned lcore_id);static rte_atomic32_t obj_count =RTE_ATOMIC32_INIT (0 );static rte_atomic32_t synchro =RTE_ATOMIC32_INIT (0 ); -#define WAIT_SYNCHRO_FOR_SLAVES () do{ \ - if (lcore_self != rte_get_master_lcore()) \ +#define WAIT_SYNCHRO_FOR_WORKERS () do{ \ + if (lcore_self != rte_get_initial_lcore()) \ while (rte_atomic32_read(&synchro) == 0); \ } while(0)
@@ -70,7 +70,7 @@ test_eal_init_once(__rte_unused void *arg) {unsigned lcore_self =rte_lcore_id (); -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();rte_atomic32_set (&obj_count,1 );/* silent the check in the caller */ if (rte_eal_init (0 ,NULL ) !=-1 )
@@ -106,7 +106,7 @@ ring_create_lookup(__rte_unused void *arg)char ring_name[MAX_STRING_SIZE ];int i; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same ring simultaneously on all threads */ for (i =0 ; i <MAX_ITER_ONCE ; i++) {
@@ -166,7 +166,7 @@ mempool_create_lookup(__rte_unused void *arg)char mempool_name[MAX_STRING_SIZE ];int i; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same mempool simultaneously on all threads */ for (i =0 ; i <MAX_ITER_ONCE ; i++) {
@@ -232,7 +232,7 @@ hash_create_free(__rte_unused void *arg) .socket_id = 0, }; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same hash simultaneously on all threads */ hash_params.name ="fr_test_once" ;
@@ -296,7 +296,7 @@ fbk_create_free(__rte_unused void *arg) .init_val = RTE_FBK_HASH_INIT_VAL_DEFAULT, }; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same fbk hash table simultaneously on all threads */ fbk_params.name ="fr_test_once" ;
@@ -359,7 +359,7 @@ lpm_create_free(__rte_unused void *arg)char lpm_name[MAX_STRING_SIZE ];int i; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same lpm simultaneously on all threads */ for (i =0 ; i <MAX_ITER_ONCE ; i++) {
@@ -430,7 +430,7 @@ launch_test(struct test_case *pt_case)rte_atomic32_set (&obj_count,0 );rte_atomic32_set (&synchro,0 ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (cores ==1 )break ; cores--;
@@ -443,7 +443,7 @@ launch_test(struct test_case *pt_case) ret =-1 ; cores = cores_save; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (cores ==1 )break ; cores--;
app/test/test_hash_multiwriter.c +2 -2
@@ -64,7 +64,7 @@ test_hash_multiwriter_worker(void *arg)/* * Calculate offset for entries based on the position of the -* logical core, from the master core (not counting not enabled cores) +* logical core, from the initial core (not counting not enabled cores) */ offset = pos_core * tbl_multiwriter_test_params.nb_tsx_insertion;
@@ -194,7 +194,7 @@ test_hash_multiwriter(void)/* Fire all threads. */ rte_eal_mp_remote_launch (test_hash_multiwriter_worker, - enabled_core_ids,CALL_MASTER ); + enabled_core_ids,CALL_INITIAL );rte_eal_mp_wait_lcore (); count =rte_hash_count (handle);
app/test/test_hash_readwrite.c +19 -19
@@ -25,7 +25,7 @@#define NUM_TEST 3unsigned int core_cnt[NUM_TEST ] = {2 ,4 ,8 }; -unsigned int slave_core_ids[RTE_MAX_LCORE ]; +unsigned int worker_core_ids[RTE_MAX_LCORE ];struct perf {uint32_t single_read;uint32_t single_write;
@@ -65,7 +65,7 @@ test_hash_readwrite_worker(__rte_unused void *arg) ret =rte_malloc (NULL ,sizeof (int ) * tbl_rw_test_param.num_insert,0 );for (i =0 ; i <rte_lcore_count (); i++) { -if (slave_core_ids[i] == lcore_id) +if (worker_core_ids[i] == lcore_id)break ; } offset = tbl_rw_test_param.num_insert * i;
@@ -206,7 +206,7 @@ test_hash_readwrite_functional(int use_htm, int use_rw_lf, int use_ext)uint32_t duplicated_keys =0 ;uint32_t lost_keys =0 ;int use_jhash =1 ; -int slave_cnt =rte_lcore_count () -1 ; +int worker_cnt =rte_lcore_count () -1 ;uint32_t tot_insert =0 ;rte_atomic64_init (&gcycles);
@@ -224,11 +224,11 @@ test_hash_readwrite_functional(int use_htm, int use_rw_lf, int use_ext) tot_insert =TOTAL_INSERT ; tbl_rw_test_param.num_insert = - tot_insert / slave_cnt; + tot_insert / worker_cnt; tbl_rw_test_param.rounded_tot_insert = tbl_rw_test_param.num_insert - * slave_cnt; + * worker_cnt;printf ("\nHTM = %d, RW-LF = %d, EXT-Table = %d\n" , use_htm, use_rw_lf, use_ext);
@@ -236,7 +236,7 @@ test_hash_readwrite_functional(int use_htm, int use_rw_lf, int use_ext)/* Fire all threads. */ rte_eal_mp_remote_launch (test_hash_readwrite_worker, -NULL ,SKIP_MASTER ); +NULL ,SKIP_INITIAL );rte_eal_mp_wait_lcore (); while (rte_hash_iterate(tbl_rw_test_param.h, &next_key,
@@ -330,7 +330,7 @@ test_rw_writer(void *arg)uint64_t offset;for (i =0 ; i <rte_lcore_count (); i++) { -if (slave_core_ids[i] == lcore_id) +if (worker_core_ids[i] == lcore_id)break ; }
@@ -433,8 +433,8 @@ test_hash_readwrite_perf(struct perf *perf_results, int use_htm, perf_results->single_read = end / i;for (n =0 ; n <NUM_TEST ; n++) { -unsigned int tot_slave_lcore =rte_lcore_count () -1 ; -if (tot_slave_lcore < core_cnt[n] *2 ) +unsigned int tot_worker_lcore =rte_lcore_count () -1 ; +if (tot_worker_lcore < core_cnt[n] *2 ) goto finish;rte_atomic64_clear (&greads);
@@ -467,7 +467,7 @@ test_hash_readwrite_perf(struct perf *perf_results, int use_htm,for (i =0 ; i < core_cnt[n]; i++)rte_eal_remote_launch (test_rw_reader, (void *)(uintptr_t )read_cnt, - slave_core_ids[i]); + worker_core_ids[i]);rte_eal_mp_wait_lcore ();
@@ -476,7 +476,7 @@ test_hash_readwrite_perf(struct perf *perf_results, int use_htm,for (; i < core_cnt[n] *2 ; i++)rte_eal_remote_launch (test_rw_writer, (void *)((uintptr_t )start_coreid), - slave_core_ids[i]); + worker_core_ids[i]);rte_eal_mp_wait_lcore ();
@@ -521,20 +521,20 @@ test_hash_readwrite_perf(struct perf *perf_results, int use_htm,for (i = core_cnt[n]; i < core_cnt[n] *2 ; i++)rte_eal_remote_launch (test_rw_writer, (void *)((uintptr_t )start_coreid), - slave_core_ids[i]); + worker_core_ids[i]);for (i =0 ; i < core_cnt[n]; i++)rte_eal_remote_launch (test_rw_reader, (void *)(uintptr_t )read_cnt, - slave_core_ids[i]); + worker_core_ids[i]); }else {for (i =0 ; i < core_cnt[n]; i++)rte_eal_remote_launch (test_rw_reader, (void *)(uintptr_t )read_cnt, - slave_core_ids[i]); + worker_core_ids[i]);for (; i < core_cnt[n] *2 ; i++)rte_eal_remote_launch (test_rw_writer, (void *)((uintptr_t )start_coreid), - slave_core_ids[i]); + worker_core_ids[i]); }rte_eal_mp_wait_lcore ();
@@ -626,8 +626,8 @@ test_hash_rw_perf_main(void)return TEST_SKIPPED ; } -RTE_LCORE_FOREACH_SLAVE (core_id) { - slave_core_ids[i] = core_id; +RTE_LCORE_FOREACH_WORKER (core_id) { + worker_core_ids[i] = core_id; i++; }
@@ -710,8 +710,8 @@ test_hash_rw_func_main(void)return TEST_SKIPPED ; } -RTE_LCORE_FOREACH_SLAVE (core_id) { - slave_core_ids[i] = core_id; +RTE_LCORE_FOREACH_WORKER (core_id) { + worker_core_ids[i] = core_id; i++; }
app/test/test_kni.c +8 -8
@@ -85,7 +85,7 @@ static struct rte_kni_ops kni_ops = { .config_promiscusity = NULL, }; -static unsigned lcore_master, lcore_ingress, lcore_egress; +static unsigned lcore_initial, lcore_ingress, lcore_egress;static struct rte_kni *test_kni_ctx;static struct test_kni_stats stats;
@@ -202,7 +202,7 @@ test_kni_link_change(void)* supported by KNI kernel module. The ingress lcore will allocate mbufs and * transmit them to kernel space; while the egress lcore will receive the mbufs * from kernel space and free them. -* On the master lcore, several commands will be run to check handling the +* On the initial lcore, several commands will be run to check handling the * kernel requests. And it will finally set the flag to exit the KNI * transmitting/receiving to/from the kernel space. *
@@ -217,7 +217,7 @@ test_kni_loop(__rte_unused void *arg)const unsigned lcore_id =rte_lcore_id ();struct rte_mbuf *pkts_burst[PKT_BURST_SZ ]; -if (lcore_id == lcore_master) { +if (lcore_id == lcore_initial) {rte_delay_ms (KNI_TIMEOUT_MS );/* tests of handling kernel request */ if (system(IFCONFIG TEST_KNI_PORT" up") == -1)
@@ -276,12 +276,12 @@ test_kni_allocate_lcores(void) {unsigned i, count =0 ; - lcore_master =rte_get_master_lcore (); -printf ("master lcore: %u\n" , lcore_master); + lcore_initial =rte_get_initial_lcore (); +printf ("initial lcore: %u\n" , lcore_initial);for (i =0 ; i <RTE_MAX_LCORE ; i++) {if (count >=2 )break ; -if (rte_lcore_is_enabled (i) && i != lcore_master) { +if (rte_lcore_is_enabled (i) && i != lcore_initial) { count ++;if (count ==1 ) lcore_ingress = i;
@@ -487,8 +487,8 @@ test_kni_processing(uint16_t port_id, struct rte_mempool *mp)if (ret !=0 ) goto fail_kni; -rte_eal_mp_remote_launch (test_kni_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (i) { +rte_eal_mp_remote_launch (test_kni_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (i) {if (rte_eal_wait_lcore (i) <0 ) { ret =-1 ; goto fail_kni;
app/test/test_malloc.c +6 -6
@@ -1007,11 +1007,11 @@ test_malloc(void)else printf ("test_realloc() passed\n" );/*----------------------------*/ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (test_align_overlap_per_lcore,NULL , lcore_id); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 ) ret =-1 ; }
@@ -1022,11 +1022,11 @@ test_malloc(void)else printf ("test_align_overlap_per_lcore() passed\n" );/*----------------------------*/ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (test_reordered_free_per_lcore,NULL , lcore_id); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 ) ret =-1 ; }
@@ -1037,11 +1037,11 @@ test_malloc(void)else printf ("test_reordered_free_per_lcore() passed\n" );/*----------------------------*/ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (test_random_alloc_free,NULL , lcore_id); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 ) ret =-1 ; }
app/test/test_mbuf.c +18 -18
@@ -72,7 +72,7 @@#ifdef RTE_MBUF_REFCNT_ATOMIC -static volatile uint32_t refcnt_stop_slaves; +static volatile uint32_t refcnt_stop_workers;static unsigned refcnt_lcore[RTE_MAX_LCORE ];#endif
@@ -1000,7 +1000,7 @@ test_pktmbuf_free_segment(struct rte_mempool *pktmbuf_pool)#ifdef RTE_MBUF_REFCNT_ATOMIC static int -test_refcnt_slave (void *arg) +test_refcnt_worker (void *arg) {unsigned lcore, free;void *mp =0 ;
@@ -1010,7 +1010,7 @@ test_refcnt_slave(void *arg)printf ("%s started at lcore %u\n" , __func__, lcore); free =0 ; -while (refcnt_stop_slaves ==0 ) { +while (refcnt_stop_workers ==0 ) {if (rte_ring_dequeue (refcnt_mbuf_ring, &mp) ==0 ) { free++;rte_pktmbuf_free (mp);
@@ -1038,7 +1038,7 @@ test_refcnt_iter(unsigned int lcore, unsigned int iter,/* For each mbuf in the pool: * - allocate mbuf, * - increment it's reference up to N+1, -* - enqueue it N times into the ring for slave cores to free. +* - enqueue it N times into the ring for worker cores to free. */ for (i = 0, n = rte_mempool_avail_count(refcnt_pool); i != n && (m = rte_pktmbuf_alloc(refcnt_pool)) != NULL;
@@ -1062,7 +1062,7 @@ test_refcnt_iter(unsigned int lcore, unsigned int iter,rte_panic ("(lcore=%u, iter=%u): was able to allocate only " "%u from %u mbufs\n" , lcore, iter, i, n); -/* wait till slave lcores will consume all mbufs */ +/* wait till worker lcores will consume all mbufs */ while (!rte_ring_empty (refcnt_mbuf_ring)) ;
@@ -1083,8 +1083,8 @@ test_refcnt_iter(unsigned int lcore, unsigned int iter, }static int -test_refcnt_master (struct rte_mempool *refcnt_pool, -struct rte_ring *refcnt_mbuf_ring) +test_refcnt_main (struct rte_mempool *refcnt_pool, +struct rte_ring *refcnt_mbuf_ring) {unsigned i, lcore;
@@ -1094,7 +1094,7 @@ test_refcnt_master(struct rte_mempool *refcnt_pool,for (i =0 ; i !=REFCNT_MAX_ITER ; i++)test_refcnt_iter (lcore, i, refcnt_pool, refcnt_mbuf_ring); - refcnt_stop_slaves =1 ; + refcnt_stop_workers =1 ;rte_wmb ();printf ("%s finished at lcore %u\n" , __func__, lcore);
@@ -1107,7 +1107,7 @@ static inttest_refcnt_mbuf (void) {#ifdef RTE_MBUF_REFCNT_ATOMIC -unsigned int master, slave, tref; +unsigned int initial, worker, tref;int ret =-1 ;struct rte_mempool *refcnt_pool =NULL ;struct rte_ring *refcnt_mbuf_ring =NULL ;
@@ -1139,26 +1139,26 @@ test_refcnt_mbuf(void) goto err; } - refcnt_stop_slaves =0 ; + refcnt_stop_workers =0 ;memset (refcnt_lcore,0 ,sizeof (refcnt_lcore)); -rte_eal_mp_remote_launch (test_refcnt_slave, refcnt_mbuf_ring, -SKIP_MASTER ); +rte_eal_mp_remote_launch (test_refcnt_worker, refcnt_mbuf_ring, +SKIP_INITIAL ); -test_refcnt_master (refcnt_pool, refcnt_mbuf_ring); +test_refcnt_main (refcnt_pool, refcnt_mbuf_ring);rte_eal_mp_wait_lcore ();/* check that we porcessed all references */ tref =0 ; - master =rte_get_master_lcore (); + initial =rte_get_initial_lcore (); -RTE_LCORE_FOREACH_SLAVE (slave) - tref += refcnt_lcore[slave]; +RTE_LCORE_FOREACH_WORKER (worker) + tref += refcnt_lcore[worker]; -if (tref != refcnt_lcore[master]) +if (tref != refcnt_lcore[initial])rte_panic ("referenced mbufs: %u, freed mbufs: %u\n" , - tref, refcnt_lcore[master]); + tref, refcnt_lcore[initial]);rte_mempool_dump (stdout, refcnt_pool);rte_ring_dump (stdout, refcnt_mbuf_ring);
app/test/test_mcslock.c +14 -14
@@ -28,7 +28,7 @@* These tests are derived from spin lock test cases. * * - The functional test takes all of these locks and launches the -* ''test_mcslock_per_core()'' function on each core (except the master). +* ''test_mcslock_per_core()'' function on each core (except the initial). * * - The function takes the global lock, display something, then releases * the global lock on each core.
@@ -123,9 +123,9 @@ test_mcslock_perf(void)printf ("\nTest with lock on %u cores...\n" , (rte_lcore_count ()));rte_atomic32_set (&synchro,0 ); -rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_MASTER ); +rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_INITIAL ); -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );load_loop_fn (&lock);
@@ -154,8 +154,8 @@ test_mcslock_try(__rte_unused void *arg)rte_mcslock_t ml_me =RTE_PER_LCORE (_ml_me);rte_mcslock_t ml_try_me =RTE_PER_LCORE (_ml_try_me); -/* Locked ml_try in the master lcore, so it should fail -* when trying to lock it in the slave lcore. +/* Locked ml_try in the initial lcore, so it should fail +* when trying to lock it in the worker lcore. */ if (rte_mcslock_trylock (&p_ml_try, &ml_try_me) ==0 ) {rte_mcslock_lock (&p_ml, &ml_me);
@@ -185,20 +185,20 @@ test_mcslock(void)* Test mcs lock & unlock on each core */ -/* slave cores should be waiting: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be waiting: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }rte_mcslock_lock (&p_ml, &ml_me); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_mcslock_per_core,NULL , i); } -/* slave cores should be busy: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be busy: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }
@@ -210,19 +210,19 @@ test_mcslock(void)/* * Test if it could return immediately from try-locking a locked object. * Here it will lock the mcs lock object first, then launch all the -* slave lcores to trylock the same mcs lock object. -* All the slave lcores should give up try-locking a locked object and +* worker lcores to trylock the same mcs lock object. +* All the worker lcores should give up try-locking a locked object and * return immediately, and then increase the "count" initialized with * zero by one per times. * We can check if the "count" is finally equal to the number of all -* slave lcores to see if the behavior of try-locking a locked +* worker lcores to see if the behavior of try-locking a locked * mcslock object is correct. */ if (rte_mcslock_trylock (&p_ml_try, &ml_try_me) ==0 )return -1 ; count =0 ; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_mcslock_try,NULL , i); }rte_eal_mp_wait_lcore ();
app/test/test_mempool_perf.c +5 -5
@@ -143,8 +143,8 @@ per_lcore_mempool_test(void *arg) stats[lcore_id].enq_count =0 ; -/* wait synchro for slaves */ -if (lcore_id !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore_id !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 ); start_cycles =rte_get_timer_cycles ();
@@ -214,7 +214,7 @@ launch_cores(struct rte_mempool *mp, unsigned int cores)return -1 ; } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (cores ==1 )break ; cores--;
@@ -222,13 +222,13 @@ launch_cores(struct rte_mempool *mp, unsigned int cores) mp, lcore_id); } -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 ); ret =per_lcore_mempool_test (mp); cores = cores_save; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (cores ==1 )break ; cores--;
app/test/test_mp_secondary.c +1 -1
@@ -94,7 +94,7 @@ run_secondary_instances(void)#endif snprintf (coremask,sizeof (coremask),"%x" , \ - (1 <<rte_get_master_lcore ())); + (1 <<rte_get_initial_lcore ())); ret |=launch_proc (argv1); ret |=launch_proc (argv2);
app/test/test_pdump.c +1 -1
@@ -184,7 +184,7 @@ run_pdump_server_tests(void) };snprintf (coremask,sizeof (coremask),"%x" , - (1 <<rte_get_master_lcore ())); + (1 <<rte_get_initial_lcore ())); ret =test_pdump_init (); ret |=launch_p (argv1);
app/test/test_per_lcore.c +7 -7
@@ -73,31 +73,31 @@ test_per_lcore(void)unsigned lcore_id;int ret; -rte_eal_mp_remote_launch (assign_vars,NULL ,SKIP_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (assign_vars,NULL ,SKIP_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; } -rte_eal_mp_remote_launch (display_vars,NULL ,SKIP_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (display_vars,NULL ,SKIP_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }/* test if it could do remote launch twice at the same time or not */ - ret =rte_eal_mp_remote_launch (test_per_lcore_delay,NULL ,SKIP_MASTER ); + ret =rte_eal_mp_remote_launch (test_per_lcore_delay,NULL ,SKIP_INITIAL );if (ret <0 ) {printf ("It fails to do remote launch but it should able to do\n" );return -1 ; }/* it should not be able to launch a lcore which is running */ - ret =rte_eal_mp_remote_launch (test_per_lcore_delay,NULL ,SKIP_MASTER ); + ret =rte_eal_mp_remote_launch (test_per_lcore_delay,NULL ,SKIP_INITIAL );if (ret ==0 ) {printf ("It does remote launch successfully but it should not at this time\n" );return -1 ; } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
app/test/test_pmd_perf.c +10 -10
@@ -278,7 +278,7 @@ alloc_lcore(uint16_t socketid)for (lcore_id =0 ; lcore_id <RTE_MAX_LCORE ; lcore_id++) {if (LCORE_AVAIL != lcore_conf[lcore_id].status || lcore_conf[lcore_id].socketid != socketid || - lcore_id ==rte_get_master_lcore ()) + lcore_id ==rte_get_initial_lcore ())continue ; lcore_conf[lcore_id].status =LCORE_USED ; lcore_conf[lcore_id].nb_ports =0 ;
@@ -664,7 +664,7 @@ exec_burst(uint32_t flags, int lcore)static int test_pmd_perf (void ) { -uint16_t nb_ports, num, nb_lcores, slave_id = (uint16_t )-1 ; +uint16_t nb_ports, num, nb_lcores, worker_id = (uint16_t )-1 ;uint16_t nb_rxd =MAX_TRAFFIC_BURST ;uint16_t nb_txd =MAX_TRAFFIC_BURST ;uint16_t portid;
@@ -702,13 +702,13 @@ test_pmd_perf(void)RTE_ETH_FOREACH_DEV (portid) {if (socketid ==-1 ) { socketid =rte_eth_dev_socket_id (portid); - slave_id =alloc_lcore (socketid); -if (slave_id == (uint16_t )-1 ) { + worker_id =alloc_lcore (socketid); +if (worker_id == (uint16_t )-1 ) {printf ("No avail lcore to run test\n" );return -1 ; }printf ("Performance test runs on lcore %u socket %u\n" , - slave_id, socketid); + worker_id, socketid); }if (socketid !=rte_eth_dev_socket_id (portid)) {
@@ -765,8 +765,8 @@ test_pmd_perf(void)"rte_eth_promiscuous_enable: err=%s, port=%d\n" , rte_strerror(-ret), portid); - lcore_conf[slave_id].portlist[num++] = portid; - lcore_conf[slave_id].nb_ports++; + lcore_conf[worker_id].portlist[num++] = portid; + lcore_conf[worker_id].nb_ports++; }check_all_ports_link_status (nb_ports,RTE_PORT_ALL );
@@ -791,13 +791,13 @@ test_pmd_perf(void)if (NULL == do_measure) do_measure = measure_rxtx; -rte_eal_remote_launch (main_loop,NULL , slave_id); +rte_eal_remote_launch (main_loop,NULL , worker_id); -if (rte_eal_wait_lcore (slave_id) <0 ) +if (rte_eal_wait_lcore (worker_id) <0 )return -1 ; }else if (sc_flag ==SC_BURST_POLL_FIRST || sc_flag ==SC_BURST_XMIT_FIRST ) -if (exec_burst (sc_flag, slave_id) <0 ) +if (exec_burst (sc_flag, worker_id) <0 )return -1 ;/* port tear down */
app/test/test_rcu_qsbr.c +1 -1
@@ -1327,7 +1327,7 @@ test_rcu_qsbr_main(void) } num_cores =0 ; -RTE_LCORE_FOREACH_SLAVE (core_id) { +RTE_LCORE_FOREACH_WORKER (core_id) { enabled_core_ids[num_cores] = core_id; num_cores++; }
app/test/test_rcu_qsbr_perf.c +1 -1
@@ -625,7 +625,7 @@ test_rcu_qsbr_main(void)rte_atomic64_init (&check_cycles); num_cores =0 ; -RTE_LCORE_FOREACH_SLAVE (core_id) { +RTE_LCORE_FOREACH_WORKER (core_id) { enabled_core_ids[num_cores] = core_id; num_cores++; }
app/test/test_ring_perf.c +7 -7
@@ -297,7 +297,7 @@ run_on_core_pair(struct lcore_pair *cores, struct rte_ring *r, const int esize) lcore_count =0 ; param1.size = param2.size = bulk_sizes[i]; param1.r = param2.r = r; -if (cores->c1 ==rte_get_master_lcore ()) { +if (cores->c1 ==rte_get_initial_lcore ()) {rte_eal_remote_launch (f2, ¶m2, cores->c2);f1 (¶m1);rte_eal_wait_lcore (cores->c2);
@@ -340,8 +340,8 @@ load_loop_fn_helper(struct thread_params *p, const int esize)if (burst ==NULL )return -1 ; -/* wait synchro for slaves */ -if (lcore !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 )rte_pause ();
@@ -396,12 +396,12 @@ run_on_all_cores(struct rte_ring *r, const int esize) param.size = bulk_sizes[i]; param.r = r; -/* clear synchro and start slaves */ +/* clear synchro and start workers */ rte_atomic32_set (&synchro,0 ); -if (rte_eal_mp_remote_launch (lcore_f, ¶m,SKIP_MASTER ) <0 ) +if (rte_eal_mp_remote_launch (lcore_f, ¶m,SKIP_INITIAL ) <0 )return -1 ; -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );lcore_f (¶m);
@@ -552,7 +552,7 @@ test_ring_perf_esize(const int esize) goto test_fail; } -printf ("\n### Testing using all slave nodes ###\n" ); +printf ("\n### Testing using all worker nodes ###\n" );if (run_on_all_cores (r, esize) <0 ) goto test_fail;
app/test/test_ring_stress_impl.h +5 -5
@@ -6,7 +6,7 @@/** * Stress test for ring enqueue/dequeue operations. -* Performs the following pattern on each slave worker: +* Performs the following pattern on each worker worker: * dequeue/read-write data from the dequeued objects/enqueue. * Serves as both functional and performance test of ring * enqueue/dequeue operations under high contention
@@ -348,8 +348,8 @@ test_mt1(int (*test)(void *))memset (arg,0 ,sizeof (arg)); -/* launch on all slaves */ -RTE_LCORE_FOREACH_SLAVE (lc) { +/* launch on all workers */ +RTE_LCORE_FOREACH_WORKER (lc) { arg[lc].rng = r; arg[lc].stats = init_stat;rte_eal_remote_launch (test, &arg[lc], lc);
@@ -365,12 +365,12 @@ test_mt1(int (*test)(void *)) wrk_cmd =WRK_CMD_STOP ;rte_smp_wmb (); -/* wait for slaves and collect stats. */ +/* wait for workers and collect stats. */ mc =rte_lcore_id (); arg[mc].stats = init_stat; rc =0 ; -RTE_LCORE_FOREACH_SLAVE (lc) { +RTE_LCORE_FOREACH_WORKER (lc) { rc |=rte_eal_wait_lcore (lc);lcore_stat_aggr (&arg[mc].stats, &arg[lc].stats);if (verbose !=0 )
app/test/test_rwlock.c +14 -14
@@ -99,8 +99,8 @@ load_loop_fn(__rte_unused void *arg)uint64_t lcount =0 ;const unsigned int lcore =rte_lcore_id (); -/* wait synchro for slaves */ -if (lcore !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 ) ;
@@ -134,12 +134,12 @@ test_rwlock_perf(void)printf ("\nRwlock Perf Test on %u cores...\n" ,rte_lcore_count ()); -/* clear synchro and start slaves */ +/* clear synchro and start workers */ rte_atomic32_set (&synchro,0 ); -if (rte_eal_mp_remote_launch (load_loop_fn,NULL ,SKIP_MASTER ) <0 ) +if (rte_eal_mp_remote_launch (load_loop_fn,NULL ,SKIP_INITIAL ) <0 )return -1 ; -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );load_loop_fn (NULL );
@@ -161,7 +161,7 @@ test_rwlock_perf(void)* - There is a global rwlock and a table of rwlocks (one per lcore). * * - The test function takes all of these locks and launches the -* ``test_rwlock_per_core()`` function on each core (except the master). +* ``test_rwlock_per_core()`` function on each core (except the initial). * * - The function takes the global write lock, display something, * then releases the global lock.
@@ -187,21 +187,21 @@ rwlock_test1(void)rte_rwlock_write_lock (&sl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_rwlock_write_lock (&sl_tab[i]);rte_eal_remote_launch (test_rwlock_per_core,NULL , i); }rte_rwlock_write_unlock (&sl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_rwlock_write_unlock (&sl_tab[i]);rte_delay_ms (100 ); }rte_rwlock_write_lock (&sl);/* this message should be the last message of test */ -printf ("Global write lock taken on master core %u\n" ,rte_lcore_id ()); +printf ("Global write lock taken on initial core %u\n" ,rte_lcore_id ());rte_rwlock_write_unlock (&sl);rte_eal_mp_wait_lcore ();
@@ -462,26 +462,26 @@ try_rwlock_test_rda(void)try_test_reset ();/* start read test on all avaialble lcores */ -rte_eal_mp_remote_launch (try_read_lcore,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (try_read_lcore,NULL ,CALL_INITIAL );rte_eal_mp_wait_lcore ();return process_try_lcore_stats (); } -/* all slave lcores grab RDLOCK, master one grabs WRLOCK */ +/* all worker lcores grab RDLOCK, initial one grabs WRLOCK */ static int try_rwlock_test_rds_wrm (void ) {try_test_reset (); -rte_eal_mp_remote_launch (try_read_lcore,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (try_read_lcore,NULL ,SKIP_INITIAL );try_write_lcore (NULL );rte_eal_mp_wait_lcore ();return process_try_lcore_stats (); } -/* master and even slave lcores grab RDLOCK, odd lcores grab WRLOCK */ +/* initial and even worker lcores grab RDLOCK, odd lcores grab WRLOCK */ static int try_rwlock_test_rde_wro (void ) {
@@ -489,7 +489,7 @@ try_rwlock_test_rde_wro(void)try_test_reset (); - mlc =rte_get_master_lcore (); + mlc =rte_get_initial_lcore ();RTE_LCORE_FOREACH (lc) {if (lc != mlc) {
app/test/test_service_cores.c +5 -5
@@ -30,7 +30,7 @@ static inttestsuite_setup (void) { slcore_id =rte_get_next_lcore (/* start core */ -1 , -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );return TEST_SUCCESS ;
@@ -532,12 +532,12 @@ service_lcore_add_del(void)TEST_ASSERT_EQUAL (1 ,rte_service_lcore_count (),"Service core count not equal to one" );uint32_t slcore_1 =rte_get_next_lcore (/* start core */ -1 , -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );TEST_ASSERT_EQUAL (0 ,rte_service_lcore_add (slcore_1),"Service core add did not return zero" );uint32_t slcore_2 =rte_get_next_lcore (/* start core */ slcore_1, -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );TEST_ASSERT_EQUAL (0 ,rte_service_lcore_add (slcore_2),"Service core add did not return zero" );
@@ -583,12 +583,12 @@ service_threaded_test(int mt_safe)/* add next 2 cores */ uint32_t slcore_1 =rte_get_next_lcore (/* start core */ -1 , -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );TEST_ASSERT_EQUAL (0 ,rte_service_lcore_add (slcore_1),"mt safe lcore add fail" );uint32_t slcore_2 =rte_get_next_lcore (/* start core */ slcore_1, -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );TEST_ASSERT_EQUAL (0 ,rte_service_lcore_add (slcore_2),"mt safe lcore add fail" );
app/test/test_spinlock.c +17 -17
@@ -28,7 +28,7 @@* - There is a global spinlock and a table of spinlocks (one per lcore). * * - The test function takes all of these locks and launches the -* ``test_spinlock_per_core()`` function on each core (except the master). +* ``test_spinlock_per_core()`` function on each core (except the initial). * * - The function takes the global lock, display something, then releases * the global lock.
@@ -109,8 +109,8 @@ load_loop_fn(void *func_param)const int use_lock = *(int *)func_param;const unsigned lcore =rte_lcore_id (); -/* wait synchro for slaves */ -if (lcore !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 ); begin =rte_get_timer_cycles ();
@@ -149,11 +149,11 @@ test_spinlock_perf(void)printf ("\nTest with lock on %u cores...\n" ,rte_lcore_count ()); -/* Clear synchro and start slaves */ +/* Clear synchro and start workers */ rte_atomic32_set (&synchro,0 ); -rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_MASTER ); +rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_INITIAL ); -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );load_loop_fn (&lock);
@@ -200,8 +200,8 @@ test_spinlock(void)int ret =0 ;int i; -/* slave cores should be waiting: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be waiting: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }
@@ -214,19 +214,19 @@ test_spinlock(void)rte_spinlock_lock (&sl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_spinlock_lock (&sl_tab[i]);rte_eal_remote_launch (test_spinlock_per_core,NULL , i); } -/* slave cores should be busy: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be busy: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }rte_spinlock_unlock (&sl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_spinlock_unlock (&sl_tab[i]);rte_delay_ms (10 ); }
@@ -245,7 +245,7 @@ test_spinlock(void) }else rte_spinlock_recursive_unlock (&slr); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_spinlock_recursive_per_core,NULL , i); }rte_spinlock_recursive_unlock (&slr);
@@ -253,12 +253,12 @@ test_spinlock(void)/* * Test if it could return immediately from try-locking a locked object. -* Here it will lock the spinlock object first, then launch all the slave +* Here it will lock the spinlock object first, then launch all the worker * lcores to trylock the same spinlock object. -* All the slave lcores should give up try-locking a locked object and +* All the worker lcores should give up try-locking a locked object and * return immediately, and then increase the "count" initialized with zero * by one per times. -* We can check if the "count" is finally equal to the number of all slave +* We can check if the "count" is finally equal to the number of all worker * lcores to see if the behavior of try-locking a locked spinlock object * is correct. */
@@ -266,7 +266,7 @@ test_spinlock(void)return -1 ; } count =0 ; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_spinlock_try,NULL , i); }rte_eal_mp_wait_lcore ();
app/test/test_stack.c +1 -1
@@ -362,7 +362,7 @@ test_stack_multithreaded(uint32_t flags)rte_atomic64_init (&size); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { args[lcore_id].s = s; args[lcore_id].sz = &size;
app/test/test_stack_perf.c +3 -3
@@ -180,7 +180,7 @@ run_on_core_pair(struct lcore_pair *cores, struct rte_stack *s, args[0 ].sz = args[1 ].sz = bulk_sizes[i]; args[0 ].s = args[1 ].s = s; -if (cores->c1 ==rte_get_master_lcore ()) { +if (cores->c1 ==rte_get_initial_lcore ()) {rte_eal_remote_launch (fn, &args[1 ], cores->c2);fn (&args[0 ]);rte_eal_wait_lcore (cores->c2);
@@ -210,7 +210,7 @@ run_on_n_cores(struct rte_stack *s, lcore_function_t fn, int n)rte_atomic32_set (&lcore_barrier, n); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (++cnt >= n)break ;
@@ -235,7 +235,7 @@ run_on_n_cores(struct rte_stack *s, lcore_function_t fn, int n) avg = args[rte_lcore_id ()].avg; cnt =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (++cnt >= n)break ; avg += args[lcore_id].avg;
app/test/test_ticketlock.c +18 -18
@@ -28,7 +28,7 @@* - There is a global ticketlock and a table of ticketlocks (one per lcore). * * - The test function takes all of these locks and launches the -* ``test_ticketlock_per_core()`` function on each core (except the master). +* ``test_ticketlock_per_core()`` function on each core (except the initial). * * - The function takes the global lock, display something, then releases * the global lock.
@@ -110,8 +110,8 @@ load_loop_fn(void *func_param)const int use_lock = *(int *)func_param;const unsigned int lcore =rte_lcore_id (); -/* wait synchro for slaves */ -if (lcore !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 ) ;
@@ -154,11 +154,11 @@ test_ticketlock_perf(void) lcount =0 ;printf ("\nTest with lock on %u cores...\n" ,rte_lcore_count ()); -/* Clear synchro and start slaves */ +/* Clear synchro and start workers */ rte_atomic32_set (&synchro,0 ); -rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_MASTER ); +rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_INITIAL ); -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );load_loop_fn (&lock);
@@ -208,8 +208,8 @@ test_ticketlock(void)int ret =0 ;int i; -/* slave cores should be waiting: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be waiting: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }
@@ -217,25 +217,25 @@ test_ticketlock(void)rte_ticketlock_init (&tl);rte_ticketlock_init (&tl_try);rte_ticketlock_recursive_init (&tlr); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_ticketlock_init (&tl_tab[i]); }rte_ticketlock_lock (&tl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_ticketlock_lock (&tl_tab[i]);rte_eal_remote_launch (test_ticketlock_per_core,NULL , i); } -/* slave cores should be busy: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be busy: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }rte_ticketlock_unlock (&tl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_ticketlock_unlock (&tl_tab[i]);rte_delay_ms (10 ); }
@@ -254,7 +254,7 @@ test_ticketlock(void) }else rte_ticketlock_recursive_unlock (&tlr); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_ticketlock_recursive_per_core,NULL , i); }
@@ -264,19 +264,19 @@ test_ticketlock(void)/* * Test if it could return immediately from try-locking a locked object. * Here it will lock the ticketlock object first, then launch all the -* slave lcores to trylock the same ticketlock object. -* All the slave lcores should give up try-locking a locked object and +* worker lcores to trylock the same ticketlock object. +* All the worker lcores should give up try-locking a locked object and * return immediately, and then increase the "count" initialized with * zero by one per times. * We can check if the "count" is finally equal to the number of all -* slave lcores to see if the behavior of try-locking a locked +* worker lcores to see if the behavior of try-locking a locked * ticketlock object is correct. */ if (rte_ticketlock_trylock (&tl_try) ==0 )return -1 ; count =0 ; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_ticketlock_try,NULL , i); }rte_eal_mp_wait_lcore ();
app/test/test_timer.c +53 -53
285 lines not on this page · raw message
app/test/test_timer_racecond.c +14 -13
@@ -56,8 +56,8 @@static struct rte_timer timer[N_TIMERS ];static unsigned timer_lcore_id[N_TIMERS ]; -static unsigned master; -static volatile unsigned stop_slaves; +static unsigned int initial_lcore; +static volatile unsigned stop_workers;static int reload_timer (struct rte_timer *tim);
@@ -95,7 +95,8 @@ reload_timer(struct rte_timer *tim) (tim - timer);int ret; - ret =rte_timer_reset (tim, ticks,PERIODICAL , master, timer_cb,NULL ); + ret =rte_timer_reset (tim, ticks,PERIODICAL , + initial_lcore, timer_cb,NULL );if (ret !=0 ) { rte_log(RTE_LOG_DEBUG, timer_logtype_test, "- core %u failed to reset timer %" PRIuPTR " (OK)\n",
@@ -106,7 +107,7 @@ reload_timer(struct rte_timer *tim) }static int -slave_main_loop(__rte_unused void *arg) +worker_main_loop(__rte_unused void *arg) {unsigned lcore_id =rte_lcore_id ();unsigned i;
@@ -115,7 +116,7 @@ slave_main_loop(__rte_unused void *arg)printf ("Starting main loop on core %u\n" , lcore_id); -while (!stop_slaves) { +while (!stop_workers) {/* Wait until the timer manager is running. * We know it's running when we see timer[0] NOT pending. */
@@ -152,7 +153,7 @@ test_timer_racecond(void)unsigned lcore_id;unsigned i; - master = lcore_id =rte_lcore_id (); + initial_lcore = lcore_id =rte_lcore_id (); hz =rte_get_timer_hz ();/* init and start timers */
@@ -161,8 +162,8 @@ test_timer_racecond(void) ret =reload_timer (&timer[i]);TEST_ASSERT (ret ==0 ,"reload_timer failed" ); -/* Distribute timers to slaves. -* Note that we assign timer[0] to the master. +/* Distribute timers to workers. +* Note that we assign timer[0] to the inital lcore. */ timer_lcore_id[i] = lcore_id; lcore_id =rte_get_next_lcore (lcore_id,1 ,1 );
@@ -172,11 +173,11 @@ test_timer_racecond(void) cur_time =rte_get_timer_cycles (); end_time = cur_time + (hz *TEST_DURATION_S ); -/* start slave cores */ - stop_slaves =0 ; +/* start worker cores */ + stop_workers =0 ;printf ("Start timer manage race condition test (%u seconds)\n" ,TEST_DURATION_S ); -rte_eal_mp_remote_launch (slave_main_loop,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (worker_main_loop,NULL ,SKIP_INITIAL );while (diff >=0 ) {/* run the timers */
@@ -189,9 +190,9 @@ test_timer_racecond(void) diff = end_time - cur_time; } -/* stop slave cores */ +/* stop worker cores */ printf ("Stopping timer manage race condition test\n" ); - stop_slaves =1 ; + stop_workers =1 ;rte_eal_mp_wait_lcore ();/* stop timers */
app/test/test_timer_secondary.c +1 -1
@@ -141,7 +141,7 @@ test_timer_secondary(void)unsigned int *mgr_lcorep = &test_info->mgr_lcore;unsigned int *sec_lcorep = &test_info->sec_lcore; - *mstr_lcorep =rte_get_master_lcore (); + *mstr_lcorep =rte_get_initial_lcore (); *mgr_lcorep =rte_get_next_lcore (*mstr_lcorep,1 ,1 ); *sec_lcorep =rte_get_next_lcore (*mgr_lcorep,1 ,1 );
app/test/test_trace_perf.c +2 -2
@@ -132,7 +132,7 @@ run_test(const char *str, lcore_function_t f, struct test_data *data, size_t sz)memset (data,0 , sz); data->nb_workers =rte_lcore_count () -1 ; -RTE_LCORE_FOREACH_SLAVE (id) +RTE_LCORE_FOREACH_WORKER (id) rte_eal_remote_launch(f, &data->ldata[worker++], id);wait_till_workers_are_ready (data);
@@ -140,7 +140,7 @@ run_test(const char *str, lcore_function_t f, struct test_data *data, size_t sz)measure_perf (str, data);signal_workers_to_finish (data); -RTE_LCORE_FOREACH_SLAVE (id) +RTE_LCORE_FOREACH_WORKER (id)rte_eal_wait_lcore (id); }
Signature · 1 line
2.26.2
RFC v2 21/26 doc: fix incorrect reference to master process
In reply to Stephen HemmingerCorrect terminolgy here is primary process.
This is a bug in original doc.
--- doc/guides/prog_guide/thread_safety_dpdk_functions.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
doc/guides/prog_guide/thread_safety_dpdk_functions.rst +2 -2
@@ -61,8 +61,8 @@ rather than subsequently in the forwarding threads. However, the DPDK performs checks to ensure that libraries are only initialized once. If initialization is attempted more than once, an error is returned. -In the multi-process case, the configuration information of shared memory will only be initialized by the master process. -Thereafter, both master and secondary processes can allocate/release any objects of memory that finally rely on rte_malloc or memzones. +In the multi-process case, the configuration information of shared memory will only be initialized by the primary process. +Thereafter, both primary and secondary processes can allocate/release any objects of memory that finally rely on rte_malloc or memzones. Interrupt Thread ----------------
Signature · 1 line
2.26.2
RFC v2 22/26 doc: update references to master/slave lcore in samples
In reply to Stephen HemmingerNew terms are initial and worker lcores.
--- doc/guides/sample_app_ug/hello_world.rst | 2 +- doc/guides/sample_app_ug/ioat.rst | 2 +- doc/guides/sample_app_ug/l3_forward_graph.rst | 6 +++--- doc/guides/sample_app_ug/multi_process.rst | 4 ++-- doc/guides/sample_app_ug/performance_thread.rst | 2 +- doc/guides/sample_app_ug/qos_scheduler.rst | 2 +- doc/guides/sample_app_ug/timer.rst | 4 ++-- 7 files changed, 11 insertions(+), 11 deletions(-)
doc/guides/sample_app_ug/hello_world.rst +1 -1
@@ -75,7 +75,7 @@ The code that launches the function on each lcore is as follows: .. code-block:: c - /* call lcore_hello() on every slave lcore */ + /* call lcore_hello() on every worker lcore */ RTE_LCORE_FOREACH_SLAVE(lcore_id) { rte_eal_remote_launch(lcore_hello, NULL, lcore_id);
doc/guides/sample_app_ug/ioat.rst +1 -1
@@ -208,7 +208,7 @@ After that each port application assigns resources needed. cfg.nb_lcores = rte_lcore_count() - 1; if (cfg.nb_lcores < 1) rte_exit(EXIT_FAILURE, - "There should be at least one slave lcore.\n"); + "There should be at least one worker lcore.\n"); ret = 0;
doc/guides/sample_app_ug/l3_forward_graph.rst +3 -3
@@ -22,7 +22,7 @@ Run-time path is main thing that differs from L3 forwarding sample application. Difference is that forwarding logic starting from Rx, followed by LPM lookup, TTL update and finally Tx is implemented inside graph nodes. These nodes are interconnected in graph framework. Application main loop needs to walk over -graph using ``rte_graph_walk()`` with graph objects created one per slave lcore. +graph using ``rte_graph_walk()`` with graph objects created one per worker lcore. The lookup method is as per implementation of ``ip4_lookup`` graph node. The ID of the output interface for the input packet is the next hop returned by
@@ -265,7 +265,7 @@ headers will be provided run-time using ``rte_node_ip4_route_add()`` and Since currently ``ip4_lookup`` and ``ip4_rewrite`` nodes don't support lock-less mechanisms(RCU, etc) to add run-time forwarding data like route and rewrite data, forwarding data is added before packet processing loop is - launched on slave lcore. + launched on worker lcore. .. code-block:: c
@@ -297,7 +297,7 @@ Packet Forwarding using Graph Walk ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Now that all the device configurations are done, graph creations are done and -forwarding data is updated with nodes, slave lcores will be launched with graph +forwarding data is updated with nodes, worker lcores will be launched with graph main loop. Graph main loop is very simple in the sense that it needs to continuously call a non-blocking API ``rte_graph_walk()`` with it's lcore specific graph object that was already created.
doc/guides/sample_app_ug/multi_process.rst +2 -2
@@ -66,7 +66,7 @@ The process should start successfully and display a command prompt as follows: EAL: check igb_uio module EAL: check module finished - EAL: Master core 0 is ready (tid=54e41820) + EAL: Initial core 0 is ready (tid=54e41820) EAL: Core 1 is ready (tid=53b32700) Starting core 1
@@ -92,7 +92,7 @@ At any stage, either process can be terminated using the quit command. .. code-block:: console - EAL: Master core 10 is ready (tid=b5f89820) EAL: Master core 8 is ready (tid=864a3820) + EAL: Initial core 10 is ready (tid=b5f89820) EAL: Master core 8 is ready (tid=864a3820) EAL: Core 11 is ready (tid=84ffe700) EAL: Core 9 is ready (tid=85995700) Starting core 11 Starting core 9 simple_mp > send hello_secondary simple_mp > core 9: Received 'hello_secondary'
doc/guides/sample_app_ug/performance_thread.rst +1 -1
@@ -1217,5 +1217,5 @@ Setting ``LTHREAD_DIAG`` also enables counting of statistics about cache and queue usage, and these statistics can be displayed by calling the function ``lthread_diag_stats_display()``. This function also performs a consistency check on the caches and queues. The function should only be called from the -master EAL thread after all slave threads have stopped and returned to the C +master EAL thread after all worker threads have stopped and returned to the C main program, otherwise the consistency check will fail.
doc/guides/sample_app_ug/qos_scheduler.rst +1 -1
@@ -71,7 +71,7 @@ Optional application parameters include: In this mode, the application shows a command line that can be used for obtaining statistics while scheduling is taking place (see interactive mode below for more information). -* --mst n: Master core index (the default value is 1). +* --mst n: Initial core index (the default value is 1). * --rsz "A, B, C": Ring sizes:
doc/guides/sample_app_ug/timer.rst +2 -2
@@ -49,11 +49,11 @@ In addition to EAL initialization, the timer subsystem must be initialized, by c rte_timer_subsystem_init(); After timer creation (see the next paragraph), -the main loop is executed on each slave lcore using the well-known rte_eal_remote_launch() and also on the master. +the main loop is executed on each worker lcore using the well-known rte_eal_remote_launch() and also on the master. .. code-block:: c - /* call lcore_mainloop() on every slave lcore */ + /* call lcore_mainloop() on every worker lcore */ RTE_LCORE_FOREACH_SLAVE(lcore_id) { rte_eal_remote_launch(lcore_mainloop, NULL, lcore_id);
Signature · 1 line
2.26.2
RFC v2 23/26 doc: replace master lcore terminology
In reply to Stephen HemmingerA few places in documentation refer to master lcore
--- doc/guides/howto/debug_troubleshoot.rst | 2 +- doc/guides/linux_gsg/eal_args.include.rst | 4 ++-- doc/guides/nics/bnxt.rst | 2 +- doc/guides/sample_app_ug/hello_world.rst | 2 +- doc/guides/sample_app_ug/timer.rst | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-)
doc/guides/howto/debug_troubleshoot.rst +1 -1
@@ -311,7 +311,7 @@ Custom worker function :numref:`dtg_distributor_worker`. SERVICE. Check performance functions are mapped to run on the cores. * For high-performance execution logic ensure running it on correct NUMA - and non-master core. + and worker core. * Analyze run logic with ``rte_dump_stack``, ``rte_dump_registers`` and ``rte_memdump`` for more insights.
doc/guides/linux_gsg/eal_args.include.rst +2 -2
@@ -33,9 +33,9 @@ Lcore-related options At a given instance only one core option ``--lcores``, ``-l`` or ``-c`` can be used. -* ``--master-lcore <core ID>`` +* ``--initial-lcore <core ID>`` - Core ID that is used as master. + Core ID that is used as initial lcore. * ``-s <service core mask>``
doc/guides/nics/bnxt.rst +1 -1
@@ -403,7 +403,7 @@ The application enables multiple TX and RX queues when it is started. .. code-block:: console - testpmd -l 1,3,5 --master-lcore 1 --txq=2 –rxq=2 --nb-cores=2 + testpmd -l 1,3,5 --initial-lcore 1 --txq=2 –rxq=2 --nb-cores=2 **TSS**
doc/guides/sample_app_ug/hello_world.rst +1 -1
@@ -77,7 +77,7 @@ The code that launches the function on each lcore is as follows: /* call lcore_hello() on every worker lcore */ - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + RTE_LCORE_FOREACH_WORKER(lcore_id) { rte_eal_remote_launch(lcore_hello, NULL, lcore_id); }
doc/guides/sample_app_ug/timer.rst +1 -1
@@ -55,7 +55,7 @@ the main loop is executed on each worker lcore using the well-known rte_eal_remo /* call lcore_mainloop() on every worker lcore */ - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + RTE_LCORE_FOREACH_WORKER(lcore_id) { rte_eal_remote_launch(lcore_mainloop, NULL, lcore_id); }
Signature · 1 line
2.26.2
RFC v2 24/26 app/pdump: replace references to master/slave lcore
In reply to Stephen HemmingerUse initial and worker lcore instead.
--- app/pdump/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
app/pdump/main.c +1 -1
@@ -947,7 +947,7 @@ dump_packets(void)rte_exit (EXIT_FAILURE ,"failed to wait\n" ); } -/* master core */ +/* initial core */ while (!quit_signal) ; }
Signature · 1 line
2.26.2
RFC v2 25/26 app/test-XXX: replace reference to master/slave
In reply to Stephen HemmingerUse new terminology for lcore's
--- app/test-acl/main.c | 2 +- app/test-bbdev/test_bbdev_perf.c | 16 ++++++++-------- app/test-compress-perf/main.c | 8 ++++---- app/test-crypto-perf/main.c | 14 +++++++------- app/test-pipeline/main.c | 4 ++-- app/test-sad/main.c | 4 ++-- 6 files changed, 24 insertions(+), 24 deletions(-)
app/test-acl/main.c +1 -1
@@ -1085,7 +1085,7 @@ main(int argc, char **argv)if (config.trace_file !=NULL )tracef_init (); -RTE_LCORE_FOREACH_SLAVE (lcore) +RTE_LCORE_FOREACH_WORKER (lcore)rte_eal_remote_launch (search_ip5tuples, NULL, lcore);search_ip5tuples (NULL );
app/test-bbdev/test_bbdev_perf.c +8 -8
@@ -3651,14 +3651,14 @@ bler_test(struct active_device *ad,rte_atomic16_set (&op_params->sync,SYNC_WAIT ); -/* Master core is set at first entry */ +/* Initial core is set at first entry */ t_params[0 ].dev_id = ad->dev_id; t_params[0 ].lcore_id =rte_lcore_id (); t_params[0 ].op_params = op_params; t_params[0 ].queue_id = ad->queue_ids[used_cores++]; t_params[0 ].iter_count =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (used_cores >= num_lcores)break ;
@@ -3675,7 +3675,7 @@ bler_test(struct active_device *ad,rte_atomic16_set (&op_params->sync,SYNC_START ); ret =bler_function (&t_params[0 ]); -/* Master core is always used */ +/* Initial core is always used */ for (used_cores =1 ; used_cores < num_lcores; used_cores++) ret |=rte_eal_wait_lcore (t_params[used_cores].lcore_id);
@@ -3769,14 +3769,14 @@ throughput_test(struct active_device *ad,rte_atomic16_set (&op_params->sync,SYNC_WAIT ); -/* Master core is set at first entry */ +/* Initial core is set at first entry */ t_params[0 ].dev_id = ad->dev_id; t_params[0 ].lcore_id =rte_lcore_id (); t_params[0 ].op_params = op_params; t_params[0 ].queue_id = ad->queue_ids[used_cores++]; t_params[0 ].iter_count =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (used_cores >= num_lcores)break ;
@@ -3793,7 +3793,7 @@ throughput_test(struct active_device *ad,rte_atomic16_set (&op_params->sync,SYNC_START ); ret =throughput_function (&t_params[0 ]); -/* Master core is always used */ +/* Initial core is always used */ for (used_cores =1 ; used_cores < num_lcores; used_cores++) ret |=rte_eal_wait_lcore (t_params[used_cores].lcore_id);
@@ -3817,7 +3817,7 @@ throughput_test(struct active_device *ad,/* In interrupt TC we need to wait for the interrupt callback to deqeue * all pending operations. Skip waiting for queues which reported an * error using processing_status variable. -* Wait for master lcore operations. +* Wait for initial lcore operations. */ tp = &t_params[0 ]; while ((rte_atomic16_read(&tp->nb_dequeued) <
@@ -3830,7 +3830,7 @@ throughput_test(struct active_device *ad, tp->mbps /=TEST_REPETITIONS ; ret |= (int )rte_atomic16_read (&tp->processing_status); -/* Wait for slave lcores operations */ +/* Wait for worker lcores operations */ for (used_cores =1 ; used_cores < num_lcores; used_cores++) { tp = &t_params[used_cores];
app/test-compress-perf/main.c +4 -4
@@ -389,7 +389,7 @@ main(int argc, char **argv) i =0 ;uint8_t qp_id =0 , cdev_index =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -413,7 +413,7 @@ main(int argc, char **argv)while (test_data->level <= test_data->level_lst.max) { i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -424,7 +424,7 @@ main(int argc, char **argv) i++; } i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -449,7 +449,7 @@ main(int argc, char **argv)case ST_DURING_TEST : i =0 ; - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + RTE_LCORE_FOREACH_WORKER(lcore_id) {if (i == total_nb_qps)break ;
app/test-crypto-perf/main.c +7 -7
@@ -590,7 +590,7 @@ main(int argc, char **argv) i =0 ;uint8_t qp_id =0 , cdev_index =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -654,7 +654,7 @@ main(int argc, char **argv) distribution_total[buffer_size_count -1 ]; i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -664,7 +664,7 @@ main(int argc, char **argv) i++; } i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -684,7 +684,7 @@ main(int argc, char **argv)while (opts.test_buffer_size <= opts.max_buffer_size) { i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -694,7 +694,7 @@ main(int argc, char **argv) i++; } i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -718,7 +718,7 @@ main(int argc, char **argv) } i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -738,7 +738,7 @@ main(int argc, char **argv) err: i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
app/test-pipeline/main.c +2 -2
@@ -66,8 +66,8 @@ main(int argc, char **argv)app_init ();/* Launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (app_lcore_main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore) { +rte_eal_mp_remote_launch (app_lcore_main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore) {if (rte_eal_wait_lcore (lcore) <0 )return -1 ; }
app/test-sad/main.c +2 -2
@@ -657,11 +657,11 @@ main(int argc, char **argv)add_rules (sad,10 );if (config.parallel_lookup) -rte_eal_mp_remote_launch (lookup, sad,SKIP_MASTER ); +rte_eal_mp_remote_launch (lookup, sad,SKIP_INITIAL );lookup (sad);if (config.parallel_lookup) - RTE_LCORE_FOREACH_SLAVE(lcore_id) + RTE_LCORE_FOREACH_WORKER(lcore_id)if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ;
Signature · 1 line
2.26.2
RFC v2 26/26 eal: mark old naming as deprecated
In reply to Stephen HemmingerUse of old RTE_LCORE_FOREACH_SLAVE and rte_get_master_lcore_id() are marked as deprecated.
All uses of these in DPDK itself is gone. This will cause warnings for applications still using them.
--- lib/librte_eal/include/rte_launch.h | 4 ++-- lib/librte_eal/include/rte_lcore.h | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-)
lib/librte_eal/include/rte_launch.h +2 -2
@@ -76,8 +76,8 @@ enum rte_rmt_call_initial_t {/** * Deprecated backward compatiable definitions */ -#define SKIP_MASTER SKIP_INITIAL -#define CALL_MASTER CALL_INITIAL +#define SKIP_MASTER _Pragma("GCC warning \"'SKIP_MASTER' is deprecated\"") SKIP_INITIAL +#define CALL_MASTER _Pragma("GCC warning \"'CALL_MASTER' is deprecated\"") CALL_INITIAL/** * Launch a function on all lcores.
lib/librte_eal/include/rte_lcore.h +3 -1
@@ -67,6 +67,7 @@ unsigned int rte_get_initial_lcore(void);* @return * the id of the initial lcore */ +__rte_deprecated unsigned int rte_get_master_lcore(void);/**
@@ -216,7 +217,8 @@ unsigned int rte_get_next_lcore(unsigned int i, int skip_initial, int wrap);/** * Backward compatibility */ -#define RTE_LCORE_FOREACH_SLAVE (x) \ +#define RTE_LCORE_FOREACH_SLAVE (x) \ + _Pragma("GCC warning \"'RTE_LCORE_FOREACH_SLAVE' macro is deprecated\"") \ RTE_LCORE_FOREACH_WORKER(x)
Signature · 1 line
2.26.2
v3 cover Replace references to master and slave
In reply to Stephen HemmingerThis set of patches changes the API and conventions around referring to DPDK lcores. The first patch changes rte_get_master_lcore_id and related calls. The rest fix the DPDK to use the new naming.
Buried in the documentation set are a couple of patches where we were using incorrect naming around primary/secondary process.
This will could/should be flagged as an API policy violation since new API is jumping the queue of EXPERIMENTAL. But we can vote on the exception.
The one area left to be fixed is the bonding device.
v3
- modify vhost to replace slave with client
- modify memif to replace slave with client
- fix variable names s2m becomes i2w etc.
Stephen Hemminger (27):
eal: rename terms used for DPDK lcores
kni: fix reference to master/slave process
bbdev: rename master to initial lcore
librte_power: change reference to rte_master_lcore
drivers: replace master/slave terminolgy examples/distrutor: rename master to initial examples/bond: replace references to master lcore examples/ethtool-app: replace references to slave with worker examples/ip_pipeline: replace references to master_lcore examples/qos_{meter/sched}: replace references to master lcore examples/l3fwd: replace references to master lcore examples/l2fwd: replace references to master lcore examples/multi_process: replace references to master lcore examples/performance-thread: replace reference to master lcore examples/ptpclient: replace references to master lcore examples/ipcsec-secgw: replace references to master lcore
examples: replace reference to master lcore app/test-pmd: change references to master/slave
test-eventdev: replace references to slave with worker lcores app/test: replace refernces to master/slave
doc: fix incorrect reference to master process
doc: update references to master/slave lcore in documentation app/pdump: replace references to master/slave lcore app/test-XXX: replace reference to master/slave
eal: mark old naming as deprecated
memif: replace master/slave with server/client
vhost: rename SLAVE to CLIENT
app/pdump/main.c | 2 +- app/test-acl/main.c | 2 +- app/test-bbdev/test_bbdev_perf.c | 16 +-- app/test-compress-perf/main.c | 8 +- app/test-crypto-perf/main.c | 14 +- app/test-eventdev/evt_options.c | 2 +- app/test-eventdev/test_order_common.c | 12 +- app/test-eventdev/test_perf_common.c | 16 +-- app/test-eventdev/test_pipeline_common.c | 8 +- app/test-flow-perf/main.c | 2 +- app/test-pipeline/main.c | 4 +- app/test-pmd/config.c | 4 +- app/test-pmd/parameters.c | 2 +- app/test-pmd/softnicfwd.c | 2 +- app/test-pmd/testpmd.c | 4 +- app/test-sad/main.c | 4 +- app/test/autotest_test_funcs.py | 2 +- app/test/test.c | 2 +- app/test/test_atomic.c | 26 ++-- app/test/test_barrier.c | 2 +- app/test/test_cryptodev.c | 16 +-- app/test/test_distributor.c | 8 +- app/test/test_distributor_perf.c | 10 +- app/test/test_eal_flags.c | 32 ++--- app/test/test_efd.c | 2 +- app/test/test_efd_perf.c | 2 +- app/test/test_func_reentrancy.c | 20 +-- app/test/test_hash_multiwriter.c | 4 +- app/test/test_hash_readwrite.c | 38 +++--- app/test/test_kni.c | 16 +-- app/test/test_malloc.c | 12 +- app/test/test_mbuf.c | 36 ++--- app/test/test_mcslock.c | 28 ++-- app/test/test_mempool_perf.c | 10 +- app/test/test_mp_secondary.c | 2 +- app/test/test_pdump.c | 2 +- app/test/test_per_lcore.c | 14 +- app/test/test_pmd_perf.c | 20 +-- app/test/test_rcu_qsbr.c | 2 +- app/test/test_rcu_qsbr_perf.c | 2 +- app/test/test_ring_perf.c | 14 +- app/test/test_ring_stress_impl.h | 10 +- app/test/test_rwlock.c | 28 ++-- app/test/test_service_cores.c | 10 +- app/test/test_spinlock.c | 34 ++--- app/test/test_stack.c | 2 +- app/test/test_stack_perf.c | 6 +- app/test/test_ticketlock.c | 36 ++--- app/test/test_timer.c | 106 +++++++-------- app/test/test_timer_racecond.c | 27 ++-- app/test/test_timer_secondary.c | 2 +- app/test/test_trace_perf.c | 4 +- doc/guides/contributing/coding_style.rst | 2 +- doc/guides/faq/faq.rst | 6 +- doc/guides/howto/debug_troubleshoot.rst | 2 +- doc/guides/linux_gsg/eal_args.include.rst | 4 +- doc/guides/nics/bnxt.rst | 2 +- doc/guides/nics/fail_safe.rst | 3 - doc/guides/nics/memif.rst | 82 +++++------ .../prog_guide/env_abstraction_layer.rst | 6 +- .../prog_guide/event_ethernet_rx_adapter.rst | 2 +- doc/guides/prog_guide/glossary.rst | 8 +- .../thread_safety_dpdk_functions.rst | 4 +- doc/guides/rel_notes/release_20_08.rst | 7 +- doc/guides/sample_app_ug/bbdev_app.rst | 2 +- doc/guides/sample_app_ug/ethtool.rst | 4 +- doc/guides/sample_app_ug/hello_world.rst | 8 +- doc/guides/sample_app_ug/ioat.rst | 12 +- doc/guides/sample_app_ug/ip_pipeline.rst | 4 +- doc/guides/sample_app_ug/keep_alive.rst | 2 +- doc/guides/sample_app_ug/l2_forward_event.rst | 4 +- .../sample_app_ug/l2_forward_real_virtual.rst | 4 +- doc/guides/sample_app_ug/l3_forward_graph.rst | 6 +- .../sample_app_ug/l3_forward_power_man.rst | 2 +- doc/guides/sample_app_ug/link_status_intr.rst | 4 +- doc/guides/sample_app_ug/multi_process.rst | 6 +- doc/guides/sample_app_ug/packet_ordering.rst | 8 +- .../sample_app_ug/performance_thread.rst | 6 +- doc/guides/sample_app_ug/qos_scheduler.rst | 4 +- doc/guides/sample_app_ug/timer.rst | 13 +- doc/guides/testpmd_app_ug/run_app.rst | 2 +- doc/guides/testpmd_app_ug/testpmd_funcs.rst | 2 +- drivers/bus/dpaa/dpaa_bus.c | 2 +- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 6 +- drivers/net/bnxt/bnxt_ring.c | 4 +- drivers/net/memif/memif.h | 40 +++--- drivers/net/memif/memif_socket.c | 54 ++++---- drivers/net/memif/memif_socket.h | 5 +- drivers/net/memif/rte_eth_memif.c | 128 +++++++++--------- drivers/net/memif/rte_eth_memif.h | 20 +-- drivers/net/mvpp2/mrvl_ethdev.c | 6 +- drivers/net/qede/base/bcm_osal.c | 4 +- drivers/net/softnic/rte_eth_softnic_thread.c | 4 +- drivers/vdpa/ifc/ifcvf_vdpa.c | 4 +- drivers/vdpa/mlx5/mlx5_vdpa.c | 4 +- examples/bbdev_app/main.c | 14 +- examples/bond/main.c | 8 +- examples/distributor/main.c | 10 +- examples/ethtool/ethtool-app/main.c | 10 +- examples/eventdev_pipeline/main.c | 2 +- examples/flow_classify/flow_classify.c | 2 +- examples/helloworld/main.c | 6 +- examples/ioat/ioatfwd.c | 6 +- examples/ip_fragmentation/main.c | 4 +- examples/ip_pipeline/main.c | 2 +- examples/ip_pipeline/thread.c | 16 +-- examples/ip_reassembly/main.c | 4 +- examples/ipsec-secgw/event_helper.c | 6 +- examples/ipsec-secgw/ipsec-secgw.c | 4 +- examples/ipv4_multicast/main.c | 4 +- examples/kni/main.c | 7 +- examples/l2fwd-cat/l2fwd-cat.c | 2 +- examples/l2fwd-crypto/main.c | 8 +- examples/l2fwd-event/l2fwd_event_generic.c | 2 +- .../l2fwd-event/l2fwd_event_internal_port.c | 2 +- examples/l2fwd-event/l2fwd_poll.c | 2 +- examples/l2fwd-event/main.c | 2 +- examples/l2fwd-jobstats/main.c | 4 +- examples/l2fwd-keepalive/main.c | 6 +- examples/l2fwd/main.c | 8 +- examples/l3fwd-acl/main.c | 4 +- examples/l3fwd-graph/main.c | 14 +- examples/l3fwd-power/main.c | 20 +-- examples/l3fwd/main.c | 2 +- examples/link_status_interrupt/main.c | 8 +- .../client_server_mp/mp_server/main.c | 10 +- examples/multi_process/simple_mp/main.c | 6 +- examples/multi_process/symmetric_mp/main.c | 2 +- examples/ntb/ntb_fwd.c | 14 +- examples/packet_ordering/main.c | 22 +-- .../performance-thread/l3fwd-thread/main.c | 12 +- .../performance-thread/pthread_shim/main.c | 4 +- examples/ptpclient/ptpclient.c | 2 +- examples/qos_meter/main.c | 4 +- examples/qos_sched/args.c | 22 +-- examples/qos_sched/cmdline.c | 2 +- examples/qos_sched/main.c | 2 +- examples/rxtx_callbacks/main.c | 2 +- examples/server_node_efd/server/main.c | 10 +- examples/skeleton/basicfwd.c | 2 +- examples/tep_termination/main.c | 12 +- examples/timer/main.c | 8 +- examples/vhost/main.c | 10 +- examples/vmdq/main.c | 4 +- examples/vmdq_dcb/main.c | 6 +- lib/librte_eal/common/eal_common_launch.c | 36 ++--- lib/librte_eal/common/eal_common_lcore.c | 11 +- lib/librte_eal/common/eal_common_options.c | 62 ++++----- lib/librte_eal/common/eal_options.h | 4 +- lib/librte_eal/common/eal_private.h | 6 +- lib/librte_eal/common/eal_thread.h | 6 +- lib/librte_eal/common/rte_random.c | 2 +- lib/librte_eal/common/rte_service.c | 2 +- lib/librte_eal/freebsd/eal.c | 31 +++-- lib/librte_eal/freebsd/eal_thread.c | 34 ++--- lib/librte_eal/include/rte_eal.h | 4 +- lib/librte_eal/include/rte_eal_trace.h | 4 +- lib/librte_eal/include/rte_launch.h | 62 +++++---- lib/librte_eal/include/rte_lcore.h | 31 ++++- lib/librte_eal/linux/eal.c | 24 ++-- lib/librte_eal/linux/eal_memory.c | 10 +- lib/librte_eal/linux/eal_thread.c | 34 ++--- lib/librte_eal/rte_eal_version.map | 1 + lib/librte_eal/windows/eal.c | 18 ++- lib/librte_eal/windows/eal_thread.c | 32 ++--- lib/librte_kni/rte_kni.h | 2 +- lib/librte_power/rte_power_empty_poll.c | 2 +- lib/librte_vhost/rte_vhost.h | 16 +-- lib/librte_vhost/rte_vhost_version.map | 2 +- lib/librte_vhost/vhost.c | 4 +- lib/librte_vhost/vhost.h | 4 +- lib/librte_vhost/vhost_crypto.c | 2 +- lib/librte_vhost/vhost_user.c | 96 ++++++------- lib/librte_vhost/vhost_user.h | 24 ++-- 174 files changed, 1076 insertions(+), 1026 deletions(-)
Signature · 1 line
2.26.2
PATCH v3 1/27 eal: rename terms used for DPDK lcores
Replace the old use of master/slave lcore with more inclusive name of initial/secondary lcore. The old visible API will stay for now.
Change master2slave to new init2worker and vice-versa.
This patch breaks the expected practice for new API's. The new rte_get_initial_lcore() will not go through the standard experimental API phase; there is no functional difference from the previous name.
--- doc/guides/nics/memif.rst | 4 +- lib/librte_eal/common/eal_common_launch.c | 36 ++++++------- lib/librte_eal/common/eal_common_lcore.c | 11 ++-- lib/librte_eal/common/eal_common_options.c | 62 +++++++++++----------- lib/librte_eal/common/eal_options.h | 4 +- lib/librte_eal/common/eal_private.h | 6 +-- lib/librte_eal/common/eal_thread.h | 6 +-- lib/librte_eal/common/rte_random.c | 2 +- lib/librte_eal/common/rte_service.c | 2 +- lib/librte_eal/freebsd/eal.c | 31 +++++++---- lib/librte_eal/freebsd/eal_thread.c | 34 ++++++------ lib/librte_eal/include/rte_eal.h | 4 +- lib/librte_eal/include/rte_eal_trace.h | 4 +- lib/librte_eal/include/rte_launch.h | 62 ++++++++++++---------- lib/librte_eal/include/rte_lcore.h | 29 +++++++--- lib/librte_eal/linux/eal.c | 24 ++++----- lib/librte_eal/linux/eal_memory.c | 10 ++-- lib/librte_eal/linux/eal_thread.c | 34 ++++++------ lib/librte_eal/rte_eal_version.map | 1 + lib/librte_eal/windows/eal.c | 18 ++++--- lib/librte_eal/windows/eal_thread.c | 32 +++++------ 21 files changed, 230 insertions(+), 186 deletions(-)
doc/guides/nics/memif.rst +2 -2
@@ -106,13 +106,13 @@ region n (no-zero-copy): +-----------------------+-------------------------------------------------------------------------+ | Rings | Buffers | +-----------+-----------+-----------------+---+---------------------------------------------------+ -| S2M rings | M2S rings | packet buffer 0 | . | pb ((1 << pmd->run.log2_ring_size)*(s2m + m2s))-1 | +| S2M rings | M2S rings | packet buffer 0 | . | pb ((1 << pmd->run.log2_ring_size)*(w2i + i2w))-1 | +-----------+-----------+-----------------+---+---------------------------------------------------+ S2M OR M2S Rings: +--------+--------+-----------------------+ -| ring 0 | ring 1 | ring num_s2m_rings - 1| +| ring 0 | ring 1 | ring num_w2i_rings - 1| +--------+--------+-----------------------+ ring 0:
lib/librte_eal/common/eal_common_launch.c +18 -18
@@ -21,55 +21,55 @@* Wait until a lcore finished its job. */ int -rte_eal_wait_lcore (unsigned slave_id) +rte_eal_wait_lcore (unsigned worker_id) { -if (lcore_config[slave_id].state ==WAIT ) +if (lcore_config[worker_id].state ==WAIT )return 0 ; -while (lcore_config[slave_id].state !=WAIT && - lcore_config[slave_id].state !=FINISHED ) +while (lcore_config[worker_id].state !=WAIT && + lcore_config[worker_id].state !=FINISHED )rte_pause ();rte_rmb ();/* we are in finished state, go to wait state */ - lcore_config[slave_id].state =WAIT ; -return lcore_config[slave_id].ret; + lcore_config[worker_id].state =WAIT ; +return lcore_config[worker_id].ret; }/* -* Check that every SLAVE lcores are in WAIT state, then call -* rte_eal_remote_launch() for all of them. If call_master is true -* (set to CALL_MASTER), also call the function on the master lcore. +* Check that every WORKER lcores are in WAIT state, then call +* rte_eal_remote_launch() for all of them. If call_initial is true +* (set to CALL_INITIAL), also call the function on the initial lcore. */ int rte_eal_mp_remote_launch (int (*f)(void *),void *arg, -enum rte_rmt_call_master_t call_master) +enum rte_rmt_call_initial_t call_initial) {int lcore_id; -int master =rte_get_master_lcore (); +int initial =rte_get_initial_lcore ();/* check state of lcores */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_config[lcore_id].state !=WAIT )return -EBUSY ; }/* send messages to cores */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (f, arg, lcore_id); } -if (call_master ==CALL_MASTER ) { - lcore_config[master].ret =f (arg); - lcore_config[master].state =FINISHED ; +if (call_initial ==CALL_INITIAL ) { + lcore_config[initial].ret =f (arg); + lcore_config[initial].state =FINISHED ; }return 0 ; }/* -* Return the state of the lcore identified by slave_id. +* Return the state of the lcore identified by worker_id. */ enum rte_lcore_state_t rte_eal_get_lcore_state (unsigned lcore_id)
@@ -86,7 +86,7 @@ rte_eal_mp_wait_lcore(void) {unsigned lcore_id; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_wait_lcore (lcore_id); } }
lib/librte_eal/common/eal_common_lcore.c +8 -3
@@ -16,9 +16,14 @@#include "eal_private.h" #include "eal_thread.h" +unsigned int rte_get_initial_lcore (void ) +{ +return rte_eal_get_configuration ()->initial_lcore; +} +unsigned int rte_get_master_lcore (void ) { -return rte_eal_get_configuration ()->master_lcore; +return rte_eal_get_configuration ()->initial_lcore; }unsigned int rte_lcore_count (void )
@@ -72,7 +77,7 @@ int rte_lcore_is_enabled(unsigned int lcore_id)return cfg->lcore_role[lcore_id] ==ROLE_RTE ; } -unsigned int rte_get_next_lcore (unsigned int i,int skip_master,int wrap) +unsigned int rte_get_next_lcore (unsigned int i,int skip_initial,int wrap) { i++;if (wrap)
@@ -80,7 +85,7 @@ unsigned int rte_get_next_lcore(unsigned int i, int skip_master, int wrap)while (i <RTE_MAX_LCORE ) {if (!rte_lcore_is_enabled (i) || - (skip_master && (i ==rte_get_master_lcore ()))) { + (skip_initial && (i ==rte_get_initial_lcore ()))) { i++;if (wrap) i %=RTE_MAX_LCORE ;
lib/librte_eal/common/eal_common_options.c +31 -31
140 lines not on this page · raw message
lib/librte_eal/common/eal_options.h +2 -2
@@ -43,8 +43,8 @@ enum {OPT_TRACE_BUF_SIZE_NUM , #define OPT_TRACE_MODE "trace-mode"OPT_TRACE_MODE_NUM , -#define OPT_MASTER_LCORE "master-lcore" -OPT_MASTER_LCORE_NUM , +#define OPT_INITIAL_LCORE "initial-lcore" +OPT_INITIAL_LCORE_NUM , #define OPT_MBUF_POOL_OPS_NAME "mbuf-pool-ops-name"OPT_MBUF_POOL_OPS_NAME_NUM , #define OPT_PROC_TYPE "proc-type"
lib/librte_eal/common/eal_private.h +3 -3
@@ -20,8 +20,8 @@*/ struct lcore_config {pthread_t thread_id;/**< pthread identifier */ -int pipe_master2slave[2 ];/**< communication pipe with master */ -int pipe_slave2master[2 ];/**< communication pipe with master */ +int pipe_init2worker[2 ];/**< communication pipe with initial core */ +int pipe_worker2init[2 ];/**< communication pipe with initial core */ lcore_function_t *volatile f;/**< function to call */ void *volatile arg;/**< argument of function */
@@ -42,7 +42,7 @@ extern struct lcore_config lcore_config[RTE_MAX_LCORE];* The global RTE configuration structure. */ struct rte_config { -uint32_t master_lcore;/**< Id of the master lcore */ +uint32_t initial_lcore;/**< Id of the initial lcore */ uint32_t lcore_count;/**< Number of available logical cores. */ uint32_t numa_node_count;/**< Number of detected NUMA nodes. */ uint32_t numa_nodes[RTE_MAX_NUMA_NODES ];/**< List of detected NUMA nodes. */
lib/librte_eal/common/eal_thread.h +3 -3
@@ -16,12 +16,12 @@ __rte_noreturn void *eal_thread_loop(void *arg);/** -* Init per-lcore info for master thread +* Init per-lcore info for initial thread * * @param lcore_id -* identifier of master lcore +* identifier of initial lcore */ -void eal_thread_init_master (unsigned lcore_id); +void eal_thread_initial_lcore (unsigned lcore_id);/** * Get the NUMA socket id from cpu id.
lib/librte_eal/common/rte_random.c +1 -1
@@ -122,7 +122,7 @@ struct rte_rand_state *__rte_rand_get_state(void) lcore_id =rte_lcore_id ();if (unlikely (lcore_id ==LCORE_ID_ANY )) - lcore_id =rte_get_master_lcore (); + lcore_id =rte_get_initial_lcore ();return &rand_states[lcore_id]; }
lib/librte_eal/common/rte_service.c +1 -1
@@ -106,7 +106,7 @@ rte_service_init(void)struct rte_config *cfg =rte_eal_get_configuration ();for (i =0 ; i <RTE_MAX_LCORE ; i++) {if (lcore_config[i].core_role ==ROLE_SERVICE ) { -if ((unsigned int )i == cfg->master_lcore) +if ((unsigned int )i == cfg->initial_lcore)continue ;rte_service_lcore_add (i); count++;
lib/librte_eal/freebsd/eal.c +22 -9
@@ -622,10 +622,14 @@ eal_check_mem_on_local_socket(void)int socket_id;const struct rte_config *config =rte_eal_get_configuration (); +<<<<<<< HEAD socket_id =rte_lcore_to_socket_id (config->master_lcore); +======= + socket_id =rte_lcore_to_socket_id (rte_config.initial_lcore); +>>>>>>> 28604a3e5a3a... eal: rename terms used for DPDK lcoresif (rte_memseg_list_walk (check_socket, &socket_id) ==0 ) -RTE_LOG (WARNING ,EAL ,"WARNING: Master core has no memory on local socket!\n" ); +RTE_LOG (WARNING ,EAL ,"WARNING: Initial core has no memory on local socket!\n" ); }
@@ -845,23 +849,32 @@ rte_eal_init(int argc, char **argv)eal_check_mem_on_local_socket (); -eal_thread_init_master (config->master_lcore); +<<<<<<< HEAD + eal_thread_initial_lcore(config->master_lcore); ret =eal_thread_dump_affinity (cpuset,sizeof (cpuset));RTE_LOG (DEBUG ,EAL ,"Master lcore %u is ready (tid=%p;cpuset=[%s%s])\n" , config->master_lcore, thread_id, cpuset, +======= + eal_thread_set_initial_lcore(rte_config.initial_lcore); + + ret = eal_thread_dump_affinity(cpuset, sizeof(cpuset)); + +RTE_LOG (DEBUG ,EAL ,"Initial lcore %u is ready (tid=%p;cpuset=[%s%s])\n" , + rte_config.initial_lcore, thread_id, cpuset, +>>>>>>> 28604a3e5a3a... eal: rename terms used for DPDK lcores ret == 0 ? "" : "..."); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {/* -* create communication pipes between master thread +* create communication pipes between initial thread * and children */ -if (pipe (lcore_config[i].pipe_master2slave) <0 ) +if (pipe (lcore_config[i].pipe_init2worker) <0 )rte_panic ("Cannot create pipe\n" ); -if (pipe (lcore_config[i].pipe_slave2master) <0 ) +if (pipe (lcore_config[i].pipe_worker2init) <0 )rte_panic ("Cannot create pipe\n" ); lcore_config[i].state =WAIT ;
@@ -874,15 +887,15 @@ rte_eal_init(int argc, char **argv)/* Set thread_name for aid in debugging. */ snprintf (thread_name,sizeof (thread_name), -"lcore-slave-%d" , i); +"lcore-work-%d" , i);rte_thread_setname (lcore_config[i].thread_id, thread_name); }/* -* Launch a dummy function on all slave lcores, so that master lcore +* Launch a dummy function on all worker lcores, so that initial lcore * knows they are all ready when this function returns. */ -rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_INITIAL );rte_eal_mp_wait_lcore ();/* initialize services so vdevs register service during bus_probe. */
lib/librte_eal/freebsd/eal_thread.c +17 -17
@@ -30,35 +30,35 @@ RTE_DEFINE_PER_LCORE(unsigned, _socket_id) = (unsigned)SOCKET_ID_ANY;RTE_DEFINE_PER_LCORE (rte_cpuset_t, _cpuset);/* -* Send a message to a slave lcore identified by slave_id to call a +* Send a message to a worker lcore identified by worker_id to call a * function f with argument arg. Once the execution is done, the * remote lcore switch in FINISHED state. */ int -rte_eal_remote_launch (int (*f)(void *),void *arg,unsigned slave_id) +rte_eal_remote_launch (int (*f)(void *),void *arg,unsigned worker_id) {int n;char c =0 ; -int m2s = lcore_config[slave_id].pipe_master2slave[1 ]; -int s2m = lcore_config[slave_id].pipe_slave2master[0 ]; +int i2w = lcore_config[worker_id].pipe_init2worker[1 ]; +int w2i = lcore_config[worker_id].pipe_worker2init[0 ];int rc = -EBUSY ; -if (lcore_config[slave_id].state !=WAIT ) +if (lcore_config[worker_id].state !=WAIT ) goto finish; - lcore_config[slave_id].f = f; - lcore_config[slave_id].arg = arg; + lcore_config[worker_id].f = f; + lcore_config[worker_id].arg = arg;/* send message */ n =0 ;while (n ==0 || (n <0 && errno ==EINTR )) - n =write (m2s, &c,1 ); + n =write (i2w, &c,1 );if (n <0 )rte_panic ("cannot write on configuration pipe\n" );/* wait ack */ do { - n =read (s2m, &c,1 ); + n =read (w2i, &c,1 ); }while (n <0 && errno ==EINTR );if (n <=0 )
@@ -66,7 +66,7 @@ rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned slave_id) rc =0 ; finish: -rte_eal_trace_thread_remote_launch (f, arg, slave_id, rc); +rte_eal_trace_thread_remote_launch (f, arg, worker_id, rc);return rc; }
@@ -83,7 +83,7 @@ eal_thread_set_affinity(void)return rte_thread_set_affinity (&lcore_config[lcore_id].cpuset); } -void eal_thread_init_master (unsigned lcore_id) +void eal_thread_set_initial_lcore (unsigned lcore_id) {/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -101,21 +101,21 @@ eal_thread_loop(__rte_unused void *arg)int n, ret;unsigned lcore_id;pthread_t thread_id; -int m2s, s2m; +int i2w, w2i;char cpuset[RTE_CPU_AFFINITY_STR_LEN ]; thread_id =pthread_self ();/* retrieve our lcore_id from the configuration structure */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (thread_id == lcore_config[lcore_id].thread_id)break ; }if (lcore_id ==RTE_MAX_LCORE )rte_panic ("cannot retrieve lcore id\n" ); - m2s = lcore_config[lcore_id].pipe_master2slave[0 ]; - s2m = lcore_config[lcore_id].pipe_slave2master[1 ]; + i2w = lcore_config[lcore_id].pipe_init2worker[0 ]; + w2i = lcore_config[lcore_id].pipe_worker2init[1 ];/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -138,7 +138,7 @@ eal_thread_loop(__rte_unused void *arg)/* wait command */ do { - n =read (m2s, &c,1 ); + n =read (i2w, &c,1 ); }while (n <0 && errno ==EINTR );if (n <=0 )
@@ -149,7 +149,7 @@ eal_thread_loop(__rte_unused void *arg)/* send ack */ n =0 ;while (n ==0 || (n <0 && errno ==EINTR )) - n =write (s2m, &c,1 ); + n =write (w2i, &c,1 );if (n <0 )rte_panic ("cannot write on configuration pipe\n" );
lib/librte_eal/include/rte_eal.h +2 -2
@@ -73,11 +73,11 @@ int rte_eal_iopl_init(void);/** * Initialize the Environment Abstraction Layer (EAL). * -* This function is to be executed on the MASTER lcore only, as soon +* This function is to be executed on the initial lcore only, as soon * as possible in the application's main() function. * * The function finishes the initialization process before main() is called. -* It puts the SLAVE lcores in the WAIT state. +* It puts the worker lcores in the WAIT state. * * When the multi-partition feature is supported, depending on the * configuration (if CONFIG_RTE_EAL_MAIN_PARTITION is disabled), this
lib/librte_eal/include/rte_eal_trace.h +2 -2
@@ -210,10 +210,10 @@ RTE_TRACE_POINT(RTE_TRACE_POINT ( rte_eal_trace_thread_remote_launch, RTE_TRACE_POINT_ARGS(int (*f)(void *), void *arg, - unsigned int slave_id, int rc), + unsigned int worker_id, int rc), rte_trace_point_emit_ptr(f);rte_trace_point_emit_ptr (arg); -rte_trace_point_emit_u32 (slave_id); +rte_trace_point_emit_u32 (worker_id);rte_trace_point_emit_int (rc); ) RTE_TRACE_POINT(
lib/librte_eal/include/rte_launch.h +34 -28
139 lines not on this page · raw message
lib/librte_eal/include/rte_lcore.h +22 -7
@@ -54,10 +54,18 @@ rte_lcore_id(void) }/** -* Get the id of the master lcore +* Get the id of the initial lcore * * @return -* the id of the master lcore +* the id of the initial lcore +*/ +unsigned int rte_get_initial_lcore (void ); + +/** +* Deprecated API to get the id of the initial lcore +* +* @return +* the id of the initial lcore */ unsigned int rte_get_master_lcore (void );
@@ -179,15 +187,15 @@ int rte_lcore_is_enabled(unsigned int lcore_id);* * @param i * The current lcore (reference). -* @param skip_master -* If true, do not return the ID of the master lcore. +* @param skip_initial +* If true, do not return the ID of the initial lcore. * @param wrap * If true, go back to 0 when RTE_MAX_LCORE is reached; otherwise, * return RTE_MAX_LCORE. * @return * The next lcore_id or RTE_MAX_LCORE if not found. */ -unsigned int rte_get_next_lcore (unsigned int i,int skip_master,int wrap); +unsigned int rte_get_next_lcore (unsigned int i,int skip_initial,int wrap);/** * Macro to browse all running lcores.
@@ -198,13 +206,20 @@ unsigned int rte_get_next_lcore(unsigned int i, int skip_master, int wrap); i = rte_get_next_lcore(i, 0, 0))/** -* Macro to browse all running lcores except the master lcore. +* Macro to browse all running lcores except the initial lcore. */ -#define RTE_LCORE_FOREACH_SLAVE (i) \ +#define RTE_LCORE_FOREACH_WORKER (i) \ for (i = rte_get_next_lcore(-1, 1, 0); \ i<RTE_MAX_LCORE; \ i = rte_get_next_lcore(i, 1, 0)) +/** +* Backward compatibility +*/ +#define RTE_LCORE_FOREACH_SLAVE (x) \ + RTE_LCORE_FOREACH_WORKER(x) + +/** * Set core affinity of the current thread. * Support both EAL and non-EAL thread and update TLS.
lib/librte_eal/linux/eal.c +12 -12
@@ -855,10 +855,10 @@ eal_check_mem_on_local_socket(void)int socket_id;const struct rte_config *config =rte_eal_get_configuration (); - socket_id =rte_lcore_to_socket_id (config->master_lcore); + socket_id =rte_lcore_to_socket_id (config->initial_lcore);if (rte_memseg_list_walk (check_socket, &socket_id) ==0 ) -RTE_LOG (WARNING ,EAL ,"WARNING: Master core has no memory on local socket!\n" ); +RTE_LOG (WARNING ,EAL ,"WARNING: Initial core has no memory on local socket!\n" ); } static int
@@ -1184,23 +1184,23 @@ rte_eal_init(int argc, char **argv)eal_check_mem_on_local_socket (); -eal_thread_init_master (config->master_lcore); +eal_thread_initial_lcore (config->initial_lcore); ret =eal_thread_dump_affinity (cpuset,sizeof (cpuset)); -RTE_LOG (DEBUG ,EAL ,"Master lcore %u is ready (tid=%zx;cpuset=[%s%s])\n" , - config->master_lcore, (uintptr_t )thread_id, cpuset, +RTE_LOG (DEBUG ,EAL ,"Initial lcore %u is ready (tid=%zx;cpuset=[%s%s])\n" , + config->initial_lcore, (uintptr_t )thread_id, cpuset, ret ==0 ?"" :"..." ); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {/* -* create communication pipes between master thread +* create communication pipes between initial thread * and children */ -if (pipe (lcore_config[i].pipe_master2slave) <0 ) +if (pipe (lcore_config[i].pipe_init2worker) <0 )rte_panic ("Cannot create pipe\n" ); -if (pipe (lcore_config[i].pipe_slave2master) <0 ) +if (pipe (lcore_config[i].pipe_worker2init) <0 )rte_panic ("Cannot create pipe\n" ); lcore_config[i].state =WAIT ;
@@ -1213,7 +1213,7 @@ rte_eal_init(int argc, char **argv)/* Set thread_name for aid in debugging. */ snprintf (thread_name,sizeof (thread_name), -"lcore-slave-%d" , i); +"lcore-work-%d" , i); ret =rte_thread_setname (lcore_config[i].thread_id, thread_name);if (ret !=0 )
@@ -1222,10 +1222,10 @@ rte_eal_init(int argc, char **argv) }/* -* Launch a dummy function on all slave lcores, so that master lcore +* Launch a dummy function on all worker lcores, so that initial lcore * knows they are all ready when this function returns. */ -rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_INITIAL );rte_eal_mp_wait_lcore ();/* initialize services so vdevs register service during bus_probe. */
lib/librte_eal/linux/eal_memory.c +5 -5
@@ -1737,7 +1737,7 @@ memseg_primary_init_32(void)/* the allocation logic is a little bit convoluted, but here's how it * works, in a nutshell: * - if user hasn't specified on which sockets to allocate memory via -* --socket-mem, we allocate all of our memory on master core socket. +* --socket-mem, we allocate all of our memory on initial core socket. * - if user has specified sockets to allocate memory on, there may be * some "unused" memory left (e.g. if user has specified --socket-mem * such that not all memory adds up to 2 gigabytes), so add it to all
@@ -1751,7 +1751,7 @@ memseg_primary_init_32(void)for (i =0 ; i <rte_socket_count (); i++) {int hp_sizes = (int ) internal_conf->num_hugepage_sizes;uint64_t max_socket_mem, cur_socket_mem; -unsigned int master_lcore_socket; +unsigned int initial_lcore_socket;struct rte_config *cfg =rte_eal_get_configuration ();bool skip;
@@ -1767,10 +1767,10 @@ memseg_primary_init_32(void) skip = active_sockets !=0 && internal_conf->socket_mem[socket_id] ==0 ;/* ...or if we didn't specifically request memory on *any* -* socket, and this is not master lcore +* socket, and this is not initial lcore */ - master_lcore_socket =rte_lcore_to_socket_id (cfg->master_lcore); - skip |= active_sockets ==0 && socket_id != master_lcore_socket; + initial_lcore_socket =rte_lcore_to_socket_id (cfg->initial_lcore); + skip |= active_sockets ==0 && socket_id != initial_lcore_socket;if (skip) { RTE_LOG(DEBUG, EAL, "Will not preallocate memory on socket %u\n",
lib/librte_eal/linux/eal_thread.c +17 -17
@@ -30,35 +30,35 @@ RTE_DEFINE_PER_LCORE(unsigned, _socket_id) = (unsigned)SOCKET_ID_ANY;RTE_DEFINE_PER_LCORE (rte_cpuset_t, _cpuset);/* -* Send a message to a slave lcore identified by slave_id to call a +* Send a message to a worker lcore identified by worker_id to call a * function f with argument arg. Once the execution is done, the * remote lcore switch in FINISHED state. */ int -rte_eal_remote_launch (int (*f)(void *),void *arg,unsigned slave_id) +rte_eal_remote_launch (int (*f)(void *),void *arg,unsigned worker_id) {int n;char c =0 ; -int m2s = lcore_config[slave_id].pipe_master2slave[1 ]; -int s2m = lcore_config[slave_id].pipe_slave2master[0 ]; +int i2w = lcore_config[worker_id].pipe_init2worker[1 ]; +int w2i = lcore_config[worker_id].pipe_worker2init[0 ];int rc = -EBUSY ; -if (lcore_config[slave_id].state !=WAIT ) +if (lcore_config[worker_id].state !=WAIT ) goto finish; - lcore_config[slave_id].f = f; - lcore_config[slave_id].arg = arg; + lcore_config[worker_id].f = f; + lcore_config[worker_id].arg = arg;/* send message */ n =0 ;while (n ==0 || (n <0 && errno ==EINTR )) - n =write (m2s, &c,1 ); + n =write (i2w, &c,1 );if (n <0 )rte_panic ("cannot write on configuration pipe\n" );/* wait ack */ do { - n =read (s2m, &c,1 ); + n =read (w2i, &c,1 ); }while (n <0 && errno ==EINTR );if (n <=0 )
@@ -66,7 +66,7 @@ rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned slave_id) rc =0 ; finish: -rte_eal_trace_thread_remote_launch (f, arg, slave_id, rc); +rte_eal_trace_thread_remote_launch (f, arg, worker_id, rc);return rc; }
@@ -83,7 +83,7 @@ eal_thread_set_affinity(void)return rte_thread_set_affinity (&lcore_config[lcore_id].cpuset); } -void eal_thread_init_master (unsigned lcore_id) +void eal_thread_initial_lcore (unsigned lcore_id) {/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -101,21 +101,21 @@ eal_thread_loop(__rte_unused void *arg)int n, ret;unsigned lcore_id;pthread_t thread_id; -int m2s, s2m; +int i2w, w2i;char cpuset[RTE_CPU_AFFINITY_STR_LEN ]; thread_id =pthread_self ();/* retrieve our lcore_id from the configuration structure */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (thread_id == lcore_config[lcore_id].thread_id)break ; }if (lcore_id ==RTE_MAX_LCORE )rte_panic ("cannot retrieve lcore id\n" ); - m2s = lcore_config[lcore_id].pipe_master2slave[0 ]; - s2m = lcore_config[lcore_id].pipe_slave2master[1 ]; + i2w = lcore_config[lcore_id].pipe_init2worker[0 ]; + w2i = lcore_config[lcore_id].pipe_worker2init[1 ];/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -138,7 +138,7 @@ eal_thread_loop(__rte_unused void *arg)/* wait command */ do { - n =read (m2s, &c,1 ); + n =read (i2w, &c,1 ); }while (n <0 && errno ==EINTR );if (n <=0 )
@@ -149,7 +149,7 @@ eal_thread_loop(__rte_unused void *arg)/* send ack */ n =0 ;while (n ==0 || (n <0 && errno ==EINTR )) - n =write (s2m, &c,1 ); + n =write (w2i, &c,1 );if (n <0 )rte_panic ("cannot write on configuration pipe\n" );
lib/librte_eal/rte_eal_version.map +1 -0
@@ -79,6 +79,7 @@ DPDK_20.0 { rte_hexdump; rte_hypervisor_get; rte_hypervisor_get_name; + rte_init_lcore_id; rte_intr_allow_others; rte_intr_callback_register; rte_intr_callback_unregister;
lib/librte_eal/windows/eal.c +11 -7
@@ -273,6 +273,7 @@ rte_eal_init(int argc, char **argv)if (fctret <0 )exit (1 ); +<<<<<<< HEAD /* Prevent creation of shared memory files. */ if (internal_conf->in_memory == 0) { RTE_LOG(WARNING, EAL, "Multi-process support is requested, "
@@ -333,7 +334,7 @@ rte_eal_init(int argc, char **argv)return -1 ; } -eal_thread_init_master (config->master_lcore); +eal_thread_initial_lcore (config->master_lcore); bscan =rte_bus_scan ();if (bscan <0 ) {
@@ -341,17 +342,20 @@ rte_eal_init(int argc, char **argv) rte_errno =ENODEV ;return -1 ; } +======= +eal_thread_set_initial_lcore (rte_config.initial_lcore); +>>>>>>> 28604a3e5a3a... eal: rename terms used for DPDK lcores -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i ) {/* -* create communication pipes between master thread +* create communication pipes between initial thread * and children */ -if (_pipe (lcore_config[i].pipe_master2slave, +if (_pipe (lcore_config[i].pipe_init2worker,sizeof (char ), _O_BINARY) <0 )rte_panic ("Cannot create pipe\n" ); -if (_pipe (lcore_config[i].pipe_slave2master, +if (_pipe (lcore_config[i].pipe_worker2init,sizeof (char ), _O_BINARY) <0 )rte_panic ("Cannot create pipe\n" );
@@ -363,10 +367,10 @@ rte_eal_init(int argc, char **argv) }/* -* Launch a dummy function on all slave lcores, so that master lcore +* Launch a dummy function on all worker lcores, so that initial lcore * knows they are all ready when this function returns. */ -rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (sync_func,NULL ,SKIP_INITIAL );rte_eal_mp_wait_lcore ();return fctret; }
lib/librte_eal/windows/eal_thread.c +16 -16
@@ -21,34 +21,34 @@ RTE_DEFINE_PER_LCORE(unsigned int, _socket_id) = (unsigned int)SOCKET_ID_ANY;RTE_DEFINE_PER_LCORE (rte_cpuset_t, _cpuset);/* -* Send a message to a slave lcore identified by slave_id to call a +* Send a message to a worker lcore identified by worker_id to call a * function f with argument arg. Once the execution is done, the * remote lcore switch in FINISHED state. */ int -rte_eal_remote_launch (lcore_function_t *f,void *arg,unsigned int slave_id) +rte_eal_remote_launch (lcore_function_t *f,void *arg,unsigned int worker_id) {int n;char c =0 ; -int m2s = lcore_config[slave_id].pipe_master2slave[1 ]; -int s2m = lcore_config[slave_id].pipe_slave2master[0 ]; +int i2w = lcore_config[worker_id].pipe_init2worker[1 ]; +int w2i = lcore_config[worker_id].pipe_worker2init[0 ]; -if (lcore_config[slave_id].state !=WAIT ) +if (lcore_config[worker_id].state !=WAIT )return -EBUSY ; - lcore_config[slave_id].f = f; - lcore_config[slave_id].arg = arg; + lcore_config[worker_id].f = f; + lcore_config[worker_id].arg = arg;/* send message */ n =0 ;while (n ==0 || (n <0 && errno ==EINTR )) - n =_write (m2s, &c,1 ); + n =_write (i2w, &c,1 );if (n <0 )rte_panic ("cannot write on configuration pipe\n" );/* wait ack */ do { - n =_read (s2m, &c,1 ); + n =_read (w2i, &c,1 ); }while (n <0 && errno ==EINTR );if (n <=0 )
@@ -58,7 +58,7 @@ rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned int slave_id) }void -eal_thread_init_master (unsigned int lcore_id) +eal_thread_set_initial_lcore (unsigned int lcore_id) {/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -72,21 +72,21 @@ eal_thread_loop(void *arg __rte_unused)int n, ret;unsigned int lcore_id;pthread_t thread_id; -int m2s, s2m; +int i2w, w2i;char cpuset[RTE_CPU_AFFINITY_STR_LEN ]; thread_id =pthread_self ();/* retrieve our lcore_id from the configuration structure */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (thread_id == lcore_config[lcore_id].thread_id)break ; }if (lcore_id ==RTE_MAX_LCORE )rte_panic ("cannot retrieve lcore id\n" ); - m2s = lcore_config[lcore_id].pipe_master2slave[0 ]; - s2m = lcore_config[lcore_id].pipe_slave2master[1 ]; + i2w = lcore_config[lcore_id].pipe_init2worker[0 ]; + w2i = lcore_config[lcore_id].pipe_worker2init[1 ];/* set the lcore ID in per-lcore memory area */ RTE_PER_LCORE (_lcore_id) = lcore_id;
@@ -100,7 +100,7 @@ eal_thread_loop(void *arg __rte_unused)/* wait command */ do { - n =_read (m2s, &c,1 ); + n =_read (i2w, &c,1 ); }while (n <0 && errno ==EINTR );if (n <=0 )
@@ -111,7 +111,7 @@ eal_thread_loop(void *arg __rte_unused)/* send ack */ n =0 ;while (n ==0 || (n <0 && errno ==EINTR )) - n =_write (s2m, &c,1 ); + n =_write (w2i, &c,1 );if (n <0 )rte_panic ("cannot write on configuration pipe\n" );
Signature · 1 line
2.26.2
PATCH v3 2/27 kni: fix reference to master/slave process
In reply to Stephen HemmingerIn DPDK, the correct terms for process are primary/secondary. This is bugfix, not a change in terms for new release.
--- lib/librte_kni/rte_kni.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
lib/librte_kni/rte_kni.h +1 -1
@@ -212,7 +212,7 @@ const char *rte_kni_get_name(const struct rte_kni *kni);/** * Register KNI request handling for a specified port,and it can -* be called by master process or slave process. +* be called by primary process or secondary process. * * @param kni * pointer to struct rte_kni.
Signature · 1 line
2.26.2
PATCH v3 3/27 bbdev: rename master to initial lcore
In reply to Stephen HemmingerConform to new API.
--- examples/bbdev_app/main.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)
examples/bbdev_app/main.c +7 -7
@@ -1042,7 +1042,7 @@ main(int argc, char **argv)struct stats_lcore_params stats_lcore;struct rte_ring *enc_to_dec_ring;bool stats_thread_started = false; -unsigned int master_lcore_id =rte_get_master_lcore (); +unsigned int initial_lcore_id =rte_get_initial_lcore ();rte_atomic16_init (&global_exit_flag);
@@ -1145,9 +1145,9 @@ main(int argc, char **argv) stats_lcore.app_params = &app_params; stats_lcore.lconf = lcore_conf; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_conf[lcore_id].core_type !=0 ) -/* launch per-lcore processing loop on slave lcores */ +/* launch per-lcore processing loop on worker lcores */ rte_eal_remote_launch (processing_loop, &lcore_conf[lcore_id], lcore_id);else if (!stats_thread_started) {
@@ -1159,15 +1159,15 @@ main(int argc, char **argv) }if (!stats_thread_started && - lcore_conf[master_lcore_id].core_type !=0 ) + lcore_conf[initial_lcore_id].core_type !=0 )rte_exit (EXIT_FAILURE ,"Not enough lcores to run the statistics printing loop!" ); -else if (lcore_conf[master_lcore_id].core_type !=0 ) -processing_loop (&lcore_conf[master_lcore_id]); +else if (lcore_conf[initial_lcore_id].core_type !=0 ) +processing_loop (&lcore_conf[initial_lcore_id]);else if (!stats_thread_started)stats_loop (&stats_lcore); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { ret |=rte_eal_wait_lcore (lcore_id); }
Signature · 1 line
2.26.2
PATCH v3 4/27 librte_power: change reference to rte_master_lcore
In reply to Stephen HemmingerNew API name is rte_get_initial_lcore()
--- lib/librte_power/rte_power_empty_poll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
lib/librte_power/rte_power_empty_poll.c +1 -1
@@ -452,7 +452,7 @@ rte_power_empty_poll_stat_init(struct ep_params **eptr, uint8_t *freq_tlb,if (get_freq_index (LOW ) > total_avail_freqs[i])return -1 ; -if (rte_get_master_lcore () != i) { +if (rte_get_initial_lcore () != i) { w->wrk_stats[i].lcore_id = i;set_policy (&w->wrk_stats[i], policy); }
Signature · 1 line
2.26.2
PATCH v3 5/27 drivers: replace master/slave terminolgy
In reply to Stephen HemmingerReplace rte_get_master_lcore() with rte_get_initial_lcore(). Replace RTE_LCORE_FOREACH_SLAVE with RTE_LCORE_FOREACH_WORKER
--- drivers/bus/dpaa/dpaa_bus.c | 2 +- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 6 +++--- drivers/net/bnxt/bnxt_ring.c | 4 ++-- drivers/net/mvpp2/mrvl_ethdev.c | 6 +++--- drivers/net/qede/base/bcm_osal.c | 4 ++-- drivers/net/softnic/rte_eth_softnic_thread.c | 4 ++-- 6 files changed, 13 insertions(+), 13 deletions(-)
drivers/bus/dpaa/dpaa_bus.c +1 -1
@@ -260,7 +260,7 @@ int rte_dpaa_portal_init(void *arg)BUS_INIT_FUNC_TRACE ();if ((size_t )arg ==1 || lcore ==LCORE_ID_ANY ) - lcore =rte_get_master_lcore (); + lcore =rte_get_initial_lcore ();else if (lcore >=RTE_MAX_LCORE )return -1 ;
drivers/bus/fslmc/portal/dpaa2_hw_dpio.c +3 -3
@@ -195,7 +195,7 @@ dpaa2_configure_stashing(struct dpaa2_dpio_dev *dpio_dev, int lcoreid)/* Set the Stashing Destination */ if (lcoreid <0 ) { - lcoreid =rte_get_master_lcore (); + lcoreid =rte_get_initial_lcore ();if (lcoreid <0 ) {DPAA2_BUS_ERR ("Getting CPU Index failed" );return -1 ;
@@ -259,7 +259,7 @@ dpaa2_affine_qbman_swp(void)uint64_t tid =syscall (SYS_gettid);if (lcore_id ==LCORE_ID_ANY ) - lcore_id =rte_get_master_lcore (); + lcore_id =rte_get_initial_lcore ();/* if the core id is not supported */ else if (lcore_id >=RTE_MAX_LCORE )return -1 ;
@@ -307,7 +307,7 @@ dpaa2_affine_qbman_ethrx_swp(void)uint64_t tid =syscall (SYS_gettid);if (lcore_id ==LCORE_ID_ANY ) - lcore_id =rte_get_master_lcore (); + lcore_id =rte_get_initial_lcore ();/* if the core id is not supported */ else if (lcore_id >=RTE_MAX_LCORE )return -1 ;
drivers/net/bnxt/bnxt_ring.c +2 -2
@@ -429,7 +429,7 @@ int bnxt_alloc_rxtx_nq_ring(struct bnxt *bp)if (!BNXT_HAS_NQ (bp) || bp->rxtx_nq_ring)return 0 ; - socket_id =rte_lcore_to_socket_id (rte_get_master_lcore ()); + socket_id =rte_lcore_to_socket_id (rte_get_initial_lcore ()); nqr = rte_zmalloc_socket("nqr", sizeof(struct bnxt_cp_ring_info),
@@ -819,7 +819,7 @@ int bnxt_alloc_async_ring_struct(struct bnxt *bp)if (BNXT_NUM_ASYNC_CPR (bp) ==0 )return 0 ; - socket_id =rte_lcore_to_socket_id (rte_get_master_lcore ()); + socket_id =rte_lcore_to_socket_id (rte_get_initial_lcore ()); cpr = rte_zmalloc_socket("cpr", sizeof(struct bnxt_cp_ring_info),
drivers/net/mvpp2/mrvl_ethdev.c +3 -3
@@ -816,7 +816,7 @@ mrvl_flush_bpool(struct rte_eth_dev *dev)unsigned int core_id =rte_lcore_id ();if (core_id ==LCORE_ID_ANY ) - core_id =rte_get_master_lcore (); + core_id =rte_get_initial_lcore (); hif =mrvl_get_hif (priv, core_id);
@@ -1620,7 +1620,7 @@ mrvl_fill_bpool(struct mrvl_rxq *rxq, int num) core_id =rte_lcore_id ();if (core_id ==LCORE_ID_ANY ) - core_id =rte_get_master_lcore (); + core_id =rte_get_initial_lcore (); hif =mrvl_get_hif (rxq->priv, core_id);if (!hif)
@@ -1770,7 +1770,7 @@ mrvl_rx_queue_release(void *rxq)unsigned int core_id =rte_lcore_id ();if (core_id ==LCORE_ID_ANY ) - core_id =rte_get_master_lcore (); + core_id =rte_get_initial_lcore ();if (!q)return ;
drivers/net/qede/base/bcm_osal.c +2 -2
@@ -112,7 +112,7 @@ void *osal_dma_alloc_coherent(struct ecore_dev *p_dev,snprintf (mz_name,sizeof (mz_name),"%lx" , (unsigned long )rte_get_timer_cycles ());if (core_id == (unsigned int )LCORE_ID_ANY ) - core_id =rte_get_master_lcore (); + core_id =rte_get_initial_lcore (); socket_id =rte_lcore_to_socket_id (core_id); mz =rte_memzone_reserve_aligned (mz_name, size, socket_id,RTE_MEMZONE_IOVA_CONTIG ,RTE_CACHE_LINE_SIZE );
@@ -151,7 +151,7 @@ void *osal_dma_alloc_coherent_aligned(struct ecore_dev *p_dev,snprintf (mz_name,sizeof (mz_name),"%lx" , (unsigned long )rte_get_timer_cycles ());if (core_id == (unsigned int )LCORE_ID_ANY ) - core_id =rte_get_master_lcore (); + core_id =rte_get_initial_lcore (); socket_id =rte_lcore_to_socket_id (core_id); mz =rte_memzone_reserve_aligned (mz_name, size, socket_id,RTE_MEMZONE_IOVA_CONTIG , align);
drivers/net/softnic/rte_eth_softnic_thread.c +2 -2
@@ -25,7 +25,7 @@ softnic_thread_free(struct pmd_internals *softnic) {uint32_t i; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {struct softnic_thread *t = &softnic->thread[i];/* MSGQs */
@@ -99,7 +99,7 @@ softnic_thread_init(struct pmd_internals *softnic)static inline int thread_is_valid (struct pmd_internals *softnic,uint32_t thread_id) { -if (thread_id ==rte_get_master_lcore ()) +if (thread_id ==rte_get_initial_lcore ())return 0 ;/* FALSE */ if (softnic->params.sc &&rte_lcore_has_role (thread_id,ROLE_SERVICE ))
Signature · 1 line
2.26.2
PATCH v3 6/27 examples/distrutor: rename master to initial
In reply to Stephen HemmingerConform to new API
--- examples/distributor/main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
examples/distributor/main.c +5 -5
@@ -612,7 +612,7 @@ static intinit_power_library (void) {int ret =0 , lcore_id; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {/* init power management library */ ret =rte_power_init (lcore_id);if (ret) {
@@ -808,7 +808,7 @@ main(int argc, char *argv[])* available, the higher frequency cores will go to the * distributor first, then rx, then tx. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_power_get_capabilities (lcore_id, &lcore_cap);
@@ -841,7 +841,7 @@ main(int argc, char *argv[])* after the high performing core assignment above, pre-assign * them here. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_id == (unsigned int )distr_core_id || lcore_id == (unsigned int )rx_core_id || lcore_id == (unsigned int )tx_core_id)
@@ -872,7 +872,7 @@ main(int argc, char *argv[])* Kick off all the worker threads first, avoiding the pre-assigned * lcore_ids for tx, rx and distributor workloads. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_id == (unsigned int )distr_core_id || lcore_id == (unsigned int )rx_core_id || lcore_id == (unsigned int )tx_core_id)
@@ -925,7 +925,7 @@ main(int argc, char *argv[])usleep (1000 ); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
Signature · 1 line
2.26.2
PATCH v3 7/27 examples/bond: replace references to master lcore
In reply to Stephen HemmingerChange the references to master lcore.
For now, leave refernces to slave for bonding since that is part of the API not addressed yet.
--- examples/bond/main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
examples/bond/main.c +4 -4
@@ -590,7 +590,7 @@ static void cmd_start_parsed(__rte_unused void *parsed_result,return ; } -/* start lcore main on core != master_core - ARP response thread */ +/* start lcore main on core != initial_core - ARP response thread */ slave_core_id =rte_get_next_lcore (rte_lcore_id (),1 ,0 );if ((slave_core_id >=RTE_MAX_LCORE ) || (slave_core_id ==0 ))return ;
@@ -802,7 +802,7 @@ cmdline_parse_ctx_t main_ctx[] = { NULL, }; -/* prompt function, called from main on MASTER lcore */ +/* prompt function, called from main on initial lcore */ static void prompt(__rte_unused void *arg1) {struct cmdline *cl;
@@ -852,12 +852,12 @@ main(int argc, char *argv[])rte_spinlock_init (&global_flag_stru_p->lock);/* check state of lcores */ -RTE_LCORE_FOREACH_SLAVE (slave_core_id) { +RTE_LCORE_FOREACH_WORKER (slave_core_id) {if (rte_eal_get_lcore_state (slave_core_id) !=WAIT )return -EBUSY ; } -/* start lcore main on core != master_core - ARP response thread */ +/* start lcore main on core != initial_core - ARP response thread */ slave_core_id =rte_get_next_lcore (rte_lcore_id (),1 ,0 );if ((slave_core_id >=RTE_MAX_LCORE ) || (slave_core_id ==0 ))return -EPERM ;
Signature · 1 line
2.26.2
PATCH v3 8/27 examples/ethtool-app: replace references to slave with worker
In reply to Stephen HemmingerConforms to new API naming conventions.
--- examples/ethtool/ethtool-app/main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
examples/ethtool/ethtool-app/main.c +5 -5
@@ -176,7 +176,7 @@ static void process_frame(struct app_port *ptr_port,rte_ether_addr_copy (&ptr_port->mac_addr, &ptr_mac_hdr->s_addr); } -static int slave_main(__rte_unused void *ptr_data) +static int worker_main(__rte_unused void *ptr_data) {struct app_port *ptr_port;struct rte_mbuf *ptr_frame;
@@ -284,16 +284,16 @@ int main(int argc, char **argv) app_cfg.cnt_ports = cnt_ports;if (rte_lcore_count () <2 ) -rte_exit (EXIT_FAILURE ,"No available slave core!\n" ); -/* Assume there is an available slave.. */ +rte_exit (EXIT_FAILURE ,"No available worker core!\n" ); +/* Assume there is an available worker.. */ id_core =rte_lcore_id (); id_core =rte_get_next_lcore (id_core,1 ,1 ); -rte_eal_remote_launch (slave_main,NULL , id_core); +rte_eal_remote_launch (worker_main,NULL , id_core);ethapp_main (); app_cfg.exit_now =1 ; -RTE_LCORE_FOREACH_SLAVE (id_core) { +RTE_LCORE_FOREACH_WORKER (id_core) {if (rte_eal_wait_lcore (id_core) <0 )return -1 ; }
Signature · 1 line
2.26.2
PATCH v3 9/27 examples/ip_pipeline: replace references to master_lcore
In reply to Stephen HemmingerUse initial lcore instead of primary lcore
--- examples/ip_pipeline/main.c | 2 +- examples/ip_pipeline/thread.c | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-)
examples/ip_pipeline/main.c +1 -1
@@ -250,7 +250,7 @@ main(int argc, char **argv)rte_eal_mp_remote_launch ( thread_main,NULL , -SKIP_MASTER ); +SKIP_INITIAL );/* Script */ if (app.script_name)
examples/ip_pipeline/thread.c +8 -8
@@ -32,7 +32,7 @@#endif /** -* Master thead: data plane thread context +* Initial thread: data plane thread context */ struct thread {struct rte_ring *msgq_req;
@@ -78,7 +78,7 @@ struct thread_data {static struct thread_data thread_data[RTE_MAX_LCORE ];/** -* Master thread: data plane thread init +* Initial thread: data plane thread init */ static void thread_free (void )
@@ -105,7 +105,7 @@ thread_init(void) {uint32_t i; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {char name[NAME_MAX ];struct rte_ring *msgq_req, *msgq_rsp;struct thread *t = &thread[i];
@@ -137,7 +137,7 @@ thread_init(void)return -1 ; } -/* Master thread records */ +/* Initial thread records */ t->msgq_req = msgq_req; t->msgq_rsp = msgq_rsp; t->enabled =1 ;
@@ -179,7 +179,7 @@ pipeline_is_running(struct pipeline *p) }/** -* Master thread & data plane threads: message passing +* Initial thread & data plane threads: message passing */ enum thread_req_type {THREAD_REQ_PIPELINE_ENABLE =0 ,
@@ -213,7 +213,7 @@ struct thread_msg_rsp { };/** -* Master thread +* Initial thread */ static struct thread_msg_req *thread_msg_alloc (void )
@@ -556,7 +556,7 @@ thread_msg_handle(struct thread_data *t) }/** -* Master thread & data plane threads: message passing +* Initial thread & data plane threads: message passing */ enum pipeline_req_type {/* Port IN */
@@ -730,7 +730,7 @@ struct pipeline_msg_rsp { };/** -* Master thread +* Initial thread */ static struct pipeline_msg_req *pipeline_msg_alloc (void )
Signature · 1 line
2.26.2
PATCH v3 10/27 examples/qos_{meter/sched}: replace references to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- examples/qos_meter/main.c | 4 ++-- examples/qos_sched/args.c | 22 +++++++++++----------- examples/qos_sched/cmdline.c | 2 +- examples/qos_sched/main.c | 2 +- 4 files changed, 15 insertions(+), 15 deletions(-)
examples/qos_meter/main.c +2 -2
@@ -457,8 +457,8 @@ main(int argc, char **argv)rte_exit (EXIT_FAILURE ,"Invalid configure flow table\n" );/* Launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/qos_sched/args.c +11 -11
@@ -22,7 +22,7 @@#define MAX_OPT_VALUES 8#define SYS_CPU_DIR "/sys/devices/system/cpu/cpu%u/topology/" -static uint32_t app_master_core =1 ; +static uint32_t app_initial_core =1 ;static uint32_t app_numa_mask;static uint64_t app_used_core_mask =0 ;static uint64_t app_used_port_mask =0 ;
@@ -40,7 +40,7 @@ static const char usage[] =" \n" "Application optional parameters: \n" " --i : run in interactive mode (default value is %u) \n" -" --mst I : master core index (default value is %u) \n" +" --mst I : initial core index (default value is %u) \n" " --rsz \"A, B, C\" : Ring sizes \n" " A = Size (in number of buffer descriptors) of each of the NIC RX \n" " rings read by the I/O RX lcores (default value is %u) \n"
@@ -72,7 +72,7 @@ static const char usage[] =static void app_usage (const char *prgname) { - printf(usage, prgname, APP_INTERACTIVE_DEFAULT, app_master_core, + printf(usage, prgname, APP_INTERACTIVE_DEFAULT, app_initial_core, APP_RX_DESC_DEFAULT, APP_RING_SIZE, APP_TX_DESC_DEFAULT, MAX_PKT_RX_BURST, PKT_ENQUEUE, PKT_DEQUEUE, MAX_PKT_TX_BURST, NB_MBUF,
@@ -98,7 +98,7 @@ app_eal_core_mask(void) cm |= (1ULL << i); } - cm |= (1ULL <<rte_get_master_lcore ()); + cm |= (1ULL <<rte_get_initial_lcore ());return cm; }
@@ -353,7 +353,7 @@ app_parse_args(int argc, char **argv)break ; }if (str_is (optname,"mst" )) { - app_master_core = (uint32_t )atoi (optarg); + app_initial_core = (uint32_t )atoi (optarg);break ; }if (str_is (optname,"rsz" )) {
@@ -408,18 +408,18 @@ app_parse_args(int argc, char **argv) } } -/* check master core index validity */ -for (i =0 ; i <= app_master_core; i++) { -if (app_used_core_mask & (1u << app_master_core)) { -RTE_LOG (ERR ,APP ,"Master core index is not configured properly\n" ); +/* check initial core index validity */ +for (i =0 ; i <= app_initial_core; i++) { +if (app_used_core_mask & (1u << app_initial_core)) { +RTE_LOG (ERR ,APP ,"Initial core index is not configured properly\n" );app_usage (prgname);return -1 ; } } - app_used_core_mask |=1u << app_master_core; + app_used_core_mask |=1u << app_initial_core;if ((app_used_core_mask !=app_eal_core_mask ()) || - (app_master_core !=rte_get_master_lcore ())) { + (app_initial_core !=rte_get_initial_lcore ())) {RTE_LOG (ERR ,APP ,"EAL core mask not configured properly, must be %" PRIx64" instead of %" PRIx64"\n" , app_used_core_mask,app_eal_core_mask ());return -1 ;
examples/qos_sched/cmdline.c +1 -1
@@ -599,7 +599,7 @@ cmdline_parse_ctx_t main_ctx[] = { NULL, }; -/* prompt function, called from main on MASTER lcore */ +/* prompt function, called from main on initial lcore */ void prompt (void ) {
examples/qos_sched/main.c +1 -1
@@ -204,7 +204,7 @@ main(int argc, char **argv)return -1 ;/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (app_main_loop,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (app_main_loop,NULL ,SKIP_INITIAL );if (interactive) {sleep (1 );
Signature · 1 line
2.26.2
PATCH v3 11/27 examples/l3fwd: replace references to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- examples/l3fwd-acl/main.c | 4 ++-- examples/l3fwd-graph/main.c | 14 +++++++------- examples/l3fwd-power/main.c | 20 ++++++++++---------- examples/l3fwd/main.c | 2 +- 4 files changed, 20 insertions(+), 20 deletions(-)
examples/l3fwd-acl/main.c +2 -2
@@ -2110,8 +2110,8 @@ main(int argc, char **argv)check_all_ports_link_status (enabled_port_mask);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l3fwd-graph/main.c +7 -7
@@ -167,8 +167,8 @@ check_lcore_params(void)return -1 ; } -if (lcore ==rte_get_master_lcore ()) { -printf ("Error: lcore %u is master lcore\n" , lcore); +if (lcore ==rte_get_initial_lcore ()) { +printf ("Error: lcore %u is initial lcore\n" , lcore);return -1 ; } socketid =rte_lcore_to_socket_id (lcore);
@@ -1099,16 +1099,16 @@ main(int argc, char **argv) route_str, i); } -/* Launch per-lcore init on every slave lcore */ -rte_eal_mp_remote_launch (graph_main_loop,NULL ,SKIP_MASTER ); +/* Launch per-lcore init on every worker lcore */ +rte_eal_mp_remote_launch (graph_main_loop,NULL ,SKIP_INITIAL ); -/* Accumulate and print stats on master until exit */ +/* Accumulate and print stats on initial until exit */ if (rte_graph_has_stats_feature ())print_stats (); -/* Wait for slave cores to exit */ +/* Wait for worker cores to exit */ ret =0 ; - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + RTE_LCORE_FOREACH_WORKER(lcore_id) { ret = rte_eal_wait_lcore(lcore_id); /* Destroy graph */ if (ret < 0 || rte_graph_destroy(
examples/l3fwd-power/main.c +10 -10
@@ -1351,7 +1351,7 @@ check_lcore_params(void) "off\n", lcore, socketid); }if (app_mode ==APP_MODE_TELEMETRY && lcore ==rte_lcore_id ()) { -printf ("cannot enable master core %d in config for telemetry mode\n" , +printf ("cannot enable initial core %d in config for telemetry mode\n" ,rte_lcore_id ());return -1 ; }
@@ -2089,7 +2089,7 @@ get_current_stat_values(uint64_t *values)uint64_t app_eps =0 , app_fps =0 , app_br =0 ;uint64_t count =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { qconf = &lcore_conf[lcore_id];if (qconf->n_rx_queue ==0 )continue ;
@@ -2181,10 +2181,10 @@ launch_timer(unsigned int lcore_id)RTE_SET_USED (lcore_id); -if (rte_get_master_lcore () != lcore_id) { -rte_panic ("timer on lcore:%d which is not master core:%d\n" , +if (rte_get_initial_lcore () != lcore_id) { +rte_panic ("timer on lcore:%d which is not initial core:%d\n" , lcore_id, -rte_get_master_lcore ()); +rte_get_initial_lcore ()); }RTE_LOG (INFO ,POWER ,"Bring up the Timer\n" );
@@ -2515,11 +2515,11 @@ main(int argc, char **argv)/* launch per-lcore init on every lcore */ if (app_mode ==APP_MODE_LEGACY ) { -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); }else if (app_mode ==APP_MODE_EMPTY_POLL ) { empty_poll_stop = false;rte_eal_mp_remote_launch (main_empty_poll_loop,NULL , -SKIP_MASTER ); +SKIP_INITIAL ); }else {unsigned int i;
@@ -2535,7 +2535,7 @@ main(int argc, char **argv)else rte_exit (EXIT_FAILURE ,"failed to register metrics names" ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_spinlock_init (&stats[lcore_id].telemetry_lock); }rte_timer_init (&telemetry_timer);
@@ -2543,13 +2543,13 @@ main(int argc, char **argv) handle_app_stats, "Returns global power stats. Parameters: None");rte_eal_mp_remote_launch (main_telemetry_loop,NULL , -SKIP_MASTER ); +SKIP_INITIAL ); }if (app_mode ==APP_MODE_EMPTY_POLL || app_mode ==APP_MODE_TELEMETRY )launch_timer (rte_lcore_id ()); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l3fwd/main.c +1 -1
@@ -1278,7 +1278,7 @@ main(int argc, char **argv) ret =0 ;/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (l3fwd_lkp.main_loop,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (l3fwd_lkp.main_loop,NULL ,CALL_INITIAL );if (evt_rsrc->enabled) {for (i =0 ; i < evt_rsrc->rx_adptr.nb_rx_adptr; i++) rte_event_eth_rx_adapter_stop(
Signature · 1 line
2.26.2
PATCH v3 12/27 examples/l2fwd: replace references to master lcore
In reply to Stephen HemmingerUse term initial lcore instead.
--- examples/l2fwd-cat/l2fwd-cat.c | 2 +- examples/l2fwd-crypto/main.c | 8 ++++---- examples/l2fwd-event/l2fwd_event_generic.c | 2 +- examples/l2fwd-event/l2fwd_event_internal_port.c | 2 +- examples/l2fwd-event/l2fwd_poll.c | 2 +- examples/l2fwd-event/main.c | 2 +- examples/l2fwd-jobstats/main.c | 4 ++-- examples/l2fwd-keepalive/main.c | 6 +++--- examples/l2fwd/main.c | 8 ++++---- 9 files changed, 18 insertions(+), 18 deletions(-)
examples/l2fwd-cat/l2fwd-cat.c +1 -1
@@ -198,7 +198,7 @@ main(int argc, char *argv[])if (rte_lcore_count () >1 )printf ("\nWARNING: Too many lcores enabled. Only 1 used.\n" ); -/* Call lcore_main on the master core only. */ +/* Call lcore_main on the initial core only. */ lcore_main ();return 0 ;
examples/l2fwd-crypto/main.c +4 -4
@@ -874,8 +874,8 @@ l2fwd_main_loop(struct l2fwd_crypto_options *options)if (unlikely (timer_tsc >= (uint64_t )timer_period)) { -/* do this only on master core */ -if (lcore_id ==rte_get_master_lcore () +/* do this only on initial core */ +if (lcore_id ==rte_get_initial_lcore () && options->refresh_period) {print_stats (); timer_tsc =0 ;
@@ -2802,8 +2802,8 @@ main(int argc, char **argv)/* launch per-lcore init on every lcore */ rte_eal_mp_remote_launch (l2fwd_launch_one_lcore, (void *)&options, -CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l2fwd-event/l2fwd_event_generic.c +1 -1
@@ -72,7 +72,7 @@ l2fwd_event_device_setup_generic(struct l2fwd_resources *rsrc) event_d_conf.nb_event_port_enqueue_depth = dev_info.max_event_port_enqueue_depth; -/* Ignore Master core and service cores. */ +/* Ignore initial core and service cores. */ num_workers =rte_lcore_count () -1 -rte_service_lcore_count ();if (dev_info.max_event_ports < num_workers) num_workers = dev_info.max_event_ports;
examples/l2fwd-event/l2fwd_event_internal_port.c +1 -1
@@ -71,7 +71,7 @@ l2fwd_event_device_setup_internal_port(struct l2fwd_resources *rsrc) event_d_conf.nb_event_port_enqueue_depth = dev_info.max_event_port_enqueue_depth; -/* Ignore Master core. */ +/* Ignore initial core. */ num_workers =rte_lcore_count () -1 ;if (dev_info.max_event_ports < num_workers) num_workers = dev_info.max_event_ports;
examples/l2fwd-event/l2fwd_poll.c +1 -1
@@ -116,7 +116,7 @@ l2fwd_poll_lcore_config(struct l2fwd_resources *rsrc)/* get the lcore_id for this port */ while (rte_lcore_is_enabled (rx_lcore_id) ==0 || - rx_lcore_id ==rte_get_master_lcore () || + rx_lcore_id ==rte_get_initial_lcore () || poll_rsrc->lcore_queue_conf[rx_lcore_id].n_rx_port == rsrc->rx_queue_per_lcore) { rx_lcore_id++;
examples/l2fwd-event/main.c +1 -1
@@ -673,7 +673,7 @@ main(int argc, char **argv)/* launch per-lcore init on every lcore */ rte_eal_mp_remote_launch (l2fwd_launch_one_lcore, rsrc, -SKIP_MASTER ); +SKIP_INITIAL );l2fwd_event_print_stats (rsrc);if (rsrc->event_mode) { struct l2fwd_event_resources *evt_rsrc =
examples/l2fwd-jobstats/main.c +2 -2
@@ -1022,8 +1022,8 @@ main(int argc, char **argv)RTE_LOG (INFO ,L2FWD ,"Stats display disabled\n" );/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (l2fwd_launch_one_lcore,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (l2fwd_launch_one_lcore,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l2fwd-keepalive/main.c +3 -3
@@ -792,8 +792,8 @@ main(int argc, char **argv) ) != 0 )rte_exit (EXIT_FAILURE ,"Stats setup failure.\n" ); } -/* launch per-lcore init on every slave lcore */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +/* launch per-lcore init on every worker lcore */ +RTE_LCORE_FOREACH_WORKER (lcore_id) {struct lcore_queue_conf *qconf = &lcore_queue_conf[lcore_id];if (qconf->n_rx_port ==0 )
@@ -816,7 +816,7 @@ main(int argc, char **argv)rte_delay_ms (5 ); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/l2fwd/main.c +4 -4
@@ -250,8 +250,8 @@ l2fwd_main_loop(void)/* if timer has reached its timeout */ if (unlikely (timer_tsc >= timer_period)) { -/* do this only on master core */ -if (lcore_id ==rte_get_master_lcore ()) { +/* do this only on initial core */ +if (lcore_id ==rte_get_initial_lcore ()) {print_stats ();/* reset the timer */ timer_tsc =0 ;
@@ -756,8 +756,8 @@ main(int argc, char **argv) ret =0 ;/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (l2fwd_launch_one_lcore,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (l2fwd_launch_one_lcore,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 ) { ret =-1 ;break ;
Signature · 1 line
2.26.2
PATCH v3 13/27 examples/multi_process: replace references to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- .../multi_process/client_server_mp/mp_server/main.c | 10 +++++----- examples/multi_process/simple_mp/main.c | 6 +++--- examples/multi_process/symmetric_mp/main.c | 2 +- 3 files changed, 9 insertions(+), 9 deletions(-)
examples/multi_process/client_server_mp/mp_server/main.c +5 -5
@@ -84,7 +84,7 @@ get_printable_mac_addr(uint16_t port)/* * This function displays the recorded statistics for each port * and for each client. It uses ANSI terminal codes to clear -* screen when called. It is called from a single non-master +* screen when called. It is called from a single worker * thread in the server process, when the process is run with more * than one lcore enabled. */
@@ -146,7 +146,7 @@ do_stats_display(void) }/* -* The function called from each non-master lcore used by the process. +* The function called from each worker lcore used by the process. * The test_and_set function is used to randomly pick a single lcore on which * the code to display the statistics will run. Otherwise, the code just * repeatedly sleeps.
@@ -244,7 +244,7 @@ process_packets(uint32_t port_num __rte_unused, }/* -* Function called by the master lcore of the DPDK process. +* Function called by the initial lcore of the DPDK process. */ static void do_packet_forwarding (void )
@@ -297,8 +297,8 @@ main(int argc, char *argv[])/* clear statistics */ clear_stats (); -/* put all other cores to sleep bar master */ -rte_eal_mp_remote_launch (sleep_lcore,NULL ,SKIP_MASTER ); +/* put all other cores to sleep execpt inital core */ +rte_eal_mp_remote_launch (sleep_lcore,NULL ,SKIP_INITIAL );do_packet_forwarding ();return 0 ;
examples/multi_process/simple_mp/main.c +3 -3
@@ -108,12 +108,12 @@ main(int argc, char **argv)RTE_LOG (INFO ,APP ,"Finished Process Init.\n" ); -/* call lcore_recv() on every slave lcore */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +/* call lcore_recv() on every worker lcore */ +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (lcore_recv,NULL , lcore_id); } -/* call cmd prompt on master lcore */ +/* call cmd prompt on initial lcore */ struct cmdline *cl =cmdline_stdin_new (simple_mp_ctx,"\nsimple_mp > " );if (cl ==NULL )rte_exit (EXIT_FAILURE ,"Cannot create cmdline instance\n" );
examples/multi_process/symmetric_mp/main.c +1 -1
@@ -473,7 +473,7 @@ main(int argc, char **argv)RTE_LOG (INFO ,APP ,"Finished Process Init.\n" ); -rte_eal_mp_remote_launch (lcore_main,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (lcore_main,NULL ,CALL_INITIAL );return 0 ; }
Signature · 1 line
2.26.2
PATCH v3 14/27 examples/performance-thread: replace reference to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- examples/performance-thread/l3fwd-thread/main.c | 12 ++++++------ examples/performance-thread/pthread_shim/main.c | 4 ++-- 2 files changed, 8 insertions(+), 8 deletions(-)
examples/performance-thread/l3fwd-thread/main.c +6 -6
@@ -2211,7 +2211,7 @@ lthread_rx(void *dummy)/* * Start scheduler with initial lthread on lcore * -* This lthread loop spawns all rx and tx lthreads on master lcore +* This lthread loop spawns all rx and tx lthreads on intial lcore */ static void *
@@ -2265,7 +2265,7 @@ lthread_spawner(__rte_unused void *arg)* (main_lthread_master). */ static int -lthread_master_spawner(__rte_unused void *arg) { +lthread_initial_spawner(__rte_unused void *arg) {struct lthread *lt;int lcore_id =rte_lcore_id ();
@@ -3765,14 +3765,14 @@ main(int argc, char **argv)#endif lthread_num_schedulers_set (nb_lcores); -rte_eal_mp_remote_launch (sched_spawner,NULL ,SKIP_MASTER ); -lthread_master_spawner (NULL ); +rte_eal_mp_remote_launch (sched_spawner,NULL ,SKIP_INITIAL ); +lthread_initial_spawner (NULL ); }else {printf ("Starting P-Threading Model\n" );/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (pthread_run,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (pthread_run,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/performance-thread/pthread_shim/main.c +2 -2
@@ -252,10 +252,10 @@ int main(int argc, char **argv)lthread_num_schedulers_set (num_sched);/* launch all threads */ -rte_eal_mp_remote_launch (lthread_scheduler, (void *)NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (lthread_scheduler, (void *)NULL ,CALL_INITIAL );/* wait for threads to stop */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_wait_lcore (lcore_id); }return 0 ;
Signature · 1 line
2.26.2
PATCH v3 15/27 examples/ptpclient: replace references to master lcore
In reply to Stephen HemmingerReplace master lcore with initial lcore.
This API still has issue with use of term master clock.
--- examples/ptpclient/ptpclient.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
examples/ptpclient/ptpclient.c +1 -1
@@ -785,7 +785,7 @@ main(int argc, char *argv[])if (rte_lcore_count () >1 )printf ("\nWARNING: Too many lcores enabled. Only 1 used.\n" ); -/* Call lcore_main on the master core only. */ +/* Call lcore_main on the initial core only. */ lcore_main ();return 0 ;
Signature · 1 line
2.26.2
PATCH v3 16/27 examples/ipcsec-secgw: replace references to master lcore
In reply to Stephen HemmingerUse initial lcore instead.
--- examples/ipsec-secgw/event_helper.c | 6 +++--- examples/ipsec-secgw/ipsec-secgw.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-)
examples/ipsec-secgw/event_helper.c +3 -3
@@ -1461,16 +1461,16 @@ eh_conf_init(void)/* Set two cores as eth cores for Rx & Tx */ -/* Use first core other than master core as Rx core */ +/* Use first core other than initial core as Rx core */ eth_core_id =rte_get_next_lcore (0 ,/* curr core */ -1 ,/* skip master core */ +1 ,/* skip initial core */ 0 /* wrap */ );rte_bitmap_set (em_conf->eth_core_mask, eth_core_id);/* Use next core as Tx core */ eth_core_id =rte_get_next_lcore (eth_core_id,/* curr core */ -1 ,/* skip master core */ +1 ,/* skip initial core */ 0 /* wrap */ );rte_bitmap_set (em_conf->eth_core_mask, eth_core_id);
examples/ipsec-secgw/ipsec-secgw.c +2 -2
@@ -2917,8 +2917,8 @@ main(int32_t argc, char **argv)check_all_ports_link_status (enabled_port_mask);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (ipsec_launch_one_lcore, eh_conf,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (ipsec_launch_one_lcore, eh_conf,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
Signature · 1 line
2.26.2
PATCH v3 17/27 examples: replace reference to master lcore
In reply to Stephen HemmingerSmall changes in several examples to replace master_lcore with initial_lcore across multiple small examples.
--- examples/eventdev_pipeline/main.c | 2 +- examples/flow_classify/flow_classify.c | 2 +- examples/helloworld/main.c | 6 +++--- examples/ioat/ioatfwd.c | 6 +++--- examples/ip_fragmentation/main.c | 4 ++-- examples/ip_reassembly/main.c | 4 ++-- examples/ipv4_multicast/main.c | 4 ++-- examples/kni/main.c | 7 +++---- examples/link_status_interrupt/main.c | 8 ++++---- examples/ntb/ntb_fwd.c | 14 +++++++------- examples/packet_ordering/main.c | 22 +++++++++++----------- examples/rxtx_callbacks/main.c | 2 +- examples/server_node_efd/server/main.c | 10 +++++----- examples/skeleton/basicfwd.c | 2 +- examples/tep_termination/main.c | 12 ++++++------ examples/timer/main.c | 8 ++++---- examples/vhost/main.c | 10 +++++----- examples/vmdq/main.c | 4 ++-- examples/vmdq_dcb/main.c | 6 +++--- 19 files changed, 66 insertions(+), 67 deletions(-)
examples/eventdev_pipeline/main.c +1 -1
@@ -395,7 +395,7 @@ main(int argc, char **argv) }int worker_idx =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (lcore_id >=MAX_NUM_CORE )break ;
examples/flow_classify/flow_classify.c +1 -1
@@ -850,7 +850,7 @@ main(int argc, char *argv[])rte_exit (EXIT_FAILURE ,"Failed to add rules\n" ); } -/* Call lcore_main on the master core only. */ +/* Call lcore_main on the initial core only. */ lcore_main (cls_app);return 0 ;
examples/helloworld/main.c +3 -3
@@ -34,12 +34,12 @@ main(int argc, char **argv)if (ret <0 )rte_panic ("Cannot init EAL\n" ); -/* call lcore_hello() on every slave lcore */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +/* call lcore_hello() on every worker lcore */ +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (lcore_hello,NULL , lcore_id); } -/* call it on master lcore too */ +/* call it on initial lcore too */ lcore_hello (NULL );rte_eal_mp_wait_lcore ();
examples/ioat/ioatfwd.c +3 -3
@@ -520,7 +520,7 @@ tx_main_loop(void)ioat_tx_port (&cfg.ports[i]); } -/* Main rx and tx loop if only one slave lcore available */ +/* Main rx and tx loop if only one worker lcore available */ static void rxtx_main_loop (void ) {
@@ -984,7 +984,7 @@ main(int argc, char **argv) cfg.nb_lcores =rte_lcore_count () -1 ;if (cfg.nb_lcores <1 )rte_exit (EXIT_FAILURE , -"There should be at least one slave lcore.\n" ); +"There should be at least one worker lcore.\n" );if (copy_mode ==COPY_MODE_IOAT_NUM )assign_rawdevs ();
@@ -992,7 +992,7 @@ main(int argc, char **argv)assign_rings ();start_forwarding_cores (); -/* master core prints stats while other cores forward */ +/* initial core prints stats while other cores forward */ print_stats (argv[0 ]);/* force_quit is true when we get here */
examples/ip_fragmentation/main.c +2 -2
@@ -1072,8 +1072,8 @@ main(int argc, char **argv)check_all_ports_link_status (enabled_port_mask);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/ip_reassembly/main.c +2 -2
@@ -1201,8 +1201,8 @@ main(int argc, char **argv)signal (SIGINT , signal_handler);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/ipv4_multicast/main.c +2 -2
@@ -801,8 +801,8 @@ main(int argc, char **argv)rte_exit (EXIT_FAILURE ,"Cannot build the multicast hash\n" );/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/kni/main.c +3 -4
@@ -956,8 +956,7 @@ kni_alloc(uint16_t port_id) conf.mbuf_size =MAX_PACKET_SZ ;/* * The first KNI device associated to a port -* is the master, for multiple kernel thread -* environment. +* is special, for multiple kernel thread environment. */ if (i ==0 ) {struct rte_kni_ops ops;
@@ -1105,8 +1104,8 @@ main(int argc, char** argv) "Could not create link status thread!\n");/* Launch per-lcore function on every lcore */ -rte_eal_mp_remote_launch (main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (i) { +rte_eal_mp_remote_launch (main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (i) {if (rte_eal_wait_lcore (i) <0 )return -1 ; }
examples/link_status_interrupt/main.c +4 -4
@@ -255,8 +255,8 @@ lsi_main_loop(void)/* if timer has reached its timeout */ if (unlikely (timer_tsc >= (uint64_t ) timer_period)) { -/* do this only on master core */ -if (lcore_id ==rte_get_master_lcore ()) { +/* do this only on initial core */ +if (lcore_id ==rte_get_initial_lcore ()) {print_stats ();/* reset the timer */ timer_tsc =0 ;
@@ -735,8 +735,8 @@ main(int argc, char **argv)check_all_ports_link_status (nb_ports, lsi_enabled_port_mask);/* launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (lsi_launch_one_lcore,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (lsi_launch_one_lcore,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/ntb/ntb_fwd.c +7 -7
@@ -162,7 +162,7 @@ cmd_quit_parsed(__rte_unused void *parsed_result,uint32_t lcore_id;/* Stop transmission first. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (!conf->nb_stream)
@@ -668,7 +668,7 @@ assign_stream_to_lcores(void)uint8_t lcore_num, nb_extra; lcore_num =rte_lcore_count (); -/* Exclude master core */ +/* Exclude initial core */ lcore_num--; nb_streams = (fwd_mode ==IOFWD ) ? num_queues *2 : num_queues;
@@ -678,7 +678,7 @@ assign_stream_to_lcores(void) sm_id =0 ; i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (i < nb_extra) {
@@ -697,7 +697,7 @@ assign_stream_to_lcores(void) }/* Print packet forwading config. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (!conf->nb_stream)
@@ -765,7 +765,7 @@ start_pkt_fwd(void)assign_stream_to_lcores (); in_test =1 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (!conf->nb_stream)
@@ -826,7 +826,7 @@ cmd_stop_parsed(__rte_unused void *parsed_result,struct ntb_fwd_lcore_conf *conf;uint32_t lcore_id; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { conf = &fwd_lcore_conf[lcore_id];if (!conf->nb_stream)
@@ -1074,7 +1074,7 @@ cmdline_parse_ctx_t main_ctx[] = { NULL, }; -/* prompt function, called from main on MASTER lcore */ +/* prompt function, called from main on initial lcore */ static void prompt (void ) {
examples/packet_ordering/main.c +11 -11
@@ -348,10 +348,10 @@ print_stats(void) {uint16_t i;struct rte_eth_stats eth_stats; -unsigned int lcore_id, last_lcore_id, master_lcore_id, end_w_lcore_id; +unsigned int lcore_id, last_lcore_id, initial_lcore_id, end_w_lcore_id; last_lcore_id =get_last_lcore_id (); - master_lcore_id =rte_get_master_lcore (); + initial_lcore_id =rte_get_initial_lcore (); end_w_lcore_id =get_previous_lcore_id (last_lcore_id);printf ("\nRX thread stats:\n" );
@@ -363,7 +363,7 @@ print_stats(void)for (lcore_id =0 ; lcore_id <= end_w_lcore_id; lcore_id++) {if (insight_worker &&rte_lcore_is_enabled (lcore_id) - && lcore_id != master_lcore_id) { + && lcore_id != initial_lcore_id) {printf ("\nWorker thread stats on core [%u]:\n" , lcore_id); printf(" - Pkts deqd from workers ring: %"PRIu64"\n",
@@ -661,7 +661,7 @@ main(int argc, char **argv) {int ret;unsigned nb_ports; -unsigned int lcore_id, last_lcore_id, master_lcore_id; +unsigned int lcore_id, last_lcore_id, initial_lcore_id;uint16_t port_id;uint16_t nb_ports_available;struct worker_thread_args worker_args = {NULL ,NULL };
@@ -748,32 +748,32 @@ main(int argc, char **argv) } last_lcore_id =get_last_lcore_id (); - master_lcore_id =rte_get_master_lcore (); + initial_lcore_id =rte_get_initial_lcore (); worker_args.ring_in = rx_to_workers; worker_args.ring_out = workers_to_tx; -/* Start worker_thread() on all the available slave cores but the last 1 */ +/* Start worker_thread() on all the available worker cores but the last 1 */ for (lcore_id =0 ; lcore_id <=get_previous_lcore_id (last_lcore_id); lcore_id++) -if (rte_lcore_is_enabled (lcore_id) && lcore_id != master_lcore_id) +if (rte_lcore_is_enabled (lcore_id) && lcore_id != initial_lcore_id)rte_eal_remote_launch (worker_thread, (void *)&worker_args, lcore_id);if (disable_reorder) { -/* Start tx_thread() on the last slave core */ +/* Start tx_thread() on the last worker core */ rte_eal_remote_launch ((lcore_function_t *)tx_thread, workers_to_tx, last_lcore_id); }else { send_args.ring_in = workers_to_tx; -/* Start send_thread() on the last slave core */ +/* Start send_thread() on the last worker core */ rte_eal_remote_launch ((lcore_function_t *)send_thread, (void *)&send_args, last_lcore_id); } -/* Start rx_thread() on the master core */ +/* Start rx_thread() on the initial core */ rx_thread (rx_to_workers); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/rxtx_callbacks/main.c +1 -1
@@ -302,7 +302,7 @@ main(int argc, char *argv[])printf ("\nWARNING: Too much enabled lcores - " "App uses only 1 lcore\n" ); -/* call lcore_main on master core only */ +/* call lcore_main on initial core only */ lcore_main ();return 0 ; }
examples/server_node_efd/server/main.c +5 -5
@@ -95,7 +95,7 @@ get_printable_mac_addr(uint16_t port)/* * This function displays the recorded statistics for each port * and for each node. It uses ANSI terminal codes to clear -* screen when called. It is called from a single non-master +* screen when called. It is called from a single worker * thread in the server process, when the process is run with more * than one lcore enabled. */
@@ -168,7 +168,7 @@ do_stats_display(void) }/* -* The function called from each non-master lcore used by the process. +* The function called from each worker lcore used by the process. * The test_and_set function is used to randomly pick a single lcore on which * the code to display the statistics will run. Otherwise, the code just * repeatedly sleeps.
@@ -290,7 +290,7 @@ process_packets(uint32_t port_num __rte_unused, struct rte_mbuf *pkts[], }/* -* Function called by the master lcore of the DPDK process. +* Function called by the initial lcore of the DPDK process. */ static void do_packet_forwarding (void )
@@ -330,8 +330,8 @@ main(int argc, char *argv[])/* clear statistics */ clear_stats (); -/* put all other cores to sleep bar master */ -rte_eal_mp_remote_launch (sleep_lcore,NULL ,SKIP_MASTER ); +/* put all other cores to sleep */ +rte_eal_mp_remote_launch (sleep_lcore,NULL ,SKIP_INITIAL );do_packet_forwarding ();return 0 ;
examples/skeleton/basicfwd.c +1 -1
@@ -202,7 +202,7 @@ main(int argc, char *argv[])if (rte_lcore_count () >1 )printf ("\nWARNING: Too many lcores enabled. Only 1 used.\n" ); -/* Call lcore_main on the master core only. */ +/* Call lcore_main on the initial core only. */ lcore_main ();return 0 ;
examples/tep_termination/main.c +6 -6
@@ -838,7 +838,7 @@ init_data_ll(void) {int lcore; -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) { lcore_info[lcore].lcore_ll =malloc (sizeof (struct lcore_ll_info ));if (lcore_info[lcore].lcore_ll ==NULL ) {
@@ -930,7 +930,7 @@ destroy_device(int vid)rm_data_ll_entry (&ll_root_used, ll_main_dev_cur, ll_main_dev_last);/* Set the dev_removal_flag on each lcore. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) { lcore_info[lcore].lcore_ll->dev_removal_flag =REQUEST_DEV_REMOVAL ; }
@@ -941,7 +941,7 @@ destroy_device(int vid)* the device removed from the linked lists and that the devices * are no longer in use. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) {while (lcore_info[lcore].lcore_ll->dev_removal_flag !=ACK_DEV_REMOVAL )rte_pause ();
@@ -1001,7 +1001,7 @@ new_device(int vid) vdev->remove =0 ;/* Find a suitable lcore to add the device. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) {if (lcore_info[lcore].lcore_ll->device_num < device_num_min) { device_num_min = lcore_info[lcore].lcore_ll->device_num; core_add = lcore;
@@ -1207,7 +1207,7 @@ main(int argc, char *argv[]) }/* Launch all data cores. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (switch_worker, mbuf_pool, lcore_id); }
@@ -1231,7 +1231,7 @@ main(int argc, char *argv[]) "failed to start vhost driver.\n"); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) +RTE_LCORE_FOREACH_WORKER (lcore_id)rte_eal_wait_lcore (lcore_id);return 0 ;
examples/timer/main.c +4 -4
@@ -100,7 +100,7 @@ main(int argc, char **argv)rte_timer_init (&timer0);rte_timer_init (&timer1); -/* load timer0, every second, on master lcore, reloaded automatically */ +/* load timer0, every second, on initial lcore, reloaded automatically */ hz =rte_get_timer_hz (); lcore_id =rte_lcore_id ();rte_timer_reset (&timer0, hz,PERIODICAL , lcore_id, timer0_cb,NULL );
@@ -109,12 +109,12 @@ main(int argc, char **argv) lcore_id =rte_get_next_lcore (lcore_id,0 ,1 );rte_timer_reset (&timer1, hz/3 ,SINGLE , lcore_id, timer1_cb,NULL ); -/* call lcore_mainloop() on every slave lcore */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +/* call lcore_mainloop() on every worker lcore */ +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (lcore_mainloop,NULL , lcore_id); } -/* call it on master lcore too */ +/* call it on initial lcore too */ (void )lcore_mainloop (NULL );return 0 ;
examples/vhost/main.c +5 -5
@@ -1205,7 +1205,7 @@ destroy_device(int vid)/* Set the dev_removal_flag on each lcore. */ -RTE_LCORE_FOREACH_SLAVE (lcore) +RTE_LCORE_FOREACH_WORKER (lcore) lcore_info[lcore].dev_removal_flag = REQUEST_DEV_REMOVAL;/*
@@ -1213,7 +1213,7 @@ destroy_device(int vid)* we can be sure that they can no longer access the device removed * from the linked lists and that the devices are no longer in use. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) {while (lcore_info[lcore].dev_removal_flag !=ACK_DEV_REMOVAL )rte_pause (); }
@@ -1258,7 +1258,7 @@ new_device(int vid) vdev->remove =0 ;/* Find a suitable lcore to add the device. */ -RTE_LCORE_FOREACH_SLAVE (lcore) { +RTE_LCORE_FOREACH_WORKER (lcore) {if (lcore_info[lcore].device_num < device_num_min) { device_num_min = lcore_info[lcore].device_num; core_add = lcore;
@@ -1507,7 +1507,7 @@ main(int argc, char *argv[]) }/* Launch all data cores. */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) +RTE_LCORE_FOREACH_WORKER (lcore_id)rte_eal_remote_launch (switch_worker, NULL, lcore_id);if (client_mode)
@@ -1568,7 +1568,7 @@ main(int argc, char *argv[]) } } -RTE_LCORE_FOREACH_SLAVE (lcore_id) +RTE_LCORE_FOREACH_WORKER (lcore_id)rte_eal_wait_lcore (lcore_id);return 0 ;
examples/vmdq/main.c +2 -2
@@ -656,8 +656,8 @@ main(int argc, char *argv[]) }/* call lcore_main() on every lcore */ -rte_eal_mp_remote_launch (lcore_main,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (lcore_main,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
examples/vmdq_dcb/main.c +3 -3
@@ -702,12 +702,12 @@ main(int argc, char *argv[])rte_exit (EXIT_FAILURE ,"Cannot initialize network ports\n" ); } -/* call lcore_main() on every slave lcore */ +/* call lcore_main() on every worker lcore */ i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (lcore_main, (void *)i++, lcore_id); } -/* call on master too */ +/* call on initial too */ (void )lcore_main ((void *)i);return 0 ;
Signature · 1 line
2.26.2
PATCH v3 18/27 app/test-pmd: change references to master/slave
In reply to Stephen HemmingerUse new API and naming convention
--- app/test-pmd/config.c | 4 ++-- app/test-pmd/parameters.c | 2 +- app/test-pmd/softnicfwd.c | 2 +- app/test-pmd/testpmd.c | 4 ++-- 4 files changed, 6 insertions(+), 6 deletions(-)
app/test-pmd/config.c +2 -2
@@ -2649,9 +2649,9 @@ set_fwd_lcores_list(unsigned int *lcorelist, unsigned int nb_lc)printf ("lcore %u not enabled\n" , lcore_cpuid);return -1 ; } -if (lcore_cpuid ==rte_get_master_lcore ()) { +if (lcore_cpuid ==rte_get_initial_lcore ()) {printf ("lcore %u cannot be masked on for running " -"packet forwarding, which is the master lcore " +"packet forwarding, which is the initial lcore " "and reserved for command line parsing only\n" , lcore_cpuid);return -1 ;
app/test-pmd/parameters.c +1 -1
@@ -88,7 +88,7 @@ usage(char* progname)printf (" --nb-ports=N: set the number of forwarding ports " "(1 <= N <= %d).\n" , nb_ports);printf (" --coremask=COREMASK: hexadecimal bitmask of cores running " -"the packet forwarding test. The master lcore is reserved for " +"the packet forwarding test. The initial lcore is reserved for " "command line parsing only, and cannot be masked on for " "packet forwarding.\n" ); printf(" --portmask=PORTMASK: hexadecimal bitmask of ports used "
app/test-pmd/softnicfwd.c +1 -1
@@ -654,7 +654,7 @@ softnic_fwd_begin(portid_t pi)if (!rte_lcore_is_enabled (lcore))continue ; -if (lcore ==rte_get_master_lcore ()) +if (lcore ==rte_get_initial_lcore ())continue ;if (fwd_core_present ==0 ) {
app/test-pmd/testpmd.c +2 -2
@@ -83,7 +83,7 @@uint16_t verbose_level =0 ;/**< Silent by default. */ int testpmd_logtype;/**< Log type for testpmd logs */ -/* use master core for command line ? */ +/* use initial core for command line ? */ uint8_t interactive =0 ;uint8_t auto_start =0 ;uint8_t tx_first;
@@ -552,7 +552,7 @@ set_default_fwd_lcores_config(void) } socket_ids[num_sockets++] = sock_num; } -if (i ==rte_get_master_lcore ()) +if (i ==rte_get_initial_lcore ())continue ; fwd_lcores_cpuids[nb_lc++] = i; }
Signature · 1 line
2.26.2
PATCH v3 19/27 test-eventdev: replace references to slave with worker lcores
In reply to Stephen HemmingerUse new API terminolgy
--- app/test-eventdev/evt_options.c | 2 +- app/test-eventdev/test_order_common.c | 12 ++++++------ app/test-eventdev/test_perf_common.c | 16 ++++++++-------- app/test-eventdev/test_pipeline_common.c | 8 ++++---- 4 files changed, 19 insertions(+), 19 deletions(-)
app/test-eventdev/evt_options.c +1 -1
@@ -438,7 +438,7 @@ evt_options_dump(struct evt_options *opt)evt_dump ("verbose_level" ,"%d" , opt->verbose_level);evt_dump ("socket_id" ,"%d" , opt->socket_id);evt_dump ("pool_sz" ,"%d" , opt->pool_sz); -evt_dump ("master lcore" ,"%d" ,rte_get_master_lcore ()); +evt_dump ("initial lcore" ,"%d" ,rte_get_initial_lcore ());evt_dump ("nb_pkts" ,"%" PRIu64, opt->nb_pkts);evt_dump ("nb_timers" ,"%" PRIu64, opt->nb_timers);evt_dump_begin ("available lcores" );
app/test-eventdev/test_order_common.c +6 -6
@@ -74,15 +74,15 @@ order_opt_check(struct evt_options *opt)return -1 ; } -/* 1 producer + N workers + 1 master */ +/* 1 producer + N workers + 1 initial lcore */ if (rte_lcore_count () <3 ) {evt_err ("test need minimum 3 lcores" );return -1 ; }/* Validate worker lcores */ -if (evt_lcores_has_overlap (opt->wlcores,rte_get_master_lcore ())) { -evt_err ("worker lcores overlaps with master lcore" ); +if (evt_lcores_has_overlap (opt->wlcores,rte_get_initial_lcore ())) { +evt_err ("worker lcores overlaps with initial lcore" );return -1 ; }
@@ -117,8 +117,8 @@ order_opt_check(struct evt_options *opt) }/* Validate producer lcore */ -if (plcore == (int )rte_get_master_lcore ()) { -evt_err ("producer lcore and master lcore should be different" ); +if (plcore == (int )rte_get_initial_lcore ()) { +evt_err ("producer lcore and initial lcore should be different" );return -1 ; }if (!rte_lcore_is_enabled (plcore)) {
@@ -245,7 +245,7 @@ order_launch_lcores(struct evt_test *test, struct evt_options *opt,int wkr_idx =0 ;/* launch workers */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (!(opt->wlcores[lcore_id]))continue ;
app/test-eventdev/test_perf_common.c +8 -8
@@ -254,7 +254,7 @@ perf_launch_lcores(struct evt_test *test, struct evt_options *opt,int port_idx =0 ;/* launch workers */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (!(opt->wlcores[lcore_id]))continue ;
@@ -268,7 +268,7 @@ perf_launch_lcores(struct evt_test *test, struct evt_options *opt, }/* launch producers */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (!(opt->plcores[lcore_id]))continue ;
@@ -541,8 +541,8 @@ perf_opt_check(struct evt_options *opt, uint64_t nb_queues) {unsigned int lcores; -/* N producer + N worker + 1 master when producer cores are used -* Else N worker + 1 master when Rx adapter is used +/* N producer + N worker + 1 initial lcore when producer cores are used +* Else N worker + 1 initial lcore when Rx adapter is used */ lcores = opt->prod_type ==EVT_PROD_TYPE_SYNT ?3 :2 ;
@@ -552,8 +552,8 @@ perf_opt_check(struct evt_options *opt, uint64_t nb_queues) }/* Validate worker lcores */ -if (evt_lcores_has_overlap (opt->wlcores,rte_get_master_lcore ())) { -evt_err ("worker lcores overlaps with master lcore" ); +if (evt_lcores_has_overlap (opt->wlcores,rte_get_initial_lcore ())) { +evt_err ("worker lcores overlaps with initial lcore" );return -1 ; }if (evt_lcores_has_overlap_multi (opt->wlcores, opt->plcores)) {
@@ -573,8 +573,8 @@ perf_opt_check(struct evt_options *opt, uint64_t nb_queues) opt->prod_type == EVT_PROD_TYPE_EVENT_TIMER_ADPTR) {/* Validate producer lcores */ if (evt_lcores_has_overlap (opt->plcores, -rte_get_master_lcore ())) { -evt_err ("producer lcores overlaps with master lcore" ); +rte_get_initial_lcore ())) { +evt_err ("producer lcores overlaps with initial lcore" );return -1 ; }if (evt_has_disabled_lcore (opt->plcores)) {
app/test-eventdev/test_pipeline_common.c +4 -4
@@ -60,7 +60,7 @@ pipeline_launch_lcores(struct evt_test *test, struct evt_options *opt,int port_idx =0 ;/* launch workers */ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (!(opt->wlcores[lcore_id]))continue ;
@@ -107,7 +107,7 @@ pipeline_opt_check(struct evt_options *opt, uint64_t nb_queues) {unsigned int lcores;/* -* N worker + 1 master +* N worker + 1 initial lcore */ lcores =2 ;
@@ -129,8 +129,8 @@ pipeline_opt_check(struct evt_options *opt, uint64_t nb_queues) }/* Validate worker lcores */ -if (evt_lcores_has_overlap (opt->wlcores,rte_get_master_lcore ())) { -evt_err ("worker lcores overlaps with master lcore" ); +if (evt_lcores_has_overlap (opt->wlcores,rte_get_initial_lcore ())) { +evt_err ("worker lcores overlaps with initial lcore" );return -1 ; }if (evt_has_disabled_lcore (opt->wlcores)) {
Signature · 1 line
2.26.2
PATCH v3 20/27 app/test: replace refernces to master/slave
In reply to Stephen HemmingerUse initial and worker when referring to lcores
--- app/test/autotest_test_funcs.py | 2 +- app/test/test.c | 2 +- app/test/test_atomic.c | 26 ++++---- app/test/test_barrier.c | 2 +- app/test/test_cryptodev.c | 16 ++--- app/test/test_distributor.c | 8 +-- app/test/test_distributor_perf.c | 10 +-- app/test/test_eal_flags.c | 32 +++++----- app/test/test_efd.c | 2 +- app/test/test_efd_perf.c | 2 +- app/test/test_func_reentrancy.c | 20 +++--- app/test/test_hash_multiwriter.c | 4 +- app/test/test_hash_readwrite.c | 38 +++++------ app/test/test_kni.c | 16 ++--- app/test/test_malloc.c | 12 ++-- app/test/test_mbuf.c | 36 +++++------ app/test/test_mcslock.c | 28 ++++---- app/test/test_mempool_perf.c | 10 +-- app/test/test_mp_secondary.c | 2 +- app/test/test_pdump.c | 2 +- app/test/test_per_lcore.c | 14 ++-- app/test/test_pmd_perf.c | 20 +++--- app/test/test_rcu_qsbr.c | 2 +- app/test/test_rcu_qsbr_perf.c | 2 +- app/test/test_ring_perf.c | 14 ++-- app/test/test_ring_stress_impl.h | 10 +-- app/test/test_rwlock.c | 28 ++++---- app/test/test_service_cores.c | 10 +-- app/test/test_spinlock.c | 34 +++++----- app/test/test_stack.c | 2 +- app/test/test_stack_perf.c | 6 +- app/test/test_ticketlock.c | 36 +++++------ app/test/test_timer.c | 106 +++++++++++++++---------------- app/test/test_timer_racecond.c | 27 ++++---- app/test/test_timer_secondary.c | 2 +- app/test/test_trace_perf.c | 4 +- 36 files changed, 294 insertions(+), 293 deletions(-)
app/test/autotest_test_funcs.py +1 -1
@@ -102,7 +102,7 @@ def rwlock_autotest(child, test_name): index = child.expect(["Test OK", "Test Failed", "Hello from core ([0-9]*) !", - "Global write lock taken on master " + "Global write lock taken on initial lcore " "core ([0-9]*)", pexpect.TIMEOUT], timeout=10) # ok
app/test/test.c +1 -1
@@ -58,7 +58,7 @@ do_recursive_call(void)#endif #endif { "test_missing_c_flag", no_action }, - { "test_master_lcore_flag", no_action }, + { "test_initial_lcore_flag", no_action }, { "test_invalid_n_flag", no_action }, { "test_no_hpet_flag", no_action }, { "test_whitelist_flag", no_action },
app/test/test_atomic.c +13 -13
@@ -456,7 +456,7 @@ test_atomic(void)printf ("usual inc/dec/add/sub functions\n" ); -rte_eal_mp_remote_launch (test_atomic_usual,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_usual,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_set (&synchro,0 );
@@ -482,7 +482,7 @@ test_atomic(void)rte_atomic32_set (&a32,0 );rte_atomic16_set (&a16,0 );rte_atomic64_set (&count,0 ); -rte_eal_mp_remote_launch (test_atomic_tas,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_tas,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_set (&synchro,0 );
@@ -499,7 +499,7 @@ test_atomic(void)rte_atomic16_set (&a16,0 );rte_atomic64_set (&count,0 );rte_eal_mp_remote_launch (test_atomic_addsub_and_return,NULL , -SKIP_MASTER ); +SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_set (&synchro,0 );
@@ -510,8 +510,8 @@ test_atomic(void) }/* -* Set a64, a32 and a16 with the same value of minus "number of slave -* lcores", launch all slave lcores to atomically increase by one and +* Set a64, a32 and a16 with the same value of minus "number of worker +* lcores", launch all worker lcores to atomically increase by one and * test them respectively. * Each lcore should have only one chance to increase a64 by one and * then check if it is equal to 0, but there should be only one lcore
@@ -519,7 +519,7 @@ test_atomic(void)* Then a variable of "count", initialized to zero, is increased by * one if a64, a32 or a16 is 0 after being increased and tested * atomically. -* We can check if "count" is finally equal to 3 to see if all slave +* We can check if "count" is finally equal to 3 to see if all worker * lcores performed "atomic inc and test" right. */ printf ("inc and test\n" );
@@ -533,7 +533,7 @@ test_atomic(void)rte_atomic64_set (&a64, (int64_t )(1 - (int64_t )rte_lcore_count ()));rte_atomic32_set (&a32, (int32_t )(1 - (int32_t )rte_lcore_count ()));rte_atomic16_set (&a16, (int16_t )(1 - (int16_t )rte_lcore_count ())); -rte_eal_mp_remote_launch (test_atomic_inc_and_test,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_inc_and_test,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_clear (&synchro);
@@ -544,7 +544,7 @@ test_atomic(void) }/* -* Same as above, but this time we set the values to "number of slave +* Same as above, but this time we set the values to "number of worker * lcores", and decrement instead of increment. */ printf ("dec and test\n" );
@@ -555,7 +555,7 @@ test_atomic(void)rte_atomic64_set (&a64, (int64_t )(rte_lcore_count () -1 ));rte_atomic32_set (&a32, (int32_t )(rte_lcore_count () -1 ));rte_atomic16_set (&a16, (int16_t )(rte_lcore_count () -1 )); -rte_eal_mp_remote_launch (test_atomic_dec_and_test,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_dec_and_test,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_clear (&synchro);
@@ -569,10 +569,10 @@ test_atomic(void)/* * This case tests the functionality of rte_atomic128_cmp_exchange * API. It calls rte_atomic128_cmp_exchange with four kinds of memory -* models successively on each slave core. Once each 128-bit atomic +* models successively on each worker core. Once each 128-bit atomic * compare and swap operation is successful, it updates the global * 128-bit counter by 2 for the first 64-bit and 1 for the second -* 64-bit. Each slave core iterates this test N times. +* 64-bit. Each worker core iterates this test N times. * At the end of test, verify whether the first 64-bits of the 128-bit * counter and the second 64bits is differ by the total iterations. If * it is, the test passes.
@@ -585,7 +585,7 @@ test_atomic(void) count128.val[1 ] =0 ;rte_eal_mp_remote_launch (test_atomic128_cmp_exchange,NULL , -SKIP_MASTER ); +SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_clear (&synchro);
@@ -619,7 +619,7 @@ test_atomic(void) token64 = ((uint64_t )get_crc8 (&t.u8[0 ],sizeof (token64) -1 ) <<56 ) | (t.u64 &0x00ffffffffffffff ); -rte_eal_mp_remote_launch (test_atomic_exchange,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (test_atomic_exchange,NULL ,SKIP_INITIAL );rte_atomic32_set (&synchro,1 );rte_eal_mp_wait_lcore ();rte_atomic32_clear (&synchro);
app/test/test_barrier.c +1 -1
@@ -236,7 +236,7 @@ plock_test(uint64_t iter, enum plock_use_type utype)/* test phase - start and wait for completion on each active lcore */ -rte_eal_mp_remote_launch (plock_test1_lcore, lpt,CALL_MASTER ); +rte_eal_mp_remote_launch (plock_test1_lcore, lpt,CALL_INITIAL );rte_eal_mp_wait_lcore ();/* validation phase - make sure that shared and local data match */
app/test/test_cryptodev.c +8 -8
@@ -474,29 +474,29 @@ testsuite_setup(void)char vdev_args[VDEV_ARGS_SIZE ] = {"" };char temp_str[VDEV_ARGS_SIZE ] = {"mode=multi-core," "ordering=enable,name=cryptodev_test_scheduler,corelist=" }; -uint16_t slave_core_count =0 ; +uint16_t worker_core_count =0 ;uint16_t socket_id =0 ;if (gbl_driver_id ==rte_cryptodev_driver_id_get (RTE_STR (CRYPTODEV_NAME_SCHEDULER_PMD ))) { -/* Identify the Slave Cores -* Use 2 slave cores for the device args +/* Identify the Worker Cores +* Use 2 worker cores for the device args */ -RTE_LCORE_FOREACH_SLAVE (i) { -if (slave_core_count >1 ) +RTE_LCORE_FOREACH_WORKER (i) { +if (worker_core_count >1 )break ;snprintf (vdev_args,sizeof (vdev_args),"%s%d" , temp_str, i);strcpy (temp_str, vdev_args);strlcat (temp_str,";" ,sizeof (temp_str)); - slave_core_count++; + worker_core_count++; socket_id =rte_lcore_to_socket_id (i); } -if (slave_core_count !=2 ) { +if (worker_core_count !=2 ) {RTE_LOG (ERR ,USER1 ,"Cryptodev scheduler test require at least " -"two slave cores to run. " +"two worker cores to run. " "Please use the correct coremask.\n" );return TEST_FAILED ; }
app/test/test_distributor.c +4 -4
@@ -654,13 +654,13 @@ test_distributor(void) sizeof(worker_params.name));rte_eal_mp_remote_launch (handle_work, - &worker_params,SKIP_MASTER ); + &worker_params,SKIP_INITIAL );if (sanity_test (&worker_params, p) <0 ) goto err;quit_workers (&worker_params, p);rte_eal_mp_remote_launch (handle_work_with_free_mbufs, - &worker_params,SKIP_MASTER ); + &worker_params,SKIP_INITIAL );if (sanity_test_with_mbuf_alloc (&worker_params, p) <0 ) goto err;quit_workers (&worker_params, p);
@@ -668,7 +668,7 @@ test_distributor(void)if (rte_lcore_count () >2 ) {rte_eal_mp_remote_launch (handle_work_for_shutdown_test, &worker_params, -SKIP_MASTER ); +SKIP_INITIAL );if (sanity_test_with_worker_shutdown (&worker_params, p) <0 ) goto err;
@@ -676,7 +676,7 @@ test_distributor(void)rte_eal_mp_remote_launch (handle_work_for_shutdown_test, &worker_params, -SKIP_MASTER ); +SKIP_INITIAL );if (test_flush_with_worker_shutdown (&worker_params, p) <0 ) goto err;
app/test/test_distributor_perf.c +5 -5
@@ -54,10 +54,10 @@ time_cache_line_switch(void)/* allocate a full cache line for data, we use only first byte of it */ uint64_t data[RTE_CACHE_LINE_SIZE *3 /sizeof (uint64_t )]; -unsigned i, slaveid =rte_get_next_lcore (rte_lcore_id (),0 ,0 ); +unsigned i, workerid =rte_get_next_lcore (rte_lcore_id (),0 ,0 );volatile uint64_t *pdata = &data[0 ]; *pdata =1 ; -rte_eal_remote_launch ((lcore_function_t *)flip_bit, &data[0 ], slaveid); +rte_eal_remote_launch ((lcore_function_t *)flip_bit, &data[0 ], workerid);while (*pdata)rte_pause ();
@@ -72,7 +72,7 @@ time_cache_line_switch(void)while (*pdata)rte_pause (); *pdata =2 ; -rte_eal_wait_lcore (slaveid); +rte_eal_wait_lcore (workerid);printf ("==== Cache line switch test ===\n" );printf ("Time for %u iterations = %" PRIu64" ticks\n" , (1 <<ITER_POWER_CL ), end_time-start_time);
@@ -251,13 +251,13 @@ test_distributor_perf(void) }printf ("=== Performance test of distributor (single mode) ===\n" ); -rte_eal_mp_remote_launch (handle_work, ds,SKIP_MASTER ); +rte_eal_mp_remote_launch (handle_work, ds,SKIP_INITIAL );if (perf_test (ds, p) <0 )return -1 ;quit_workers (ds, p);printf ("=== Performance test of distributor (burst mode) ===\n" ); -rte_eal_mp_remote_launch (handle_work, db,SKIP_MASTER ); +rte_eal_mp_remote_launch (handle_work, db,SKIP_INITIAL );if (perf_test (db, p) <0 )return -1 ;quit_workers (db, p);
app/test/test_eal_flags.c +16 -16
@@ -596,10 +596,10 @@ test_missing_c_flag(void) }/* -* Test --master-lcore option with matching coremask +* Test --initial-lcore option with matching coremask */ static int -test_master_lcore_flag (void ) +test_initial_lcore_flag (void ) {#ifdef RTE_EXEC_ENV_FREEBSD /* BSD target doesn't support prefixes at this point */
@@ -616,34 +616,34 @@ test_master_lcore_flag(void)if (!rte_lcore_is_enabled (0 ) || !rte_lcore_is_enabled (1 ))return TEST_SKIPPED ; -/* --master-lcore flag but no value */ +/* --initial-lcore flag but no value */ const char *argv1[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" }; -/* --master-lcore flag with invalid value */ +"-c" ,"3" ,"--initial-lcore" }; +/* --initial-lcore flag with invalid value */ const char *argv2[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" ,"-1" }; +"-c" ,"3" ,"--initial-lcore" ,"-1" };const char *argv3[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" ,"X" }; -/* master lcore not in coremask */ +"-c" ,"3" ,"--initial-lcore" ,"X" }; +/* initial lcore not in coremask */ const char *argv4[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" ,"2" }; +"-c" ,"3" ,"--initial-lcore" ,"2" };/* valid value */ const char *argv5[] = { prgname, prefix, mp_flag, -"-c" ,"3" ,"--master-lcore" ,"1" }; +"-c" ,"3" ,"--initial-lcore" ,"1" };/* valid value set before coremask */ const char *argv6[] = { prgname, prefix, mp_flag, -"--master-lcore" ,"1" ,"-c" ,"3" }; +"--initial-lcore" ,"1" ,"-c" ,"3" };if (launch_proc (argv1) ==0 ||launch_proc (argv2) ==0 ||launch_proc (argv3) ==0 ||launch_proc (argv4) ==0 ) { -printf ("Error - process ran without error with wrong --master-lcore\n" ); +printf ("Error - process ran without error with wrong --initial-lcore\n" );return -1 ; }if (launch_proc (argv5) !=0 ||launch_proc (argv6) !=0 ) { -printf ("Error - process did not run ok with valid --master-lcore\n" ); +printf ("Error - process did not run ok with valid --initial-lcore\n" );return -1 ; }return 0 ;
@@ -1465,9 +1465,9 @@ test_eal_flags(void)return ret; } - ret =test_master_lcore_flag (); + ret =test_initial_lcore_flag ();if (ret <0 ) { -printf ("Error in test_master_lcore_flag()\n" ); +printf ("Error in test_initial_lcore_flag()\n" );return ret; }
@@ -1539,7 +1539,7 @@ REGISTER_TEST_COMMAND(eal_flags_autotest, test_eal_flags);/* subtests used in meson for CI */ REGISTER_TEST_COMMAND (eal_flags_c_opt_autotest, test_missing_c_flag); -REGISTER_TEST_COMMAND (eal_flags_master_opt_autotest, test_master_lcore_flag); +REGISTER_TEST_COMMAND (eal_flags_master_opt_autotest, test_initial_lcore_flag);REGISTER_TEST_COMMAND (eal_flags_n_opt_autotest, test_invalid_n_flag);REGISTER_TEST_COMMAND (eal_flags_hpet_autotest, test_no_hpet_flag);REGISTER_TEST_COMMAND (eal_flags_no_huge_autotest, test_no_huge_flag);
app/test/test_efd.c +1 -1
@@ -100,7 +100,7 @@ static inline uint8_t efd_get_all_sockets_bitmask(void) {uint8_t all_cpu_sockets_bitmask =0 ;unsigned int i; -unsigned int next_lcore =rte_get_master_lcore (); +unsigned int next_lcore =rte_get_initial_lcore ();const int val_true =1 , val_false =0 ;for (i =0 ; i <rte_lcore_count (); i++) { all_cpu_sockets_bitmask |=1 <<rte_lcore_to_socket_id (next_lcore);
app/test/test_efd_perf.c +1 -1
@@ -33,7 +33,7 @@ static inline uint8_t efd_get_all_sockets_bitmask(void) {uint8_t all_cpu_sockets_bitmask =0 ;unsigned int i; -unsigned int next_lcore =rte_get_master_lcore (); +unsigned int next_lcore =rte_get_initial_lcore ();const int val_true =1 , val_false =0 ;for (i =0 ; i <rte_lcore_count (); i++) { all_cpu_sockets_bitmask |=1 <<rte_lcore_to_socket_id (next_lcore);
app/test/test_func_reentrancy.c +10 -10
@@ -57,8 +57,8 @@ typedef void (*case_clean_t)(unsigned lcore_id);static rte_atomic32_t obj_count =RTE_ATOMIC32_INIT (0 );static rte_atomic32_t synchro =RTE_ATOMIC32_INIT (0 ); -#define WAIT_SYNCHRO_FOR_SLAVES () do{ \ - if (lcore_self != rte_get_master_lcore()) \ +#define WAIT_SYNCHRO_FOR_WORKERS () do{ \ + if (lcore_self != rte_get_initial_lcore()) \ while (rte_atomic32_read(&synchro) == 0); \ } while(0)
@@ -70,7 +70,7 @@ test_eal_init_once(__rte_unused void *arg) {unsigned lcore_self =rte_lcore_id (); -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();rte_atomic32_set (&obj_count,1 );/* silent the check in the caller */ if (rte_eal_init (0 ,NULL ) !=-1 )
@@ -106,7 +106,7 @@ ring_create_lookup(__rte_unused void *arg)char ring_name[MAX_STRING_SIZE ];int i; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same ring simultaneously on all threads */ for (i =0 ; i <MAX_ITER_ONCE ; i++) {
@@ -166,7 +166,7 @@ mempool_create_lookup(__rte_unused void *arg)char mempool_name[MAX_STRING_SIZE ];int i; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same mempool simultaneously on all threads */ for (i =0 ; i <MAX_ITER_ONCE ; i++) {
@@ -232,7 +232,7 @@ hash_create_free(__rte_unused void *arg) .socket_id = 0, }; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same hash simultaneously on all threads */ hash_params.name ="fr_test_once" ;
@@ -296,7 +296,7 @@ fbk_create_free(__rte_unused void *arg) .init_val = RTE_FBK_HASH_INIT_VAL_DEFAULT, }; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same fbk hash table simultaneously on all threads */ fbk_params.name ="fr_test_once" ;
@@ -359,7 +359,7 @@ lpm_create_free(__rte_unused void *arg)char lpm_name[MAX_STRING_SIZE ];int i; -WAIT_SYNCHRO_FOR_SLAVES (); +WAIT_SYNCHRO_FOR_WORKERS ();/* create the same lpm simultaneously on all threads */ for (i =0 ; i <MAX_ITER_ONCE ; i++) {
@@ -430,7 +430,7 @@ launch_test(struct test_case *pt_case)rte_atomic32_set (&obj_count,0 );rte_atomic32_set (&synchro,0 ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (cores ==1 )break ; cores--;
@@ -443,7 +443,7 @@ launch_test(struct test_case *pt_case) ret =-1 ; cores = cores_save; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (cores ==1 )break ; cores--;
app/test/test_hash_multiwriter.c +2 -2
@@ -64,7 +64,7 @@ test_hash_multiwriter_worker(void *arg)/* * Calculate offset for entries based on the position of the -* logical core, from the master core (not counting not enabled cores) +* logical core, from the initial core (not counting not enabled cores) */ offset = pos_core * tbl_multiwriter_test_params.nb_tsx_insertion;
@@ -194,7 +194,7 @@ test_hash_multiwriter(void)/* Fire all threads. */ rte_eal_mp_remote_launch (test_hash_multiwriter_worker, - enabled_core_ids,CALL_MASTER ); + enabled_core_ids,CALL_INITIAL );rte_eal_mp_wait_lcore (); count =rte_hash_count (handle);
app/test/test_hash_readwrite.c +19 -19
@@ -25,7 +25,7 @@#define NUM_TEST 3unsigned int core_cnt[NUM_TEST ] = {2 ,4 ,8 }; -unsigned int slave_core_ids[RTE_MAX_LCORE ]; +unsigned int worker_core_ids[RTE_MAX_LCORE ];struct perf {uint32_t single_read;uint32_t single_write;
@@ -65,7 +65,7 @@ test_hash_readwrite_worker(__rte_unused void *arg) ret =rte_malloc (NULL ,sizeof (int ) * tbl_rw_test_param.num_insert,0 );for (i =0 ; i <rte_lcore_count (); i++) { -if (slave_core_ids[i] == lcore_id) +if (worker_core_ids[i] == lcore_id)break ; } offset = tbl_rw_test_param.num_insert * i;
@@ -206,7 +206,7 @@ test_hash_readwrite_functional(int use_htm, int use_rw_lf, int use_ext)uint32_t duplicated_keys =0 ;uint32_t lost_keys =0 ;int use_jhash =1 ; -int slave_cnt =rte_lcore_count () -1 ; +int worker_cnt =rte_lcore_count () -1 ;uint32_t tot_insert =0 ;rte_atomic64_init (&gcycles);
@@ -224,11 +224,11 @@ test_hash_readwrite_functional(int use_htm, int use_rw_lf, int use_ext) tot_insert =TOTAL_INSERT ; tbl_rw_test_param.num_insert = - tot_insert / slave_cnt; + tot_insert / worker_cnt; tbl_rw_test_param.rounded_tot_insert = tbl_rw_test_param.num_insert - * slave_cnt; + * worker_cnt;printf ("\nHTM = %d, RW-LF = %d, EXT-Table = %d\n" , use_htm, use_rw_lf, use_ext);
@@ -236,7 +236,7 @@ test_hash_readwrite_functional(int use_htm, int use_rw_lf, int use_ext)/* Fire all threads. */ rte_eal_mp_remote_launch (test_hash_readwrite_worker, -NULL ,SKIP_MASTER ); +NULL ,SKIP_INITIAL );rte_eal_mp_wait_lcore (); while (rte_hash_iterate(tbl_rw_test_param.h, &next_key,
@@ -330,7 +330,7 @@ test_rw_writer(void *arg)uint64_t offset;for (i =0 ; i <rte_lcore_count (); i++) { -if (slave_core_ids[i] == lcore_id) +if (worker_core_ids[i] == lcore_id)break ; }
@@ -433,8 +433,8 @@ test_hash_readwrite_perf(struct perf *perf_results, int use_htm, perf_results->single_read = end / i;for (n =0 ; n <NUM_TEST ; n++) { -unsigned int tot_slave_lcore =rte_lcore_count () -1 ; -if (tot_slave_lcore < core_cnt[n] *2 ) +unsigned int tot_worker_lcore =rte_lcore_count () -1 ; +if (tot_worker_lcore < core_cnt[n] *2 ) goto finish;rte_atomic64_clear (&greads);
@@ -467,7 +467,7 @@ test_hash_readwrite_perf(struct perf *perf_results, int use_htm,for (i =0 ; i < core_cnt[n]; i++)rte_eal_remote_launch (test_rw_reader, (void *)(uintptr_t )read_cnt, - slave_core_ids[i]); + worker_core_ids[i]);rte_eal_mp_wait_lcore ();
@@ -476,7 +476,7 @@ test_hash_readwrite_perf(struct perf *perf_results, int use_htm,for (; i < core_cnt[n] *2 ; i++)rte_eal_remote_launch (test_rw_writer, (void *)((uintptr_t )start_coreid), - slave_core_ids[i]); + worker_core_ids[i]);rte_eal_mp_wait_lcore ();
@@ -521,20 +521,20 @@ test_hash_readwrite_perf(struct perf *perf_results, int use_htm,for (i = core_cnt[n]; i < core_cnt[n] *2 ; i++)rte_eal_remote_launch (test_rw_writer, (void *)((uintptr_t )start_coreid), - slave_core_ids[i]); + worker_core_ids[i]);for (i =0 ; i < core_cnt[n]; i++)rte_eal_remote_launch (test_rw_reader, (void *)(uintptr_t )read_cnt, - slave_core_ids[i]); + worker_core_ids[i]); }else {for (i =0 ; i < core_cnt[n]; i++)rte_eal_remote_launch (test_rw_reader, (void *)(uintptr_t )read_cnt, - slave_core_ids[i]); + worker_core_ids[i]);for (; i < core_cnt[n] *2 ; i++)rte_eal_remote_launch (test_rw_writer, (void *)((uintptr_t )start_coreid), - slave_core_ids[i]); + worker_core_ids[i]); }rte_eal_mp_wait_lcore ();
@@ -626,8 +626,8 @@ test_hash_rw_perf_main(void)return TEST_SKIPPED ; } -RTE_LCORE_FOREACH_SLAVE (core_id) { - slave_core_ids[i] = core_id; +RTE_LCORE_FOREACH_WORKER (core_id) { + worker_core_ids[i] = core_id; i++; }
@@ -710,8 +710,8 @@ test_hash_rw_func_main(void)return TEST_SKIPPED ; } -RTE_LCORE_FOREACH_SLAVE (core_id) { - slave_core_ids[i] = core_id; +RTE_LCORE_FOREACH_WORKER (core_id) { + worker_core_ids[i] = core_id; i++; }
app/test/test_kni.c +8 -8
@@ -85,7 +85,7 @@ static struct rte_kni_ops kni_ops = { .config_promiscusity = NULL, }; -static unsigned lcore_master, lcore_ingress, lcore_egress; +static unsigned lcore_initial, lcore_ingress, lcore_egress;static struct rte_kni *test_kni_ctx;static struct test_kni_stats stats;
@@ -202,7 +202,7 @@ test_kni_link_change(void)* supported by KNI kernel module. The ingress lcore will allocate mbufs and * transmit them to kernel space; while the egress lcore will receive the mbufs * from kernel space and free them. -* On the master lcore, several commands will be run to check handling the +* On the initial lcore, several commands will be run to check handling the * kernel requests. And it will finally set the flag to exit the KNI * transmitting/receiving to/from the kernel space. *
@@ -217,7 +217,7 @@ test_kni_loop(__rte_unused void *arg)const unsigned lcore_id =rte_lcore_id ();struct rte_mbuf *pkts_burst[PKT_BURST_SZ ]; -if (lcore_id == lcore_master) { +if (lcore_id == lcore_initial) {rte_delay_ms (KNI_TIMEOUT_MS );/* tests of handling kernel request */ if (system(IFCONFIG TEST_KNI_PORT" up") == -1)
@@ -276,12 +276,12 @@ test_kni_allocate_lcores(void) {unsigned i, count =0 ; - lcore_master =rte_get_master_lcore (); -printf ("master lcore: %u\n" , lcore_master); + lcore_initial =rte_get_initial_lcore (); +printf ("initial lcore: %u\n" , lcore_initial);for (i =0 ; i <RTE_MAX_LCORE ; i++) {if (count >=2 )break ; -if (rte_lcore_is_enabled (i) && i != lcore_master) { +if (rte_lcore_is_enabled (i) && i != lcore_initial) { count ++;if (count ==1 ) lcore_ingress = i;
@@ -487,8 +487,8 @@ test_kni_processing(uint16_t port_id, struct rte_mempool *mp)if (ret !=0 ) goto fail_kni; -rte_eal_mp_remote_launch (test_kni_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (i) { +rte_eal_mp_remote_launch (test_kni_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (i) {if (rte_eal_wait_lcore (i) <0 ) { ret =-1 ; goto fail_kni;
app/test/test_malloc.c +6 -6
@@ -1007,11 +1007,11 @@ test_malloc(void)else printf ("test_realloc() passed\n" );/*----------------------------*/ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (test_align_overlap_per_lcore,NULL , lcore_id); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 ) ret =-1 ; }
@@ -1022,11 +1022,11 @@ test_malloc(void)else printf ("test_align_overlap_per_lcore() passed\n" );/*----------------------------*/ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (test_reordered_free_per_lcore,NULL , lcore_id); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 ) ret =-1 ; }
@@ -1037,11 +1037,11 @@ test_malloc(void)else printf ("test_reordered_free_per_lcore() passed\n" );/*----------------------------*/ -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {rte_eal_remote_launch (test_random_alloc_free,NULL , lcore_id); } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 ) ret =-1 ; }
app/test/test_mbuf.c +18 -18
@@ -72,7 +72,7 @@#ifdef RTE_MBUF_REFCNT_ATOMIC -static volatile uint32_t refcnt_stop_slaves; +static volatile uint32_t refcnt_stop_workers;static unsigned refcnt_lcore[RTE_MAX_LCORE ];#endif
@@ -1000,7 +1000,7 @@ test_pktmbuf_free_segment(struct rte_mempool *pktmbuf_pool)#ifdef RTE_MBUF_REFCNT_ATOMIC static int -test_refcnt_slave (void *arg) +test_refcnt_worker (void *arg) {unsigned lcore, free;void *mp =0 ;
@@ -1010,7 +1010,7 @@ test_refcnt_slave(void *arg)printf ("%s started at lcore %u\n" , __func__, lcore); free =0 ; -while (refcnt_stop_slaves ==0 ) { +while (refcnt_stop_workers ==0 ) {if (rte_ring_dequeue (refcnt_mbuf_ring, &mp) ==0 ) { free++;rte_pktmbuf_free (mp);
@@ -1038,7 +1038,7 @@ test_refcnt_iter(unsigned int lcore, unsigned int iter,/* For each mbuf in the pool: * - allocate mbuf, * - increment it's reference up to N+1, -* - enqueue it N times into the ring for slave cores to free. +* - enqueue it N times into the ring for worker cores to free. */ for (i = 0, n = rte_mempool_avail_count(refcnt_pool); i != n && (m = rte_pktmbuf_alloc(refcnt_pool)) != NULL;
@@ -1062,7 +1062,7 @@ test_refcnt_iter(unsigned int lcore, unsigned int iter,rte_panic ("(lcore=%u, iter=%u): was able to allocate only " "%u from %u mbufs\n" , lcore, iter, i, n); -/* wait till slave lcores will consume all mbufs */ +/* wait till worker lcores will consume all mbufs */ while (!rte_ring_empty (refcnt_mbuf_ring)) ;
@@ -1083,8 +1083,8 @@ test_refcnt_iter(unsigned int lcore, unsigned int iter, }static int -test_refcnt_master (struct rte_mempool *refcnt_pool, -struct rte_ring *refcnt_mbuf_ring) +test_refcnt_main (struct rte_mempool *refcnt_pool, +struct rte_ring *refcnt_mbuf_ring) {unsigned i, lcore;
@@ -1094,7 +1094,7 @@ test_refcnt_master(struct rte_mempool *refcnt_pool,for (i =0 ; i !=REFCNT_MAX_ITER ; i++)test_refcnt_iter (lcore, i, refcnt_pool, refcnt_mbuf_ring); - refcnt_stop_slaves =1 ; + refcnt_stop_workers =1 ;rte_wmb ();printf ("%s finished at lcore %u\n" , __func__, lcore);
@@ -1107,7 +1107,7 @@ static inttest_refcnt_mbuf (void) {#ifdef RTE_MBUF_REFCNT_ATOMIC -unsigned int master, slave, tref; +unsigned int initial, worker, tref;int ret =-1 ;struct rte_mempool *refcnt_pool =NULL ;struct rte_ring *refcnt_mbuf_ring =NULL ;
@@ -1139,26 +1139,26 @@ test_refcnt_mbuf(void) goto err; } - refcnt_stop_slaves =0 ; + refcnt_stop_workers =0 ;memset (refcnt_lcore,0 ,sizeof (refcnt_lcore)); -rte_eal_mp_remote_launch (test_refcnt_slave, refcnt_mbuf_ring, -SKIP_MASTER ); +rte_eal_mp_remote_launch (test_refcnt_worker, refcnt_mbuf_ring, +SKIP_INITIAL ); -test_refcnt_master (refcnt_pool, refcnt_mbuf_ring); +test_refcnt_main (refcnt_pool, refcnt_mbuf_ring);rte_eal_mp_wait_lcore ();/* check that we porcessed all references */ tref =0 ; - master =rte_get_master_lcore (); + initial =rte_get_initial_lcore (); -RTE_LCORE_FOREACH_SLAVE (slave) - tref += refcnt_lcore[slave]; +RTE_LCORE_FOREACH_WORKER (worker) + tref += refcnt_lcore[worker]; -if (tref != refcnt_lcore[master]) +if (tref != refcnt_lcore[initial])rte_panic ("referenced mbufs: %u, freed mbufs: %u\n" , - tref, refcnt_lcore[master]); + tref, refcnt_lcore[initial]);rte_mempool_dump (stdout, refcnt_pool);rte_ring_dump (stdout, refcnt_mbuf_ring);
app/test/test_mcslock.c +14 -14
@@ -28,7 +28,7 @@* These tests are derived from spin lock test cases. * * - The functional test takes all of these locks and launches the -* ''test_mcslock_per_core()'' function on each core (except the master). +* ''test_mcslock_per_core()'' function on each core (except the initial). * * - The function takes the global lock, display something, then releases * the global lock on each core.
@@ -123,9 +123,9 @@ test_mcslock_perf(void)printf ("\nTest with lock on %u cores...\n" , (rte_lcore_count ()));rte_atomic32_set (&synchro,0 ); -rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_MASTER ); +rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_INITIAL ); -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );load_loop_fn (&lock);
@@ -154,8 +154,8 @@ test_mcslock_try(__rte_unused void *arg)rte_mcslock_t ml_me =RTE_PER_LCORE (_ml_me);rte_mcslock_t ml_try_me =RTE_PER_LCORE (_ml_try_me); -/* Locked ml_try in the master lcore, so it should fail -* when trying to lock it in the slave lcore. +/* Locked ml_try in the initial lcore, so it should fail +* when trying to lock it in the worker lcore. */ if (rte_mcslock_trylock (&p_ml_try, &ml_try_me) ==0 ) {rte_mcslock_lock (&p_ml, &ml_me);
@@ -185,20 +185,20 @@ test_mcslock(void)* Test mcs lock & unlock on each core */ -/* slave cores should be waiting: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be waiting: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }rte_mcslock_lock (&p_ml, &ml_me); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_mcslock_per_core,NULL , i); } -/* slave cores should be busy: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be busy: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }
@@ -210,19 +210,19 @@ test_mcslock(void)/* * Test if it could return immediately from try-locking a locked object. * Here it will lock the mcs lock object first, then launch all the -* slave lcores to trylock the same mcs lock object. -* All the slave lcores should give up try-locking a locked object and +* worker lcores to trylock the same mcs lock object. +* All the worker lcores should give up try-locking a locked object and * return immediately, and then increase the "count" initialized with * zero by one per times. * We can check if the "count" is finally equal to the number of all -* slave lcores to see if the behavior of try-locking a locked +* worker lcores to see if the behavior of try-locking a locked * mcslock object is correct. */ if (rte_mcslock_trylock (&p_ml_try, &ml_try_me) ==0 )return -1 ; count =0 ; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_mcslock_try,NULL , i); }rte_eal_mp_wait_lcore ();
app/test/test_mempool_perf.c +5 -5
@@ -143,8 +143,8 @@ per_lcore_mempool_test(void *arg) stats[lcore_id].enq_count =0 ; -/* wait synchro for slaves */ -if (lcore_id !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore_id !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 ); start_cycles =rte_get_timer_cycles ();
@@ -214,7 +214,7 @@ launch_cores(struct rte_mempool *mp, unsigned int cores)return -1 ; } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (cores ==1 )break ; cores--;
@@ -222,13 +222,13 @@ launch_cores(struct rte_mempool *mp, unsigned int cores) mp, lcore_id); } -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 ); ret =per_lcore_mempool_test (mp); cores = cores_save; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (cores ==1 )break ; cores--;
app/test/test_mp_secondary.c +1 -1
@@ -94,7 +94,7 @@ run_secondary_instances(void)#endif snprintf (coremask,sizeof (coremask),"%x" , \ - (1 <<rte_get_master_lcore ())); + (1 <<rte_get_initial_lcore ())); ret |=launch_proc (argv1); ret |=launch_proc (argv2);
app/test/test_pdump.c +1 -1
@@ -184,7 +184,7 @@ run_pdump_server_tests(void) };snprintf (coremask,sizeof (coremask),"%x" , - (1 <<rte_get_master_lcore ())); + (1 <<rte_get_initial_lcore ())); ret =test_pdump_init (); ret |=launch_p (argv1);
app/test/test_per_lcore.c +7 -7
@@ -73,31 +73,31 @@ test_per_lcore(void)unsigned lcore_id;int ret; -rte_eal_mp_remote_launch (assign_vars,NULL ,SKIP_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (assign_vars,NULL ,SKIP_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; } -rte_eal_mp_remote_launch (display_vars,NULL ,SKIP_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +rte_eal_mp_remote_launch (display_vars,NULL ,SKIP_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }/* test if it could do remote launch twice at the same time or not */ - ret =rte_eal_mp_remote_launch (test_per_lcore_delay,NULL ,SKIP_MASTER ); + ret =rte_eal_mp_remote_launch (test_per_lcore_delay,NULL ,SKIP_INITIAL );if (ret <0 ) {printf ("It fails to do remote launch but it should able to do\n" );return -1 ; }/* it should not be able to launch a lcore which is running */ - ret =rte_eal_mp_remote_launch (test_per_lcore_delay,NULL ,SKIP_MASTER ); + ret =rte_eal_mp_remote_launch (test_per_lcore_delay,NULL ,SKIP_INITIAL );if (ret ==0 ) {printf ("It does remote launch successfully but it should not at this time\n" );return -1 ; } -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ; }
app/test/test_pmd_perf.c +10 -10
@@ -278,7 +278,7 @@ alloc_lcore(uint16_t socketid)for (lcore_id =0 ; lcore_id <RTE_MAX_LCORE ; lcore_id++) {if (LCORE_AVAIL != lcore_conf[lcore_id].status || lcore_conf[lcore_id].socketid != socketid || - lcore_id ==rte_get_master_lcore ()) + lcore_id ==rte_get_initial_lcore ())continue ; lcore_conf[lcore_id].status =LCORE_USED ; lcore_conf[lcore_id].nb_ports =0 ;
@@ -664,7 +664,7 @@ exec_burst(uint32_t flags, int lcore)static int test_pmd_perf (void ) { -uint16_t nb_ports, num, nb_lcores, slave_id = (uint16_t )-1 ; +uint16_t nb_ports, num, nb_lcores, worker_id = (uint16_t )-1 ;uint16_t nb_rxd =MAX_TRAFFIC_BURST ;uint16_t nb_txd =MAX_TRAFFIC_BURST ;uint16_t portid;
@@ -702,13 +702,13 @@ test_pmd_perf(void)RTE_ETH_FOREACH_DEV (portid) {if (socketid ==-1 ) { socketid =rte_eth_dev_socket_id (portid); - slave_id =alloc_lcore (socketid); -if (slave_id == (uint16_t )-1 ) { + worker_id =alloc_lcore (socketid); +if (worker_id == (uint16_t )-1 ) {printf ("No avail lcore to run test\n" );return -1 ; }printf ("Performance test runs on lcore %u socket %u\n" , - slave_id, socketid); + worker_id, socketid); }if (socketid !=rte_eth_dev_socket_id (portid)) {
@@ -765,8 +765,8 @@ test_pmd_perf(void)"rte_eth_promiscuous_enable: err=%s, port=%d\n" , rte_strerror(-ret), portid); - lcore_conf[slave_id].portlist[num++] = portid; - lcore_conf[slave_id].nb_ports++; + lcore_conf[worker_id].portlist[num++] = portid; + lcore_conf[worker_id].nb_ports++; }check_all_ports_link_status (nb_ports,RTE_PORT_ALL );
@@ -791,13 +791,13 @@ test_pmd_perf(void)if (NULL == do_measure) do_measure = measure_rxtx; -rte_eal_remote_launch (main_loop,NULL , slave_id); +rte_eal_remote_launch (main_loop,NULL , worker_id); -if (rte_eal_wait_lcore (slave_id) <0 ) +if (rte_eal_wait_lcore (worker_id) <0 )return -1 ; }else if (sc_flag ==SC_BURST_POLL_FIRST || sc_flag ==SC_BURST_XMIT_FIRST ) -if (exec_burst (sc_flag, slave_id) <0 ) +if (exec_burst (sc_flag, worker_id) <0 )return -1 ;/* port tear down */
app/test/test_rcu_qsbr.c +1 -1
@@ -1327,7 +1327,7 @@ test_rcu_qsbr_main(void) } num_cores =0 ; -RTE_LCORE_FOREACH_SLAVE (core_id) { +RTE_LCORE_FOREACH_WORKER (core_id) { enabled_core_ids[num_cores] = core_id; num_cores++; }
app/test/test_rcu_qsbr_perf.c +1 -1
@@ -625,7 +625,7 @@ test_rcu_qsbr_main(void)rte_atomic64_init (&check_cycles); num_cores =0 ; -RTE_LCORE_FOREACH_SLAVE (core_id) { +RTE_LCORE_FOREACH_WORKER (core_id) { enabled_core_ids[num_cores] = core_id; num_cores++; }
app/test/test_ring_perf.c +7 -7
@@ -297,7 +297,7 @@ run_on_core_pair(struct lcore_pair *cores, struct rte_ring *r, const int esize) lcore_count =0 ; param1.size = param2.size = bulk_sizes[i]; param1.r = param2.r = r; -if (cores->c1 ==rte_get_master_lcore ()) { +if (cores->c1 ==rte_get_initial_lcore ()) {rte_eal_remote_launch (f2, ¶m2, cores->c2);f1 (¶m1);rte_eal_wait_lcore (cores->c2);
@@ -340,8 +340,8 @@ load_loop_fn_helper(struct thread_params *p, const int esize)if (burst ==NULL )return -1 ; -/* wait synchro for slaves */ -if (lcore !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 )rte_pause ();
@@ -397,12 +397,12 @@ run_on_all_cores(struct rte_ring *r, const int esize) param.size = bulk_sizes[i]; param.r = r; -/* clear synchro and start slaves */ +/* clear synchro and start workers */ rte_atomic32_set (&synchro,0 ); -if (rte_eal_mp_remote_launch (lcore_f, ¶m,SKIP_MASTER ) <0 ) +if (rte_eal_mp_remote_launch (lcore_f, ¶m,SKIP_INITIAL ) <0 )return -1 ; -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );lcore_f (¶m);
@@ -553,7 +553,7 @@ test_ring_perf_esize(const int esize) goto test_fail; } -printf ("\n### Testing using all slave nodes ###\n" ); +printf ("\n### Testing using all worker nodes ###\n" );if (run_on_all_cores (r, esize) <0 ) goto test_fail;
app/test/test_ring_stress_impl.h +5 -5
@@ -6,7 +6,7 @@/** * Stress test for ring enqueue/dequeue operations. -* Performs the following pattern on each slave worker: +* Performs the following pattern on each worker worker: * dequeue/read-write data from the dequeued objects/enqueue. * Serves as both functional and performance test of ring * enqueue/dequeue operations under high contention
@@ -348,8 +348,8 @@ test_mt1(int (*test)(void *))memset (arg,0 ,sizeof (arg)); -/* launch on all slaves */ -RTE_LCORE_FOREACH_SLAVE (lc) { +/* launch on all workers */ +RTE_LCORE_FOREACH_WORKER (lc) { arg[lc].rng = r; arg[lc].stats = init_stat;rte_eal_remote_launch (test, &arg[lc], lc);
@@ -365,12 +365,12 @@ test_mt1(int (*test)(void *)) wrk_cmd =WRK_CMD_STOP ;rte_smp_wmb (); -/* wait for slaves and collect stats. */ +/* wait for workers and collect stats. */ mc =rte_lcore_id (); arg[mc].stats = init_stat; rc =0 ; -RTE_LCORE_FOREACH_SLAVE (lc) { +RTE_LCORE_FOREACH_WORKER (lc) { rc |=rte_eal_wait_lcore (lc);lcore_stat_aggr (&arg[mc].stats, &arg[lc].stats);if (verbose !=0 )
app/test/test_rwlock.c +14 -14
@@ -99,8 +99,8 @@ load_loop_fn(__rte_unused void *arg)uint64_t lcount =0 ;const unsigned int lcore =rte_lcore_id (); -/* wait synchro for slaves */ -if (lcore !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 ) ;
@@ -134,12 +134,12 @@ test_rwlock_perf(void)printf ("\nRwlock Perf Test on %u cores...\n" ,rte_lcore_count ()); -/* clear synchro and start slaves */ +/* clear synchro and start workers */ rte_atomic32_set (&synchro,0 ); -if (rte_eal_mp_remote_launch (load_loop_fn,NULL ,SKIP_MASTER ) <0 ) +if (rte_eal_mp_remote_launch (load_loop_fn,NULL ,SKIP_INITIAL ) <0 )return -1 ; -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );load_loop_fn (NULL );
@@ -161,7 +161,7 @@ test_rwlock_perf(void)* - There is a global rwlock and a table of rwlocks (one per lcore). * * - The test function takes all of these locks and launches the -* ``test_rwlock_per_core()`` function on each core (except the master). +* ``test_rwlock_per_core()`` function on each core (except the initial). * * - The function takes the global write lock, display something, * then releases the global lock.
@@ -187,21 +187,21 @@ rwlock_test1(void)rte_rwlock_write_lock (&sl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_rwlock_write_lock (&sl_tab[i]);rte_eal_remote_launch (test_rwlock_per_core,NULL , i); }rte_rwlock_write_unlock (&sl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_rwlock_write_unlock (&sl_tab[i]);rte_delay_ms (100 ); }rte_rwlock_write_lock (&sl);/* this message should be the last message of test */ -printf ("Global write lock taken on master core %u\n" ,rte_lcore_id ()); +printf ("Global write lock taken on initial core %u\n" ,rte_lcore_id ());rte_rwlock_write_unlock (&sl);rte_eal_mp_wait_lcore ();
@@ -462,26 +462,26 @@ try_rwlock_test_rda(void)try_test_reset ();/* start read test on all avaialble lcores */ -rte_eal_mp_remote_launch (try_read_lcore,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (try_read_lcore,NULL ,CALL_INITIAL );rte_eal_mp_wait_lcore ();return process_try_lcore_stats (); } -/* all slave lcores grab RDLOCK, master one grabs WRLOCK */ +/* all worker lcores grab RDLOCK, initial one grabs WRLOCK */ static int try_rwlock_test_rds_wrm (void ) {try_test_reset (); -rte_eal_mp_remote_launch (try_read_lcore,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (try_read_lcore,NULL ,SKIP_INITIAL );try_write_lcore (NULL );rte_eal_mp_wait_lcore ();return process_try_lcore_stats (); } -/* master and even slave lcores grab RDLOCK, odd lcores grab WRLOCK */ +/* initial and even worker lcores grab RDLOCK, odd lcores grab WRLOCK */ static int try_rwlock_test_rde_wro (void ) {
@@ -489,7 +489,7 @@ try_rwlock_test_rde_wro(void)try_test_reset (); - mlc =rte_get_master_lcore (); + mlc =rte_get_initial_lcore ();RTE_LCORE_FOREACH (lc) {if (lc != mlc) {
app/test/test_service_cores.c +5 -5
@@ -30,7 +30,7 @@ static inttestsuite_setup (void) { slcore_id =rte_get_next_lcore (/* start core */ -1 , -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );return TEST_SUCCESS ;
@@ -532,12 +532,12 @@ service_lcore_add_del(void)TEST_ASSERT_EQUAL (1 ,rte_service_lcore_count (),"Service core count not equal to one" );uint32_t slcore_1 =rte_get_next_lcore (/* start core */ -1 , -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );TEST_ASSERT_EQUAL (0 ,rte_service_lcore_add (slcore_1),"Service core add did not return zero" );uint32_t slcore_2 =rte_get_next_lcore (/* start core */ slcore_1, -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );TEST_ASSERT_EQUAL (0 ,rte_service_lcore_add (slcore_2),"Service core add did not return zero" );
@@ -583,12 +583,12 @@ service_threaded_test(int mt_safe)/* add next 2 cores */ uint32_t slcore_1 =rte_get_next_lcore (/* start core */ -1 , -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );TEST_ASSERT_EQUAL (0 ,rte_service_lcore_add (slcore_1),"mt safe lcore add fail" );uint32_t slcore_2 =rte_get_next_lcore (/* start core */ slcore_1, -/* skip master */ 1 , +/* skip initial */ 1 ,/* wrap */ 0 );TEST_ASSERT_EQUAL (0 ,rte_service_lcore_add (slcore_2),"mt safe lcore add fail" );
app/test/test_spinlock.c +17 -17
@@ -28,7 +28,7 @@* - There is a global spinlock and a table of spinlocks (one per lcore). * * - The test function takes all of these locks and launches the -* ``test_spinlock_per_core()`` function on each core (except the master). +* ``test_spinlock_per_core()`` function on each core (except the initial). * * - The function takes the global lock, display something, then releases * the global lock.
@@ -109,8 +109,8 @@ load_loop_fn(void *func_param)const int use_lock = *(int *)func_param;const unsigned lcore =rte_lcore_id (); -/* wait synchro for slaves */ -if (lcore !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 ); begin =rte_get_timer_cycles ();
@@ -149,11 +149,11 @@ test_spinlock_perf(void)printf ("\nTest with lock on %u cores...\n" ,rte_lcore_count ()); -/* Clear synchro and start slaves */ +/* Clear synchro and start workers */ rte_atomic32_set (&synchro,0 ); -rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_MASTER ); +rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_INITIAL ); -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );load_loop_fn (&lock);
@@ -200,8 +200,8 @@ test_spinlock(void)int ret =0 ;int i; -/* slave cores should be waiting: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be waiting: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }
@@ -214,19 +214,19 @@ test_spinlock(void)rte_spinlock_lock (&sl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_spinlock_lock (&sl_tab[i]);rte_eal_remote_launch (test_spinlock_per_core,NULL , i); } -/* slave cores should be busy: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be busy: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }rte_spinlock_unlock (&sl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_spinlock_unlock (&sl_tab[i]);rte_delay_ms (10 ); }
@@ -245,7 +245,7 @@ test_spinlock(void) }else rte_spinlock_recursive_unlock (&slr); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_spinlock_recursive_per_core,NULL , i); }rte_spinlock_recursive_unlock (&slr);
@@ -253,12 +253,12 @@ test_spinlock(void)/* * Test if it could return immediately from try-locking a locked object. -* Here it will lock the spinlock object first, then launch all the slave +* Here it will lock the spinlock object first, then launch all the worker * lcores to trylock the same spinlock object. -* All the slave lcores should give up try-locking a locked object and +* All the worker lcores should give up try-locking a locked object and * return immediately, and then increase the "count" initialized with zero * by one per times. -* We can check if the "count" is finally equal to the number of all slave +* We can check if the "count" is finally equal to the number of all worker * lcores to see if the behavior of try-locking a locked spinlock object * is correct. */
@@ -266,7 +266,7 @@ test_spinlock(void)return -1 ; } count =0 ; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_spinlock_try,NULL , i); }rte_eal_mp_wait_lcore ();
app/test/test_stack.c +1 -1
@@ -362,7 +362,7 @@ test_stack_multithreaded(uint32_t flags)rte_atomic64_init (&size); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) { args[lcore_id].s = s; args[lcore_id].sz = &size;
app/test/test_stack_perf.c +3 -3
@@ -180,7 +180,7 @@ run_on_core_pair(struct lcore_pair *cores, struct rte_stack *s, args[0 ].sz = args[1 ].sz = bulk_sizes[i]; args[0 ].s = args[1 ].s = s; -if (cores->c1 ==rte_get_master_lcore ()) { +if (cores->c1 ==rte_get_initial_lcore ()) {rte_eal_remote_launch (fn, &args[1 ], cores->c2);fn (&args[0 ]);rte_eal_wait_lcore (cores->c2);
@@ -210,7 +210,7 @@ run_on_n_cores(struct rte_stack *s, lcore_function_t fn, int n)rte_atomic32_set (&lcore_barrier, n); -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (++cnt >= n)break ;
@@ -235,7 +235,7 @@ run_on_n_cores(struct rte_stack *s, lcore_function_t fn, int n) avg = args[rte_lcore_id ()].avg; cnt =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (++cnt >= n)break ; avg += args[lcore_id].avg;
app/test/test_ticketlock.c +18 -18
@@ -28,7 +28,7 @@* - There is a global ticketlock and a table of ticketlocks (one per lcore). * * - The test function takes all of these locks and launches the -* ``test_ticketlock_per_core()`` function on each core (except the master). +* ``test_ticketlock_per_core()`` function on each core (except the initial). * * - The function takes the global lock, display something, then releases * the global lock.
@@ -110,8 +110,8 @@ load_loop_fn(void *func_param)const int use_lock = *(int *)func_param;const unsigned int lcore =rte_lcore_id (); -/* wait synchro for slaves */ -if (lcore !=rte_get_master_lcore ()) +/* wait synchro for workers */ +if (lcore !=rte_get_initial_lcore ())while (rte_atomic32_read (&synchro) ==0 ) ;
@@ -154,11 +154,11 @@ test_ticketlock_perf(void) lcount =0 ;printf ("\nTest with lock on %u cores...\n" ,rte_lcore_count ()); -/* Clear synchro and start slaves */ +/* Clear synchro and start workers */ rte_atomic32_set (&synchro,0 ); -rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_MASTER ); +rte_eal_mp_remote_launch (load_loop_fn, &lock,SKIP_INITIAL ); -/* start synchro and launch test on master */ +/* start synchro and launch test on initial lcore */ rte_atomic32_set (&synchro,1 );load_loop_fn (&lock);
@@ -208,8 +208,8 @@ test_ticketlock(void)int ret =0 ;int i; -/* slave cores should be waiting: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be waiting: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }
@@ -217,25 +217,25 @@ test_ticketlock(void)rte_ticketlock_init (&tl);rte_ticketlock_init (&tl_try);rte_ticketlock_recursive_init (&tlr); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_ticketlock_init (&tl_tab[i]); }rte_ticketlock_lock (&tl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_ticketlock_lock (&tl_tab[i]);rte_eal_remote_launch (test_ticketlock_per_core,NULL , i); } -/* slave cores should be busy: print it */ -RTE_LCORE_FOREACH_SLAVE (i) { +/* worker cores should be busy: print it */ +RTE_LCORE_FOREACH_WORKER (i) {printf ("lcore %d state: %d\n" , i, (int )rte_eal_get_lcore_state (i)); }rte_ticketlock_unlock (&tl); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_ticketlock_unlock (&tl_tab[i]);rte_delay_ms (10 ); }
@@ -254,7 +254,7 @@ test_ticketlock(void) }else rte_ticketlock_recursive_unlock (&tlr); -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_ticketlock_recursive_per_core,NULL , i); }
@@ -264,19 +264,19 @@ test_ticketlock(void)/* * Test if it could return immediately from try-locking a locked object. * Here it will lock the ticketlock object first, then launch all the -* slave lcores to trylock the same ticketlock object. -* All the slave lcores should give up try-locking a locked object and +* worker lcores to trylock the same ticketlock object. +* All the worker lcores should give up try-locking a locked object and * return immediately, and then increase the "count" initialized with * zero by one per times. * We can check if the "count" is finally equal to the number of all -* slave lcores to see if the behavior of try-locking a locked +* worker lcores to see if the behavior of try-locking a locked * ticketlock object is correct. */ if (rte_ticketlock_trylock (&tl_try) ==0 )return -1 ; count =0 ; -RTE_LCORE_FOREACH_SLAVE (i) { +RTE_LCORE_FOREACH_WORKER (i) {rte_eal_remote_launch (test_ticketlock_try,NULL , i); }rte_eal_mp_wait_lcore ();
app/test/test_timer.c +53 -53
285 lines not on this page · raw message
app/test/test_timer_racecond.c +14 -13
@@ -56,8 +56,8 @@static struct rte_timer timer[N_TIMERS ];static unsigned timer_lcore_id[N_TIMERS ]; -static unsigned master; -static volatile unsigned stop_slaves; +static unsigned int initial_lcore; +static volatile unsigned stop_workers;static int reload_timer (struct rte_timer *tim);
@@ -95,7 +95,8 @@ reload_timer(struct rte_timer *tim) (tim - timer);int ret; - ret =rte_timer_reset (tim, ticks,PERIODICAL , master, timer_cb,NULL ); + ret =rte_timer_reset (tim, ticks,PERIODICAL , + initial_lcore, timer_cb,NULL );if (ret !=0 ) { rte_log(RTE_LOG_DEBUG, timer_logtype_test, "- core %u failed to reset timer %" PRIuPTR " (OK)\n",
@@ -106,7 +107,7 @@ reload_timer(struct rte_timer *tim) }static int -slave_main_loop(__rte_unused void *arg) +worker_main_loop(__rte_unused void *arg) {unsigned lcore_id =rte_lcore_id ();unsigned i;
@@ -115,7 +116,7 @@ slave_main_loop(__rte_unused void *arg)printf ("Starting main loop on core %u\n" , lcore_id); -while (!stop_slaves) { +while (!stop_workers) {/* Wait until the timer manager is running. * We know it's running when we see timer[0] NOT pending. */
@@ -152,7 +153,7 @@ test_timer_racecond(void)unsigned lcore_id;unsigned i; - master = lcore_id =rte_lcore_id (); + initial_lcore = lcore_id =rte_lcore_id (); hz =rte_get_timer_hz ();/* init and start timers */
@@ -161,8 +162,8 @@ test_timer_racecond(void) ret =reload_timer (&timer[i]);TEST_ASSERT (ret ==0 ,"reload_timer failed" ); -/* Distribute timers to slaves. -* Note that we assign timer[0] to the master. +/* Distribute timers to workers. +* Note that we assign timer[0] to the inital lcore. */ timer_lcore_id[i] = lcore_id; lcore_id =rte_get_next_lcore (lcore_id,1 ,1 );
@@ -172,11 +173,11 @@ test_timer_racecond(void) cur_time =rte_get_timer_cycles (); end_time = cur_time + (hz *TEST_DURATION_S ); -/* start slave cores */ - stop_slaves =0 ; +/* start worker cores */ + stop_workers =0 ;printf ("Start timer manage race condition test (%u seconds)\n" ,TEST_DURATION_S ); -rte_eal_mp_remote_launch (slave_main_loop,NULL ,SKIP_MASTER ); +rte_eal_mp_remote_launch (worker_main_loop,NULL ,SKIP_INITIAL );while (diff >=0 ) {/* run the timers */
@@ -189,9 +190,9 @@ test_timer_racecond(void) diff = end_time - cur_time; } -/* stop slave cores */ +/* stop worker cores */ printf ("Stopping timer manage race condition test\n" ); - stop_slaves =1 ; + stop_workers =1 ;rte_eal_mp_wait_lcore ();/* stop timers */
app/test/test_timer_secondary.c +1 -1
@@ -141,7 +141,7 @@ test_timer_secondary(void)unsigned int *mgr_lcorep = &test_info->mgr_lcore;unsigned int *sec_lcorep = &test_info->sec_lcore; - *mstr_lcorep =rte_get_master_lcore (); + *mstr_lcorep =rte_get_initial_lcore (); *mgr_lcorep =rte_get_next_lcore (*mstr_lcorep,1 ,1 ); *sec_lcorep =rte_get_next_lcore (*mgr_lcorep,1 ,1 );
app/test/test_trace_perf.c +2 -2
@@ -132,7 +132,7 @@ run_test(const char *str, lcore_function_t f, struct test_data *data, size_t sz)memset (data,0 , sz); data->nb_workers =rte_lcore_count () -1 ; -RTE_LCORE_FOREACH_SLAVE (id) +RTE_LCORE_FOREACH_WORKER (id) rte_eal_remote_launch(f, &data->ldata[worker++], id);wait_till_workers_are_ready (data);
@@ -140,7 +140,7 @@ run_test(const char *str, lcore_function_t f, struct test_data *data, size_t sz)measure_perf (str, data);signal_workers_to_finish (data); -RTE_LCORE_FOREACH_SLAVE (id) +RTE_LCORE_FOREACH_WORKER (id)rte_eal_wait_lcore (id); }
Signature · 1 line
2.26.2
PATCH v3 21/27 doc: fix incorrect reference to master process
In reply to Stephen HemmingerCorrect terminolgy here is primary process.
This is a bug in original doc.
--- doc/guides/prog_guide/thread_safety_dpdk_functions.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
doc/guides/prog_guide/thread_safety_dpdk_functions.rst +2 -2
@@ -61,8 +61,8 @@ rather than subsequently in the forwarding threads. However, the DPDK performs checks to ensure that libraries are only initialized once. If initialization is attempted more than once, an error is returned. -In the multi-process case, the configuration information of shared memory will only be initialized by the master process. -Thereafter, both master and secondary processes can allocate/release any objects of memory that finally rely on rte_malloc or memzones. +In the multi-process case, the configuration information of shared memory will only be initialized by the primary process. +Thereafter, both primary and secondary processes can allocate/release any objects of memory that finally rely on rte_malloc or memzones. Interrupt Thread ----------------
Signature · 1 line
2.26.2
PATCH v3 22/27 doc: update references to master/slave lcore in documentation
In reply to Stephen HemmingerNew terms are initial and worker lcores.
--- doc/guides/contributing/coding_style.rst | 2 +- doc/guides/faq/faq.rst | 6 +++--- doc/guides/howto/debug_troubleshoot.rst | 2 +- doc/guides/linux_gsg/eal_args.include.rst | 4 ++-- doc/guides/nics/bnxt.rst | 2 +- doc/guides/nics/fail_safe.rst | 3 --- doc/guides/prog_guide/env_abstraction_layer.rst | 6 +++--- doc/guides/prog_guide/event_ethernet_rx_adapter.rst | 2 +- doc/guides/prog_guide/glossary.rst | 8 ++++---- doc/guides/rel_notes/release_20_08.rst | 7 ++++++- doc/guides/sample_app_ug/bbdev_app.rst | 2 +- doc/guides/sample_app_ug/ethtool.rst | 4 ++-- doc/guides/sample_app_ug/hello_world.rst | 8 ++++---- doc/guides/sample_app_ug/ioat.rst | 12 ++++++------ doc/guides/sample_app_ug/ip_pipeline.rst | 4 ++-- doc/guides/sample_app_ug/keep_alive.rst | 2 +- doc/guides/sample_app_ug/l2_forward_event.rst | 4 ++-- .../sample_app_ug/l2_forward_real_virtual.rst | 4 ++-- doc/guides/sample_app_ug/l3_forward_graph.rst | 6 +++--- doc/guides/sample_app_ug/l3_forward_power_man.rst | 2 +- doc/guides/sample_app_ug/link_status_intr.rst | 4 ++-- doc/guides/sample_app_ug/multi_process.rst | 6 +++--- doc/guides/sample_app_ug/packet_ordering.rst | 8 ++++---- doc/guides/sample_app_ug/performance_thread.rst | 6 +++--- doc/guides/sample_app_ug/qos_scheduler.rst | 4 ++-- doc/guides/sample_app_ug/timer.rst | 13 +++++++------ doc/guides/testpmd_app_ug/run_app.rst | 2 +- doc/guides/testpmd_app_ug/testpmd_funcs.rst | 2 +- 28 files changed, 69 insertions(+), 66 deletions(-)
doc/guides/contributing/coding_style.rst +1 -1
@@ -334,7 +334,7 @@ For example: typedef int (lcore_function_t)(void *); /* launch a function of lcore_function_t type */ - int rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned slave_id); + int rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned id); C Indentation
doc/guides/faq/faq.rst +3 -3
@@ -42,13 +42,13 @@ I am running a 32-bit DPDK application on a NUMA system, and sometimes the appli If your system has a lot (>1 GB size) of hugepage memory, not all of it will be allocated. Due to hugepages typically being allocated on a local NUMA node, the hugepages allocation the application gets during the initialization depends on which NUMA node it is running on (the EAL does not affinitize cores until much later in the initialization process). -Sometimes, the Linux OS runs the DPDK application on a core that is located on a different NUMA node from DPDK master core and +Sometimes, the Linux OS runs the DPDK application on a core that is located on a different NUMA node from DPDK initial core and therefore all the hugepages are allocated on the wrong socket. To avoid this scenario, either lower the amount of hugepage memory available to 1 GB size (or less), or run the application with taskset -affinitizing the application to a would-be master core. +affinitizing the application to a would-be initial core. -For example, if your EAL coremask is 0xff0, the master core will usually be the first core in the coremask (0x10); this is what you have to supply to taskset:: +For example, if your EAL coremask is 0xff0, the initial core will usually be the first core in the coremask (0x10); this is what you have to supply to taskset:: taskset 0x10 ./l2fwd -l 4-11 -n 2
doc/guides/howto/debug_troubleshoot.rst +1 -1
@@ -311,7 +311,7 @@ Custom worker function :numref:`dtg_distributor_worker`. SERVICE. Check performance functions are mapped to run on the cores. * For high-performance execution logic ensure running it on correct NUMA - and non-master core. + and worker core. * Analyze run logic with ``rte_dump_stack``, ``rte_dump_registers`` and ``rte_memdump`` for more insights.
doc/guides/linux_gsg/eal_args.include.rst +2 -2
@@ -33,9 +33,9 @@ Lcore-related options At a given instance only one core option ``--lcores``, ``-l`` or ``-c`` can be used. -* ``--master-lcore <core ID>`` +* ``--initial-lcore <core ID>`` - Core ID that is used as master. + Core ID that is used as initial lcore. * ``-s <service core mask>``
doc/guides/nics/bnxt.rst +1 -1
@@ -385,7 +385,7 @@ The application enables multiple TX and RX queues when it is started. .. code-block:: console - testpmd -l 1,3,5 --master-lcore 1 --txq=2 –rxq=2 --nb-cores=2 + testpmd -l 1,3,5 --initial-lcore 1 --txq=2 –rxq=2 --nb-cores=2 **TSS**
doc/guides/nics/fail_safe.rst +0 -3
@@ -236,9 +236,6 @@ Upkeep round (brought down or up accordingly). Additionally, any sub-device marked for removal is cleaned-up. -Slave - In the context of the fail-safe PMD, synonymous to sub-device. - Sub-device A device being utilized by the fail-safe PMD. This is another PMD running underneath the fail-safe PMD.
doc/guides/prog_guide/env_abstraction_layer.rst +3 -3
@@ -64,7 +64,7 @@ It consist of calls to the pthread library (more specifically, pthread_self(), p .. note:: Initialization of objects, such as memory zones, rings, memory pools, lpm tables and hash tables, - should be done as part of the overall application initialization on the master lcore. + should be done as part of the overall application initialization on the initial lcore. The creation and initialization functions for these objects are not multi-thread safe. However, once initialized, the objects themselves can safely be used in multiple threads simultaneously.
@@ -186,7 +186,7 @@ very dependent on the memory allocation patterns of the application. Additional restrictions are present when running in 32-bit mode. In dynamic memory mode, by default maximum of 2 gigabytes of VA space will be preallocated, -and all of it will be on master lcore NUMA node unless ``--socket-mem`` flag is +and all of it will be on initial lcore NUMA node unless ``--socket-mem`` flag is used. In legacy mode, VA space will only be preallocated for segments that were
@@ -603,7 +603,7 @@ controlled with tools like taskset (Linux) or cpuset (FreeBSD), - with affinity restricted to 2-4, the Control Threads will end up on CPU 4. - with affinity restricted to 2-3, the Control Threads will end up on - CPU 2 (master lcore, which is the default when no CPU is available). + CPU 2 (initial lcore, which is the default when no CPU is available). .. _known_issue_label:
doc/guides/prog_guide/event_ethernet_rx_adapter.rst +1 -1
@@ -172,7 +172,7 @@ converts the received packets to events in the same manner as packets received on a polled Rx queue. The interrupt thread is affinitized to the same CPUs as the lcores of the Rx adapter service function, if the Rx adapter service function has not been mapped to any lcores, the interrupt thread -is mapped to the master lcore. +is mapped to the initial lcore. Rx Callback for SW Rx Adapter ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
doc/guides/prog_guide/glossary.rst +4 -4
@@ -124,9 +124,9 @@ LAN LPM Longest Prefix Match -master lcore +initial lcore The execution unit that executes the main() function and that launches - other lcores. + other lcores. Described in older versions as master lcore. mbuf An mbuf is a data structure used internally to carry messages (mainly
@@ -184,8 +184,8 @@ RTE Rx Reception -Slave lcore - Any *lcore* that is not the *master lcore*. +Worker lcore + Any *lcore* that is not the *initial lcore*. Socket A physical CPU, that includes several *cores*.
doc/guides/rel_notes/release_20_08.rst +6 -1
@@ -107,6 +107,9 @@ New Features * Dump ``rte_flow`` memory consumption. * Measure packet per second forwarding. +* **Renamed master lcore to initial lcore.** + + The name given to the first thread in DPDK is changed from master lcore to initial lcore. Removed Items -------------
@@ -122,7 +125,6 @@ Removed Items * Removed ``RTE_KDRV_NONE`` based PCI device driver probing. - API Changes -----------
@@ -143,6 +145,9 @@ API Changes * vhost: The API of ``rte_vhost_host_notifier_ctrl`` was changed to be per queue and not per device, a qid parameter was added to the arguments list. +* ``rte_get_master_lcore`` was renamed to ``rte_get_initial_lcore`` + The old function is deprecated and will be removed in future release. + ABI Changes -----------
doc/guides/sample_app_ug/bbdev_app.rst +1 -1
@@ -94,7 +94,7 @@ device gets linked to a corresponding ethernet port as whitelisted by the parameter -w. 3 cores are allocated to the application, and assigned as: - - core 3 is the master and used to print the stats live on screen, + - core 3 is the initial and used to print the stats live on screen, - core 4 is the encoding lcore performing Rx and Turbo Encode operations
doc/guides/sample_app_ug/ethtool.rst +2 -2
@@ -64,8 +64,8 @@ Explanation ----------- The sample program has two parts: A background `packet reflector`_ -that runs on a slave core, and a foreground `Ethtool Shell`_ that -runs on the master core. These are described below. +that runs on a worker core, and a foreground `Ethtool Shell`_ that +runs on the initial core. These are described below. Packet Reflector ~~~~~~~~~~~~~~~~
doc/guides/sample_app_ug/hello_world.rst +4 -4
@@ -75,13 +75,13 @@ The code that launches the function on each lcore is as follows: .. code-block:: c - /* call lcore_hello() on every slave lcore */ + /* call lcore_hello() on every worker lcore */ - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + RTE_LCORE_FOREACH_WORKER(lcore_id) { rte_eal_remote_launch(lcore_hello, NULL, lcore_id); } - /* call it on master lcore too */ + /* call it on initial lcore too */ lcore_hello(NULL);
@@ -89,6 +89,6 @@ The following code is equivalent and simpler: .. code-block:: c - rte_eal_mp_remote_launch(lcore_hello, NULL, CALL_MASTER); + rte_eal_mp_remote_launch(lcore_hello, NULL, CALL_INITIAL); Refer to the *DPDK API Reference* for detailed information on the rte_eal_mp_remote_launch() function.
doc/guides/sample_app_ug/ioat.rst +6 -6
@@ -69,13 +69,13 @@ provided parameters. The app can use up to 2 lcores: one of them receives incoming traffic and makes a copy of each packet. The second lcore then updates MAC address and sends the copy. If one lcore per port is used, both operations are done sequentially. For each configuration an additional -lcore is needed since the master lcore does not handle traffic but is +lcore is needed since the initial lcore does not handle traffic but is responsible for configuration, statistics printing and safe shutdown of all ports and devices. The application can use a maximum of 8 ports. -To run the application in a Linux environment with 3 lcores (the master lcore, +To run the application in a Linux environment with 3 lcores (the initial lcore, plus two forwarding cores), a single port (port 0), software copying and MAC updating issue the command:
@@ -83,7 +83,7 @@ updating issue the command: $ ./build/ioatfwd -l 0-2 -n 2 -- -p 0x1 --mac-updating -c sw -To run the application in a Linux environment with 2 lcores (the master lcore, +To run the application in a Linux environment with 2 lcores (the initial lcore, plus one forwarding core), 2 ports (ports 0 and 1), hardware copying and no MAC updating issue the command:
@@ -208,7 +208,7 @@ After that each port application assigns resources needed. cfg.nb_lcores = rte_lcore_count() - 1; if (cfg.nb_lcores < 1) rte_exit(EXIT_FAILURE, - "There should be at least one slave lcore.\n"); + "There should be at least one worker lcore.\n"); ret = 0;
@@ -310,8 +310,8 @@ If initialization is successful, memory for hardware device statistics is allocated. Finally ``main()`` function starts all packet handling lcores and starts -printing stats in a loop on the master lcore. The application can be -interrupted and closed using ``Ctrl-C``. The master lcore waits for +printing stats in a loop on the initial lcore. The application can be +interrupted and closed using ``Ctrl-C``. The initial lcore waits for all slave processes to finish, deallocates resources and exits. The processing lcores launching function are described below.
doc/guides/sample_app_ug/ip_pipeline.rst +2 -2
@@ -122,7 +122,7 @@ is displayed and the application is terminated. Run-time ~~~~~~~~ -The master thread is creating and managing all the application objects based on CLI input. +The initial thread is creating and managing all the application objects based on CLI input. Each data plane thread runs one or several pipelines previously assigned to it in round-robin order. Each data plane thread executes two tasks in time-sharing mode:
@@ -130,7 +130,7 @@ executes two tasks in time-sharing mode: 1. *Packet processing task*: Process bursts of input packets read from the pipeline input ports. 2. *Message handling task*: Periodically, the data plane thread pauses the packet processing task and polls for request - messages send by the master thread. Examples: add/remove pipeline to/from current data plane thread, add/delete rules + messages send by the initial thread. Examples: add/remove pipeline to/from current data plane thread, add/delete rules to/from given table of a specific pipeline owned by the current data plane thread, read statistics, etc. Examples
doc/guides/sample_app_ug/keep_alive.rst +1 -1
@@ -16,7 +16,7 @@ Overview -------- The application demonstrates how to protect against 'silent outages' -on packet processing cores. A Keep Alive Monitor Agent Core (master) +on packet processing cores. A Keep Alive Monitor Agent Core (initial) monitors the state of packet processing cores (worker cores) by dispatching pings at a regular time interval (default is 5ms) and monitoring the state of the cores. Cores states are: Alive, MIA, Dead
doc/guides/sample_app_ug/l2_forward_event.rst +2 -2
@@ -630,8 +630,8 @@ not many packets to send, however it improves performance: /* if timer has reached its timeout */ if (unlikely(timer_tsc >= timer_period)) { - /* do this only on master core */ - if (lcore_id == rte_get_master_lcore()) { + /* do this only on initial core */ + if (lcore_id == rte_get_initial_lcore()) { print_stats(); /* reset the timer */ timer_tsc = 0;
doc/guides/sample_app_ug/l2_forward_real_virtual.rst +2 -2
@@ -440,9 +440,9 @@ however it improves performance: /* if timer has reached its timeout */ if (unlikely(timer_tsc >= (uint64_t) timer_period)) { - /* do this only on master core */ + /* do this only on initial core */ - if (lcore_id == rte_get_master_lcore()) { + if (lcore_id == rte_get_initial_lcore()) { print_stats(); /* reset the timer */
doc/guides/sample_app_ug/l3_forward_graph.rst +3 -3
@@ -22,7 +22,7 @@ Run-time path is main thing that differs from L3 forwarding sample application. Difference is that forwarding logic starting from Rx, followed by LPM lookup, TTL update and finally Tx is implemented inside graph nodes. These nodes are interconnected in graph framework. Application main loop needs to walk over -graph using ``rte_graph_walk()`` with graph objects created one per slave lcore. +graph using ``rte_graph_walk()`` with graph objects created one per worker lcore. The lookup method is as per implementation of ``ip4_lookup`` graph node. The ID of the output interface for the input packet is the next hop returned by
@@ -265,7 +265,7 @@ headers will be provided run-time using ``rte_node_ip4_route_add()`` and Since currently ``ip4_lookup`` and ``ip4_rewrite`` nodes don't support lock-less mechanisms(RCU, etc) to add run-time forwarding data like route and rewrite data, forwarding data is added before packet processing loop is - launched on slave lcore. + launched on worker lcore. .. code-block:: c
@@ -297,7 +297,7 @@ Packet Forwarding using Graph Walk ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Now that all the device configurations are done, graph creations are done and -forwarding data is updated with nodes, slave lcores will be launched with graph +forwarding data is updated with nodes, worker lcores will be launched with graph main loop. Graph main loop is very simple in the sense that it needs to continuously call a non-blocking API ``rte_graph_walk()`` with it's lcore specific graph object that was already created.
doc/guides/sample_app_ug/l3_forward_power_man.rst +1 -1
@@ -441,7 +441,7 @@ The telemetry mode support for ``l3fwd-power`` is a standalone mode, in this mod ``l3fwd-power`` does simple l3fwding along with calculating empty polls, full polls, and busy percentage for each forwarding core. The aggregation of these values of all cores is reported as application level telemetry to metric -library for every 500ms from the master core. +library for every 500ms from the initial core. The busy percentage is calculated by recording the poll_count and when the count reaches a defined value the total
doc/guides/sample_app_ug/link_status_intr.rst +2 -2
@@ -401,9 +401,9 @@ However, it improves performance: /* if timer has reached its timeout */ if (unlikely(timer_tsc >= (uint64_t) timer_period)) { - /* do this only on master core */ + /* do this only on initial core */ - if (lcore_id == rte_get_master_lcore()) { + if (lcore_id == rte_get_initial_lcore()) { print_stats(); /* reset the timer */
doc/guides/sample_app_ug/multi_process.rst +3 -3
@@ -66,7 +66,7 @@ The process should start successfully and display a command prompt as follows: EAL: check igb_uio module EAL: check module finished - EAL: Master core 0 is ready (tid=54e41820) + EAL: Initial core 0 is ready (tid=54e41820) EAL: Core 1 is ready (tid=53b32700) Starting core 1
@@ -92,7 +92,7 @@ At any stage, either process can be terminated using the quit command. .. code-block:: console - EAL: Master core 10 is ready (tid=b5f89820) EAL: Master core 8 is ready (tid=864a3820) + EAL: Initial core 10 is ready (tid=b5f89820) EAL: Initial core 8 is ready (tid=864a3820) EAL: Core 11 is ready (tid=84ffe700) EAL: Core 9 is ready (tid=85995700) Starting core 11 Starting core 9 simple_mp > send hello_secondary simple_mp > core 9: Received 'hello_secondary'
@@ -273,7 +273,7 @@ In addition to the EAL parameters, the application- specific parameters are: .. note:: - In the server process, a single thread, the master thread, that is, the lowest numbered lcore in the coremask/corelist, performs all packet I/O. + In the server process, a single thread, the initial thread, that is, the lowest numbered lcore in the coremask/corelist, performs all packet I/O. If a coremask/corelist is specified with more than a single lcore bit set in it, an additional lcore will be used for a thread to periodically print packet count statistics.
doc/guides/sample_app_ug/packet_ordering.rst +4 -4
@@ -12,14 +12,14 @@ Overview The application uses at least three CPU cores: -* RX core (maser core) receives traffic from the NIC ports and feeds Worker +* RX core (initial core) receives traffic from the NIC ports and feeds Worker cores with traffic through SW queues. -* Worker core (slave core) basically do some light work on the packet. +* Worker cores basically do some light work on the packet. Currently it modifies the output port of the packet for configurations with more than one port enabled. -* TX Core (slave core) receives traffic from Worker cores through software queues, +* TX Core receives traffic from Worker cores through software queues, inserts out-of-order packets into reorder buffer, extracts ordered packets from the reorder buffer and sends them to the NIC ports for transmission.
@@ -46,7 +46,7 @@ The application execution command line is: ./packet_ordering [EAL options] -- -p PORTMASK [--disable-reorder] [--insight-worker] The -c EAL CPU_COREMASK option has to contain at least 3 CPU cores. -The first CPU core in the core mask is the master core and would be assigned to +The first CPU core in the core mask is the initial core and would be assigned to RX core, the last to TX core and the rest to Worker cores. The PORTMASK parameter must contain either 1 or even enabled port numbers.
doc/guides/sample_app_ug/performance_thread.rst +3 -3
@@ -280,8 +280,8 @@ functionality into different threads, and the pairs of RX and TX threads are interconnected via software rings. On initialization an L-thread scheduler is started on every EAL thread. On all -but the master EAL thread only a dummy L-thread is initially started. -The L-thread started on the master EAL thread then spawns other L-threads on +but the initial EAL thread only a dummy L-thread is initially started. +The L-thread started on the initial EAL thread then spawns other L-threads on different L-thread schedulers according the command line parameters. The RX threads poll the network interface queues and post received packets
@@ -1217,5 +1217,5 @@ Setting ``LTHREAD_DIAG`` also enables counting of statistics about cache and queue usage, and these statistics can be displayed by calling the function ``lthread_diag_stats_display()``. This function also performs a consistency check on the caches and queues. The function should only be called from the -master EAL thread after all slave threads have stopped and returned to the C +initial EAL thread after all worker threads have stopped and returned to the C main program, otherwise the consistency check will fail.
doc/guides/sample_app_ug/qos_scheduler.rst +2 -2
@@ -71,7 +71,7 @@ Optional application parameters include: In this mode, the application shows a command line that can be used for obtaining statistics while scheduling is taking place (see interactive mode below for more information). -* --mst n: Master core index (the default value is 1). +* --mst n: Initial core index (the default value is 1). * --rsz "A, B, C": Ring sizes:
@@ -329,7 +329,7 @@ Another example with 2 packet flow configurations using different ports but shar Note that independent cores for the packet flow configurations for each of the RX, WT and TX thread are also supported, providing flexibility to balance the work. -The EAL coremask/corelist is constrained to contain the default mastercore 1 and the RX, WT and TX cores only. +The EAL coremask/corelist is constrained to contain the default initial lcore 1 and the RX, WT and TX cores only. Explanation -----------
doc/guides/sample_app_ug/timer.rst +7 -6
@@ -49,17 +49,18 @@ In addition to EAL initialization, the timer subsystem must be initialized, by c rte_timer_subsystem_init(); After timer creation (see the next paragraph), -the main loop is executed on each slave lcore using the well-known rte_eal_remote_launch() and also on the master. +the main loop is executed on each worker lcore using the well-known rte_eal_remote_launch() and +also on the initial lcore. .. code-block:: c - /* call lcore_mainloop() on every slave lcore */ + /* call lcore_mainloop() on every worker lcore */ - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + RTE_LCORE_FOREACH_WORKER(lcore_id) { rte_eal_remote_launch(lcore_mainloop, NULL, lcore_id); } - /* call it on master lcore too */ + /* call it on initial lcore too */ (void) lcore_mainloop(NULL);
@@ -105,7 +106,7 @@ This call to rte_timer_init() is necessary before doing any other operation on t Then, the two timers are configured: -* The first timer (timer0) is loaded on the master lcore and expires every second. +* The first timer (timer0) is loaded on the initial lcore and expires every second. Since the PERIODICAL flag is provided, the timer is reloaded automatically by the timer subsystem. The callback function is timer0_cb().
@@ -115,7 +116,7 @@ Then, the two timers are configured: .. code-block:: c - /* load timer0, every second, on master lcore, reloaded automatically */ + /* load timer0, every second, on initial lcore, reloaded automatically */ hz = rte_get_hpet_hz();
doc/guides/testpmd_app_ug/run_app.rst +1 -1
@@ -71,7 +71,7 @@ The command line options are: * ``--coremask=0xXX`` Set the hexadecimal bitmask of the cores running the packet forwarding test. - The master lcore is reserved for command line parsing only and cannot be masked on for packet forwarding. + The initial lcore is reserved for command line parsing only and cannot be masked on for packet forwarding. * ``--portmask=0xXX``
doc/guides/testpmd_app_ug/testpmd_funcs.rst +1 -1
@@ -692,7 +692,7 @@ This is equivalent to the ``--coremask`` command-line option. .. note:: - The master lcore is reserved for command line parsing only and cannot be masked on for packet forwarding. + The initial lcore is reserved for command line parsing only and cannot be masked on for packet forwarding. set portmask ~~~~~~~~~~~~
Signature · 1 line
2.26.2
PATCH v3 23/27 app/pdump: replace references to master/slave lcore
In reply to Stephen HemmingerUse initial and worker lcore instead.
--- app/pdump/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
app/pdump/main.c +1 -1
@@ -947,7 +947,7 @@ dump_packets(void)rte_exit (EXIT_FAILURE ,"failed to wait\n" ); } -/* master core */ +/* initial core */ while (!quit_signal) ; }
Signature · 1 line
2.26.2
PATCH v3 24/27 app/test-XXX: replace reference to master/slave
In reply to Stephen HemmingerUse new terminology for lcore's
--- app/test-acl/main.c | 2 +- app/test-bbdev/test_bbdev_perf.c | 16 ++++++++-------- app/test-compress-perf/main.c | 8 ++++---- app/test-crypto-perf/main.c | 14 +++++++------- app/test-flow-perf/main.c | 2 +- app/test-pipeline/main.c | 4 ++-- app/test-sad/main.c | 4 ++-- 7 files changed, 25 insertions(+), 25 deletions(-)
app/test-acl/main.c +1 -1
@@ -1085,7 +1085,7 @@ main(int argc, char **argv)if (config.trace_file !=NULL )tracef_init (); -RTE_LCORE_FOREACH_SLAVE (lcore) +RTE_LCORE_FOREACH_WORKER (lcore)rte_eal_remote_launch (search_ip5tuples, NULL, lcore);search_ip5tuples (NULL );
app/test-bbdev/test_bbdev_perf.c +8 -8
@@ -3651,14 +3651,14 @@ bler_test(struct active_device *ad,rte_atomic16_set (&op_params->sync,SYNC_WAIT ); -/* Master core is set at first entry */ +/* Initial core is set at first entry */ t_params[0 ].dev_id = ad->dev_id; t_params[0 ].lcore_id =rte_lcore_id (); t_params[0 ].op_params = op_params; t_params[0 ].queue_id = ad->queue_ids[used_cores++]; t_params[0 ].iter_count =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (used_cores >= num_lcores)break ;
@@ -3675,7 +3675,7 @@ bler_test(struct active_device *ad,rte_atomic16_set (&op_params->sync,SYNC_START ); ret =bler_function (&t_params[0 ]); -/* Master core is always used */ +/* Initial core is always used */ for (used_cores =1 ; used_cores < num_lcores; used_cores++) ret |=rte_eal_wait_lcore (t_params[used_cores].lcore_id);
@@ -3769,14 +3769,14 @@ throughput_test(struct active_device *ad,rte_atomic16_set (&op_params->sync,SYNC_WAIT ); -/* Master core is set at first entry */ +/* Initial core is set at first entry */ t_params[0 ].dev_id = ad->dev_id; t_params[0 ].lcore_id =rte_lcore_id (); t_params[0 ].op_params = op_params; t_params[0 ].queue_id = ad->queue_ids[used_cores++]; t_params[0 ].iter_count =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (used_cores >= num_lcores)break ;
@@ -3793,7 +3793,7 @@ throughput_test(struct active_device *ad,rte_atomic16_set (&op_params->sync,SYNC_START ); ret =throughput_function (&t_params[0 ]); -/* Master core is always used */ +/* Initial core is always used */ for (used_cores =1 ; used_cores < num_lcores; used_cores++) ret |=rte_eal_wait_lcore (t_params[used_cores].lcore_id);
@@ -3817,7 +3817,7 @@ throughput_test(struct active_device *ad,/* In interrupt TC we need to wait for the interrupt callback to deqeue * all pending operations. Skip waiting for queues which reported an * error using processing_status variable. -* Wait for master lcore operations. +* Wait for initial lcore operations. */ tp = &t_params[0 ]; while ((rte_atomic16_read(&tp->nb_dequeued) <
@@ -3830,7 +3830,7 @@ throughput_test(struct active_device *ad, tp->mbps /=TEST_REPETITIONS ; ret |= (int )rte_atomic16_read (&tp->processing_status); -/* Wait for slave lcores operations */ +/* Wait for worker lcores operations */ for (used_cores =1 ; used_cores < num_lcores; used_cores++) { tp = &t_params[used_cores];
app/test-compress-perf/main.c +4 -4
@@ -389,7 +389,7 @@ main(int argc, char **argv) i =0 ;uint8_t qp_id =0 , cdev_index =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -413,7 +413,7 @@ main(int argc, char **argv)while (test_data->level <= test_data->level_lst.max) { i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -424,7 +424,7 @@ main(int argc, char **argv) i++; } i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -449,7 +449,7 @@ main(int argc, char **argv)case ST_DURING_TEST : i =0 ; - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + RTE_LCORE_FOREACH_WORKER(lcore_id) {if (i == total_nb_qps)break ;
app/test-crypto-perf/main.c +7 -7
@@ -590,7 +590,7 @@ main(int argc, char **argv) i =0 ;uint8_t qp_id =0 , cdev_index =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -654,7 +654,7 @@ main(int argc, char **argv) distribution_total[buffer_size_count -1 ]; i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -664,7 +664,7 @@ main(int argc, char **argv) i++; } i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -684,7 +684,7 @@ main(int argc, char **argv)while (opts.test_buffer_size <= opts.max_buffer_size) { i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -694,7 +694,7 @@ main(int argc, char **argv) i++; } i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -718,7 +718,7 @@ main(int argc, char **argv) } i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
@@ -738,7 +738,7 @@ main(int argc, char **argv) err: i =0 ; -RTE_LCORE_FOREACH_SLAVE (lcore_id) { +RTE_LCORE_FOREACH_WORKER (lcore_id) {if (i == total_nb_qps)break ;
app/test-flow-perf/main.c +1 -1
@@ -1097,7 +1097,7 @@ main(int argc, char **argv)if (enable_fwd) {init_lcore_info (); -rte_eal_mp_remote_launch (start_forwarding,NULL ,CALL_MASTER ); +rte_eal_mp_remote_launch (start_forwarding,NULL ,CALL_INITIAL ); }RTE_ETH_FOREACH_DEV (port) {
app/test-pipeline/main.c +2 -2
@@ -66,8 +66,8 @@ main(int argc, char **argv)app_init ();/* Launch per-lcore init on every lcore */ -rte_eal_mp_remote_launch (app_lcore_main_loop,NULL ,CALL_MASTER ); -RTE_LCORE_FOREACH_SLAVE (lcore) { +rte_eal_mp_remote_launch (app_lcore_main_loop,NULL ,CALL_INITIAL ); +RTE_LCORE_FOREACH_WORKER (lcore) {if (rte_eal_wait_lcore (lcore) <0 )return -1 ; }
app/test-sad/main.c +2 -2
@@ -657,11 +657,11 @@ main(int argc, char **argv)add_rules (sad,10 );if (config.parallel_lookup) -rte_eal_mp_remote_launch (lookup, sad,SKIP_MASTER ); +rte_eal_mp_remote_launch (lookup, sad,SKIP_INITIAL );lookup (sad);if (config.parallel_lookup) - RTE_LCORE_FOREACH_SLAVE(lcore_id) + RTE_LCORE_FOREACH_WORKER(lcore_id)if (rte_eal_wait_lcore (lcore_id) <0 )return -1 ;
Signature · 1 line
2.26.2
PATCH v3 25/27 eal: mark old naming as deprecated
In reply to Stephen HemmingerUse of old RTE_LCORE_FOREACH_SLAVE and rte_get_master_lcore_id() are marked as deprecated.
All uses of these in DPDK itself is gone. This will cause warnings for applications still using them.
--- lib/librte_eal/include/rte_launch.h | 4 ++-- lib/librte_eal/include/rte_lcore.h | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-)
lib/librte_eal/include/rte_launch.h +2 -2
@@ -76,8 +76,8 @@ enum rte_rmt_call_initial_t {/** * Deprecated backward compatiable definitions */ -#define SKIP_MASTER SKIP_INITIAL -#define CALL_MASTER CALL_INITIAL +#define SKIP_MASTER _Pragma("GCC warning \"'SKIP_MASTER' is deprecated\"") SKIP_INITIAL +#define CALL_MASTER _Pragma("GCC warning \"'CALL_MASTER' is deprecated\"") CALL_INITIAL/** * Launch a function on all lcores.
lib/librte_eal/include/rte_lcore.h +3 -1
@@ -67,6 +67,7 @@ unsigned int rte_get_initial_lcore(void);* @return * the id of the initial lcore */ +__rte_deprecated unsigned int rte_get_master_lcore(void);/**
@@ -216,7 +217,8 @@ unsigned int rte_get_next_lcore(unsigned int i, int skip_initial, int wrap);/** * Backward compatibility */ -#define RTE_LCORE_FOREACH_SLAVE (x) \ +#define RTE_LCORE_FOREACH_SLAVE (x) \ + _Pragma("GCC warning \"'RTE_LCORE_FOREACH_SLAVE' macro is deprecated\"") \ RTE_LCORE_FOREACH_WORKER(x)
Signature · 1 line
2.26.2
PATCH v3 26/27 memif: replace master/slave with server/client
In reply to Stephen HemmingerThe names master and slave should be changed in this driver. It is really a traditional client server model, so use those names.
--- doc/guides/nics/memif.rst | 78 +++++++++--------- drivers/net/memif/memif.h | 40 +++++----- drivers/net/memif/memif_socket.c | 54 ++++++------- drivers/net/memif/memif_socket.h | 5 +- drivers/net/memif/rte_eth_memif.c | 128 +++++++++++++++--------------- drivers/net/memif/rte_eth_memif.h | 20 ++--- 6 files changed, 163 insertions(+), 162 deletions(-)
doc/guides/nics/memif.rst +39 -39
@@ -13,13 +13,13 @@ The created device transmits packets in a raw format. It can be used with Ethernet mode, IP mode, or Punt/Inject. At this moment, only Ethernet mode is supported in DPDK memif implementation. -Memif works in two roles: master and slave. Slave connects to master over an +Memif works in two roles: server and client. Client connects to server over an existing socket. It is also a producer of shared memory file and initializes the shared memory. Each interface can be connected to one peer interface -at same time. The peer interface is identified by id parameter. Master -creates the socket and listens for any slave connection requests. The socket +at same time. The peer interface is identified by id parameter. Server +creates the socket and listens for any client connection requests. The socket may already exist on the system. Be sure to remove any such sockets, if you -are creating a master interface, or you will see an "Address already in use" +are creating a server interface, or you will see an "Address already in use" error. Function ``rte_pmd_memif_remove()``, which removes memif interface, will also remove a listener socket, if it is not being used by any other interface.
@@ -31,57 +31,57 @@ net_memif1, and so on. Memif uses unix domain socket to transmit control messages. Each memif has a unique id per socket. This id is used to identify peer interface. If you are connecting multiple interfaces using same socket, be sure to specify unique ids ``id=0``, ``id=1``, -etc. Note that if you assign a socket to a master interface it becomes a -listener socket. Listener socket can not be used by a slave interface on same +etc. Note that if you assign a socket to a server interface it becomes a +listener socket. Listener socket can not be used by a client interface on same client. .. csv-table:: **Memif configuration options** :header: "Option", "Description", "Default", "Valid value" "id=0", "Used to identify peer interface", "0", "uint32_t" - "role=master", "Set memif role", "slave", "master|slave" + "role=server", "Set memif role", "client", "server|client" "bsize=1024", "Size of single packet buffer", "2048", "uint16_t" "rsize=11", "Log2 of ring size. If rsize is 10, actual ring size is 1024", "10", "1-14" "socket=/tmp/memif.sock", "Socket filename", "/tmp/memif.sock", "string len 108" "mac=01:23:45:ab:cd:ef", "Mac address", "01:ab:23:cd:45:ef", "" "secret=abc123", "Secret is an optional security option, which if specified, must be matched by peer", "", "string len 24" - "zero-copy=yes", "Enable/disable zero-copy slave mode. Only relevant to slave, requires '--single-file-segments' eal argument", "no", "yes|no" + "zero-copy=yes", "Enable/disable zero-copy client mode. Only relevant to client, requires '--single-file-segments' eal argument", "no", "yes|no" **Connection establishment** In order to create memif connection, two memif interfaces, each in separate -process, are needed. One interface in ``master`` role and other in -``slave`` role. It is not possible to connect two interfaces in a single +process, are needed. One interface in ``server`` role and other in +``client`` role. It is not possible to connect two interfaces in a single process. Each interface can be connected to one interface at same time, identified by matching id parameter. Memif driver uses unix domain socket to exchange required information between memif interfaces. Socket file path is specified at interface creation see -*Memif configuration options* table above. If socket is used by ``master`` +*Memif configuration options* table above. If socket is used by ``server`` interface, it's marked as listener socket (in scope of current process) and listens to connection requests from other processes. One socket can be used by -multiple interfaces. One process can have ``slave`` and ``master`` interfaces +multiple interfaces. One process can have ``client`` and ``server`` interfaces at the same time, provided each role is assigned unique socket. For detailed information on memif control messages, see: net/memif/memif.h. -Slave interface attempts to make a connection on assigned socket. Process +Client interface attempts to make a connection on assigned socket. Process listening on this socket will extract the connection request and create a new connected socket (control channel). Then it sends the 'hello' message -(``MEMIF_MSG_TYPE_HELLO``), containing configuration boundaries. Slave interface +(``MEMIF_MSG_TYPE_HELLO``), containing configuration boundaries. Client interface adjusts its configuration accordingly, and sends 'init' message (``MEMIF_MSG_TYPE_INIT``). This message among others contains interface id. Driver -uses this id to find master interface, and assigns the control channel to this +uses this id to find server interface, and assigns the control channel to this interface. If such interface is found, 'ack' message (``MEMIF_MSG_TYPE_ACK``) is -sent. Slave interface sends 'add region' message (``MEMIF_MSG_TYPE_ADD_REGION``) for -every region allocated. Master responds to each of these messages with 'ack' -message. Same behavior applies to rings. Slave sends 'add ring' message -(``MEMIF_MSG_TYPE_ADD_RING``) for every initialized ring. Master again responds to -each message with 'ack' message. To finalize the connection, slave interface +sent. Client interface sends 'add region' message (``MEMIF_MSG_TYPE_ADD_REGION``) for +every region allocated. Server responds to each of these messages with 'ack' +message. Same behavior applies to rings. Client sends 'add ring' message +(``MEMIF_MSG_TYPE_ADD_RING``) for every initialized ring. Server again responds to +each message with 'ack' message. To finalize the connection, client interface sends 'connect' message (``MEMIF_MSG_TYPE_CONNECT``). Upon receiving this message -master maps regions to its address space, initializes rings and responds with +server maps regions to its address space, initializes rings and responds with 'connected' message (``MEMIF_MSG_TYPE_CONNECTED``). Disconnect -(``MEMIF_MSG_TYPE_DISCONNECT``) can be sent by both master and slave interfaces at +(``MEMIF_MSG_TYPE_DISCONNECT``) can be sent by both server and client interfaces at any time, due to driver error or if the interface is being deleted. Files
@@ -95,8 +95,8 @@ Shared memory **Shared memory format** -Slave is producer and master is consumer. Memory regions, are mapped shared memory files, -created by memif slave and provided to master at connection establishment. +Client is producer and server is consumer. Memory regions, are mapped shared memory files, +created by memif client and provided to server at connection establishment. Regions contain rings and buffers. Rings and buffers can also be separated into multiple regions. For no-zero-copy, rings and buffers are stored inside single memory region to reduce the number of opened files.
@@ -171,11 +171,11 @@ Files - net/memif/memif.h *- descriptor and ring definitions* - net/memif/rte_eth_memif.c *- eth_memif_rx() eth_memif_tx()* -Zero-copy slave +Zero-copy client ~~~~~~~~~~~~~~~ -Zero-copy slave can be enabled with memif configuration option 'zero-copy=yes'. This option -is only relevant to slave and requires eal argument '--single-file-segments'. +Zero-copy client can be enabled with memif configuration option 'zero-copy=yes'. This option +is only relevant to client and requires eal argument '--single-file-segments'. This limitation is in place, because it is too expensive to identify memseg for each packet buffer, resulting in worse performance than with zero-copy disabled. With single file segments we can calculate offset from the beginning of the file
@@ -183,9 +183,9 @@ for each packet buffer. **Shared memory format** -Region 0 is created by memif driver and contains rings. Slave interface exposes DPDK memory (memseg). +Region 0 is created by memif driver and contains rings. Client interface exposes DPDK memory (memseg). Instead of using memfd_create() to create new shared file, existing memsegs are used. -Master interface functions the same as with zero-copy disabled. +Server interface functions the same as with zero-copy disabled. region 0:
@@ -211,24 +211,24 @@ Example: testpmd ---------------------------- In this example we run two instances of testpmd application and transmit packets over memif. -First create ``master`` interface:: +First create ``server`` interface:: - #./build/app/testpmd -l 0-1 --proc-type=primary --file-prefix=pmd1 --vdev=net_memif,role=master -- -i + #./build/app/testpmd -l 0-1 --proc-type=primary --file-prefix=pmd1 --vdev=net_memif,role=server -- -i -Now create ``slave`` interface (master must be already running so the slave will connect):: +Now create ``client`` interface (server must be already running so the client will connect):: #./build/app/testpmd -l 2-3 --proc-type=primary --file-prefix=pmd2 --vdev=net_memif -- -i -You can also enable ``zero-copy`` on ``slave`` interface:: +You can also enable ``zero-copy`` on ``client`` interface:: #./build/app/testpmd -l 2-3 --proc-type=primary --file-prefix=pmd2 --vdev=net_memif,zero-copy=yes --single-file-segments -- -i Start forwarding packets:: - Slave: + Client: testpmd> start - Master: + Server: testpmd> start tx_first Show status::
@@ -241,9 +241,9 @@ Example: testpmd and VPP ------------------------ For information on how to get and run VPP please see `<https://wiki.fd.io/view/VPP>`_. -Start VPP in interactive mode (should be by default). Create memif master interface in VPP:: +Start VPP in interactive mode (should be by default). Create memif server interface in VPP:: - vpp# create interface memif id 0 master no-zero-copy + vpp# create interface memif id 0 server no-zero-copy vpp# set interface state memif0/0 up vpp# set interface ip address memif0/0 192.168.1.1/24
@@ -259,7 +259,7 @@ Now create memif interface by running testpmd with these command line options:: #./testpmd --vdev=net_memif,socket=/run/vpp/memif.sock -- -i -Testpmd should now create memif slave interface and try to connect to master. +Testpmd should now create memif client interface and try to connect to server. In testpmd set forward option to icmpecho and start forwarding:: testpmd> set fwd icmpecho
@@ -280,7 +280,7 @@ The situation is analogous to cross connecting 2 ports of the NIC by cable. To set the loopback, just use the same socket and id with different roles:: - #./testpmd --vdev=net_memif0,role=master,id=0 --vdev=net_memif1,role=slave,id=0 -- -i + #./testpmd --vdev=net_memif0,role=server,id=0 --vdev=net_memif1,role=client,id=0 -- -i Then start the communication::
drivers/net/memif/memif.h +20 -20
@@ -12,8 +12,8 @@#define MEMIF_NAME_SZ 32/* -* S2M: direction slave -> master -* M2S: direction master -> slave +* C2S: direction client -> server +* S2C: direction server -> client */ /*
@@ -33,8 +33,8 @@ typedef enum memif_msg_type { } memif_msg_type_t;typedef enum { -MEMIF_RING_S2M ,/**< buffer ring in direction slave -> master */ -MEMIF_RING_M2S ,/**< buffer ring in direction master -> slave */ +MEMIF_RING_C2S ,/**< buffer ring in direction client -> server */ +MEMIF_RING_S2C ,/**< buffer ring in direction server -> client */ }memif_ring_type_t ; typedef enum {
@@ -56,23 +56,23 @@ typedef uint8_t memif_log2_ring_size_t;*/ /** -* M2S -* Contains master interfaces configuration. +* S2C +* Contains server interfaces configuration. */ typedef struct __rte_packed {uint8_t name[MEMIF_NAME_SZ ];/**< Client app name. In this case DPDK version */ memif_version_t min_version;/**< lowest supported memif version */ memif_version_t max_version;/**< highest supported memif version */ memif_region_index_t max_region;/**< maximum num of regions */ -memif_ring_index_t max_m2s_ring;/**< maximum num of M2S ring */ -memif_ring_index_t max_s2m_ring;/**< maximum num of S2M rings */ +memif_ring_index_t max_s2c_ring;/**< maximum num of S2C ring */ +memif_ring_index_t max_c2s_ring;/**< maximum num of C2S rings */ memif_log2_ring_size_t max_log2_ring_size;/**< maximum ring size (as log2) */ }memif_msg_hello_t ;/** -* S2M +* C2S * Contains information required to identify interface -* to which the slave wants to connect. +* to which the client wants to connect. */ typedef struct __rte_packed { memif_version_t version; /**< memif version */
@@ -83,8 +83,8 @@ typedef struct __rte_packed { } memif_msg_init_t;/** -* S2M -* Request master to add new shared memory region to master interface. +* C2S +* Request server to add new shared memory region to server interface. * Shared files file descriptor is passed in cmsghdr. */ typedef struct __rte_packed {
@@ -93,12 +93,12 @@ typedef struct __rte_packed { } memif_msg_add_region_t;/** -* S2M -* Request master to add new ring to master interface. +* C2S +* Request server to add new ring to server interface. */ typedef struct __rte_packed { uint16_t flags; /**< flags */ -#define MEMIF_MSG_ADD_RING_FLAG_S2M 1 /**< ring is in S2M direction */ +#define MEMIF_MSG_ADD_RING_FLAG_C2S 1 /**< ring is in C2S direction */ memif_ring_index_t index; /**< ring index */ memif_region_index_t region; /**< region index on which this ring is located */ memif_region_offset_t offset; /**< buffer start offset */
@@ -107,23 +107,23 @@ typedef struct __rte_packed { } memif_msg_add_ring_t;/** -* S2M +* C2S * Finalize connection establishment. */ typedef struct __rte_packed { -uint8_t if_name[MEMIF_NAME_SZ ];/**< slave interface name */ +uint8_t if_name[MEMIF_NAME_SZ ];/**< client interface name */ }memif_msg_connect_t ;/** -* M2S +* S2C * Finalize connection establishment. */ typedef struct __rte_packed { -uint8_t if_name[MEMIF_NAME_SZ ];/**< master interface name */ +uint8_t if_name[MEMIF_NAME_SZ ];/**< server interface name */ }memif_msg_connected_t ;/** -* S2M & M2S +* C2S & S2C * Disconnect interfaces. */ typedef struct __rte_packed {
drivers/net/memif/memif_socket.c +27 -27
146 lines not on this page · raw message
drivers/net/memif/memif_socket.h +3 -2
@@ -60,7 +60,8 @@ void memif_disconnect(struct rte_eth_dev *dev);* - On success, zero. * - On failure, a negative value. */ -int memif_connect_master (struct rte_eth_dev *dev); +int memif_connect_server (struct rte_eth_dev *dev); +/** * If device is properly configured, send connection request.
@@ -71,7 +72,7 @@ int memif_connect_master(struct rte_eth_dev *dev);* - On success, zero. * - On failure, a negative value. */ -int memif_connect_slave (struct rte_eth_dev *dev); +int memif_connect_client (struct rte_eth_dev *dev);struct memif_socket_dev_list_elt {TAILQ_ENTRY (memif_socket_dev_list_elt) next;
drivers/net/memif/rte_eth_memif.c +64 -64
372 lines not on this page · raw message
drivers/net/memif/rte_eth_memif.h +10 -10
@@ -36,8 +36,8 @@ extern int memif_logtype; "%s(): " fmt "\n", __func__, ##args)enum memif_role_t { -MEMIF_ROLE_MASTER , -MEMIF_ROLE_SLAVE , +MEMIF_ROLE_SERVER , +MEMIF_ROLE_CLIENT , };struct memif_region {
@@ -64,8 +64,8 @@ struct memif_queue {uint16_t last_tail;/**< last ring tail */ struct rte_mbuf **buffers; -/**< Stored mbufs. Used in zero-copy tx. Slave stores transmitted -* mbufs to free them once master has received them. +/**< Stored mbufs. Used in zero-copy tx. Client stores transmitted +* mbufs to free them once server has received them. */ /* rx/tx info */
@@ -102,15 +102,15 @@ struct pmd_internals {struct {memif_log2_ring_size_t log2_ring_size;/**< log2 of ring size */ -uint8_t num_s2m_rings;/**< number of slave to master rings */ -uint8_t num_m2s_rings;/**< number of master to slave rings */ +uint8_t num_c2s_rings;/**< number of client to server rings */ +uint8_t num_s2c_rings;/**< number of server to client rings */ uint16_t pkt_buffer_size;/**< buffer size */ } cfg;/**< Configured parameters (max values) */ struct {memif_log2_ring_size_t log2_ring_size;/**< log2 of ring size */ -uint8_t num_s2m_rings;/**< number of slave to master rings */ -uint8_t num_m2s_rings;/**< number of master to slave rings */ +uint8_t num_c2s_rings;/**< number of client to server rings */ +uint8_t num_s2c_rings;/**< number of server to client rings */ uint16_t pkt_buffer_size;/**< buffer size */ } run;/**< Parameters used in active connection */
@@ -137,7 +137,7 @@ void memif_free_regions(struct rte_eth_dev *dev);/** * Finalize connection establishment process. Map shared memory file -* (master role), initialize ring queue, set link status up. +* (server role), initialize ring queue, set link status up. * * @param dev * memif device
@@ -149,7 +149,7 @@ int memif_connect(struct rte_eth_dev *dev);/** * Create shared memory file and initialize ring queue. -* Only called by slave when establishing connection +* Only called by client when establishing connection * * @param dev * memif device
Signature · 1 line
2.26.2