lttng-modules system call tracing filtering
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 11 lines · Mathieu Desnoyers
Hi!
I just create a dev branch with system call filtering within LTTng modules. Currently, only enable-event is supported at the lttng-tools level for this. With this feature, you can specify exactly which system calls you want to trace.
Here are the dev branches:
https://github.com/compudj/lttng-modules-dev branch: syscall-filtering
https://github.com/compudj/lttng-tools-dev/ branch: syscall-filtering
Great !
Just to clarify, what happens to the exit_syscall event ? Is it still emitted for every syscall exit or only for the ones we selected ?
Is it renamed ?
For the CLI usage, I think having a coma separated list would be more friendly that having to enable each syscall in a separate command, but I'm sure it is easy to have that.
Thanks !
Julien
Quoted 70 lines
To use it:
#ex 1
lttng create
lttng enable-event -k --syscallsys_openlttng enable-event -k --syscallsys_closelttng start; sleep 3; lttng stop; lttng view -> should only showsys_openandsys_closesyscalls.#ex 2
lttng create
lttng enable-event -k --syscall -a
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls#ex 3
lttng create
lttng enable-event -k --syscall -a
lttng enable-event -k --syscallsys_open
-> returns that the system call is already enabled. lttng start; sleep 3; lttng stop; lttng view -> should show all syscalls#ex 4
lttng create
lttng enable-event -k --syscallsys_open
lttng enable-event -k --syscall -a
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls### Now about the disable-event part (not implemented in tools yet) ### This is the behavior I would like:
#ex 5 (TODO)
lttng create
lttng enable-event -k --syscall -a
lttng disable-event -k --syscallsys_open
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls exceptsys_open#ex 6 (TODO)
lttng create
lttng disable-event -k --syscallsys_open
-> should fail.For the curious, I implement this "filtering" with a per-channel bitmap that represents which system calls to trace. We might need to double-check that I got the
NR_syscallsright for each architecture, especially those with compatibility system call tables (64-bit archs having 32-bit compat syscalls). For the common case (all system calls are traced), the pointer to the array is NULL, so this is a simple pointer check, which is less expensive cache-wise than looking up within the bitmap.As far as lttng-tools is concerned, what is a bit different is that system calls don't each get a file descriptor assigned, unlike other tracepoint events. Therefore, we interact with them at the channel level. If we can find a way to send the disable-event command directly to the channel, with the new "u.syscall.disable" flag I added to the lttng ABI, we should be able to use disable-event with syscalls. However, I'm not sure how deeply we need to modify lttng-tools for this.
Feedback is welcome,
Thanks !
Mathieu
A message that is not in the archive (sent off-list or not yet received): [email protected]
----- Original Message -----
Quoted 16 lines
From: "Julien Desfossez" <[email protected]>
To: "Mathieu Desnoyers" <[email protected]>, "lttng-dev" <[email protected]>
Cc: "David Goulet ([email protected])" <[email protected]>
Sent: Sunday, July 20, 2014 11:54:53 AM
Subject: Re: [RFC] lttng-modules system call tracing filteringQuoted 9 lines · Mathieu Desnoyers
Hi!
I just create a dev branch with system call filtering within LTTng modules. Currently, only enable-event is supported at the lttng-tools level for this. With this feature, you can specify exactly which system calls you want to trace.
Here are the dev branches:
Quoted 8 lines
Quoted 2 lines
https://github.com/compudj/lttng-modules-dev branch: syscall-filtering
https://github.com/compudj/lttng-tools-dev/ branch: syscall-filteringGreat !
Just to clarify, what happens to the
exit_syscallevent ? Is it still emitted for every syscall exit or only for the ones we selected ?
Just for the ones selected.
Quoted 1 line
Is it renamed ?
Yes, I'm planning to rename it, given that I want to extract the system call output parameter at syscall exit anyway, so we need to specialize this event.
Quoted 4 lines
For the CLI usage, I think having a coma separated list would be more friendly that having to enable each syscall in a separate command, but I'm sure it is easy to have that.
Perhaps this already works actually, I have not tried it though.
Thanks for the feedback!
Mathieu
Quoted 76 lines
Thanks !
Julien
Quoted 70 lines
To use it:
#ex 1
lttng create
lttng enable-event -k --syscallsys_openlttng enable-event -k --syscallsys_closelttng start; sleep 3; lttng stop; lttng view -> should only showsys_openandsys_closesyscalls.#ex 2
lttng create
lttng enable-event -k --syscall -a
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls#ex 3
lttng create
lttng enable-event -k --syscall -a
lttng enable-event -k --syscallsys_open
-> returns that the system call is already enabled. lttng start; sleep 3; lttng stop; lttng view -> should show all syscalls#ex 4
lttng create
lttng enable-event -k --syscallsys_open
lttng enable-event -k --syscall -a
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls### Now about the disable-event part (not implemented in tools yet) ### This is the behavior I would like:
#ex 5 (TODO)
lttng create
lttng enable-event -k --syscall -a
lttng disable-event -k --syscallsys_open
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls exceptsys_open#ex 6 (TODO)
lttng create
lttng disable-event -k --syscallsys_open
-> should fail.For the curious, I implement this "filtering" with a per-channel bitmap that represents which system calls to trace. We might need to double-check that I got the
NR_syscallsright for each architecture, especially those with compatibility system call tables (64-bit archs having 32-bit compat syscalls). For the common case (all system calls are traced), the pointer to the array is NULL, so this is a simple pointer check, which is less expensive cache-wise than looking up within the bitmap.As far as lttng-tools is concerned, what is a bit different is that system calls don't each get a file descriptor assigned, unlike other tracepoint events. Therefore, we interact with them at the channel level. If we can find a way to send the disable-event command directly to the channel, with the new "u.syscall.disable" flag I added to the lttng ABI, we should be able to use disable-event with syscalls. However, I'm not sure how deeply we need to modify lttng-tools for this.
Feedback is welcome,
Thanks !
Mathieu
Signature · 3 lines
Mathieu Desnoyers EfficiOS Inc. http://www.efficios.com
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 35 lines · Mathieu Desnoyers
----- Original Message -----
Quoted 16 lines
From: "Julien Desfossez" <[email protected]>
To: "Mathieu Desnoyers" <[email protected]>, "lttng-dev" <[email protected]>
Cc: "David Goulet ([email protected])" <[email protected]>
Sent: Sunday, July 20, 2014 11:54:53 AM
Subject: Re: [RFC] lttng-modules system call tracing filteringQuoted 9 lines · Mathieu Desnoyers
Hi!
I just create a dev branch with system call filtering within LTTng modules. Currently, only enable-event is supported at the lttng-tools level for this. With this feature, you can specify exactly which system calls you want to trace.
Here are the dev branches:
Quoted 8 lines
Quoted 2 lines
https://github.com/compudj/lttng-modules-dev branch: syscall-filtering
https://github.com/compudj/lttng-tools-dev/ branch: syscall-filteringGreat !
Just to clarify, what happens to the
exit_syscallevent ? Is it still emitted for every syscall exit or only for the ones we selected ?Just for the ones selected.
Quoted 1 line
Is it renamed ?
Yes, I'm planning to rename it, given that I want to extract the system call output parameter at syscall exit anyway, so we need to specialize this event.
Quoted 1 line
Quoted 5 lines
Quoted 3 lines
For the CLI usage, I think having a coma separated list would be more friendly that having to enable each syscall in a separate command, but I'm sure it is easy to have that.
Perhaps this already works actually, I have not tried it though.
No reason this shouldn’t work out of the box :). You're inside the event striping loop so everything is fine.
Cheers!
Quoted 82 lines
Thanks for the feedback!
Mathieu
Quoted 76 lines
Thanks !
Julien
Quoted 70 lines
To use it:
#ex 1
lttng create
lttng enable-event -k --syscallsys_openlttng enable-event -k --syscallsys_closelttng start; sleep 3; lttng stop; lttng view -> should only showsys_openandsys_closesyscalls.#ex 2
lttng create
lttng enable-event -k --syscall -a
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls#ex 3
lttng create
lttng enable-event -k --syscall -a
lttng enable-event -k --syscallsys_open
-> returns that the system call is already enabled. lttng start; sleep 3; lttng stop; lttng view -> should show all syscalls#ex 4
lttng create
lttng enable-event -k --syscallsys_open
lttng enable-event -k --syscall -a
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls### Now about the disable-event part (not implemented in tools yet) ### This is the behavior I would like:
#ex 5 (TODO)
lttng create
lttng enable-event -k --syscall -a
lttng disable-event -k --syscallsys_open
lttng start; sleep 3; lttng stop; lttng view
-> should show all syscalls exceptsys_open#ex 6 (TODO)
lttng create
lttng disable-event -k --syscallsys_open
-> should fail.For the curious, I implement this "filtering" with a per-channel bitmap that represents which system calls to trace. We might need to double-check that I got the
NR_syscallsright for each architecture, especially those with compatibility system call tables (64-bit archs having 32-bit compat syscalls). For the common case (all system calls are traced), the pointer to the array is NULL, so this is a simple pointer check, which is less expensive cache-wise than looking up within the bitmap.As far as lttng-tools is concerned, what is a bit different is that system calls don't each get a file descriptor assigned, unlike other tracepoint events. Therefore, we interact with them at the channel level. If we can find a way to send the disable-event command directly to the channel, with the new "u.syscall.disable" flag I added to the lttng ABI, we should be able to use disable-event with syscalls. However, I'm not sure how deeply we need to modify lttng-tools for this.
Feedback is welcome,
Thanks !
Mathieu