Skip to contentSkip to conversation

perf: support enable and disable commands in stat and record modes

PATCH Applied Alexey Budankov 2 participants 25 messages Jul 17, 2020 – Jul 22, 2020 perf events

lore
Share & tools
lore
#0 lore raw

v12 cover perf: support enable and disable commands in stat and record modes

Changes in v12:
- fixed fdarray sanity test (36) failure - due to usage of uninitialized memory after realloc() of priv data; added explicit memset(0) for newly allocated part
- captured and mentioned acquired Acked-by tags

v11: https://lore.kernel.org/lkml/[email protected]/

Changes in v11:
- added comments to struct ctl_fd
- explicitly coded data_size decrement

v10: https://lore.kernel.org/lkml/[email protected]/

Changes in v10:
- reused struct priv, renamed props into flags and used unsigned int type as a storage
- implemented and adopted usage of evlist__ctlfd_initialized() function
- updated while condition with checking !(done || stop)
- implemented compute_tts() to calculate the remainder of timeout to wait in poll()

v9: https://lore.kernel.org/lkml/[email protected]/

Changes in v9:
- avoided screwing of fds by fdarray__filter() to fix staleness of pos returned by fdarray__add()
- implemented notion of properties for fds kept by fdarray object and introduced nonfilterable property for control fd
- avoided counting of nonfilterable fds by fdarray__filter()
- replaced strlen() with sizeof(str)-1 for CMD_TAGS
- avoided mixing timeout and interval processing in one function
- renamed child to child_exited variable
- processed time_to_sleep < time_diff condition
- placed evlist__ctlfd_process() call after evlist__poll() and evlist__filter_pollfd() calls in record mode

v8: https://lore.kernel.org/lkml/[email protected]/

Changes in v8:
- avoided moving of fds at fdarray__filter() call
- skipped counting of fds with zeroed revents at fdarray__filter() call
- converted explicit --ctl-fd[-ack] into --control fd:ctl-fd[,ack-fd option
- updated docs to accommodate --control fd:ctl-fd[,ack-fd] option

v7: https://lore.kernel.org/lkml/[email protected]/

Changes in v7:
- added missing perf-record.txt changes
- adjusted docs wording for --ctl-fd,ctl-fd-ack options to additionally mention --delay=-1 effect

v6: https://lore.kernel.org/lkml/[email protected]/

Changes in v6:
- split re-factoring of events handling loops for stat mode into smaller incremental parts
- added parts missing at v5
- corrected v5 runtime issues

v5: https://lore.kernel.org/lkml/[email protected]/

Changes in v5:
- split re-factoring of events handling loops for stat mode into smaller incremental parts

v4: https://lore.kernel.org/lkml/[email protected]/

Changes in v4:
- made checking of ctlfd state unconditional in record trace streaming loop
- introduced static poll fds to keep evlist__filter_pollfd() unaffected
- handled ret code of evlist__initialize_ctlfd() where need
- renamed and structured handle_events() function
- applied anonymous structs where needed

v3: https://lore.kernel.org/lkml/[email protected]/

Changes in v3:
- renamed functions and types from perf_evlist_ to evlist_ to avoid clash with libperf code;
- extended commands to be strings of variable length consisting of command name and also possibly including command specific data;
- merged docs update with the code changes;
- updated docs for -D,--delay=-1 option for stat and record modes;

v2: https://lore.kernel.org/lkml/[email protected]/

Changes in v2:
- renamed resume and pause commands to enable and disable ones, renamed CTL_CMD_RESUME and CTL_CMD_PAUSE to CTL_CMD_ENABLE and CTL_CMD_DISABLE to fit to the appropriate ioctls and avoid mixing up with PAUSE_OUTPUT ioctl;
- factored out event handling loop into a handle_events() for stat mode;
- separated -D,--delay=-1 into separate patches for stat and record modes;

v1: https://lore.kernel.org/lkml/[email protected]/

repo: tip of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git perf/core

The patch set implements handling of 'start disabled', 'enable' and 'disable' external control commands which can be provided for stat and record modes of the tool from an external controlling process. 'start disabled' command can be used to postpone enabling of events in the beginning of a monitoring session. 'enable' and 'disable' commands can be used to enable and disable events correspondingly any time after the start of the session.

The 'start disabled', 'enable' and 'disable' external control commands can be used to focus measurement on specially selected time intervals of workload execution. Focused measurement reduces tool intrusion and influence on workload behavior, reduces distortion and amount of collected and stored data, mitigates data accuracy loss because measurement and data capturing happen only during intervals of interest.

A controlling process can be a bash shell script [1], native executable or any other language program that can directly work with file descriptors, e.g. pipes [2], and spawn a process, specially the tool one.

-D,--delay <val> option is extended with -1 value to skip events enabling in the beginning of a monitoring session ('start disabled' command). --control fd:ctl-fd[,ack-fd] command line option is introduced to provide the tool with a pair of file descriptors to listen to control commands and reply to the controlling process on the completion of received commands.

The tool reads control command message from ctl-fd descriptor, handles the command and optionally replies acknowledgement message to ack-fd descriptor, if it is specified on the command line. 'enable' command is recognized as 'enable' string message and 'disable' command is recognized as 'disable' string message both received from ctl-fd descriptor. Completion message is 'ack\n' and sent to ack-fd descriptor.

Example bash script demonstrating simple use case follows:

#!/bin/bash

ctl_dir=/tmp/

ctl_fifo=${ctl_dir}perf_ctl.fifo
test -p ${ctl_fifo} && unlink ${ctl_fifo}
mkfifo ${ctl_fifo} && exec {ctl_fd}<>${ctl_fifo}

ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo
test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} mkfifo ${ctl_ack_fifo} && exec {ctl_fd_ack}<>${ctl_ack_fifo}

perf stat -D -1 -e cpu-cycles -a -I 1000       \
          --control fd:${ctl_fd},${ctl_fd_ack} \
          -- sleep 40 &

perf_pid=$!

sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e2 && echo "enabled(${e2})" sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d2 && echo "disabled(${d2})"

exec {ctl_fd_ack}>&- && unlink ${ctl_ack_fifo}
exec {ctl_fd}>&- && unlink ${ctl_fifo}

wait -n ${perf_pid}
exit $?

Script output:

[root@host dir] example
Events disabled
# time counts unit events

     1.001101062      <not counted>      cpu-cycles                                                  
     2.002994944      <not counted>      cpu-cycles                                                  
     3.004864340      <not counted>      cpu-cycles                                                  
     4.006727177      <not counted>      cpu-cycles                                                  
Events enabled
enabled(ack)
     4.993808464          3,124,246      cpu-cycles                                                  
     5.008597004          3,325,624      cpu-cycles                                                  
     6.010387483         83,472,992      cpu-cycles                                                  
     7.012266598         55,877,621      cpu-cycles                                                  
     8.014175695         97,892,729      cpu-cycles                                                  
     9.016056093         68,461,242      cpu-cycles                                                  
    10.017937507         55,449,643      cpu-cycles                                                  
    11.019830154         68,938,167      cpu-cycles                                                  
    12.021719952         55,164,101      cpu-cycles                                                  
    13.023627550         70,535,720      cpu-cycles                                                  
    14.025580995         53,240,125      cpu-cycles                                                  
disabled(ack)
    14.997518260         53,558,068      cpu-cycles                                                  
Events disabled
    15.027216416      <not counted>      cpu-cycles                                                  
    16.029052729      <not counted>      cpu-cycles                                                  
    17.030904762      <not counted>      cpu-cycles                                                  
    18.032073424      <not counted>      cpu-cycles                                                  
    19.033805074      <not counted>      cpu-cycles                                                  
Events enabled
enabled(ack)
    20.001279097          3,021,022      cpu-cycles                                                  
    20.035044381          6,434,367      cpu-cycles                                                  
    21.036923813         89,358,251      cpu-cycles                                                  
    22.038825169         72,516,351      cpu-cycles                                                  
#           time             counts unit events
    23.040715596         55,046,157      cpu-cycles                                                  
    24.042643757         78,128,649      cpu-cycles                                                  
    25.044558535         61,052,428      cpu-cycles                                                  
    26.046452785         62,142,806      cpu-cycles                                                  
    27.048353021         74,477,971      cpu-cycles                                                  
    28.050241286         61,001,623      cpu-cycles                                                  
    29.052149961         61,653,502      cpu-cycles                                                  
disabled(ack)
    30.004980264         82,729,640      cpu-cycles                                                  
Events disabled
    30.053516176      <not counted>      cpu-cycles                                                  
    31.055348366      <not counted>      cpu-cycles                                                  
    32.057202097      <not counted>      cpu-cycles                                                  
    33.059040702      <not counted>      cpu-cycles                                                  
    34.060843288      <not counted>      cpu-cycles                                                  
    35.000888624      <not counted>      cpu-cycles                                                  

[root@host dir]#

[1] http://man7.org/linux/man-pages/man1/bash.1.html
[2] http://man7.org/linux/man-pages/man2/pipe.2.html

---
Alexey Budankov (15):
tools/libperf: avoid internal moving of fdarray fds tools/libperf: add flags to fdarray fds objects tools/libperf: avoid counting of nonfilterable fdarray fds perf evlist: introduce control file descriptors
perf evlist: implement control command handling functions perf stat: factor out body of event handling loop for system wide perf stat: move target check to loop control statement perf stat: factor out body of event handling loop for fork case perf stat: factor out event handling loop into dispatch_events() perf stat: extend -D,--delay option with -1 value
perf stat: implement control commands handling
perf stat: introduce --control fd:ctl-fd[,ack-fd] options perf record: extend -D,--delay option with -1 value perf record: implement control commands handling
perf record: introduce --control fd:ctl-fd[,ack-fd] options

 tools/lib/api/fd/array.c                 |  23 +--
 tools/lib/api/fd/array.h                 |  16 +-
 tools/lib/perf/evlist.c                  |   6 +-
 tools/lib/perf/include/internal/evlist.h |   2 +-
 tools/perf/Documentation/perf-record.txt |  44 +++++-
 tools/perf/Documentation/perf-stat.txt   |  44 +++++-
 tools/perf/builtin-record.c              |  65 +++++++-
 tools/perf/builtin-stat.c                | 183 ++++++++++++++++++-----
 tools/perf/builtin-trace.c               |   2 +-
 tools/perf/tests/fdarray.c               |  22 +--
 tools/perf/util/evlist.c                 | 145 +++++++++++++++++-
 tools/perf/util/evlist.h                 |  26 ++++
 tools/perf/util/record.h                 |   4 +-
 tools/perf/util/stat.h                   |   4 +-
 14 files changed, 500 insertions(+), 86 deletions(-)
Signature · 1 line
2.24.1
#1 lore raw

PATCH v12 1/15 tools/libperf: avoid internal moving of fdarray fds

Avoid moving of fds by fdarray__filter() so fds indices returned by fdarray__add() can be used for access and processing of objects at struct pollfd *entries.

---
 tools/lib/api/fd/array.c   | 11 +++++------
 tools/perf/tests/fdarray.c | 20 ++------------------
 2 files changed, 7 insertions(+), 24 deletions(-)
tools/lib/api/fd/array.c +5 -6
index 58d44d5eee31..89f9a2193c2d 100644
@@ -93,22 +93,21 @@ int fdarray__filter(struct fdarray *fda, short revents,
 		return 0;
 
 	for (fd = 0; fd < fda->nr; ++fd) {
+		if (!fda->entries[fd].events)
+			continue;
+
 		if (fda->entries[fd].revents & revents) {
 			if (entry_destructor)
 				entry_destructor(fda, fd, arg);
 
+			fda->entries[fd].revents = fda->entries[fd].events = 0;
 			continue;
 		}
 
-		if (fd != nr) {
-			fda->entries[nr] = fda->entries[fd];
-			fda->priv[nr]	 = fda->priv[fd];
-		}
-
 		++nr;
 	}
 
-	return fda->nr = nr;
+	return nr;
 }
 
 int fdarray__poll(struct fdarray *fda, int timeout)
tools/perf/tests/fdarray.c +2 -18
index c7c81c4a5b2b..d0c8a05aab2f 100644
@@ -12,6 +12,7 @@ static void fdarray__init_revents(struct fdarray *fda, short revents)
 
 	for (fd = 0; fd < fda->nr; ++fd) {
 		fda->entries[fd].fd	 = fda->nr - fd;
+		fda->entries[fd].events  = revents;
 		fda->entries[fd].revents = revents;
 	}
 }
@@ -29,7 +30,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
 
 int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
-	int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
+	int nr_fds, err = TEST_FAIL;
 	struct fdarray *fda = fdarray__new(5, 5);
 
 	if (fda == NULL) {
@@ -55,7 +56,6 @@ int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_
 
 	fdarray__init_revents(fda, POLLHUP);
 	fda->entries[2].revents = POLLIN;
-	expected_fd[0] = fda->entries[2].fd;
 
 	pr_debug("\nfiltering all but fda->entries[2]:");
 	fdarray__fprintf_prefix(fda, "before", stderr);
@@ -66,17 +66,9 @@ int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_
 		goto out_delete;
 	}
 
-	if (fda->entries[0].fd != expected_fd[0]) {
-		pr_debug("\nfda->entries[0].fd=%d != %d\n",
-			 fda->entries[0].fd, expected_fd[0]);
-		goto out_delete;
-	}
-
 	fdarray__init_revents(fda, POLLHUP);
 	fda->entries[0].revents = POLLIN;
-	expected_fd[0] = fda->entries[0].fd;
 	fda->entries[3].revents = POLLIN;
-	expected_fd[1] = fda->entries[3].fd;
 
 	pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):");
 	fdarray__fprintf_prefix(fda, "before", stderr);
@@ -88,14 +80,6 @@ int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_
 		goto out_delete;
 	}
 
-	for (fd = 0; fd < 2; ++fd) {
-		if (fda->entries[fd].fd != expected_fd[fd]) {
-			pr_debug("\nfda->entries[%d].fd=%d != %d\n", fd,
-				 fda->entries[fd].fd, expected_fd[fd]);
-			goto out_delete;
-		}
-	}
-
 	pr_debug("\n");
 
 	err = 0;
Signature · 1 line
2.24.1
maintainer Applied
#2 lore raw

Re: [PATCH v12 01/15] tools/libperf: avoid internal moving of fdarray fds

Em Fri, Jul 17, 2020 at 09:59:12AM +0300, Alexey Budankov escreveu:

Quoted 4 lines

Avoid moving of fds by fdarray__filter() so fds indices returned by fdarray__add() can be used for access and processing of objects at struct pollfd *entries.

Thanks, applied.

- Arnaldo

Quoted 106 lines
---
 tools/lib/api/fd/array.c   | 11 +++++------
 tools/perf/tests/fdarray.c | 20 ++------------------
 2 files changed, 7 insertions(+), 24 deletions(-)
tools/lib/api/fd/array.c +5 -6
index 58d44d5eee31..89f9a2193c2d 100644
@@ -93,22 +93,21 @@ int fdarray__filter(struct fdarray *fda, short revents,
 		return 0;
 
 	for (fd = 0; fd < fda->nr; ++fd) {
+		if (!fda->entries[fd].events)
+			continue;
+
 		if (fda->entries[fd].revents & revents) {
 			if (entry_destructor)
 				entry_destructor(fda, fd, arg);
 
+			fda->entries[fd].revents = fda->entries[fd].events = 0;
 			continue;
 		}
 
-		if (fd != nr) {
-			fda->entries[nr] = fda->entries[fd];
-			fda->priv[nr]	 = fda->priv[fd];
-		}
-
 		++nr;
 	}
 
-	return fda->nr = nr;
+	return nr;
 }
 
 int fdarray__poll(struct fdarray *fda, int timeout)
tools/perf/tests/fdarray.c +2 -18
index c7c81c4a5b2b..d0c8a05aab2f 100644
@@ -12,6 +12,7 @@ static void fdarray__init_revents(struct fdarray *fda, short revents)
 
 	for (fd = 0; fd < fda->nr; ++fd) {
 		fda->entries[fd].fd	 = fda->nr - fd;
+		fda->entries[fd].events  = revents;
 		fda->entries[fd].revents = revents;
 	}
 }
@@ -29,7 +30,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
 
 int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
-	int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
+	int nr_fds, err = TEST_FAIL;
 	struct fdarray *fda = fdarray__new(5, 5);
 
 	if (fda == NULL) {
@@ -55,7 +56,6 @@ int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_
 
 	fdarray__init_revents(fda, POLLHUP);
 	fda->entries[2].revents = POLLIN;
-	expected_fd[0] = fda->entries[2].fd;
 
 	pr_debug("\nfiltering all but fda->entries[2]:");
 	fdarray__fprintf_prefix(fda, "before", stderr);
@@ -66,17 +66,9 @@ int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_
 		goto out_delete;
 	}
 
-	if (fda->entries[0].fd != expected_fd[0]) {
-		pr_debug("\nfda->entries[0].fd=%d != %d\n",
-			 fda->entries[0].fd, expected_fd[0]);
-		goto out_delete;
-	}
-
 	fdarray__init_revents(fda, POLLHUP);
 	fda->entries[0].revents = POLLIN;
-	expected_fd[0] = fda->entries[0].fd;
 	fda->entries[3].revents = POLLIN;
-	expected_fd[1] = fda->entries[3].fd;
 
 	pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):");
 	fdarray__fprintf_prefix(fda, "before", stderr);
@@ -88,14 +80,6 @@ int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_
 		goto out_delete;
 	}
 
-	for (fd = 0; fd < 2; ++fd) {
-		if (fda->entries[fd].fd != expected_fd[fd]) {
-			pr_debug("\nfda->entries[%d].fd=%d != %d\n", fd,
-				 fda->entries[fd].fd, expected_fd[fd]);
-			goto out_delete;
-		}
-	}
-
 	pr_debug("\n");
 
 	err = 0;
Signature · 1 line
2.24.1
Signature · 1 line
- Arnaldo
#3 lore raw

PATCH v12 2/15 tools/libperf: add flags to fdarray fds objects

In reply to Alexey Budankov

Store flags per struct pollfd *entries object in a bitmap of int size. Implement fdarray_flag__nonfilterable flag to skip object from counting by fdarray__filter(). Fixed fdarray test issue reported by kernel test robot.

---
 tools/lib/api/fd/array.c                 |  9 +++++++--
 tools/lib/api/fd/array.h                 | 16 ++++++++++++----
 tools/lib/perf/evlist.c                  |  6 +++---
 tools/lib/perf/include/internal/evlist.h |  2 +-
 tools/perf/tests/fdarray.c               |  2 +-
 tools/perf/util/evlist.c                 |  2 +-
 6 files changed, 25 insertions(+), 12 deletions(-)
tools/lib/api/fd/array.c +7 -2
index 89f9a2193c2d..01b3b89f9797 100644
@@ -8,6 +8,7 @@
 #include <poll.h>
 #include <stdlib.h>
 #include <unistd.h>
+#include <string.h>
 
 void fdarray__init(struct fdarray *fda, int nr_autogrow)
 {
@@ -19,7 +20,7 @@ void fdarray__init(struct fdarray *fda, int nr_autogrow)
 
 int fdarray__grow(struct fdarray *fda, int nr)
 {
-	void *priv;
+	struct priv *priv;
 	int nr_alloc = fda->nr_alloc + nr;
 	size_t psize = sizeof(fda->priv[0]) * nr_alloc;
 	size_t size  = sizeof(struct pollfd) * nr_alloc;
@@ -34,6 +35,9 @@ int fdarray__grow(struct fdarray *fda, int nr)
 		return -ENOMEM;
 	}
 
+	memset(&entries[fda->nr_alloc], 0, sizeof(struct pollfd) * nr);
+	memset(&priv[fda->nr_alloc], 0, sizeof(fda->priv[0]) * nr);
+
 	fda->nr_alloc = nr_alloc;
 	fda->entries  = entries;
 	fda->priv     = priv;
@@ -69,7 +73,7 @@ void fdarray__delete(struct fdarray *fda)
 	free(fda);
 }
 
-int fdarray__add(struct fdarray *fda, int fd, short revents)
+int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags)
 {
 	int pos = fda->nr;
 
@@ -79,6 +83,7 @@ int fdarray__add(struct fdarray *fda, int fd, short revents)
 
 	fda->entries[fda->nr].fd     = fd;
 	fda->entries[fda->nr].events = revents;
+	fda->priv[fda->nr].flags = flags;
 	fda->nr++;
 	return pos;
 }
tools/lib/api/fd/array.h +12 -4
index b39557d1a88f..7fcf21a33c0c 100644
@@ -21,19 +21,27 @@ struct fdarray {
 	int	       nr_alloc;
 	int	       nr_autogrow;
 	struct pollfd *entries;
-	union {
-		int    idx;
-		void   *ptr;
+	struct priv {
+		union {
+			int    idx;
+			void   *ptr;
+		};
+		unsigned int flags;
 	} *priv;
 };
 
+enum fdarray_flags {
+	fdarray_flag__default	    = 0x00000000,
+	fdarray_flag__nonfilterable = 0x00000001
+};
+
 void fdarray__init(struct fdarray *fda, int nr_autogrow);
 void fdarray__exit(struct fdarray *fda);
 
 struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow);
 void fdarray__delete(struct fdarray *fda);
 
-int fdarray__add(struct fdarray *fda, int fd, short revents);
+int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags);
 int fdarray__poll(struct fdarray *fda, int timeout);
 int fdarray__filter(struct fdarray *fda, short revents,
 		    void (*entry_destructor)(struct fdarray *fda, int fd, void *arg),
tools/lib/perf/evlist.c +3 -3
index 6a875a0f01bb..2208444ecb44 100644
@@ -305,9 +305,9 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 }
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
-			    void *ptr, short revent)
+			    void *ptr, short revent, enum fdarray_flags flags)
 {
-	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP);
+	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP, flags);
 
 	if (pos >= 0) {
 		evlist->pollfd.priv[pos].ptr = ptr;
@@ -488,7 +488,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 		revent = !overwrite ? POLLIN : 0;
 
 		if (!evsel->system_wide &&
-		    perf_evlist__add_pollfd(evlist, fd, map, revent) < 0) {
+		    perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) {
 			perf_mmap__put(map);
 			return -1;
 		}
tools/lib/perf/include/internal/evlist.h +1 -1
index 74dc8c3f0b66..2d0fa02b036f 100644
@@ -45,7 +45,7 @@ struct perf_evlist_mmap_ops {
 
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
-			    void *ptr, short revent);
+			    void *ptr, short revent, enum fdarray_flags flags);
 
 int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_evlist_mmap_ops *ops,
tools/perf/tests/fdarray.c +1 -1
index d0c8a05aab2f..d9eca8e86a6b 100644
@@ -112,7 +112,7 @@ int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unu
 	}
 
 #define FDA_ADD(_idx, _fd, _revents, _nr)				   \
-	if (fdarray__add(fda, _fd, _revents) < 0) {			   \
+	if (fdarray__add(fda, _fd, _revents, fdarray_flag__default) < 0) { \
 		pr_debug("\n%d: fdarray__add(fda, %d, %d) failed!",	   \
 			 __LINE__,_fd, _revents);			   \
 		goto out_delete;					   \
tools/perf/util/evlist.c +1 -1
index 1b884695b4d3..bcbe0cb8482e 100644
@@ -497,7 +497,7 @@ int perf_evlist__enable_event_idx(struct evlist *evlist,
 
 int evlist__add_pollfd(struct evlist *evlist, int fd)
 {
-	return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN);
+	return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN, fdarray_flag__default);
 }
 
 int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask)
Signature · 1 line
2.24.1
maintainer Applied
#4 lore raw

Re: [PATCH v12 02/15] tools/libperf: add flags to fdarray fds objects

Em Fri, Jul 17, 2020 at 09:59:45AM +0300, Alexey Budankov escreveu:

Quoted 5 lines

Store flags per struct pollfd *entries object in a bitmap of int size. Implement fdarray_flag__nonfilterable flag to skip object from counting by fdarray__filter(). Fixed fdarray test issue reported by kernel test robot.

Thanks, applied.

- Arnaldo

Quoted 165 lines
---
 tools/lib/api/fd/array.c                 |  9 +++++++--
 tools/lib/api/fd/array.h                 | 16 ++++++++++++----
 tools/lib/perf/evlist.c                  |  6 +++---
 tools/lib/perf/include/internal/evlist.h |  2 +-
 tools/perf/tests/fdarray.c               |  2 +-
 tools/perf/util/evlist.c                 |  2 +-
 6 files changed, 25 insertions(+), 12 deletions(-)
tools/lib/api/fd/array.c +7 -2
index 89f9a2193c2d..01b3b89f9797 100644
@@ -8,6 +8,7 @@
 #include <poll.h>
 #include <stdlib.h>
 #include <unistd.h>
+#include <string.h>
 
 void fdarray__init(struct fdarray *fda, int nr_autogrow)
 {
@@ -19,7 +20,7 @@ void fdarray__init(struct fdarray *fda, int nr_autogrow)
 
 int fdarray__grow(struct fdarray *fda, int nr)
 {
-	void *priv;
+	struct priv *priv;
 	int nr_alloc = fda->nr_alloc + nr;
 	size_t psize = sizeof(fda->priv[0]) * nr_alloc;
 	size_t size  = sizeof(struct pollfd) * nr_alloc;
@@ -34,6 +35,9 @@ int fdarray__grow(struct fdarray *fda, int nr)
 		return -ENOMEM;
 	}
 
+	memset(&entries[fda->nr_alloc], 0, sizeof(struct pollfd) * nr);
+	memset(&priv[fda->nr_alloc], 0, sizeof(fda->priv[0]) * nr);
+
 	fda->nr_alloc = nr_alloc;
 	fda->entries  = entries;
 	fda->priv     = priv;
@@ -69,7 +73,7 @@ void fdarray__delete(struct fdarray *fda)
 	free(fda);
 }
 
-int fdarray__add(struct fdarray *fda, int fd, short revents)
+int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags)
 {
 	int pos = fda->nr;
 
@@ -79,6 +83,7 @@ int fdarray__add(struct fdarray *fda, int fd, short revents)
 
 	fda->entries[fda->nr].fd     = fd;
 	fda->entries[fda->nr].events = revents;
+	fda->priv[fda->nr].flags = flags;
 	fda->nr++;
 	return pos;
 }
tools/lib/api/fd/array.h +12 -4
index b39557d1a88f..7fcf21a33c0c 100644
@@ -21,19 +21,27 @@ struct fdarray {
 	int	       nr_alloc;
 	int	       nr_autogrow;
 	struct pollfd *entries;
-	union {
-		int    idx;
-		void   *ptr;
+	struct priv {
+		union {
+			int    idx;
+			void   *ptr;
+		};
+		unsigned int flags;
 	} *priv;
 };
 
+enum fdarray_flags {
+	fdarray_flag__default	    = 0x00000000,
+	fdarray_flag__nonfilterable = 0x00000001
+};
+
 void fdarray__init(struct fdarray *fda, int nr_autogrow);
 void fdarray__exit(struct fdarray *fda);
 
 struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow);
 void fdarray__delete(struct fdarray *fda);
 
-int fdarray__add(struct fdarray *fda, int fd, short revents);
+int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags);
 int fdarray__poll(struct fdarray *fda, int timeout);
 int fdarray__filter(struct fdarray *fda, short revents,
 		    void (*entry_destructor)(struct fdarray *fda, int fd, void *arg),
tools/lib/perf/evlist.c +3 -3
index 6a875a0f01bb..2208444ecb44 100644
@@ -305,9 +305,9 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 }
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
-			    void *ptr, short revent)
+			    void *ptr, short revent, enum fdarray_flags flags)
 {
-	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP);
+	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP, flags);
 
 	if (pos >= 0) {
 		evlist->pollfd.priv[pos].ptr = ptr;
@@ -488,7 +488,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 		revent = !overwrite ? POLLIN : 0;
 
 		if (!evsel->system_wide &&
-		    perf_evlist__add_pollfd(evlist, fd, map, revent) < 0) {
+		    perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) {
 			perf_mmap__put(map);
 			return -1;
 		}
tools/lib/perf/include/internal/evlist.h +1 -1
index 74dc8c3f0b66..2d0fa02b036f 100644
@@ -45,7 +45,7 @@ struct perf_evlist_mmap_ops {
 
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
-			    void *ptr, short revent);
+			    void *ptr, short revent, enum fdarray_flags flags);
 
 int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_evlist_mmap_ops *ops,
tools/perf/tests/fdarray.c +1 -1
index d0c8a05aab2f..d9eca8e86a6b 100644
@@ -112,7 +112,7 @@ int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unu
 	}
 
 #define FDA_ADD(_idx, _fd, _revents, _nr)				   \
-	if (fdarray__add(fda, _fd, _revents) < 0) {			   \
+	if (fdarray__add(fda, _fd, _revents, fdarray_flag__default) < 0) { \
 		pr_debug("\n%d: fdarray__add(fda, %d, %d) failed!",	   \
 			 __LINE__,_fd, _revents);			   \
 		goto out_delete;					   \
tools/perf/util/evlist.c +1 -1
index 1b884695b4d3..bcbe0cb8482e 100644
@@ -497,7 +497,7 @@ int perf_evlist__enable_event_idx(struct evlist *evlist,
 
 int evlist__add_pollfd(struct evlist *evlist, int fd)
 {
-	return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN);
+	return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN, fdarray_flag__default);
 }
 
 int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask)
Signature · 1 line
2.24.1
Signature · 1 line
- Arnaldo
#5 lore raw

PATCH v12 3/15 tools/libperf: avoid counting of nonfilterable fdarray fds

In reply to Alexey Budankov

Avoid counting of struct pollfd *entries objects with fdarray_flag__nonfilterable flag by fdarray__filter(). Nonfilterable objects are still processed if requested revents have been signaled for them.

---
 tools/lib/api/fd/array.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
tools/lib/api/fd/array.c +2 -1
index 01b3b89f9797..5e6cb9debe37 100644
@@ -109,7 +109,8 @@ int fdarray__filter(struct fdarray *fda, short revents,
 			continue;
 		}
 
-		++nr;
+		if (!(fda->priv[fd].flags & fdarray_flag__nonfilterable))
+			++nr;
 	}
 
 	return nr;
Signature · 1 line
2.24.1
maintainer Applied
#6 lore raw

Re: [PATCH v12 03/15] tools/libperf: avoid counting of nonfilterable fdarray fds

Em Fri, Jul 17, 2020 at 10:00:15AM +0300, Alexey Budankov escreveu:

Quoted 5 lines

Avoid counting of struct pollfd *entries objects with fdarray_flag__nonfilterable flag by fdarray__filter(). Nonfilterable objects are still processed if requested revents have been signaled for them.

Thanks, applied.

- Arnaldo

Quoted 25 lines
---
 tools/lib/api/fd/array.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
tools/lib/api/fd/array.c +2 -1
index 01b3b89f9797..5e6cb9debe37 100644
@@ -109,7 +109,8 @@ int fdarray__filter(struct fdarray *fda, short revents,
 			continue;
 		}
 
-		++nr;
+		if (!(fda->priv[fd].flags & fdarray_flag__nonfilterable))
+			++nr;
 	}
 
 	return nr;
Signature · 1 line
2.24.1
Signature · 1 line
- Arnaldo
#7 lore raw

PATCH v12 4/15 perf evlist: introduce control file descriptors

In reply to Alexey Budankov

Define and initialize control file descriptors.

---
 tools/perf/util/evlist.c | 3 +++
 tools/perf/util/evlist.h | 5 +++++
 2 files changed, 8 insertions(+)
tools/perf/util/evlist.c +3 -0
index bcbe0cb8482e..36eb50aba1f5 100644
@@ -63,6 +63,9 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
 	evlist->workload.pid = -1;
 	evlist->bkw_mmap_state = BKW_MMAP_NOTREADY;
+	evlist->ctl_fd.fd = -1;
+	evlist->ctl_fd.ack = -1;
+	evlist->ctl_fd.pos = -1;
 }
 
 struct evlist *evlist__new(void)
tools/perf/util/evlist.h +5 -0
index 38901c0d1599..fe1fe40e044b 100644
@@ -74,6 +74,11 @@ struct evlist {
 		pthread_t		th;
 		volatile int		done;
 	} thread;
+	struct {
+		int	fd;	/* control file descriptor */
+		int	ack;	/* ack file descriptor for control commands */
+		int	pos;	/* index at evlist core object to check signals */
+	} ctl_fd;
 };
 
 struct evsel_str_handler {
Signature · 1 line
2.24.1
#8 lore raw

PATCH v12 5/15 perf evlist: implement control command handling functions

In reply to Alexey Budankov

Implement functions of initialization, finalization and processing of control command messages coming from control file descriptors. Allocate control file descriptor as descriptor at struct pollfd object of evsel_list for atomic poll() operation.

---
 tools/perf/util/evlist.c | 140 +++++++++++++++++++++++++++++++++++++++
 tools/perf/util/evlist.h |  18 +++++
 2 files changed, 158 insertions(+)
tools/perf/util/evlist.c +140 -0
index 36eb50aba1f5..fe900d82815c 100644
@@ -1714,3 +1714,143 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
 	}
 	return leader;
 }
+
+int evlist__initialize_ctlfd(struct evlist *evlist, int fd, int ack)
+{
+	if (fd == -1) {
+		pr_debug("Control descriptor is not initialized\n");
+		return 0;
+	}
+
+	evlist->ctl_fd.pos = perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN,
+						     fdarray_flag__nonfilterable);
+	if (evlist->ctl_fd.pos < 0) {
+		evlist->ctl_fd.pos = -1;
+		pr_err("Failed to add ctl fd entry: %m\n");
+		return -1;
+	}
+
+	evlist->ctl_fd.fd = fd;
+	evlist->ctl_fd.ack = ack;
+
+	return 0;
+}
+
+bool evlist__ctlfd_initialized(struct evlist *evlist)
+{
+	return evlist->ctl_fd.pos >= 0;
+}
+
+int evlist__finalize_ctlfd(struct evlist *evlist)
+{
+	struct pollfd *entries = evlist->core.pollfd.entries;
+
+	if (!evlist__ctlfd_initialized(evlist))
+		return 0;
+
+	entries[evlist->ctl_fd.pos].fd = -1;
+	entries[evlist->ctl_fd.pos].events = 0;
+	entries[evlist->ctl_fd.pos].revents = 0;
+
+	evlist->ctl_fd.pos = -1;
+	evlist->ctl_fd.ack = -1;
+	evlist->ctl_fd.fd = -1;
+
+	return 0;
+}
+
+static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd,
+			      char *cmd_data, size_t data_size)
+{
+	int err;
+	char c;
+	size_t bytes_read = 0;
+
+	memset(cmd_data, 0, data_size);
+	data_size--;
+
+	do {
+		err = read(evlist->ctl_fd.fd, &c, 1);
+		if (err > 0) {
+			if (c == '\n' || c == '\0')
+				break;
+			cmd_data[bytes_read++] = c;
+			if (bytes_read == data_size)
+				break;
+		} else {
+			if (err == -1)
+				pr_err("Failed to read from ctlfd %d: %m\n", evlist->ctl_fd.fd);
+			break;
+		}
+	} while (1);
+
+	pr_debug("Message from ctl_fd: \"%s%s\"\n", cmd_data,
+		 bytes_read == data_size ? "" : c == '\n' ? "\\n" : "\\0");
+
+	if (err > 0) {
+		if (!strncmp(cmd_data, EVLIST_CTL_CMD_ENABLE_TAG,
+			     (sizeof(EVLIST_CTL_CMD_ENABLE_TAG)-1))) {
+			*cmd = EVLIST_CTL_CMD_ENABLE;
+		} else if (!strncmp(cmd_data, EVLIST_CTL_CMD_DISABLE_TAG,
+				    (sizeof(EVLIST_CTL_CMD_DISABLE_TAG)-1))) {
+			*cmd = EVLIST_CTL_CMD_DISABLE;
+		}
+	}
+
+	return err;
+}
+
+static int evlist__ctlfd_ack(struct evlist *evlist)
+{
+	int err;
+
+	if (evlist->ctl_fd.ack == -1)
+		return 0;
+
+	err = write(evlist->ctl_fd.ack, EVLIST_CTL_CMD_ACK_TAG,
+		    sizeof(EVLIST_CTL_CMD_ACK_TAG));
+	if (err == -1)
+		pr_err("failed to write to ctl_ack_fd %d: %m\n", evlist->ctl_fd.ack);
+
+	return err;
+}
+
+int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd)
+{
+	int err = 0;
+	char cmd_data[EVLIST_CTL_CMD_MAX_LEN];
+	int ctlfd_pos = evlist->ctl_fd.pos;
+	struct pollfd *entries = evlist->core.pollfd.entries;
+
+	if (!evlist__ctlfd_initialized(evlist) || !entries[ctlfd_pos].revents)
+		return 0;
+
+	if (entries[ctlfd_pos].revents & POLLIN) {
+		err = evlist__ctlfd_recv(evlist, cmd, cmd_data,
+					 EVLIST_CTL_CMD_MAX_LEN);
+		if (err > 0) {
+			switch (*cmd) {
+			case EVLIST_CTL_CMD_ENABLE:
+				evlist__enable(evlist);
+				break;
+			case EVLIST_CTL_CMD_DISABLE:
+				evlist__disable(evlist);
+				break;
+			case EVLIST_CTL_CMD_ACK:
+			case EVLIST_CTL_CMD_UNSUPPORTED:
+			default:
+				pr_debug("ctlfd: unsupported %d\n", *cmd);
+				break;
+			}
+			if (!(*cmd == EVLIST_CTL_CMD_ACK || *cmd == EVLIST_CTL_CMD_UNSUPPORTED))
+				evlist__ctlfd_ack(evlist);
+		}
+	}
+
+	if (entries[ctlfd_pos].revents & (POLLHUP | POLLERR))
+		evlist__finalize_ctlfd(evlist);
+	else
+		entries[ctlfd_pos].revents = 0;
+
+	return err;
+}
tools/perf/util/evlist.h +18 -0
index fe1fe40e044b..cc628798734d 100644
@@ -359,4 +359,22 @@ void perf_evlist__force_leader(struct evlist *evlist);
 struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
 						 struct evsel *evsel,
 						bool close);
+#define EVLIST_CTL_CMD_ENABLE_TAG  "enable"
+#define EVLIST_CTL_CMD_DISABLE_TAG "disable"
+#define EVLIST_CTL_CMD_ACK_TAG     "ack\n"
+
+#define EVLIST_CTL_CMD_MAX_LEN 64
+
+enum evlist_ctl_cmd {
+	EVLIST_CTL_CMD_UNSUPPORTED = 0,
+	EVLIST_CTL_CMD_ENABLE,
+	EVLIST_CTL_CMD_DISABLE,
+	EVLIST_CTL_CMD_ACK
+};
+
+int evlist__initialize_ctlfd(struct evlist *evlist, int ctl_fd, int ctl_fd_ack);
+int evlist__finalize_ctlfd(struct evlist *evlist);
+bool evlist__ctlfd_initialized(struct evlist *evlist);
+int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd);
+
 #endif /* __PERF_EVLIST_H */
Signature · 1 line
2.24.1
#9 lore raw

Re: [PATCH v12 05/15] perf evlist: implement control command handling functions

Em Fri, Jul 17, 2020 at 10:01:33AM +0300, Alexey Budankov escreveu:

Quoted 9 lines

Implement functions of initialization, finalization and processing of control command messages coming from control file descriptors. Allocate control file descriptor as descriptor at struct pollfd object of evsel_list for atomic poll() operation.

I'm applying locally for testing, but can you answer what is the reason for that newline in the CMD_ACK_TAG? I tried looking at previous discussion but couldn't quickly find any reasoning for that

- Arnaldo

tools/perf/util/evlist.h void perf_evlist__force_leader(struct evlist *evlist); · line 364

Quoted 8 lines

+++ b/tools/perf/util/evlist.h

tools/perf/util/evlist.h +3 -0
@@ -359,4 +359,22 @@ void perf_evlist__force_leader(struct evlist *evlist);
 struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
 						 struct evsel *evsel,
 						bool close);
+#define EVLIST_CTL_CMD_ENABLE_TAG  "enable"
+#define EVLIST_CTL_CMD_DISABLE_TAG "disable"
+#define EVLIST_CTL_CMD_ACK_TAG     "ack\n"

What for? That '\n'?

#10 lore raw

Re: [PATCH v12 05/15] perf evlist: implement control command handling functions

Em Wed, Jul 22, 2020 at 09:27:34AM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 17 lines

Em Fri, Jul 17, 2020 at 10:01:33AM +0300, Alexey Budankov escreveu:

Quoted 9 lines

Implement functions of initialization, finalization and processing of control command messages coming from control file descriptors. Allocate control file descriptor as descriptor at struct pollfd object of evsel_list for atomic poll() operation.

I'm applying locally for testing, but can you answer what is the reason for that newline in the CMD_ACK_TAG? I tried looking at previous discussion but couldn't quickly find any reasoning for that

- Arnaldo

Quoted 10 lines

tools/perf/util/evlist.h void perf_evlist__force_leader(struct evlist *evlist); · line 364

Quoted 8 lines

+++ b/tools/perf/util/evlist.h

tools/perf/util/evlist.h +3 -0
@@ -359,4 +359,22 @@ void perf_evlist__force_leader(struct evlist *evlist);
 struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
 						 struct evsel *evsel,
 						bool close);
+#define EVLIST_CTL_CMD_ENABLE_TAG  "enable"
+#define EVLIST_CTL_CMD_DISABLE_TAG "disable"
+#define EVLIST_CTL_CMD_ACK_TAG     "ack\n"

What for? That '\n'?

Oh, I see, this is not a _command_, it is a _response_, and the sender expects a newline, right?

So I think this needs to be marked clearly as:

// Commands accepted by 'perf record'

#define EVLIST_CTL_CMD_ENABLE_TAG "enable"
#define EVLIST_CTL_CMD_DISABLE_TAG "disable"

// Responses sent by 'perf record'

#define EVLIST_CTL_RSP_ACK "ack"

And then make the response add the newline, as conceivably we could have something like "nack", "invalid", "enoperm", etc, no?

Anyway, this can be done on top of this series, so I'm continuing processing it locally.

- Arnaldo

#11 lore raw

Re: [PATCH v12 05/15] perf evlist: implement control command handling functions

Quoted 29 lines · Arnaldo Carvalho de Melo

Em Wed, Jul 22, 2020 at 09:27:34AM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 17 lines

Em Fri, Jul 17, 2020 at 10:01:33AM +0300, Alexey Budankov escreveu:

Quoted 9 lines

Implement functions of initialization, finalization and processing of control command messages coming from control file descriptors. Allocate control file descriptor as descriptor at struct pollfd object of evsel_list for atomic poll() operation.

I'm applying locally for testing, but can you answer what is the reason for that newline in the CMD_ACK_TAG? I tried looking at previous discussion but couldn't quickly find any reasoning for that

- Arnaldo

Quoted 10 lines

tools/perf/util/evlist.h void perf_evlist__force_leader(struct evlist *evlist); · line 364

Quoted 8 lines

+++ b/tools/perf/util/evlist.h

tools/perf/util/evlist.h +3 -0
@@ -359,4 +359,22 @@ void perf_evlist__force_leader(struct evlist *evlist);
 struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
 						 struct evsel *evsel,
 						bool close);
+#define EVLIST_CTL_CMD_ENABLE_TAG  "enable"
+#define EVLIST_CTL_CMD_DISABLE_TAG "disable"
+#define EVLIST_CTL_CMD_ACK_TAG     "ack\n"

What for? That '\n'?

Quoted 2 lines

Oh, I see, this is not a _command_, it is a _response_, and the sender expects a newline, right?

Right. Shell commands can expect strings terminated by \n, e.g. 'read -u'. See sample bash script in 00/15 for example.

Quoted 9 lines

So I think this needs to be marked clearly as:

// Commands accepted by 'perf record'

#define EVLIST_CTL_CMD_ENABLE_TAG "enable"
#define EVLIST_CTL_CMD_DISABLE_TAG "disable"

Quoted 6 lines

// Responses sent by 'perf record'

#define EVLIST_CTL_RSP_ACK "ack"

And then make the response add the newline, as conceivably we could have something like "nack", "invalid", "enoperm", etc, no?

That above makes sense.

Quoted 6 lines

Anyway, this can be done on top of this series, so I'm continuing processing it locally.

- Arnaldo

Alexei

#12 lore raw

Re: [PATCH v12 05/15] perf evlist: implement control command handling functions

In reply to Alexey Budankov

Em Fri, Jul 17, 2020 at 10:01:33AM +0300, Alexey Budankov escreveu:

Quoted 81 lines

Implement functions of initialization, finalization and processing of control command messages coming from control file descriptors. Allocate control file descriptor as descriptor at struct pollfd object of evsel_list for atomic poll() operation.

---
 tools/perf/util/evlist.c | 140 +++++++++++++++++++++++++++++++++++++++
 tools/perf/util/evlist.h |  18 +++++
 2 files changed, 158 insertions(+)
tools/perf/util/evlist.c +59 -0
index 36eb50aba1f5..fe900d82815c 100644
@@ -1714,3 +1714,143 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
 	}
 	return leader;
 }
+
+int evlist__initialize_ctlfd(struct evlist *evlist, int fd, int ack)
+{
+	if (fd == -1) {
+		pr_debug("Control descriptor is not initialized\n");
+		return 0;
+	}
+
+	evlist->ctl_fd.pos = perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN,
+						     fdarray_flag__nonfilterable);
+	if (evlist->ctl_fd.pos < 0) {
+		evlist->ctl_fd.pos = -1;
+		pr_err("Failed to add ctl fd entry: %m\n");
+		return -1;
+	}
+
+	evlist->ctl_fd.fd = fd;
+	evlist->ctl_fd.ack = ack;
+
+	return 0;
+}
+
+bool evlist__ctlfd_initialized(struct evlist *evlist)
+{
+	return evlist->ctl_fd.pos >= 0;
+}
+
+int evlist__finalize_ctlfd(struct evlist *evlist)
+{
+	struct pollfd *entries = evlist->core.pollfd.entries;
+
+	if (!evlist__ctlfd_initialized(evlist))
+		return 0;
+
+	entries[evlist->ctl_fd.pos].fd = -1;
+	entries[evlist->ctl_fd.pos].events = 0;
+	entries[evlist->ctl_fd.pos].revents = 0;
+
+	evlist->ctl_fd.pos = -1;
+	evlist->ctl_fd.ack = -1;
+	evlist->ctl_fd.fd = -1;
+
+	return 0;
+}
+
+static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd,
+			      char *cmd_data, size_t data_size)
+{
+	int err;
+	char c;
+	size_t bytes_read = 0;
+
+	memset(cmd_data, 0, data_size);
+	data_size--;
+
+	do {
+		err = read(evlist->ctl_fd.fd, &c, 1);
+		if (err > 0) {
+			if (c == '\n' || c == '\0')

tools/perf/util/evlist.c struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, · line 1785

Quoted 10 lines
tools/perf/util/evlist.c +10 -0
+				break;
+			cmd_data[bytes_read++] = c;
+			if (bytes_read == data_size)
+				break;
+		} else {
+			if (err == -1)
+				pr_err("Failed to read from ctlfd %d: %m\n", evlist->ctl_fd.fd);
+			break;
+		}
+	} while (1);

Ok, here you don't know how many bytes you have to read, the protocol is a string ending in \n or \0, so you can't use 'readn()', but see below for the write() case.

Also is this ctf_fd in non-blocking mode? Can't this get stuck waiting forever?

Quoted 17 lines
tools/perf/util/evlist.c +17 -0
+	pr_debug("Message from ctl_fd: \"%s%s\"\n", cmd_data,
+		 bytes_read == data_size ? "" : c == '\n' ? "\\n" : "\\0");
+
+	if (err > 0) {
+		if (!strncmp(cmd_data, EVLIST_CTL_CMD_ENABLE_TAG,
+			     (sizeof(EVLIST_CTL_CMD_ENABLE_TAG)-1))) {
+			*cmd = EVLIST_CTL_CMD_ENABLE;
+		} else if (!strncmp(cmd_data, EVLIST_CTL_CMD_DISABLE_TAG,
+				    (sizeof(EVLIST_CTL_CMD_DISABLE_TAG)-1))) {
+			*cmd = EVLIST_CTL_CMD_DISABLE;
+		}
+	}
+
+	return err;
+}
+
+static int evlist__ctlfd_ack(struct evlist *evlist)

tools/perf/util/evlist.c struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, · line 1813

Quoted 10 lines
tools/perf/util/evlist.c +10 -0
+{
+	int err;
+
+	if (evlist->ctl_fd.ack == -1)
+		return 0;
+
+	err = write(evlist->ctl_fd.ack, EVLIST_CTL_CMD_ACK_TAG,
+		    sizeof(EVLIST_CTL_CMD_ACK_TAG));
+	if (err == -1)
+		pr_err("failed to write to ctl_ack_fd %d: %m\n", evlist->ctl_fd.ack);

Also the function to use here is 'writen()':

/*
* Write exactly 'n' bytes or return an error.
*/
ssize_t writen(int fd, const void *buf, size_t n)

{
        /* ion does not modify buf. */
        return ion(false, fd, (void *)buf, n);
}

"tools/lib/perf/lib.c"

-----------------------------

I.e. libperf's fd based fwrite().

Again, this can be done on top of this patch set, so I'll continue as-is.

- Arnaldo

#13 lore raw

PATCH v12 6/15 perf stat: factor out body of event handling loop for system wide

In reply to Alexey Budankov

Introduce handle_interval() function that factors out body of event handling loop for attach and system wide monitoring use cases.

---
 tools/perf/builtin-stat.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)
tools/perf/builtin-stat.c +11 -6
index 922d9961ba98..80aea49e4dac 100644
@@ -475,6 +475,16 @@ static void process_interval(void)
 	print_counters(&rs, 0, NULL);
 }
 
+static bool handle_interval(unsigned int interval, int *times)
+{
+	if (interval) {
+		process_interval();
+		if (interval_count && !(--(*times)))
+			return true;
+	}
+	return false;
+}
+
 static void enable_counters(void)
 {
 	if (stat_config.initial_delay)
@@ -809,13 +819,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			nanosleep(&ts, NULL);
 			if (!is_target_alive(&target, evsel_list->core.threads))
 				break;
-			if (timeout)
+			if (timeout || handle_interval(interval, &times))
 				break;
-			if (interval) {
-				process_interval();
-				if (interval_count && !(--times))
-					break;
-			}
 		}
 	}
 
Signature · 1 line
2.24.1
#14 lore raw

PATCH v12 7/15 perf stat: move target check to loop control statement

In reply to Alexey Budankov

Check for target existence in loop control statement jointly external asynchronous 'done' signal.

---
 tools/perf/builtin-stat.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
tools/perf/builtin-stat.c +1 -3
index 80aea49e4dac..87eebf3f55ae 100644
@@ -815,10 +815,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
 		enable_counters();
-		while (!done) {
+		while (!done && is_target_alive(&target, evsel_list->core.threads)) {
 			nanosleep(&ts, NULL);
-			if (!is_target_alive(&target, evsel_list->core.threads))
-				break;
 			if (timeout || handle_interval(interval, &times))
 				break;
 		}
Signature · 1 line
2.24.1
#15 lore raw

PATCH v12 8/15 perf stat: factor out body of event handling loop for fork case

In reply to Alexey Budankov

Factor out body of event handling loop for fork case reusing handle_interval() function.

---
 tools/perf/builtin-stat.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)
tools/perf/builtin-stat.c +1 -4
index 87eebf3f55ae..91f31518948e 100644
@@ -792,10 +792,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		if (interval || timeout) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
 				nanosleep(&ts, NULL);
-				if (timeout)
-					break;
-				process_interval();
-				if (interval_count && !(--times))
+				if (timeout || handle_interval(interval, &times))
 					break;
 			}
 		}
Signature · 1 line
2.24.1
#16 lore raw

PATCH v12 9/15 perf stat: factor out event handling loop into dispatch_events()

In reply to Alexey Budankov

Consolidate event dispatching loops for fork, attach and system wide monitoring use cases into common dispatch_events() function.

---
 tools/perf/builtin-stat.c | 36 ++++++++++++++++++++++++------------
 1 file changed, 24 insertions(+), 12 deletions(-)
tools/perf/builtin-stat.c +24 -12
index 91f31518948e..a5a0f4841003 100644
@@ -550,6 +550,27 @@ static bool is_target_alive(struct target *_target,
 	return false;
 }
 
+static int dispatch_events(bool forks, int timeout, int interval, int *times, struct timespec *ts)
+{
+	int child_exited = 0, status = 0;
+
+	while (!done) {
+		if (forks)
+			child_exited = waitpid(child_pid, &status, WNOHANG);
+		else
+			child_exited = !is_target_alive(&target, evsel_list->core.threads) ? 1 : 0;
+
+		if (child_exited)
+			break;
+
+		nanosleep(ts, NULL);
+		if (timeout || handle_interval(interval, times))
+			break;
+	}
+
+	return status;
+}
+
 enum counter_recovery {
 	COUNTER_SKIP,
 	COUNTER_RETRY,
@@ -789,13 +810,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		perf_evlist__start_workload(evsel_list);
 		enable_counters();
 
-		if (interval || timeout) {
-			while (!waitpid(child_pid, &status, WNOHANG)) {
-				nanosleep(&ts, NULL);
-				if (timeout || handle_interval(interval, &times))
-					break;
-			}
-		}
+		if (interval || timeout)
+			status = dispatch_events(forks, timeout, interval, &times, &ts);
 		if (child_pid != -1) {
 			if (timeout)
 				kill(child_pid, SIGTERM);
@@ -812,11 +828,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
 		enable_counters();
-		while (!done && is_target_alive(&target, evsel_list->core.threads)) {
-			nanosleep(&ts, NULL);
-			if (timeout || handle_interval(interval, &times))
-				break;
-		}
+		status = dispatch_events(forks, timeout, interval, &times, &ts);
 	}
 
 	disable_counters();
Signature · 1 line
2.24.1
#17 lore raw

PATCH v12 10/15 perf stat: extend -D,--delay option with -1 value

In reply to Alexey Budankov

Extend -D,--delay option with -1 value to start monitoring with events disabled to be enabled later by enable command provided via control file descriptor.

---
 tools/perf/Documentation/perf-stat.txt |  5 +++--
 tools/perf/builtin-stat.c              | 18 ++++++++++++++----
 tools/perf/util/evlist.h               |  3 +++
 tools/perf/util/stat.h                 |  2 +-
 4 files changed, 21 insertions(+), 7 deletions(-)
tools/perf/Documentation/perf-stat.txt +3 -2
index b029ee728a0b..9f32f6cd558d 100644
@@ -238,8 +238,9 @@ mode, use --per-node in addition to -a. (system-wide).
 
 -D msecs::
 --delay msecs::
-After starting the program, wait msecs before measuring. This is useful to
-filter out the startup phase of the program, which is often very different.
+After starting the program, wait msecs before measuring (-1: start with events
+disabled). This is useful to filter out the startup phase of the program,
+which is often very different.
 
 -T::
 --transaction::
tools/perf/builtin-stat.c +14 -4
index a5a0f4841003..9d5c503e698f 100644
@@ -487,16 +487,26 @@ static bool handle_interval(unsigned int interval, int *times)
 
 static void enable_counters(void)
 {
-	if (stat_config.initial_delay)
+	if (stat_config.initial_delay < 0) {
+		pr_info(EVLIST_DISABLED_MSG);
+		return;
+	}
+
+	if (stat_config.initial_delay > 0) {
+		pr_info(EVLIST_DISABLED_MSG);
 		usleep(stat_config.initial_delay * USEC_PER_MSEC);
+	}
 
 	/*
 	 * We need to enable counters only if:
 	 * - we don't have tracee (attaching to task or cpu)
 	 * - we have initial delay configured
 	 */
-	if (!target__none(&target) || stat_config.initial_delay)
+	if (!target__none(&target) || stat_config.initial_delay) {
 		evlist__enable(evsel_list);
+		if (stat_config.initial_delay > 0)
+			pr_info(EVLIST_ENABLED_MSG);
+	}
 }
 
 static void disable_counters(void)
@@ -1053,8 +1063,8 @@ static struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_SET_UINT(0, "per-node", &stat_config.aggr_mode,
 		     "aggregate counts per numa node", AGGR_NODE),
-	OPT_UINTEGER('D', "delay", &stat_config.initial_delay,
-		     "ms to wait before starting measurement after program start"),
+	OPT_INTEGER('D', "delay", &stat_config.initial_delay,
+		    "ms to wait before starting measurement after program start (-1: start with events disabled)"),
 	OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL,
 			"Only print computed metrics. No raw values", enable_metric_only),
 	OPT_BOOLEAN(0, "metric-no-group", &stat_config.metric_no_group,
tools/perf/util/evlist.h +3 -0
index cc628798734d..8ee12c1f0526 100644
@@ -377,4 +377,7 @@ int evlist__finalize_ctlfd(struct evlist *evlist);
 bool evlist__ctlfd_initialized(struct evlist *evlist);
 int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd);
 
+#define EVLIST_ENABLED_MSG "Events enabled\n"
+#define EVLIST_DISABLED_MSG "Events disabled\n"
+
 #endif /* __PERF_EVLIST_H */
tools/perf/util/stat.h +1 -1
index 6911c7249199..41d59f192931 100644
@@ -116,7 +116,7 @@ struct perf_stat_config {
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-	unsigned int		 initial_delay;
+	int			 initial_delay;
 	unsigned int		 unit_width;
 	unsigned int		 metric_only_len;
 	int			 times;
Signature · 1 line
2.24.1
#18 lore raw

PATCH v12 11/15 perf stat: implement control commands handling

In reply to Alexey Budankov

Implement handling of 'enable' and 'disable' control commands coming from control file descriptor. If poll event splits initiated timeout interval then the reminder is calculated and still waited in the following evlist__poll() call.

---
 tools/perf/builtin-stat.c | 83 ++++++++++++++++++++++++++++++---------
 1 file changed, 65 insertions(+), 18 deletions(-)
tools/perf/builtin-stat.c +65 -18
index 9d5c503e698f..5280a45af5dc 100644
@@ -560,9 +560,61 @@ static bool is_target_alive(struct target *_target,
 	return false;
 }
 
-static int dispatch_events(bool forks, int timeout, int interval, int *times, struct timespec *ts)
+static void process_evlist(struct evlist *evlist, unsigned int interval)
+{
+	enum evlist_ctl_cmd cmd = EVLIST_CTL_CMD_UNSUPPORTED;
+
+	if (evlist__ctlfd_process(evlist, &cmd) > 0) {
+		switch (cmd) {
+		case EVLIST_CTL_CMD_ENABLE:
+			pr_info(EVLIST_ENABLED_MSG);
+			if (interval)
+				process_interval();
+			break;
+		case EVLIST_CTL_CMD_DISABLE:
+			if (interval)
+				process_interval();
+			pr_info(EVLIST_DISABLED_MSG);
+			break;
+		case EVLIST_CTL_CMD_ACK:
+		case EVLIST_CTL_CMD_UNSUPPORTED:
+		default:
+			break;
+		}
+	}
+}
+
+static void compute_tts(struct timespec *time_start, struct timespec *time_stop,
+			int *time_to_sleep)
+{
+	int tts = *time_to_sleep;
+	struct timespec time_diff;
+
+	diff_timespec(&time_diff, time_stop, time_start);
+
+	tts -= time_diff.tv_sec * MSEC_PER_SEC +
+	       time_diff.tv_nsec / NSEC_PER_MSEC;
+
+	if (tts < 0)
+		tts = 0;
+
+	*time_to_sleep = tts;
+}
+
+static int dispatch_events(bool forks, int timeout, int interval, int *times)
 {
 	int child_exited = 0, status = 0;
+	int time_to_sleep, sleep_time;
+	struct timespec time_start, time_stop;
+
+	if (interval)
+		sleep_time = interval;
+	else if (timeout)
+		sleep_time = timeout;
+	else
+		sleep_time = 1000;
+
+	time_to_sleep = sleep_time;
 
 	while (!done) {
 		if (forks)
@@ -573,9 +625,16 @@ static int dispatch_events(bool forks, int timeout, int interval, int *times, st
 		if (child_exited)
 			break;
 
-		nanosleep(ts, NULL);
-		if (timeout || handle_interval(interval, times))
-			break;
+		clock_gettime(CLOCK_MONOTONIC, &time_start);
+		if (!(evlist__poll(evsel_list, time_to_sleep) > 0)) { /* poll timeout or EINTR */
+			if (timeout || handle_interval(interval, times))
+				break;
+			time_to_sleep = sleep_time;
+		} else { /* fd revent */
+			process_evlist(evsel_list, interval);
+			clock_gettime(CLOCK_MONOTONIC, &time_stop);
+			compute_tts(&time_start, &time_stop, &time_to_sleep);
+		}
 	}
 
 	return status;
@@ -644,7 +703,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	char msg[BUFSIZ];
 	unsigned long long t0, t1;
 	struct evsel *counter;
-	struct timespec ts;
 	size_t l;
 	int status = 0;
 	const bool forks = (argc > 0);
@@ -653,17 +711,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	int i, cpu;
 	bool second_pass = false;
 
-	if (interval) {
-		ts.tv_sec  = interval / USEC_PER_MSEC;
-		ts.tv_nsec = (interval % USEC_PER_MSEC) * NSEC_PER_MSEC;
-	} else if (timeout) {
-		ts.tv_sec  = timeout / USEC_PER_MSEC;
-		ts.tv_nsec = (timeout % USEC_PER_MSEC) * NSEC_PER_MSEC;
-	} else {
-		ts.tv_sec  = 1;
-		ts.tv_nsec = 0;
-	}
-
 	if (forks) {
 		if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,
 						  workload_exec_failed_signal) < 0) {
@@ -821,7 +868,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		enable_counters();
 
 		if (interval || timeout)
-			status = dispatch_events(forks, timeout, interval, &times, &ts);
+			status = dispatch_events(forks, timeout, interval, &times);
 		if (child_pid != -1) {
 			if (timeout)
 				kill(child_pid, SIGTERM);
@@ -838,7 +885,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
 		enable_counters();
-		status = dispatch_events(forks, timeout, interval, &times, &ts);
+		status = dispatch_events(forks, timeout, interval, &times);
 	}
 
 	disable_counters();
Signature · 1 line
2.24.1
#19 lore raw

Re: [PATCH v12 11/15] perf stat: implement control commands handling

Em Fri, Jul 17, 2020 at 10:05:06AM +0300, Alexey Budankov escreveu:

Quoted 5 lines

Implement handling of 'enable' and 'disable' control commands coming from control file descriptor. If poll event splits initiated timeout interval then the reminder is calculated and still waited in the following evlist__poll() call.

So the cover letter is not preserved in the git history, only going from the Link tag to the patch series to then lookup the cover letter and then find examples of each feature, I'll now have to do that and collect the parts that are needed to test this specific feature implemented in this specific patch, add the command here so that we can test patch by patch, please next time try to have the testing steps in each patch.

This way we avoid introducing bisection regressions, as having the set of instructions only on the cover letter encourages testing only the whole patchkit, not patch by patch.

Thanks,

- Arnaldo

Quoted 142 lines
---
 tools/perf/builtin-stat.c | 83 ++++++++++++++++++++++++++++++---------
 1 file changed, 65 insertions(+), 18 deletions(-)
tools/perf/builtin-stat.c +65 -18
index 9d5c503e698f..5280a45af5dc 100644
@@ -560,9 +560,61 @@ static bool is_target_alive(struct target *_target,
 	return false;
 }
 
-static int dispatch_events(bool forks, int timeout, int interval, int *times, struct timespec *ts)
+static void process_evlist(struct evlist *evlist, unsigned int interval)
+{
+	enum evlist_ctl_cmd cmd = EVLIST_CTL_CMD_UNSUPPORTED;
+
+	if (evlist__ctlfd_process(evlist, &cmd) > 0) {
+		switch (cmd) {
+		case EVLIST_CTL_CMD_ENABLE:
+			pr_info(EVLIST_ENABLED_MSG);
+			if (interval)
+				process_interval();
+			break;
+		case EVLIST_CTL_CMD_DISABLE:
+			if (interval)
+				process_interval();
+			pr_info(EVLIST_DISABLED_MSG);
+			break;
+		case EVLIST_CTL_CMD_ACK:
+		case EVLIST_CTL_CMD_UNSUPPORTED:
+		default:
+			break;
+		}
+	}
+}
+
+static void compute_tts(struct timespec *time_start, struct timespec *time_stop,
+			int *time_to_sleep)
+{
+	int tts = *time_to_sleep;
+	struct timespec time_diff;
+
+	diff_timespec(&time_diff, time_stop, time_start);
+
+	tts -= time_diff.tv_sec * MSEC_PER_SEC +
+	       time_diff.tv_nsec / NSEC_PER_MSEC;
+
+	if (tts < 0)
+		tts = 0;
+
+	*time_to_sleep = tts;
+}
+
+static int dispatch_events(bool forks, int timeout, int interval, int *times)
 {
 	int child_exited = 0, status = 0;
+	int time_to_sleep, sleep_time;
+	struct timespec time_start, time_stop;
+
+	if (interval)
+		sleep_time = interval;
+	else if (timeout)
+		sleep_time = timeout;
+	else
+		sleep_time = 1000;
+
+	time_to_sleep = sleep_time;
 
 	while (!done) {
 		if (forks)
@@ -573,9 +625,16 @@ static int dispatch_events(bool forks, int timeout, int interval, int *times, st
 		if (child_exited)
 			break;
 
-		nanosleep(ts, NULL);
-		if (timeout || handle_interval(interval, times))
-			break;
+		clock_gettime(CLOCK_MONOTONIC, &time_start);
+		if (!(evlist__poll(evsel_list, time_to_sleep) > 0)) { /* poll timeout or EINTR */
+			if (timeout || handle_interval(interval, times))
+				break;
+			time_to_sleep = sleep_time;
+		} else { /* fd revent */
+			process_evlist(evsel_list, interval);
+			clock_gettime(CLOCK_MONOTONIC, &time_stop);
+			compute_tts(&time_start, &time_stop, &time_to_sleep);
+		}
 	}
 
 	return status;
@@ -644,7 +703,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	char msg[BUFSIZ];
 	unsigned long long t0, t1;
 	struct evsel *counter;
-	struct timespec ts;
 	size_t l;
 	int status = 0;
 	const bool forks = (argc > 0);
@@ -653,17 +711,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	int i, cpu;
 	bool second_pass = false;
 
-	if (interval) {
-		ts.tv_sec  = interval / USEC_PER_MSEC;
-		ts.tv_nsec = (interval % USEC_PER_MSEC) * NSEC_PER_MSEC;
-	} else if (timeout) {
-		ts.tv_sec  = timeout / USEC_PER_MSEC;
-		ts.tv_nsec = (timeout % USEC_PER_MSEC) * NSEC_PER_MSEC;
-	} else {
-		ts.tv_sec  = 1;
-		ts.tv_nsec = 0;
-	}
-
 	if (forks) {
 		if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,
 						  workload_exec_failed_signal) < 0) {
@@ -821,7 +868,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		enable_counters();
 
 		if (interval || timeout)
-			status = dispatch_events(forks, timeout, interval, &times, &ts);
+			status = dispatch_events(forks, timeout, interval, &times);
 		if (child_pid != -1) {
 			if (timeout)
 				kill(child_pid, SIGTERM);
@@ -838,7 +885,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
 		enable_counters();
-		status = dispatch_events(forks, timeout, interval, &times, &ts);
+		status = dispatch_events(forks, timeout, interval, &times);
 	}
 
 	disable_counters();
Signature · 1 line
2.24.1
Signature · 1 line
- Arnaldo
#20 lore raw

Re: [PATCH v12 11/15] perf stat: implement control commands handling

Quoted 7 lines · Arnaldo Carvalho de Melo

Em Fri, Jul 17, 2020 at 10:05:06AM +0300, Alexey Budankov escreveu:

Quoted 5 lines

Implement handling of 'enable' and 'disable' control commands coming from control file descriptor. If poll event splits initiated timeout interval then the reminder is calculated and still waited in the following evlist__poll() call.

Quoted 6 lines

So the cover letter is not preserved in the git history, only going from the Link tag to the patch series to then lookup the cover letter and then find examples of each feature, I'll now have to do that and collect the parts that are needed to test this specific feature implemented in this specific patch, add the command here so that we can test patch by patch, please next time try to have the testing steps in each patch.

Accepted. Will be providing possible test steps as a part of description for relevant patches.

Thanks,
Alexei

#21 lore raw

PATCH v12 12/15 perf stat: introduce --control fd:ctl-fd[,ack-fd] options

In reply to Alexey Budankov

Introduce --control fd:ctl-fd[,ack-fd] options to pass open file descriptors numbers from command line. Extend perf-stat.txt file with --control fd:ctl-fd[,ack-fd] options description. Document possible usage model introduced by --control fd:ctl-fd[,ack-fd] options by providing example bash shell script.

---
 tools/perf/Documentation/perf-stat.txt | 39 +++++++++++++++++++++++++
 tools/perf/builtin-stat.c              | 40 +++++++++++++++++++++++++-
 tools/perf/util/stat.h                 |  2 ++
 3 files changed, 80 insertions(+), 1 deletion(-)
tools/perf/Documentation/perf-stat.txt +39 -0
index 9f32f6cd558d..c9bfefc051fb 100644
@@ -176,6 +176,45 @@ with it.  --append may be used here.  Examples:
      3>results  perf stat --log-fd 3          -- $cmd
      3>>results perf stat --log-fd 3 --append -- $cmd
 
+--control fd:ctl-fd[,ack-fd]
+Listen on ctl-fd descriptor for command to control measurement ('enable': enable events,
+'disable': disable events). Measurements can be started with events disabled using
+--delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor
+to synchronize with the controlling process. Example of bash shell script to enable and
+disable events during measurements:
+
+#!/bin/bash
+
+ctl_dir=/tmp/
+
+ctl_fifo=${ctl_dir}perf_ctl.fifo
+test -p ${ctl_fifo} && unlink ${ctl_fifo}
+mkfifo ${ctl_fifo}
+exec {ctl_fd}<>${ctl_fifo}
+
+ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo
+test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo}
+mkfifo ${ctl_ack_fifo}
+exec {ctl_fd_ack}<>${ctl_ack_fifo}
+
+perf stat -D -1 -e cpu-cycles -a -I 1000       \
+          --control fd:${ctl_fd},${ctl_fd_ack} \
+          -- sleep 30 &
+perf_pid=$!
+
+sleep 5  && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})"
+sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})"
+
+exec {ctl_fd_ack}>&-
+unlink ${ctl_ack_fifo}
+
+exec {ctl_fd}>&-
+unlink ${ctl_fifo}
+
+wait -n ${perf_pid}
+exit $?
+
+
 --pre::
 --post::
 	Pre and post measurement hooks, e.g.:
tools/perf/builtin-stat.c +39 -1
index 5280a45af5dc..483a28ef4ec4 100644
@@ -188,6 +188,8 @@ static struct perf_stat_config stat_config = {
 	.metric_only_len	= METRIC_ONLY_LEN,
 	.walltime_nsecs_stats	= &walltime_nsecs_stats,
 	.big_num		= true,
+	.ctl_fd			= -1,
+	.ctl_fd_ack		= -1
 };
 
 static bool cpus_map_matched(struct evsel *a, struct evsel *b)
@@ -867,7 +869,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		perf_evlist__start_workload(evsel_list);
 		enable_counters();
 
-		if (interval || timeout)
+		if (interval || timeout || evlist__ctlfd_initialized(evsel_list))
 			status = dispatch_events(forks, timeout, interval, &times);
 		if (child_pid != -1) {
 			if (timeout)
@@ -1039,6 +1041,33 @@ static int parse_metric_groups(const struct option *opt,
 					 &stat_config.metric_events);
 }
 
+static int parse_control_option(const struct option *opt,
+				const char *str,
+				int unset __maybe_unused)
+{
+	char *comma = NULL, *endptr = NULL;
+	struct perf_stat_config *config = (struct perf_stat_config *)opt->value;
+
+	if (strncmp(str, "fd:", 3))
+		return -EINVAL;
+
+	config->ctl_fd = strtoul(&str[3], &endptr, 0);
+	if (endptr == &str[3])
+		return -EINVAL;
+
+	comma = strchr(str, ',');
+	if (comma) {
+		if (endptr != comma)
+			return -EINVAL;
+
+		config->ctl_fd_ack = strtoul(comma + 1, &endptr, 0);
+		if (endptr == comma + 1 || *endptr != '\0')
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct option stat_options[] = {
 	OPT_BOOLEAN('T', "transaction", &transaction_run,
 		    "hardware transaction statistics"),
@@ -1140,6 +1169,10 @@ static struct option stat_options[] = {
 		"libpfm4 event selector. use 'perf list' to list available events",
 		parse_libpfm_events_option),
 #endif
+	OPT_CALLBACK(0, "control", &stat_config, "fd:ctl-fd[,ack-fd]",
+		     "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).\n"
+		     "\t\t\t  Optionally send control command completion ('ack\\n') to ack-fd descriptor.",
+		      parse_control_option),
 	OPT_END()
 };
 
@@ -2309,6 +2342,9 @@ int cmd_stat(int argc, const char **argv)
 	signal(SIGALRM, skip_signal);
 	signal(SIGABRT, skip_signal);
 
+	if (evlist__initialize_ctlfd(evsel_list, stat_config.ctl_fd, stat_config.ctl_fd_ack))
+		goto out;
+
 	status = 0;
 	for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) {
 		if (stat_config.run_count != 1 && verbose > 0)
@@ -2328,6 +2364,8 @@ int cmd_stat(int argc, const char **argv)
 	if (!forever && status != -1 && (!interval || stat_config.summary))
 		print_counters(NULL, argc, argv);
 
+	evlist__finalize_ctlfd(evsel_list);
+
 	if (STAT_RECORD) {
 		/*
 		 * We synthesize the kernel mmap record just so that older tools
tools/perf/util/stat.h +2 -0
index 41d59f192931..f8778cffd941 100644
@@ -133,6 +133,8 @@ struct perf_stat_config {
 	struct perf_cpu_map		*cpus_aggr_map;
 	u64			*walltime_run;
 	struct rblist		 metric_events;
+	int			 ctl_fd;
+	int			 ctl_fd_ack;
 };
 
 void perf_stat__set_big_num(int set);
Signature · 1 line
2.24.1
#22 lore raw

PATCH v12 13/15 perf record: extend -D,--delay option with -1 value

In reply to Alexey Budankov

Extend -D,--delay option with -1 to start collection with events disabled to be enabled later by 'enable' command provided via control file descriptor.

---
 tools/perf/Documentation/perf-record.txt |  5 +++--
 tools/perf/builtin-record.c              | 12 ++++++++----
 tools/perf/builtin-trace.c               |  2 +-
 tools/perf/util/record.h                 |  2 +-
 4 files changed, 13 insertions(+), 8 deletions(-)
tools/perf/Documentation/perf-record.txt +3 -2
index fa8a5fcd27ab..a84376605805 100644
@@ -407,8 +407,9 @@ if combined with -a or -C options.
 
 -D::
 --delay=::
-After starting the program, wait msecs before measuring. This is useful to
-filter out the startup phase of the program, which is often very different.
+After starting the program, wait msecs before measuring (-1: start with events
+disabled). This is useful to filter out the startup phase of the program, which
+is often very different.
 
 -I::
 --intr-regs::
tools/perf/builtin-record.c +8 -4
index 19b1d5effb7a..cd1892c4844b 100644
@@ -1749,8 +1749,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	if (opts->initial_delay) {
-		usleep(opts->initial_delay * USEC_PER_MSEC);
-		evlist__enable(rec->evlist);
+		pr_info(EVLIST_DISABLED_MSG);
+		if (opts->initial_delay > 0) {
+			usleep(opts->initial_delay * USEC_PER_MSEC);
+			evlist__enable(rec->evlist);
+			pr_info(EVLIST_ENABLED_MSG);
+		}
 	}
 
 	trigger_ready(&auxtrace_snapshot_trigger);
@@ -2462,8 +2466,8 @@ static struct option __record_options[] = {
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
-	OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
-		  "ms to wait before starting measurement after program start"),
+	OPT_INTEGER('D', "delay", &record.opts.initial_delay,
+		  "ms to wait before starting measurement after program start (-1: start with events disabled)"),
 	OPT_BOOLEAN(0, "kcore", &record.opts.kcore, "copy /proc/kcore"),
 	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
 		   "user to profile"),
tools/perf/builtin-trace.c +1 -1
index a333a9a64f27..bea461b6f937 100644
@@ -4812,7 +4812,7 @@ int cmd_trace(int argc, const char **argv)
 			"per thread proc mmap processing timeout in ms"),
 	OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only",
 		     trace__parse_cgroups),
-	OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
+	OPT_INTEGER('D', "delay", &trace.opts.initial_delay,
 		     "ms to wait before starting measurement after program "
 		     "start"),
 	OPTS_EVSWITCH(&trace.evswitch),
tools/perf/util/record.h +1 -1
index 39d1de4b2a36..da138dcb4d34 100644
@@ -61,7 +61,7 @@ struct record_opts {
 	const char    *auxtrace_snapshot_opts;
 	const char    *auxtrace_sample_opts;
 	bool	      sample_transaction;
-	unsigned      initial_delay;
+	int	      initial_delay;
 	bool	      use_clockid;
 	clockid_t     clockid;
 	u64	      clockid_res_ns;
Signature · 1 line
2.24.1
#23 lore raw

PATCH v12 14/15 perf record: implement control commands handling

In reply to Alexey Budankov

Implement handling of 'enable' and 'disable' control commands coming from control file descriptor.

---
 tools/perf/builtin-record.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
tools/perf/builtin-record.c +16 -0
index cd1892c4844b..632e61fe70bd 100644
@@ -1527,6 +1527,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	bool disabled = false, draining = false;
 	int fd;
 	float ratio = 0;
+	enum evlist_ctl_cmd cmd = EVLIST_CTL_CMD_UNSUPPORTED;
 
 	atexit(record__sig_exit);
 	signal(SIGCHLD, sig_handler);
@@ -1846,6 +1847,21 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 				draining = true;
 		}
 
+		if (evlist__ctlfd_process(rec->evlist, &cmd) > 0) {
+			switch (cmd) {
+			case EVLIST_CTL_CMD_ENABLE:
+				pr_info(EVLIST_ENABLED_MSG);
+				break;
+			case EVLIST_CTL_CMD_DISABLE:
+				pr_info(EVLIST_DISABLED_MSG);
+				break;
+			case EVLIST_CTL_CMD_ACK:
+			case EVLIST_CTL_CMD_UNSUPPORTED:
+			default:
+				break;
+			}
+		}
+
 		/*
 		 * When perf is starting the traced process, at the end events
 		 * die with the process and we wait for that. Thus no need to
Signature · 1 line
2.24.1
#24 lore raw

PATCH v12 15/15 perf record: introduce --control fd:ctl-fd[,ack-fd] options

In reply to Alexey Budankov

Introduce --control fd:ctl-fd[,ack-fd] options to pass open file descriptors numbers from command line. Extend perf-record.txt file with --control fd:ctl-fd[,ack-fd] options description. Document possible usage model introduced by --control fd:ctl-fd[,ack-fd] options by providing example bash shell script.

---
 tools/perf/Documentation/perf-record.txt | 39 ++++++++++++++++++++++++
 tools/perf/builtin-record.c              | 37 ++++++++++++++++++++++
 tools/perf/util/record.h                 |  2 ++
 3 files changed, 78 insertions(+)
tools/perf/Documentation/perf-record.txt +39 -0
index a84376605805..3f72d8e261f3 100644
@@ -627,6 +627,45 @@ option. The -e option and this one can be mixed and matched.  Events
 can be grouped using the {} notation.
 endif::HAVE_LIBPFM[]
 
+--control fd:ctl-fd[,ack-fd]
+Listen on ctl-fd descriptor for command to control measurement ('enable': enable events,
+'disable': disable events). Measurements can be started with events disabled using
+--delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor
+to synchronize with the controlling process. Example of bash shell script to enable and
+disable events during measurements:
+
+#!/bin/bash
+
+ctl_dir=/tmp/
+
+ctl_fifo=${ctl_dir}perf_ctl.fifo
+test -p ${ctl_fifo} && unlink ${ctl_fifo}
+mkfifo ${ctl_fifo}
+exec {ctl_fd}<>${ctl_fifo}
+
+ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo
+test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo}
+mkfifo ${ctl_ack_fifo}
+exec {ctl_fd_ack}<>${ctl_ack_fifo}
+
+perf record -D -1 -e cpu-cycles -a               \
+            --control fd:${ctl_fd},${ctl_fd_ack} \
+            -- sleep 30 &
+perf_pid=$!
+
+sleep 5  && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})"
+sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})"
+
+exec {ctl_fd_ack}>&-
+unlink ${ctl_ack_fifo}
+
+exec {ctl_fd}>&-
+unlink ${ctl_fifo}
+
+wait -n ${perf_pid}
+exit $?
+
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
tools/perf/builtin-record.c +37 -0
index 632e61fe70bd..0718aa71b4ba 100644
@@ -1749,6 +1749,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		perf_evlist__start_workload(rec->evlist);
 	}
 
+	if (evlist__initialize_ctlfd(rec->evlist, opts->ctl_fd, opts->ctl_fd_ack))
+		goto out_child;
+
 	if (opts->initial_delay) {
 		pr_info(EVLIST_DISABLED_MSG);
 		if (opts->initial_delay > 0) {
@@ -1895,6 +1898,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		record__synthesize_workload(rec, true);
 
 out_child:
+	evlist__finalize_ctlfd(rec->evlist);
 	record__mmap_read_all(rec, true);
 	record__aio_mmap_read_sync(rec);
 
@@ -2244,6 +2248,33 @@ static int record__parse_mmap_pages(const struct option *opt,
 	return ret;
 }
 
+static int parse_control_option(const struct option *opt,
+				const char *str,
+				int unset __maybe_unused)
+{
+	char *comma = NULL, *endptr = NULL;
+	struct record_opts *config = (struct record_opts *)opt->value;
+
+	if (strncmp(str, "fd:", 3))
+		return -EINVAL;
+
+	config->ctl_fd = strtoul(&str[3], &endptr, 0);
+	if (endptr == &str[3])
+		return -EINVAL;
+
+	comma = strchr(str, ',');
+	if (comma) {
+		if (endptr != comma)
+			return -EINVAL;
+
+		config->ctl_fd_ack = strtoul(comma + 1, &endptr, 0);
+		if (endptr == comma + 1 || *endptr != '\0')
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void switch_output_size_warn(struct record *rec)
 {
 	u64 wakeup_size = evlist__mmap_size(rec->opts.mmap_pages);
@@ -2380,6 +2411,8 @@ static struct record record = {
 		},
 		.mmap_flush          = MMAP_FLUSH_DEFAULT,
 		.nr_threads_synthesize = 1,
+		.ctl_fd              = -1,
+		.ctl_fd_ack          = -1,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -2581,6 +2614,10 @@ static struct option __record_options[] = {
 		"libpfm4 event selector. use 'perf list' to list available events",
 		parse_libpfm_events_option),
 #endif
+	OPT_CALLBACK(0, "control", &record.opts, "fd:ctl-fd[,ack-fd]",
+		     "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).\n"
+		     "\t\t\t  Optionally send control command completion ('ack\\n') to ack-fd descriptor.",
+		      parse_control_option),
 	OPT_END()
 };
 
tools/perf/util/record.h +2 -0
index da138dcb4d34..4cb72a478af1 100644
@@ -70,6 +70,8 @@ struct record_opts {
 	int	      mmap_flush;
 	unsigned int  comp_level;
 	unsigned int  nr_threads_synthesize;
+	int	      ctl_fd;
+	int	      ctl_fd_ack;
 };
 
 extern const char * const *record_usage;
Signature · 1 line
2.24.1