perf util: Use target->per_thread and target->system_wide flags
PATCH v2 1/1 perf util: Use target->per_thread and target->system_wide flags
Mathieu Poirier reports issue in commit ("73c0ca1eee3d perf thread_map:
Enumerate all threads from /proc") that it has negative impact on 'perf record --per-thread'. It has the effect of creating a kernel event for each thread in the system for 'perf record --per-thread'.
Mathieu Poirier's patch ("perf util: Do not reuse target->per_thread flag") can fix this issue by creating a new target->all_threads flag.
This patch is based on Mathieu Poirier's patch but it doesn't use a new target->all_threads flag. This patch just uses 'target->per_thread && target->system_wide' as a condition to check for all threads case.
v2:
---
According to Jiri's comment, add description to explain why the patch uses 'target->per_thread && target->system_wide'.
v2 doesn't have functional change.
--- tools/perf/util/evlist.c | 20 +++++++++++++++++++- tools/perf/util/thread_map.c | 4 ++-- tools/perf/util/thread_map.h | 2 +- 3 files changed, 22 insertions(+), 4 deletions(-)
tools/perf/util/evlist.c +19 -1
@@ -1106,8 +1106,26 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)struct cpu_map *cpus;struct thread_map *threads; +/* +* If specify '-a' and '--per-thread' to perf record, perf record +* will override '--per-thread'. target->per_thread = false and +* target->system_wide = true. +* +* If specify '--per-thread' only to perf record, +* target->per_thread = true and target->system_wide = false. +* +* So target->per_thread && target->system_wide is false. +* For perf record, thread_map__new_str doesn't call +* thread_map__new_all_cpus. That will keep perf record's +* current behavior. +* +* For perf stat, it allows the case that target->per_thread and +* target->system_wide are all true. It means to collect system-wide +* per-thread data. thread_map__new_str will call +* thread_map__new_all_cpus to enumerate all threads. +*/ threads =thread_map__new_str (target->pid, target->tid, target->uid, - target->per_thread); + target->per_thread && target->system_wide);if (!threads)return -1 ;
tools/perf/util/thread_map.c +2 -2
@@ -323,7 +323,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) }struct thread_map *thread_map__new_str (const char *pid,const char *tid, -uid_t uid,bool per_thread) +uid_t uid,bool all_threads) {if (pid)return thread_map__new_by_pid_str (pid);
@@ -331,7 +331,7 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,if (!tid && uid !=UINT_MAX )return thread_map__new_by_uid (uid); -if (per_thread) +if (all_threads)return thread_map__new_all_cpus ();return thread_map__new_by_tid_str (tid);
tools/perf/util/thread_map.h +1 -1
@@ -31,7 +31,7 @@ struct thread_map *thread_map__get(struct thread_map *map);void thread_map__put (struct thread_map *map);struct thread_map *thread_map__new_str (const char *pid, -const char *tid,uid_t uid,bool per_thread); +const char *tid,uid_t uid,bool all_threads);struct thread_map *thread_map__new_by_tid_str (const char *tid_str);
Signature · 1 line
2.7.4
Quoted 12 lines · Jin Yao
Mathieu Poirier reports issue in commit ("
73c0ca1eee3dperfthread_map:
Enumerate all threads from /proc") that it has negative impact on 'perf record --per-thread'. It has the effect of creating a kernel event for each thread in the system for 'perf record --per-thread'.Mathieu Poirier's patch ("perf util: Do not reuse
target->per_threadflag") can fix this issue by creating a newtarget->all_threadsflag.This patch is based on Mathieu Poirier's patch but it doesn't use a new
target->all_threadsflag. This patch just uses 'target->per_thread&&target->system_wide' as a condition to check for all threads case.
Quoted 6 lines
v2:
---
According to Jiri's comment, add description to explain why the patch uses 'target->per_thread&&target->system_wide'.v2 doesn't have functional change.
thanks,
jirka