perf/sched: fix for getting task's execute time
PATCH 1/1 perf/sched: fix for getting task's execute time
In current code, we get task's execute time by reading "/proc/<pid>/sched" file, it's wrong if the task is created by pthread_create(), because every thread task has same pid. So, the correct way is reading "/proc/<ppid>/task/<tid>/sched" file.
This patch also remove redundant include files since <sys/types.h> is included in "perf.h"
--- tools/perf/builtin-sched.c | 7 ++++--- 1 files changed, 4 insertions(+), 3 deletions(-)
tools/perf/builtin-sched.c +4 -3
@@ -13,7 +13,6 @@#include "util/debug.h" #include "util/data_map.h" -#include <sys/types.h> #include <sys/prctl.h> #include <semaphore.h>
@@ -416,7 +415,7 @@ static u64 get_cpu_usage_nsec_parent(void)static u64 get_cpu_usage_nsec_self (void ) { -char filename [] ="/proc/1234567890/sched" ; +char filename [] ="/proc/1234567890/task/1234567890/sched" ;unsigned long msecs, nsecs;char *line =NULL ;u64 total =0 ;
@@ -425,7 +424,9 @@ static u64 get_cpu_usage_nsec_self(void)FILE *file;int ret; -sprintf (filename,"/proc/%d/sched" ,getpid ()); +sprintf (filename,"/proc/%d/task/%d/sched" ,getpid (), + (pid_t )syscall (SYS_gettid)); + file =fopen (filename,"r" );BUG_ON (!file);
Signature · 1 line
1.6.1.2
Peter Zijlstra
maintainerQuoted 8 lines · Xiao Guangrong
In current code, we get task's execute time by reading "/proc/<pid>/sched" file, it's wrong if the task is created by
pthread_create(), because every thread task has same pid. So, the correct way is reading "/proc/<ppid>/task/<tid>/sched" file.This patch also remove redundant include files since <
sys/types.h> is included in "perf.h"
We really should not be using these proc files but instead make sure this information gets transferred through a tracepoint or similar.
Reading these proc files is too prone to races.
Peter Zijlstra
maintainerQuoted 7 lines · Peter Zijlstra
Quoted 6 lines · Xiao Guangrong
In current code, we get task's execute time by reading "/proc/<pid>/sched" file, it's wrong if the task is created by
pthread_create(), because every thread task has same pid. So, the correct way is reading "/proc/<ppid>/task/<tid>/sched" file.
Quoted 7 lines
Quoted 2 lines
This patch also remove redundant include files since <
sys/types.h> is included in "perf.h"We really should not be using these proc files but instead make sure this information gets transferred through a tracepoint or similar.
Reading these proc files is too prone to races.
We can probably get the runtime by grouping a task-clock swcounter with an appropriate other event.
Quoted 8 lines · Peter Zijlstra
Quoted 7 lines · Peter Zijlstra
Quoted 6 lines · Xiao Guangrong
In current code, we get task's execute time by reading "/proc/<pid>/sched" file, it's wrong if the task is created by
pthread_create(), because every thread task has same pid. So, the correct way is reading "/proc/<ppid>/task/<tid>/sched" file.
Quoted 7 lines
Quoted 7 lines
Quoted 2 lines
This patch also remove redundant include files since <
sys/types.h> is included in "perf.h"We really should not be using these proc files but instead make sure this information gets transferred through a tracepoint or similar.
Reading these proc files is too prone to races.
yeah. Ideally we'd want all valuable information that is available via /proc to be available via perf events as well. In the future it should be possible to run perf even without /proc mounted for example.
Furthermore it's good for consistency and simplicity as well, plus it's faster too to get the information from the perf syscall and mmap-ed ringbuffer than to read things via /proc. No need for ASCII conversion, fixed record formats, fast streaming and buffering, no read() overhead, etc.
Quoted 2 lines
We can probably get the runtime by grouping a task-clock swcounter with an appropriate other event.
Would be lovely.
Ingo
Quoted 8 lines · Peter Zijlstra
Quoted 4 lines
We really should not be using these proc files but instead make sure this information gets transferred through a tracepoint or similar.
Reading these proc files is too prone to races.
We can probably get the runtime by grouping a task-clock swcounter with an appropriate other event.
Hi Peter,
Thanks your suggestion.
Actually, we can call getrusage(RUSAGE_THREAD, ru) to get current task's execute time, and I think this is a simpler way.
I'll send v2 patch later.
Thanks,
Xiao
PATCH v2 1/1 perf/sched: fix for getting task's execution time
In current code, task's execute time is got by reading '/proc/<pid>/sched' file, it's wrong if the task is created by pthread_create(), because every thread task has same pid.
This way also has two demerits:
1: 'perf sched replay' can't work if the kernel not compile with
'CONFIG_SCHED_DEBUG' option
2: perf tool should depend on proc file system
So, this patch call getrusage() to get task's execution time instead of reading /proc file
--- tools/perf/builtin-sched.c | 46 ++++++++++++++----------------------------- 1 files changed, 15 insertions(+), 31 deletions(-)
tools/perf/builtin-sched.c +15 -31
@@ -13,7 +13,6 @@#include "util/debug.h" #include "util/data_map.h" -#include <sys/types.h> #include <sys/prctl.h> #include <semaphore.h>
@@ -399,49 +398,34 @@ process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom) } } +static u64 get_sum_time (struct rusage *ru) +{ +u64 sum; + + sum = ru->ru_utime.tv_sec*1e9 + ru->ru_utime.tv_usec*1e3 ; + sum += ru->ru_stime.tv_sec*1e9 + ru->ru_stime.tv_usec*1e3 ; +return sum; +} +static u64 get_cpu_usage_nsec_parent (void ) {struct rusage ru; -u64 sum;int err; err =getrusage (RUSAGE_SELF , &ru);BUG_ON (err); - sum = ru.ru_utime.tv_sec*1e9 + ru.ru_utime.tv_usec*1e3 ; - sum += ru.ru_stime.tv_sec*1e9 + ru.ru_stime.tv_usec*1e3 ; - -return sum; +return get_sum_time (&ru); }static u64 get_cpu_usage_nsec_self (void ) { -char filename [] ="/proc/1234567890/sched" ; -unsigned long msecs, nsecs; -char *line =NULL ; -u64 total =0 ; -size_t len =0 ; -ssize_t chars; -FILE *file; -int ret; - -sprintf (filename,"/proc/%d/sched" ,getpid ()); - file =fopen (filename,"r" ); -BUG_ON (!file); - -while ((chars =getline (&line, &len, file)) !=-1 ) { - ret =sscanf (line,"se.sum_exec_runtime : %ld.%06ld\n" , - &msecs, &nsecs); -if (ret ==2 ) { - total = msecs*1e6 + nsecs; -break ; - } - } -if (line) -free (line); -fclose (file); +struct rusage ru; +int err; -return total; + err =getrusage (RUSAGE_THREAD , &ru); +BUG_ON (err); +return get_sum_time (&ru); }static void *thread_func (void *ctx)
Signature · 1 line
1.6.1.2
Re: [PATCH v2] perf/sched: fix for getting task's execution time
Quoted 4 lines · Xiao Guangrong
In current code, task's execute time is got by reading '/proc/<pid>/sched' file, it's wrong if the task is created by
pthread_create(), because every thread task has same pid.
Quoted 8 lines
This way also has two demerits:
1: 'perf sched replay' can't work if the kernel not compile with
'CONFIG_SCHED_DEBUG' option
2: perf tool should depend on proc file systemSo, this patch call
getrusage()to get task's execution time instead of reading /proc file
ok, that's better than /proc, but how about using PERF_COUNT_SW_TASK_CLOCK instead of rusage, to recover the CPU time used? It would be more precise, and it would use the perf API. (Some helper functions in tools/perf/lib/ would be nice to make it as easy to use as rusage (or even easier if possible).)
Ingo
PATCH v3 1/1 perf/sched: fix for getting task's execution time
In current code, task's execute time is got by reading '/proc/<pid>/sched' file, it's wrong if the task is created by pthread_create(), because every thread task has same pid.
This way also has two demerits:
1: 'perf sched replay' can't work if the kernel not compile
with 'CONFIG_SCHED_DEBUG' option
2: perf tool should depend on proc file system
So, this patch use PERF_COUNT_SW_TASK_CLOCK to get task's execution time instead of reading /proc file
Changelog v2 -> v3:
use PERF_COUNT_SW_TASK_CLOCK instead of rusage() as Ingo's suggestion
--- tools/perf/builtin-sched.c | 55 +++++++++++++++++++++---------------------- 1 files changed, 27 insertions(+), 28 deletions(-)
tools/perf/builtin-sched.c +27 -28
@@ -13,7 +13,6 @@#include "util/debug.h" #include "util/data_map.h" -#include <sys/types.h> #include <sys/prctl.h> #include <semaphore.h>
@@ -414,34 +413,33 @@ static u64 get_cpu_usage_nsec_parent(void)return sum; } -static u64 get_cpu_usage_nsec_self (void ) +static int self_open_counters (void ) { -char filename [] ="/proc/1234567890/sched" ; -unsigned long msecs, nsecs; -char *line =NULL ; -u64 total =0 ; -size_t len =0 ; -ssize_t chars; -FILE *file; -int ret; +struct perf_event_attr attr; +int fd; -sprintf (filename,"/proc/%d/sched" ,getpid ()); - file =fopen (filename,"r" ); -BUG_ON (!file); +memset (&attr,0 ,sizeof (attr)); -while ((chars =getline (&line, &len, file)) !=-1 ) { - ret =sscanf (line,"se.sum_exec_runtime : %ld.%06ld\n" , - &msecs, &nsecs); -if (ret ==2 ) { - total = msecs*1e6 + nsecs; -break ; - } - } -if (line) -free (line); -fclose (file); + attr.type =PERF_TYPE_SOFTWARE ; + attr.config =PERF_COUNT_SW_TASK_CLOCK ; -return total; + fd =sys_perf_event_open (&attr,0 ,-1 ,-1 ,0 ); + +if (fd <0 ) +die ("Error: sys_perf_event_open() syscall returned" +"with %d (%s)\n" , fd,strerror (errno)); +return fd; +} + +static u64 get_cpu_usage_nsec_self (int fd) +{ +u64 runtime; +int ret; + + ret =read (fd, &runtime,sizeof (runtime)); +BUG_ON (ret !=sizeof (runtime)); + +return runtime; }static void *thread_func (void *ctx)
@@ -450,9 +448,11 @@ static void *thread_func(void *ctx)u64 cpu_usage_0, cpu_usage_1;unsigned long i, ret;char comm2[22 ]; +int fd;sprintf (comm2,":%s" , this_task->comm);prctl (PR_SET_NAME , comm2); + fd =self_open_counters (); again: ret =sem_post (&this_task->ready_for_work);
@@ -462,16 +462,15 @@ again: ret =pthread_mutex_unlock (&start_work_mutex);BUG_ON (ret); - cpu_usage_0 =get_cpu_usage_nsec_self (); + cpu_usage_0 =get_cpu_usage_nsec_self (fd);for (i =0 ; i < this_task->nr_events; i++) { this_task->curr_event = i;process_sched_event (this_task, this_task->atoms[i]); } - cpu_usage_1 =get_cpu_usage_nsec_self (); + cpu_usage_1 =get_cpu_usage_nsec_self (fd); this_task->cpu_usage = cpu_usage_1 - cpu_usage_0; - ret =sem_post (&this_task->work_done_sem);BUG_ON (ret);
Signature · 1 line
1.6.1.2
Re: [PATCH v3] perf/sched: fix for getting task's execution time
Sorry, miss Reported-by, please ignore this mail, i'll resend it
Quoted 17 lines · Xiao Guangrong
In current code, task's execute time is got by reading '/proc/<pid>/sched' file, it's wrong if the task is created by
pthread_create(), because every thread task has same pid.This way also has two demerits:
1: 'perf sched replay' can't work if the kernel not compile
with 'CONFIG_SCHED_DEBUG' option
2: perf tool should depend on proc file systemSo, this patch use
PERF_COUNT_SW_TASK_CLOCKto get task's execution time instead of reading /proc fileChangelog v2 -> v3:
usePERF_COUNT_SW_TASK_CLOCKinstead ofrusage()as Ingo's suggestionSigned-off-by Xiao Guangrong <[email protected]>
Re: [PATCH v3] perf/sched: fix for getting task's execution time
Quoted 1 line · Xiao Guangrong
Sorry, miss Reported-by, please ignore this mail, i'll resend it
I've added Edwin's Reported-by, no need to resend.
Ingo
Ingo Molnar
AppliedRe: [PATCH v3] perf/sched: fix for getting task's execution time
In reply to Xiao GuangrongQuoted 111 lines · Xiao Guangrong
In current code, task's execute time is got by reading '/proc/<pid>/sched' file, it's wrong if the task is created by
pthread_create(), because every thread task has same pid.This way also has two demerits:
1: 'perf sched replay' can't work if the kernel not compile
with 'CONFIG_SCHED_DEBUG' option
2: perf tool should depend on proc file systemSo, this patch use
PERF_COUNT_SW_TASK_CLOCKto get task's execution time instead of reading /proc fileChangelog v2 -> v3:
usePERF_COUNT_SW_TASK_CLOCKinstead ofrusage()as Ingo's suggestionSigned-off-by Xiao Guangrong <[email protected]>--- tools/perf/builtin-sched.c | 55 +++++++++++++++++++++---------------------- 1 files changed, 27 insertions(+), 28 deletions(-)tools/perf/builtin-sched.c +26
-26@@ -13,7 +13,6 @@#include "util/debug.h" #include "util/data_map.h" -#include <sys/types.h> #include <sys/prctl.h> #include <semaphore.h> @@ -414,34 +413,33 @@ static u64 get_cpu_usage_nsec_parent(void)return sum; } -static u64 get_cpu_usage_nsec_self (void ) +static int self_open_counters (void ) { -char filename [] ="/proc/1234567890/sched" ; -unsigned long msecs, nsecs; -char *line =NULL ; -u64 total =0 ; -size_t len =0 ; -ssize_t chars; -FILE *file; -int ret; +struct perf_event_attr attr; +int fd; -sprintf (filename,"/proc/%d/sched" ,getpid ()); - file =fopen (filename,"r" ); -BUG_ON (!file); +memset (&attr,0 ,sizeof (attr)); -while ((chars =getline (&line, &len, file)) !=-1 ) { - ret =sscanf (line,"se.sum_exec_runtime : %ld.%06ld\n" , - &msecs, &nsecs); -if (ret ==2 ) { - total = msecs*1e6 + nsecs; -break ; - } - } -if (line) -free (line); -fclose (file); + attr.type =PERF_TYPE_SOFTWARE ; + attr.config =PERF_COUNT_SW_TASK_CLOCK ; -return total; + fd =sys_perf_event_open (&attr,0 ,-1 ,-1 ,0 ); + +if (fd <0 ) +die ("Error: sys_perf_event_open() syscall returned" +"with %d (%s)\n" , fd,strerror (errno)); +return fd; +} + +static u64 get_cpu_usage_nsec_self (int fd) +{ +u64 runtime; +int ret; + + ret =read (fd, &runtime,sizeof (runtime)); +BUG_ON (ret !=sizeof (runtime)); + +return runtime; }static void *thread_func (void *ctx)@@ -450,9 +448,11 @@ static void *thread_func(void *ctx)u64 cpu_usage_0, cpu_usage_1;unsigned long i, ret;char comm2[22 ]; +int fd;sprintf (comm2,":%s" , this_task->comm);prctl (PR_SET_NAME , comm2); + fd =self_open_counters (); again: ret =sem_post (&this_task->ready_for_work);@@ -462,16 +462,15 @@ again: ret =pthread_mutex_unlock (&start_work_mutex);BUG_ON (ret); - cpu_usage_0 =get_cpu_usage_nsec_self (); + cpu_usage_0 =get_cpu_usage_nsec_self (fd);for (i =0 ; i < this_task->nr_events; i++) {
tools/perf/builtin-sched.c again: · line 475
Quoted 10 lines
tools/perf/builtin-sched.c +1
-2this_task->curr_event = i;process_sched_event (this_task, this_task->atoms[i]); } - cpu_usage_1 =get_cpu_usage_nsec_self (); + cpu_usage_1 =get_cpu_usage_nsec_self (fd); this_task->cpu_usage = cpu_usage_1 - cpu_usage_0; - ret =sem_post (&this_task->work_done_sem);BUG_ON (ret);
Very nice - and the code even got shorter a tiny bit.
Applied, thanks!
Ingo
PATCH v3 1/1 perf/sched: fix for getting task's execution time
In reply to Xiao GuangrongIn current code, task's execute time is got by reading '/proc/<pid>/sched' file, it's wrong if the task is created by pthread_create(), because every thread task has same pid.
This way also has two demerits:
1: 'perf sched replay' can't work if the kernel not compile
with 'CONFIG_SCHED_DEBUG' option
2: perf tool should depend on proc file system
So, this patch use PERF_COUNT_SW_TASK_CLOCK to get task's execution time instead of reading /proc file
Changelog v2 -> v3:
use PERF_COUNT_SW_TASK_CLOCK instead of rusage() as Ingo's suggestion
--- tools/perf/builtin-sched.c | 55 +++++++++++++++++++++---------------------- 1 files changed, 27 insertions(+), 28 deletions(-)
tools/perf/builtin-sched.c +27 -28
@@ -13,7 +13,6 @@#include "util/debug.h" #include "util/data_map.h" -#include <sys/types.h> #include <sys/prctl.h> #include <semaphore.h>
@@ -414,34 +413,33 @@ static u64 get_cpu_usage_nsec_parent(void)return sum; } -static u64 get_cpu_usage_nsec_self (void ) +static int self_open_counters (void ) { -char filename [] ="/proc/1234567890/sched" ; -unsigned long msecs, nsecs; -char *line =NULL ; -u64 total =0 ; -size_t len =0 ; -ssize_t chars; -FILE *file; -int ret; +struct perf_event_attr attr; +int fd; -sprintf (filename,"/proc/%d/sched" ,getpid ()); - file =fopen (filename,"r" ); -BUG_ON (!file); +memset (&attr,0 ,sizeof (attr)); -while ((chars =getline (&line, &len, file)) !=-1 ) { - ret =sscanf (line,"se.sum_exec_runtime : %ld.%06ld\n" , - &msecs, &nsecs); -if (ret ==2 ) { - total = msecs*1e6 + nsecs; -break ; - } - } -if (line) -free (line); -fclose (file); + attr.type =PERF_TYPE_SOFTWARE ; + attr.config =PERF_COUNT_SW_TASK_CLOCK ; -return total; + fd =sys_perf_event_open (&attr,0 ,-1 ,-1 ,0 ); + +if (fd <0 ) +die ("Error: sys_perf_event_open() syscall returned" +"with %d (%s)\n" , fd,strerror (errno)); +return fd; +} + +static u64 get_cpu_usage_nsec_self (int fd) +{ +u64 runtime; +int ret; + + ret =read (fd, &runtime,sizeof (runtime)); +BUG_ON (ret !=sizeof (runtime)); + +return runtime; }static void *thread_func (void *ctx)
@@ -450,9 +448,11 @@ static void *thread_func(void *ctx)u64 cpu_usage_0, cpu_usage_1;unsigned long i, ret;char comm2[22 ]; +int fd;sprintf (comm2,":%s" , this_task->comm);prctl (PR_SET_NAME , comm2); + fd =self_open_counters (); again: ret =sem_post (&this_task->ready_for_work);
@@ -462,16 +462,15 @@ again: ret =pthread_mutex_unlock (&start_work_mutex);BUG_ON (ret); - cpu_usage_0 =get_cpu_usage_nsec_self (); + cpu_usage_0 =get_cpu_usage_nsec_self (fd);for (i =0 ; i < this_task->nr_events; i++) { this_task->curr_event = i;process_sched_event (this_task, this_task->atoms[i]); } - cpu_usage_1 =get_cpu_usage_nsec_self (); + cpu_usage_1 =get_cpu_usage_nsec_self (fd); this_task->cpu_usage = cpu_usage_1 - cpu_usage_0; - ret =sem_post (&this_task->work_done_sem);BUG_ON (ret);
Signature · 1 line
1.6.1.2
[tip:perf/urgent] perf sched: Fix for getting task's execution time
In reply to Xiao GuangrongCommit-ID: c0c9e72150c07b4a6766cd24a6f685ec2dc9c343 Gitweb: http://git.kernel.org/tip/c0c9e72150c07b4a6766cd24a6f685ec2dc9c343 Author: Xiao Guangrong <[email protected]> AuthorDate: Wed, 9 Dec 2009 17:51:30 +0800 Committer: Ingo Molnar <[email protected]> CommitDate: Wed, 9 Dec 2009 10:59:12 +0100
perf sched: Fix for getting task's execution time
In current code, task's execute time is got by reading '/proc/<pid>/sched' file, it's wrong if the task is created by pthread_create(), because every thread task has same pid.
This way also has two demerits:
1: 'perf sched replay' can't work if the kernel is not
compiled with the 'CONFIG_SCHED_DEBUG' option
2: perf tool should depend on proc file system
So, this patch uses PERF_COUNT_SW_TASK_CLOCK to get task's execution time instead of reading /proc file.
Changelog v2 -> v3:
use PERF_COUNT_SW_TASK_CLOCK instead of rusage() as Ingo's suggestion
LKML-Reference: <[email protected]>
--- tools/perf/builtin-sched.c | 55 +++++++++++++++++++++---------------------- 1 files changed, 27 insertions(+), 28 deletions(-)
tools/perf/builtin-sched.c +27 -28
@@ -13,7 +13,6 @@#include "util/debug.h" #include "util/data_map.h" -#include <sys/types.h> #include <sys/prctl.h> #include <semaphore.h>
@@ -414,34 +413,33 @@ static u64 get_cpu_usage_nsec_parent(void)return sum; } -static u64 get_cpu_usage_nsec_self (void ) +static int self_open_counters (void ) { -char filename [] ="/proc/1234567890/sched" ; -unsigned long msecs, nsecs; -char *line =NULL ; -u64 total =0 ; -size_t len =0 ; -ssize_t chars; -FILE *file; -int ret; +struct perf_event_attr attr; +int fd; -sprintf (filename,"/proc/%d/sched" ,getpid ()); - file =fopen (filename,"r" ); -BUG_ON (!file); +memset (&attr,0 ,sizeof (attr)); -while ((chars =getline (&line, &len, file)) !=-1 ) { - ret =sscanf (line,"se.sum_exec_runtime : %ld.%06ld\n" , - &msecs, &nsecs); -if (ret ==2 ) { - total = msecs*1e6 + nsecs; -break ; - } - } -if (line) -free (line); -fclose (file); + attr.type =PERF_TYPE_SOFTWARE ; + attr.config =PERF_COUNT_SW_TASK_CLOCK ; -return total; + fd =sys_perf_event_open (&attr,0 ,-1 ,-1 ,0 ); + +if (fd <0 ) +die ("Error: sys_perf_event_open() syscall returned" +"with %d (%s)\n" , fd,strerror (errno)); +return fd; +} + +static u64 get_cpu_usage_nsec_self (int fd) +{ +u64 runtime; +int ret; + + ret =read (fd, &runtime,sizeof (runtime)); +BUG_ON (ret !=sizeof (runtime)); + +return runtime; }static void *thread_func (void *ctx)
@@ -450,9 +448,11 @@ static void *thread_func(void *ctx)u64 cpu_usage_0, cpu_usage_1;unsigned long i, ret;char comm2[22 ]; +int fd;sprintf (comm2,":%s" , this_task->comm);prctl (PR_SET_NAME , comm2); + fd =self_open_counters (); again: ret =sem_post (&this_task->ready_for_work);
@@ -462,16 +462,15 @@ again: ret =pthread_mutex_unlock (&start_work_mutex);BUG_ON (ret); - cpu_usage_0 =get_cpu_usage_nsec_self (); + cpu_usage_0 =get_cpu_usage_nsec_self (fd);for (i =0 ; i < this_task->nr_events; i++) { this_task->curr_event = i;process_sched_event (this_task, this_task->atoms[i]); } - cpu_usage_1 =get_cpu_usage_nsec_self (); + cpu_usage_1 =get_cpu_usage_nsec_self (fd); this_task->cpu_usage = cpu_usage_1 - cpu_usage_0; - ret =sem_post (&this_task->work_done_sem);BUG_ON (ret);