sched: Make schedstats a runtime tunable that is disabled by default v3
Subsystems (3)
PATCH 1/1 sched: Make schedstats a runtime tunable that is disabled by default v3
Changelog since V2
o Print stats that are not related to schedstat
o Reintroduce a static inline for update_stats_dequeue
Changelog since V1
o Introduce schedstat_enabled and address Ingo's feedback
o More schedstat-only paths eliminated, particularly ttwu_stat
schedstats is very useful during debugging and performance tuning but it incurs overhead. As such, even though it can be disabled at build time, it is often enabled as the information is useful. This patch adds a kernel command-line and sysctl tunable to enable or disable schedstats on demand. It is disabled by default as someone who knows they need it can also learn to enable it when necessary.
The benefits are workload-dependent but when it gets down to it, the difference will be whether cache misses are incurred updating the shared stats or not. These measurements were taken from a 48-core 2-socket machine with Xeon(R) E5-2670 v3 cpus although they were also tested on a single socket machine 8-core machine with Intel i7-3770 processors.
netperf-tcp
4.5.0-rc1 4.5.0-rc1
vanilla nostats-v3r1
Hmean 64 560.45 ( 0.00%) 575.98 ( 2.77%)
Hmean 128 766.66 ( 0.00%) 795.79 ( 3.80%)
Hmean 256 950.51 ( 0.00%) 981.50 ( 3.26%)
Hmean 1024 1433.25 ( 0.00%) 1466.51 ( 2.32%)
Hmean 2048 2810.54 ( 0.00%) 2879.75 ( 2.46%)
Hmean 3312 4618.18 ( 0.00%) 4682.09 ( 1.38%)
Hmean 4096 5306.42 ( 0.00%) 5346.39 ( 0.75%)
Hmean 8192 10581.44 ( 0.00%) 10698.15 ( 1.10%)
Hmean 16384 18857.70 ( 0.00%) 18937.61 ( 0.42%)Small gains here, UDP_STREAM showed nothing intresting and neither did the TCP_RR tests. The gains on the 8-core machine were very similar.
tbench4
4.5.0-rc1 4.5.0-rc1
vanilla nostats-v3r1
Hmean mb/sec-1 500.85 ( 0.00%) 522.43 ( 4.31%)
Hmean mb/sec-2 984.66 ( 0.00%) 1018.19 ( 3.41%)
Hmean mb/sec-4 1827.91 ( 0.00%) 1847.78 ( 1.09%)
Hmean mb/sec-8 3561.36 ( 0.00%) 3611.28 ( 1.40%)
Hmean mb/sec-16 5824.52 ( 0.00%) 5929.03 ( 1.79%)
Hmean mb/sec-32 10943.10 ( 0.00%) 10802.83 ( -1.28%)
Hmean mb/sec-64 15950.81 ( 0.00%) 16211.31 ( 1.63%)
Hmean mb/sec-128 15302.17 ( 0.00%) 15445.11 ( 0.93%)
Hmean mb/sec-256 14866.18 ( 0.00%) 15088.73 ( 1.50%)
Hmean mb/sec-512 15223.31 ( 0.00%) 15373.69 ( 0.99%)
Hmean mb/sec-1024 14574.25 ( 0.00%) 14598.02 ( 0.16%)
Hmean mb/sec-2048 13569.02 ( 0.00%) 13733.86 ( 1.21%)
Hmean mb/sec-3072 12865.98 ( 0.00%) 13209.23 ( 2.67%)Small gains of 2-4% at low thread counts and otherwise flat. The gains on the 8-core machine were slightly different
tbench4 on 8-core i7-3770 single socket machine
Hmean mb/sec-1 442.59 ( 0.00%) 448.73 ( 1.39%) Hmean mb/sec-2 796.68 ( 0.00%) 794.39 ( -0.29%) Hmean mb/sec-4 1322.52 ( 0.00%) 1343.66 ( 1.60%) Hmean mb/sec-8 2611.65 ( 0.00%) 2694.86 ( 3.19%) Hmean mb/sec-16 2537.07 ( 0.00%) 2609.34 ( 2.85%) Hmean mb/sec-32 2506.02 ( 0.00%) 2578.18 ( 2.88%) Hmean mb/sec-64 2511.06 ( 0.00%) 2569.16 ( 2.31%) Hmean mb/sec-128 2313.38 ( 0.00%) 2395.50 ( 3.55%) Hmean mb/sec-256 2110.04 ( 0.00%) 2177.45 ( 3.19%) Hmean mb/sec-512 2072.51 ( 0.00%) 2053.97 ( -0.89%)
In constract, this shows a relatively steady 2-3% gain at higher thread counts. Due to the nature of the patch and the type of workload, it's not a surprise that the result will depend on the CPU used.
hackbench-pipes
4.5.0-rc1 4.5.0-rc1
vanilla nostats-v3r1
Amean 1 0.0637 ( 0.00%) 0.0660 ( -3.59%)
Amean 4 0.1229 ( 0.00%) 0.1181 ( 3.84%)
Amean 7 0.1921 ( 0.00%) 0.1911 ( 0.52%)
Amean 12 0.3117 ( 0.00%) 0.2923 ( 6.23%)
Amean 21 0.4050 ( 0.00%) 0.3899 ( 3.74%)
Amean 30 0.4586 ( 0.00%) 0.4433 ( 3.33%)
Amean 48 0.5910 ( 0.00%) 0.5694 ( 3.65%)
Amean 79 0.8663 ( 0.00%) 0.8626 ( 0.43%)
Amean 110 1.1543 ( 0.00%) 1.1517 ( 0.22%)
Amean 141 1.4457 ( 0.00%) 1.4290 ( 1.16%)
Amean 172 1.7090 ( 0.00%) 1.6924 ( 0.97%)
Amean 192 1.9126 ( 0.00%) 1.9089 ( 0.19%)Some small gains and losses and while the variance data is not included, it's close to the noise. The UMA machine did not show anything particularly different
pipetest
4.5.0-rc1 4.5.0-rc1
vanilla nostats-v2r2
Min Time 4.13 ( 0.00%) 3.99 ( 3.39%)
1st-qrtle Time 4.38 ( 0.00%) 4.27 ( 2.51%)
2nd-qrtle Time 4.46 ( 0.00%) 4.39 ( 1.57%)
3rd-qrtle Time 4.56 ( 0.00%) 4.51 ( 1.10%)
Max-90% Time 4.67 ( 0.00%) 4.60 ( 1.50%)
Max-93% Time 4.71 ( 0.00%) 4.65 ( 1.27%)
Max-95% Time 4.74 ( 0.00%) 4.71 ( 0.63%)
Max-99% Time 4.88 ( 0.00%) 4.79 ( 1.84%)
Max Time 4.93 ( 0.00%) 4.83 ( 2.03%)
Mean Time 4.48 ( 0.00%) 4.39 ( 1.91%)
Best99%Mean Time 4.47 ( 0.00%) 4.39 ( 1.91%)
Best95%Mean Time 4.46 ( 0.00%) 4.38 ( 1.93%)
Best90%Mean Time 4.45 ( 0.00%) 4.36 ( 1.98%)
Best50%Mean Time 4.36 ( 0.00%) 4.25 ( 2.49%)
Best10%Mean Time 4.23 ( 0.00%) 4.10 ( 3.13%)
Best5%Mean Time 4.19 ( 0.00%) 4.06 ( 3.20%)
Best1%Mean Time 4.13 ( 0.00%) 4.00 ( 3.39%)Small improvement and similar gains were seen on the UMA machine.
The gain is small but it'll depend on the CPU and the workload whether this patch makes a different. However, it stands to reason that doing less work in the scheduler is a good thing. The downside is that the lack of schedstats and tracepoints will be surprising to experts doing performance analysis until they find the existance of the schedstats= parameter or schedstats sysctl.
--- Documentation/kernel-parameters.txt | 5 ++ Documentation/sysctl/kernel.txt | 8 +++ include/linux/sched/sysctl.h | 4 ++ kernel/sched/core.c | 62 +++++++++++++++++++++- kernel/sched/debug.c | 102 +++++++++++++++++++----------------- kernel/sched/fair.c | 90 +++++++++++++++++++------------ kernel/sched/sched.h | 1 + kernel/sched/stats.h | 8 +-- kernel/sysctl.c | 11 ++++ 9 files changed, 204 insertions(+), 87 deletions(-)
Documentation/kernel-parameters.txt +5 -0
@@ -3523,6 +3523,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. sched_debug [KNL] Enables verbose scheduler debug messages. + schedstats= [KNL,X86] Enable or disable scheduled statistics. + Allowed values are enable and disable. This feature + incurs a small amount of overhead in the scheduler + but is useful for debugging and performance tuning. + skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate xtime_lock contention on larger systems, and/or RCU lock contention on all systems with CONFIG_MAXSMP set.
Documentation/sysctl/kernel.txt +8 -0
@@ -760,6 +760,14 @@ rtsig-nr shows the number of RT signals currently queued. ============================================================== +schedstats: + +Enables/disables scheduler statistics. Enabling this feature +incurs a small amount of overhead in the scheduler but is +useful for debugging and performance tuning. + +============================================================== + sg-big-buff: This file shows the size of the generic SCSI (sg) buffer.
include/linux/sched/sysctl.h +4 -0
@@ -95,4 +95,8 @@ extern int sysctl_numa_balancing(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +extern int sysctl_schedstats (struct ctl_table *table,int write, +void __user *buffer,size_t *lenp, +loff_t *ppos); +#endif /* _SCHED_SYSCTL_H */
kernel/sched/core.c +60 -2
86 lines not on this page · raw message
kernel/sched/debug.c +54 -48
135 lines not on this page · raw message
kernel/sched/fair.c +56 -34
153 lines not on this page · raw message
kernel/sched/sched.h +1 -0
@@ -1022,6 +1022,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ extern struct static_key_false sched_numa_balancing; +extern struct static_key_false sched_schedstats;static inline u64 global_rt_period (void ) {
kernel/sched/stats.h +5 -3
@@ -29,9 +29,10 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)if (rq) rq->rq_sched_info.run_delay += delta; } -# define schedstat_inc (rq, field) do { (rq)->field++; } while (0) -# define schedstat_add (rq, field, amt) do { (rq)->field += (amt); } while (0) -# define schedstat_set (var, val) do { var = (val); } while (0) +# define schedstat_enabled () static_branch_unlikely(&sched_schedstats) +# define schedstat_inc (rq, field) do { if (schedstat_enabled()) { (rq)->field++; } } while (0) +# define schedstat_add (rq, field, amt) do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0) +# define schedstat_set (var, val) do { if (schedstat_enabled()) { var = (val); } } while (0)#else /* !CONFIG_SCHEDSTATS */ static inline void rq_sched_info_arrive (struct rq *rq,unsigned long long delta)
@@ -42,6 +43,7 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)static inline void rq_sched_info_depart (struct rq *rq,unsigned long long delta) {} +# define schedstat_enabled () 0# define schedstat_inc (rq, field) do { } while (0)# define schedstat_add (rq, field, amt) do { } while (0)# define schedstat_set (var, val) do { } while (0)
kernel/sysctl.c +11 -0
@@ -350,6 +350,17 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_SCHEDSTATS + { + .procname = "sched_schedstats", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_schedstats, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_SCHEDSTATS */ #endif /* CONFIG_SMP */ #ifdef CONFIG_NUMA_BALANCING {
Signature · 1 line
2.6.4
Quoted 20 lines · Mel Gorman
Changelog since V2
o Print stats that are not related to schedstat
o Reintroduce a static inline forupdate_stats_dequeueChangelog since V1
o Introduceschedstat_enabledand address Ingo's feedback
o More schedstat-only paths eliminated, particularlyttwu_statschedstats is very useful during debugging and performance tuning but it incurs overhead. As such, even though it can be disabled at build time, it is often enabled as the information is useful. This patch adds a kernel command-line and sysctl tunable to enable or disable schedstats on demand. It is disabled by default as someone who knows they need it can also learn to enable it when necessary.
The benefits are workload-dependent but when it gets down to it, the difference will be whether cache misses are incurred updating the shared stats or not. These measurements were taken from a 48-core 2-socket machine with Xeon(R) E5-2670 v3 cpus although they were also tested on a single socket machine 8-core machine with Intel i7-3770 processors.
[...]
Quoted 8 lines
The gain is small but it'll depend on the CPU and the workload whether this patch makes a different. However, it stands to reason that doing less work in the scheduler is a good thing. The downside is that the lack of schedstats and tracepoints will be surprising to experts doing performance analysis until they find the existance of the schedstats= parameter or schedstats sysctl.
Signed-off-by Mel Gorman <[email protected]>
Quoted 11 lines
--- Documentation/kernel-parameters.txt | 5 ++ Documentation/sysctl/kernel.txt | 8 +++ include/linux/sched/sysctl.h | 4 ++ kernel/sched/core.c | 62 +++++++++++++++++++++- kernel/sched/debug.c | 102 +++++++++++++++++++----------------- kernel/sched/fair.c | 90 +++++++++++++++++++------------ kernel/sched/sched.h | 1 + kernel/sched/stats.h | 8 +-- kernel/sysctl.c | 11 ++++ 9 files changed, 204 insertions(+), 87 deletions(-)
Dont we need changes for sched_info_on()?
If we disable schedstats dynamically but CONFIG_TASK_DELAY_ACCT is not set, then sched_info_on will return true, This could impact guest steal time stats as well as data read from /proc/<PID>/schedstat
Also when schedstats is dynamically disabled, and user tries to enable kernel sleep profiling profile_setup(), the kernel may not be able to do the right profiling since enqueue_sleeper() may not get called. Should we alert the user saying kernel sleep profiling is disabled?
Signature · 2 lines
Thanks and Regards Srikar Dronamraju
Quoted 5 lines · Srikar Dronamraju
Dont we need changes for
sched_info_on()?If we disable schedstats dynamically but
CONFIG_TASK_DELAY_ACCTis not set, thensched_info_onwill return true,
Is this really a problem?
sched_info_on() guards sched_info_dequeued(), sched_info_queued(), __sched_info_switch(). These update fields in the sched_info struct with the exception of rq->rq_cpu_time. In the case of rq_cpu_time, the values it's updated depend on sched_info.
I'm not spotting the case where the current information for delayacct is inaccurate. Where is it? Granted, there is some scope for also disabling the delayacct information unless explicitly enabled.
Quoted 8 lines
This could impact guest steal
time stats as well as data read from /proc/<PID>/schedstatAlso when schedstats is dynamically disabled, and user tries to enable kernel sleep profiling
profile_setup(), the kernel may not be able to do the right profiling sinceenqueue_sleeper()may not get called. Should we alert the user saying kernel sleep profiling is disabled?
Yes. This on top? It's not completely bullet proof as a user could both force schedstat disabled and enable sleep profiling but it's a waste of memory to guard against it
include/linux/sched.h +8 -0
@@ -920,6 +920,14 @@ static inline int sched_info_on(void)#endif } +#ifdef CONFIG_SCHEDSTATS +void force_schedstat_enabled (void ); +#else +static inline void force_schedstat_enabled (void ) +{ +} +#endif +enum cpu_idle_type {CPU_IDLE ,CPU_NOT_IDLE ,
kernel/profile.c +1 -0
@@ -59,6 +59,7 @@ int profile_setup(char *str)if (!strncmp (str, sleepstr,strlen (sleepstr))) {#ifdef CONFIG_SCHEDSTATS +force_schedstat_enabled (); prof_on =SLEEP_PROFILING ;if (str[strlen (sleepstr)] ==',' ) str +=strlen (sleepstr) +1 ;
kernel/sched/core.c +8 -0
@@ -2295,6 +2295,14 @@ static void set_schedstats(bool enabled)static_branch_disable (&sched_schedstats); } +void force_schedstat_enabled (void ) +{ +if (!schedstat_enabled ()) { +pr_info ("kernel sleep profiling force enabled sched_schedstats\n" ); +static_branch_enable (&sched_schedstats); + } +} +static int __init setup_schedstats (char *str) {int ret =0 ;
Signature · 2 lines
Mel Gorman SUSE Labs
Quoted 5 lines
Quoted 2 lines
If we disable schedstats dynamically but
CONFIG_TASK_DELAY_ACCTis not set, thensched_info_onwill return true,Is this really a problem?
Quoted 8 lines
sched_info_on()guardssched_info_dequeued(),sched_info_queued(),__sched_info_switch(). These update fields in thesched_infostruct with the exception ofrq->rq_cpu_time. In the case ofrq_cpu_time, the values it's updated depend onsched_info.I'm not spotting the case where the current information for delayacct is inaccurate. Where is it? Granted, there is some scope for also disabling the delayacct information unless explicitly enabled.
ah, the run_delay gets updated. So yes its not a problem.
Quoted 19 lines
Quoted 9 lines
This could impact guest steal
time stats as well as data read from /proc/<PID>/schedstatAlso when schedstats is dynamically disabled, and user tries to enable kernel sleep profiling
profile_setup(), the kernel may not be able to do the right profiling sinceenqueue_sleeper()may not get called. Should we alert the user saying kernel sleep profiling is disabled?Yes. This on top? It's not completely bullet proof as a user could both force schedstat disabled and enable sleep profiling but it's a waste of memory to guard against it
include/linux/sched.h +0
-0
include/linux/sched.h static inline int sched_info_on(void) · line 929
Quoted 10 lines
include/linux/sched.h +7
-0@@ -920,6 +920,14 @@ static inline int sched_info_on(void)#endif } +#ifdef CONFIG_SCHEDSTATS +void force_schedstat_enabled (void ); +#else +static inline void force_schedstat_enabled (void ) +{ +} +#endif
One nit:
Since force_schedstat_enabled is called under CONFIG_SCHEDSTATS we may not want the static define.
Quoted 16 lines
include/linux/sched.h +1
-0+enum cpu_idle_type {CPU_IDLE ,CPU_NOT_IDLE ,kernel/profile.c +1
-0@@ -59,6 +59,7 @@ int profile_setup(char *str)if (!strncmp (str, sleepstr,strlen (sleepstr))) {#ifdef CONFIG_SCHEDSTATS +force_schedstat_enabled (); prof_on =SLEEP_PROFILING ;if (str[strlen (sleepstr)] ==',' ) str +=strlen (sleepstr) +1 ;
Signature · 2 lines
Thanks and Regards Srikar Dronamraju
Quoted 12 lines · Srikar Dronamraju
Quoted 12 lines
Yes. This on top? It's not completely bullet proof as a user could both force schedstat disabled and enable sleep profiling but it's a waste of memory to guard against it
include/linux/sched.h +0
-0@@ -920,6 +920,14 @@ static inline int sched_info_on(void)#endif }
Quoted 12 lines
include/linux/sched.h static inline int sched_info_on(void) · line 929
Quoted 7 lines
include/linux/sched.h +7
-0+#ifdef CONFIG_SCHEDSTATS +void force_schedstat_enabled (void ); +#else +static inline void force_schedstat_enabled (void ) +{ +} +#endif One nit:
Sinceforce_schedstat_enabledis called underCONFIG_SCHEDSTATSwe may not want the static define.
I'm not sure I get this either :(. It is a static inline that does nothing under !CONFIG_SCHEDSTAT because tehre is nothing to do. Otherwise it needs to be available for profiling and I just spotted it's needed by latencytop too.
Signature · 2 lines
Mel Gorman SUSE Labs