cfda7bb9ecb: +14.7% will-it-scale.per_thread_ops
Hi Andy,
FYI, we noticed the below changes on
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
commit cfda7bb9ecbf9d96264bb5bade33a842966d1062 ("x86, vdso: Move syscall and sysenter setup into kernel/cpu/common.c")
test case: nhm4/will-it-scale/sched_yield
3d7ee969bffcc98 cfda7bb9ecbf9d96264bb5bad
--------------- -------------------------
5497021 ~ 0% +14.7% 6303424 ~ 0% TOTAL will-it-scale.per_thread_ops
0.54 ~ 0% +5.6% 0.57 ~ 0% TOTAL will-it-scale.scalability
6209483 ~ 0% +1.6% 6305917 ~ 0% TOTAL will-it-scale.per_process_ops
2455 ~ 5% +16.9% 2870 ~ 5% TOTAL cpuidle.C1-NHM.usage
8829 ~ 7% +15.2% 10169 ~10% TOTAL slabinfo.kmalloc-64.active_objs
24.13 ~12% +48.9% 35.93 ~14% TOTAL time.user_time
393 ~ 0% -3.0% 382 ~ 1% TOTAL time.system_timeLegend:
~XX% - stddev percent
[+-]XX% - change percent
Thanks,
Jet
echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu1/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu2/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu3/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu4/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu5/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu6/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu7/cpufreq/scaling_governor ./runtest.py sched_yield 32 1 4 6 8
Quoted 7 lines · Jet Chen
Hi Andy,
FYI, we noticed the below changes on
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.gitx86/vdso commitcfda7bb9ecbf9d96264bb5bade33a842966d1062("x86, vdso: Move syscall and sysenter setup intokernel/cpu/common.c")
This is really strange. That change shouldn't have any effect except that some kernels might boot a cycle or two faster.
Quoted 5 lines
test case: nhm4/will-it-scale/sched_yield
3d7ee969bffcc98cfda7bb9ecbf9d96264bb5bad
--------------- -------------------------
Quoted 11 lines
5497021 ~ 0% +14.7% 6303424 ~ 0% TOTAL
will-it-scale.per_thread_ops
0.54 ~ 0% +5.6% 0.57 ~ 0% TOTAL will-it-scale.scalability
6209483 ~ 0% +1.6% 6305917 ~ 0% TOTAL
will-it-scale.per_process_ops
2455 ~ 5% +16.9% 2870 ~ 5% TOTAL cpuidle.C1-NHM.usage
8829 ~ 7% +15.2% 10169 ~10% TOTAL
slabinfo.kmalloc-64.active_objs
24.13 ~12% +48.9% 35.93 ~14% TOTAL time.user_time
393 ~ 0% -3.0% 382 ~ 1% TOTAL time.system_timeIs this a speedup or a slowdown?
--Andy
Hi Andy,
Quoted 29 lines · Andy Lutomirski
Quoted 7 lines · Jet Chen
Hi Andy,
FYI, we noticed the below changes on
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.gitx86/vdso commitcfda7bb9ecbf9d96264bb5bade33a842966d1062("x86, vdso: Move syscall and sysenter setup intokernel/cpu/common.c")This is really strange. That change shouldn't have any effect except that some kernels might boot a cycle or two faster.
Quoted 5 lines
test case: nhm4/will-it-scale/sched_yield
3d7ee969bffcc98cfda7bb9ecbf9d96264bb5bad
--------------- -------------------------Quoted 11 lines
5497021 ~ 0% +14.7% 6303424 ~ 0% TOTAL will-it-scale.per_thread_ops 0.54 ~ 0% +5.6% 0.57 ~ 0% TOTAL will-it-scale.scalability 6209483 ~ 0% +1.6% 6305917 ~ 0% TOTAL will-it-scale.per_process_ops 2455 ~ 5% +16.9% 2870 ~ 5% TOTAL cpuidle.C1-NHM.usage 8829 ~ 7% +15.2% 10169 ~10% TOTAL slabinfo.kmalloc-64.active_objs 24.13 ~12% +48.9% 35.93 ~14% TOTAL time.user_time 393 ~ 0% -3.0% 382 ~ 1% TOTAL time.system_time
Quoted 1 line
Is this a speedup or a slowdown?
It's a speedup. The will-it-scale/sched_yield test case's throughput increased by +14.7% (multi-thread case) and +1.6% (multi-process case).
However the CPU %user time increased more, by +48.9%.
Thanks,
Fengguang
Quoted 17 lines · Fengguang Wu
Quoted 17 lines
Quoted 16 lines
test case: nhm4/will-it-scale/sched_yield
3d7ee969bffcc98cfda7bb9ecbf9d96264bb5bad
--------------- -------------------------5497021 ~ 0% +14.7% 6303424 ~ 0% TOTAL will-it-scale.per_thread_ops 0.54 ~ 0% +5.6% 0.57 ~ 0% TOTAL will-it-scale.scalability 6209483 ~ 0% +1.6% 6305917 ~ 0% TOTAL will-it-scale.per_process_ops 2455 ~ 5% +16.9% 2870 ~ 5% TOTAL cpuidle.C1-NHM.usage 8829 ~ 7% +15.2% 10169 ~10% TOTAL slabinfo.kmalloc-64.active_objs 24.13 ~12% +48.9% 35.93 ~14% TOTAL time.user_time 393 ~ 0% -3.0% 382 ~ 1% TOTAL time.system_time
Quoted 7 lines
Quoted 1 line
Is this a speedup or a slowdown?
It's a speedup. The will-it-scale/sched_yield test case's throughput increased by +14.7% (multi-thread case) and +1.6% (multi-process case).
However the CPU %user time increased more, by +48.9%.
That would be consistent with spending less time in the kernel, no?
But I agree... that is completely bizarre. That checkin should have absolutely zero effect on performance.
-hpa