* [linus:master] [sched/core] 118a2cf4ce: stress-ng.schedpolicy.ops_per_sec 14.1% regression
@ 2026-10-23 11:49 kernel test robot
2026-10-23 16:14 ` Paul E. McKenney
0 siblings, 1 reply; 4+ messages in thread
From: kernel test robot @ 2026-10-23 11:49 UTC (permalink / raw)
To: K Prateek Nayak
Cc: oe-lkp, lkp, linux-kernel, Peter Zijlstra, Paul E. McKenney,
Vincent Guittot, Phil Auld, aubrey.li, yu.c.chen, yi1.lai
Hello,
kernel test robot noticed a 14.1% regression of stress-ng.schedpolicy.ops_per_sec on:
commit: 118a2cf4ced60777a2408001e2b4838fed1cea55 ("sched/core: Call wakeup_preempt() for queued tasks during class change") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
testcase: stress-ng
config: x86_64-rhel-9.4
compiler: gcc-14
test machine: 224 threads 2 sockets Intel(R) Xeon(R) Platinum 8480CTDX (Sapphire Rapids) with 256G memory
parameters:
nr_threads: 100%
testtime: 60s
test: schedpolicy
cpufreq_governor: performance
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <yi1.lai@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202610231954.51716452-lkp@intel.com
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20261023/202610231954.51716452-lkp@intel.com
=========================================================================================
compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
gcc-14/performance/x86_64-rhel-9.4/100%/debian-13-x86_64-20250902.cgz/lkp-spr-r02/schedpolicy/stress-ng/60s
commit:
v7.3-rc7
118a2cf4ce ("sched/core: Call wakeup_preempt() for queued tasks during class change")
v7.3-rc7 118a2cf4ced60777a2408001e2b
---------------- ---------------------------
%stddev %change %stddev
\ | \
246.24 -14.1% 211.56 stress-ng.schedpolicy.SCHED_BATCH_schedules_per_sec
246.24 -14.1% 211.56 stress-ng.schedpolicy.SCHED_DEADLINE_schedules_per_sec
246.24 -14.1% 211.55 stress-ng.schedpolicy.SCHED_FIFO_schedules_per_sec
246.23 -14.1% 211.55 stress-ng.schedpolicy.SCHED_OTHER_schedules_per_sec
246.24 -14.1% 211.56 stress-ng.schedpolicy.SCHED_RR_schedules_per_sec
16540375 -14.1% 14210394 stress-ng.schedpolicy.ops
275785 -14.1% 236940 stress-ng.schedpolicy.ops_per_sec
85768 ± 3% +734.4% 715671 ± 2% stress-ng.time.involuntary_context_switches
32443 ± 2% +13.9% 36955 ± 2% stress-ng.time.minor_page_faults
21807 -10.3% 19559 stress-ng.time.percent_of_cpu_this_job_got
13087 -10.3% 11737 stress-ng.time.system_time
78783 ± 2% +634.5% 578684 stress-ng.time.voluntary_context_switches
Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [linus:master] [sched/core] 118a2cf4ce: stress-ng.schedpolicy.ops_per_sec 14.1% regression
2026-10-23 11:49 [linus:master] [sched/core] 118a2cf4ce: stress-ng.schedpolicy.ops_per_sec 14.1% regression kernel test robot
@ 2026-10-23 16:14 ` Paul E. McKenney
2026-10-23 17:00 ` Peter Zijlstra
0 siblings, 1 reply; 4+ messages in thread
From: Paul E. McKenney @ 2026-10-23 16:14 UTC (permalink / raw)
To: kernel test robot
Cc: K Prateek Nayak, oe-lkp, lkp, linux-kernel, Peter Zijlstra,
Vincent Guittot, Phil Auld, aubrey.li, yu.c.chen
On Fri, Oct 23, 2026 at 07:49:20PM +0800, kernel test robot wrote:
>
>
> Hello,
>
> kernel test robot noticed a 14.1% regression of stress-ng.schedpolicy.ops_per_sec on:
>
>
> commit: 118a2cf4ced60777a2408001e2b4838fed1cea55 ("sched/core: Call wakeup_preempt() for queued tasks during class change") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
>
> testcase: stress-ng
> config: x86_64-rhel-9.4
> compiler: gcc-14
> test machine: 224 threads 2 sockets Intel(R) Xeon(R) Platinum 8480CTDX (Sapphire Rapids) with 256G memory
> parameters:
>
> nr_threads: 100%
> testtime: 60s
> test: schedpolicy
> cpufreq_governor: performance
>
>
> If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
> | Reported-by: kernel test robot <yi1.lai@intel.com>
> | Closes: https://lore.kernel.org/oe-lkp/202610231954.51716452-lkp@intel.com
This regression is not a good thing, but this commit is fixing a real bug.
Thanx, Paul
> Details are as below:
> -------------------------------------------------------------------------------------------------->
>
>
> The kernel config and materials to reproduce are available at:
> https://download.01.org/0day-ci/archive/20261023/202610231954.51716452-lkp@intel.com
>
> =========================================================================================
> compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
> gcc-14/performance/x86_64-rhel-9.4/100%/debian-13-x86_64-20250902.cgz/lkp-spr-r02/schedpolicy/stress-ng/60s
>
> commit:
> v7.3-rc7
> 118a2cf4ce ("sched/core: Call wakeup_preempt() for queued tasks during class change")
>
> v7.3-rc7 118a2cf4ced60777a2408001e2b
> ---------------- ---------------------------
> %stddev %change %stddev
> \ | \
> 246.24 -14.1% 211.56 stress-ng.schedpolicy.SCHED_BATCH_schedules_per_sec
> 246.24 -14.1% 211.56 stress-ng.schedpolicy.SCHED_DEADLINE_schedules_per_sec
> 246.24 -14.1% 211.55 stress-ng.schedpolicy.SCHED_FIFO_schedules_per_sec
> 246.23 -14.1% 211.55 stress-ng.schedpolicy.SCHED_OTHER_schedules_per_sec
> 246.24 -14.1% 211.56 stress-ng.schedpolicy.SCHED_RR_schedules_per_sec
> 16540375 -14.1% 14210394 stress-ng.schedpolicy.ops
> 275785 -14.1% 236940 stress-ng.schedpolicy.ops_per_sec
> 85768 ± 3% +734.4% 715671 ± 2% stress-ng.time.involuntary_context_switches
> 32443 ± 2% +13.9% 36955 ± 2% stress-ng.time.minor_page_faults
> 21807 -10.3% 19559 stress-ng.time.percent_of_cpu_this_job_got
> 13087 -10.3% 11737 stress-ng.time.system_time
> 78783 ± 2% +634.5% 578684 stress-ng.time.voluntary_context_switches
>
>
> Disclaimer:
> Results have been estimated based on internal Intel analysis and are provided
> for informational purposes only. Any difference in system hardware or software
> design or configuration may affect actual performance.
>
>
> --
> 0-DAY CI Kernel Test Service
> https://github.com/intel/lkp-tests/wiki
>
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [linus:master] [sched/core] 118a2cf4ce: stress-ng.schedpolicy.ops_per_sec 14.1% regression
2026-10-23 16:14 ` Paul E. McKenney
@ 2026-10-23 17:00 ` Peter Zijlstra
2026-10-23 18:51 ` Paul E. McKenney
0 siblings, 1 reply; 4+ messages in thread
From: Peter Zijlstra @ 2026-10-23 17:00 UTC (permalink / raw)
To: Paul E. McKenney
Cc: kernel test robot, K Prateek Nayak, oe-lkp, lkp, linux-kernel,
Vincent Guittot, Phil Auld, aubrey.li, yu.c.chen
On Fri, Oct 23, 2026 at 09:14:02AM -0700, Paul E. McKenney wrote:
> On Fri, Oct 23, 2026 at 07:49:20PM +0800, kernel test robot wrote:
> >
> >
> > Hello,
> >
> > kernel test robot noticed a 14.1% regression of stress-ng.schedpolicy.ops_per_sec on:
> >
> >
> > commit: 118a2cf4ced60777a2408001e2b4838fed1cea55 ("sched/core: Call wakeup_preempt() for queued tasks during class change") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
> >
> > testcase: stress-ng
> > config: x86_64-rhel-9.4
> > compiler: gcc-14
> > test machine: 224 threads 2 sockets Intel(R) Xeon(R) Platinum 8480CTDX (Sapphire Rapids) with 256G memory
> > parameters:
> >
> > nr_threads: 100%
> > testtime: 60s
> > test: schedpolicy
> > cpufreq_governor: performance
> >
> >
> > If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
> > | Reported-by: kernel test robot <yi1.lai@intel.com>
> > | Closes: https://lore.kernel.org/oe-lkp/202610231954.51716452-lkp@intel.com
>
> This regression is not a good thing, but this commit is fixing a real bug.
I think I have a patch somewhere stuck in my review queue for -rc1 that
might help with this:
https://patch.msgid.link/CANGjgdmNCfm%3DSctvKZ44y8b5n8t_JSp4meX%3DDKGnG74B3g1vVw%40mail.gmail.com
If not, too bad, correctness first and all that.
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [linus:master] [sched/core] 118a2cf4ce: stress-ng.schedpolicy.ops_per_sec 14.1% regression
2026-10-23 17:00 ` Peter Zijlstra
@ 2026-10-23 18:51 ` Paul E. McKenney
0 siblings, 0 replies; 4+ messages in thread
From: Paul E. McKenney @ 2026-10-23 18:51 UTC (permalink / raw)
To: Peter Zijlstra
Cc: kernel test robot, K Prateek Nayak, oe-lkp, lkp, linux-kernel,
Vincent Guittot, Phil Auld, aubrey.li, yu.c.chen
On Fri, Oct 23, 2026 at 07:00:23PM +0200, Peter Zijlstra wrote:
> On Fri, Oct 23, 2026 at 09:14:02AM -0700, Paul E. McKenney wrote:
> > On Fri, Oct 23, 2026 at 07:49:20PM +0800, kernel test robot wrote:
> > >
> > >
> > > Hello,
> > >
> > > kernel test robot noticed a 14.1% regression of stress-ng.schedpolicy.ops_per_sec on:
> > >
> > >
> > > commit: 118a2cf4ced60777a2408001e2b4838fed1cea55 ("sched/core: Call wakeup_preempt() for queued tasks during class change") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
> > >
> > > testcase: stress-ng
> > > config: x86_64-rhel-9.4
> > > compiler: gcc-14
> > > test machine: 224 threads 2 sockets Intel(R) Xeon(R) Platinum 8480CTDX (Sapphire Rapids) with 256G memory
> > > parameters:
> > >
> > > nr_threads: 100%
> > > testtime: 60s
> > > test: schedpolicy
> > > cpufreq_governor: performance
> > >
> > >
> > > If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
> > > | Reported-by: kernel test robot <yi1.lai@intel.com>
> > > | Closes: https://lore.kernel.org/oe-lkp/202610231954.51716452-lkp@intel.com
> >
> > This regression is not a good thing, but this commit is fixing a real bug.
>
> I think I have a patch somewhere stuck in my review queue for -rc1 that
> might help with this:
>
> https://patch.msgid.link/CANGjgdmNCfm%3DSctvKZ44y8b5n8t_JSp4meX%3DDKGnG74B3g1vVw%40mail.gmail.com
Here is hoping!
> If not, too bad, correctness first and all that.
Hear, hear! ;-)
Thanx, Paul
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2026-10-23 18:51 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-10-23 11:49 [linus:master] [sched/core] 118a2cf4ce: stress-ng.schedpolicy.ops_per_sec 14.1% regression kernel test robot
2026-10-23 16:14 ` Paul E. McKenney
2026-10-23 17:00 ` Peter Zijlstra
2026-10-23 18:51 ` Paul E. McKenney
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®