lkml.org 
[lkml]   [2022]   [Mar]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
SubjectRe: [LKP] Re: [sched/numa] 0fb3978b0a: stress-ng.fstat.ops_per_sec -18.9% regression
Date
Hi, All,

"Huang, Ying" <ying.huang@intel.com> writes:

> Hi, Oliver,
>
> Thanks for report.
>
> I still cannot connect the regression with the patch yet. To double
> check, I have run test again with "sched_verbose" kernel command line,
> and verified that the sched_domain isn't changed at all with the patch.
>
> kernel test robot <oliver.sang@intel.com> writes:
>> 0.11 6% +0.1 0.16 4% perf-profile.self.cycles-pp.update_rq_clock
>> 0.00 +0.1 0.06 6% perf-profile.self.cycles-pp.memset_erms
>> 0.00 +0.1 0.07 5% perf-profile.self.cycles-pp.get_pid_task
>> 0.06 7% +0.1 0.17 6% perf-profile.self.cycles-pp.select_task_rq_fair
>> 0.54 5% +0.1 0.68 perf-profile.self.cycles-pp.lockref_put_return
>> 4.26 +1.1 5.33 perf-profile.self.cycles-pp.common_perm_cond
>> 15.45 +4.9 20.37 perf-profile.self.cycles-pp.lockref_put_or_lock
>> 20.12 +6.7 26.82 perf-profile.self.cycles-pp.lockref_get_not_dead
>
> From the perf-profile above, the most visible change is more cycles in
> lockref_get_not_dead(), which will loop with cmpxchg on
> dentry->d_lockref. So this appears to be related to the memory layout.
> I will try to debug that.
>
> Because stress-ng is a weird "benchmark" although it's a very good
> functionality test, and I cannot connect the patch with the test case
> and performance metrics collected. I think this regression should be a
> low priority one which shouldn't prevent the merging etc. But I will
> continue to investigate the regression to try to root cause it.

Done more investigation for this. It turns out the sched_domain has
been changed after commit 0fb3978b0a, although it's not shown in default
sched_verbose output. sd->imb_numa_nr of level "NUMA" has been changed
from 24 to 12 after the commit. So the following debug patch restore
the performance.

From 6c79c858248196ea71da4be02a0774bb6e277581 Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Wed, 9 Mar 2022 10:45:18 +0800
Subject: [PATCH] dbg: restore sd->imb_numa_nr

---
kernel/sched/topology.c | 4 ++++
1 file changed, 4 insertions(+)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 5e05fb7a817b..c348747e4166 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2351,6 +2351,10 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
sd->name, imb, factor, sd->imb_numa_nr);
#endif
}
+#ifdef CONFIG_SCHED_DEBUG
+ if (!strcmp(sd->name, "NUMA"))
+ sd->imb_numa_nr = 24;
+#endif
}
}

--
2.30.2
I haven't researched much about the influence of sd->imb_numa_nr. But
it seems that commit 0fb3978b0a just follows the behavior of a normal 2
sockets (2 LLCs) machine. This is intended. So the regression report
isn't important for the commit itself.

About the impact of sd->imb_numa_nr, we will continue work on that.

Best Regards,
Huang, Ying

\
 
 \ /
  Last update: 2022-03-09 10:30    [W:3.123 / U:0.008 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site