lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
Open Source and information security mailing list archives
| ||
|
Message-ID: <87tuc7fp9k.fsf@yhuang6-desk2.ccr.corp.intel.com> Date: Wed, 09 Mar 2022 17:28:55 +0800 From: "Huang, Ying" <ying.huang@...el.com> To: Peter Zijlstra <peterz@...radead.org>, kernel test robot <oliver.sang@...el.com>, Mel Gorman <mgorman@...hsingularity.net> Cc: LKML <linux-kernel@...r.kernel.org>, x86@...nel.org, lkp@...ts.01.org, lkp@...el.com, fengwei.yin@...el.com, aubrey.li@...ux.intel.com, yu.c.chen@...el.com Subject: Re: [LKP] Re: [sched/numa] 0fb3978b0a: stress-ng.fstat.ops_per_sec -18.9% regression Hi, All, "Huang, Ying" <ying.huang@...el.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@...el.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@...el.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
Powered by blists - more mailing lists