netdev - Re: [linux-next:master] [af_unix] dcf70df204: stress-ng.epoll.ops_per

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20240410174026.9989-1-kuniyu@amazon.com>
Date: Wed, 10 Apr 2024 10:40:26 -0700
From: Kuniyuki Iwashima <kuniyu@...zon.com>
To: <oliver.sang@...el.com>
CC: <feng.tang@...el.com>, <fengwei.yin@...el.com>, <kuba@...nel.org>,
	<kuniyu@...zon.com>, <linux-mm@...ck.org>, <lkp@...el.com>,
	<netdev@...r.kernel.org>, <oe-lkp@...ts.linux.dev>, <pabeni@...hat.com>,
	<ying.huang@...el.com>
Subject: Re: [linux-next:master] [af_unix]  dcf70df204: stress-ng.epoll.ops_per_sec -92.6% regression

From: kernel test robot <oliver.sang@...el.com>
Date: Wed, 10 Apr 2024 16:08:00 +0800
> Hello,
> 
> kernel test robot noticed a -92.6% regression of stress-ng.epoll.ops_per_sec on:
> 
> 
> commit: dcf70df2048d27c5d186f013f101a4aefd63aa41 ("af_unix: Fix up unix_edge.successor for embryo socket.")
> https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
> 
> testcase: stress-ng
> test machine: 64 threads 2 sockets Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz (Ice Lake) with 256G memory
> parameters:
> 
> 	nr_threads: 100%
> 	testtime: 60s
> 	test: epoll
> 	cpufreq_governor: performance

I'll add few checks so that non-inflight listener need not
hold gc lock during accept().

Thanks!