From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mga07.intel.com (mga07.intel.com [134.134.136.100]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B4B1733C3 for ; Mon, 27 Jun 2022 15:13:04 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1656342784; x=1687878784; h=date:from:to:cc:subject:message-id:references: mime-version:in-reply-to; bh=xJP9OefAMxCTgdzZDCaOuKXFij4QIj41i5jxXMS1AdM=; b=LvRGzLjcGYY0Nr50YYBbypz8vukHydOo5wS1A5JsmEyEWoSLlQel+YTl 4UaDzGU4EAkCGLXJtuVtsct9HI33j7//o+Fz2B6ChYmh4oHat6pTYn7hm by8HyTuBCQN3B6pcuP72fprJwaBRGsEQC+sQobsEaZdWAnkbhoOqcR/QO HKVLYGvgw1AN+EZKfp2HfFKyIcy7qJzLftsvFOJknha2pJTtNCEfwUFrO qd8gEiXg+ZshiVK2NnSuol03B1IqPmb+IH9al1mWVq0dkrPf+Fw+7xF0J aRoZ6Y74yU+9xBTrcD0e8xc+fTDz8jWFNTSB3c018MNyQ+c7bxbid8gGb A==; X-IronPort-AV: E=McAfee;i="6400,9594,10390"; a="345468882" X-IronPort-AV: E=Sophos;i="5.92,226,1650956400"; d="scan'208";a="345468882" Received: from orsmga005.jf.intel.com ([10.7.209.41]) by orsmga105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Jun 2022 08:13:04 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.92,226,1650956400"; d="scan'208";a="766731304" Received: from shbuild999.sh.intel.com (HELO localhost) ([10.239.146.138]) by orsmga005.jf.intel.com with ESMTP; 27 Jun 2022 08:12:58 -0700 Date: Mon, 27 Jun 2022 23:12:58 +0800 From: Feng Tang To: Shakeel Butt Cc: Eric Dumazet , Linux MM , Andrew Morton , Roman Gushchin , Michal Hocko , Johannes Weiner , Muchun Song , Jakub Kicinski , Xin Long , Marcelo Ricardo Leitner , kernel test robot , Soheil Hassas Yeganeh , LKML , network dev , linux-s390@vger.kernel.org, MPTCP Upstream , "linux-sctp @ vger . kernel . org" , lkp@lists.01.org, kbuild test robot , Huang Ying , Xing Zhengjun , Yin Fengwei , Ying Xu Subject: Re: [net] 4890b686f4: netperf.Throughput_Mbps -69.4% regression Message-ID: <20220627151258.GB20878@shbuild999.sh.intel.com> References: <20220623185730.25b88096@kernel.org> <20220624070656.GE79500@shbuild999.sh.intel.com> <20220624144358.lqt2ffjdry6p5u4d@google.com> <20220625023642.GA40868@shbuild999.sh.intel.com> <20220627023812.GA29314@shbuild999.sh.intel.com> <20220627123415.GA32052@shbuild999.sh.intel.com> Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: On Mon, Jun 27, 2022 at 07:52:55AM -0700, Shakeel Butt wrote: > On Mon, Jun 27, 2022 at 5:34 AM Feng Tang wrote: > > Yes, 1% is just around noise level for a microbenchmark. > > > > I went check the original test data of Oliver's report, the tests was > > run 6 rounds and the performance data is pretty stable (0Day's report > > will show any std deviation bigger than 2%) > > > > The test platform is a 4 sockets 72C/144T machine, and I run the > > same job (nr_tasks = 25% * nr_cpus) on one CascadeLake AP (4 nodes) > > and one Icelake 2 sockets platform, and saw 75% and 53% regresson on > > them. > > > > In the first email, there is a file named 'reproduce', it shows the > > basic test process: > > > > " > > use 'performane' cpufre governor for all CPUs > > > > netserver -4 -D > > modprobe sctp > > netperf -4 -H 127.0.0.1 -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K & > > netperf -4 -H 127.0.0.1 -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K & > > netperf -4 -H 127.0.0.1 -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K & > > (repeat 36 times in total) > > ... > > > > " > > > > Which starts 36 (25% of nr_cpus) netperf clients. And the clients number > > also matters, I tried to increase the client number from 36 to 72(50%), > > and the regression is changed from 69.4% to 73.7% > > > > Am I understanding correctly that this 69.4% (or 73.7%) regression is > with cgroup v2? Yes. > Eric did the experiments on v2 but on real hardware where the > performance impact was negligible. > > BTW do you see similar regression for tcp as well or just sctp? Yes, I run TCP_SENDFILE case with 'send_size'==10K, it hits a 70%+ regressioin. Thanks, Feng