Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751474AbaLOGzu (ORCPT ); Mon, 15 Dec 2014 01:55:50 -0500 Received: from mga03.intel.com ([134.134.136.65]:4024 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750837AbaLOGzt (ORCPT ); Mon, 15 Dec 2014 01:55:49 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.04,691,1406617200"; d="yaml'?scan'208";a="498758636" Message-ID: <1418626546.5745.183.camel@linux.intel.com> Subject: [LKP] [sched] 05bfb65f52c: -5.2% thrulay.throughput From: Huang Ying To: Vincent Guittot Cc: LKML , LKP ML Date: Mon, 15 Dec 2014 14:55:46 +0800 Content-Type: multipart/mixed; boundary="=-rA/T2kpl1mnz9Vq2/58p" X-Mailer: Evolution 3.12.9-1 Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --=-rA/T2kpl1mnz9Vq2/58p Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8bit FYI, we noticed the below changes on commit 05bfb65f52cbdabe26ebb629959416a6cffb034d ("sched: Remove a wake_affine() condition") testbox/testcase/testparams: ivb42/thrulay/performance-300s afdeee0510db918b 05bfb65f52cbdabe26ebb62995 ---------------- -------------------------- %stddev %change %stddev \ | \ 37071 ± 1% -5.2% 35155 ± 1% thrulay.throughput 9 ± 39% +294.4% 35 ± 45% sched_debug.cpu#41.cpu_load[4] 127 ± 43% +199.0% 380 ± 33% sched_debug.cpu#30.curr->pid 89726 ± 35% +249.9% 313930 ± 40% sched_debug.cpu#12.sched_goidle 180377 ± 34% +248.9% 629297 ± 40% sched_debug.cpu#12.nr_switches 186401 ± 33% +239.4% 632605 ± 39% sched_debug.cpu#12.sched_count 467 ± 9% -51.9% 224 ± 46% sched_debug.cfs_rq[27]:/.tg_load_contrib 73 ± 13% -58.6% 30 ± 41% sched_debug.cpu#2.cpu_load[1] 97 ± 28% -59.1% 39 ± 47% sched_debug.cpu#11.load 30 ± 45% +86.1% 56 ± 26% sched_debug.cpu#9.cpu_load[2] 122 ± 37% -50.9% 60 ± 46% sched_debug.cpu#1.cpu_load[1] 16 ± 38% +100.0% 32 ± 31% sched_debug.cfs_rq[41]:/.tg_runnable_contrib 782 ± 34% +93.8% 1517 ± 29% sched_debug.cfs_rq[41]:/.avg->runnable_avg_sum 445 ± 31% -43.3% 252 ± 35% sched_debug.cpu#11.curr->pid 5983 ± 11% +106.3% 12342 ± 12% sched_debug.cfs_rq[12]:/.exec_clock 53 ± 24% -38.5% 32 ± 21% sched_debug.cpu#27.load 1636 ± 24% -42.9% 934 ± 22% sched_debug.cpu#15.curr->pid 285 ± 48% -44.8% 157 ± 33% sched_debug.cpu#26.curr->pid 8138 ± 9% +96.5% 15989 ± 11% sched_debug.cfs_rq[12]:/.min_vruntime 174 ± 26% -46.4% 93 ± 25% sched_debug.cpu#15.load 55 ± 39% +49.8% 82 ± 28% sched_debug.cfs_rq[35]:/.tg_load_contrib 47 ± 22% +82.1% 86 ± 28% sched_debug.cpu#6.cpu_load[2] 26 ± 22% -45.3% 14 ± 28% numa-numastat.node1.other_node 90 ± 24% -39.7% 54 ± 19% sched_debug.cpu#2.cpu_load[3] 24 ± 37% +76.5% 43 ± 6% sched_debug.cpu#32.cpu_load[4] 107188 ± 22% +46.3% 156809 ± 18% sched_debug.cpu#32.sched_count 409 ± 12% +54.5% 633 ± 34% sched_debug.cpu#11.ttwu_local 131 ± 27% -43.5% 74 ± 39% sched_debug.cpu#1.cpu_load[2] 247 ± 32% +64.1% 406 ± 29% sched_debug.cpu#2.curr->pid 89 ± 29% -55.3% 39 ± 47% sched_debug.cfs_rq[11]:/.load 83 ± 16% -50.7% 41 ± 26% sched_debug.cpu#2.cpu_load[2] 194662 ± 18% +49.5% 290986 ± 10% sched_debug.cpu#8.sched_count 24 ± 22% +75.5% 43 ± 25% sched_debug.cpu#31.cpu_load[1] 28 ± 46% +57.5% 44 ± 15% sched_debug.cpu#29.cpu_load[4] 70637 ± 23% +34.4% 94908 ± 17% sched_debug.cpu#27.ttwu_count 26 ± 40% +62.5% 42 ± 15% sched_debug.cpu#32.cpu_load[3] 65 ± 20% -30.2% 45 ± 19% sched_debug.cfs_rq[26]:/.tg_runnable_contrib 3044 ± 20% -29.7% 2139 ± 19% sched_debug.cfs_rq[26]:/.avg->runnable_avg_sum 28 ± 6% -33.0% 19 ± 16% sched_debug.cfs_rq[39]:/.tg_runnable_contrib 1357 ± 6% -32.5% 915 ± 17% sched_debug.cfs_rq[39]:/.avg->runnable_avg_sum 277 ± 14% -38.6% 170 ± 18% sched_debug.cfs_rq[40]:/.runnable_load_avg 279 ± 14% -39.1% 170 ± 18% sched_debug.cfs_rq[40]:/.load 575205 ± 11% +29.6% 745663 ± 10% sched_debug.cpu#11.avg_idle 151626 ± 19% +17.5% 178195 ± 13% sched_debug.cpu#3.ttwu_count 349553 ± 6% +33.4% 466210 ± 11% sched_debug.cpu#0.ttwu_count 133 ± 5% -29.6% 94 ± 26% sched_debug.cpu#40.cpu_load[3] 3767 ± 16% -28.8% 2680 ± 15% sched_debug.cpu#40.curr->pid 279 ± 14% -25.3% 209 ± 9% sched_debug.cpu#40.load 39 ± 8% -24.7% 29 ± 7% sched_debug.cfs_rq[15]:/.tg_runnable_contrib 1855 ± 7% -24.0% 1410 ± 6% sched_debug.cfs_rq[15]:/.avg->runnable_avg_sum 309 ± 7% -32.9% 207 ± 20% sched_debug.cpu#40.cpu_load[0] 213 ± 5% -32.4% 144 ± 22% sched_debug.cpu#40.cpu_load[2] 602662 ± 11% +20.9% 728740 ± 7% sched_debug.cpu#30.avg_idle 84865 ± 16% +26.5% 107350 ± 8% sched_debug.cpu#26.ttwu_count 285 ± 6% -34.0% 188 ± 20% sched_debug.cpu#40.cpu_load[1] 178498 ± 12% +21.2% 216368 ± 12% sched_debug.cpu#2.ttwu_count 5368 ± 9% +14.5% 6147 ± 9% sched_debug.cfs_rq[28]:/.exec_clock 229046 ± 6% -10.9% 204016 ± 7% sched_debug.cpu#8.ttwu_count 716125 ± 9% +22.4% 876793 ± 4% sched_debug.cpu#14.avg_idle 921 ± 4% +15.3% 1062 ± 5% sched_debug.cpu#25.ttwu_local 628697 ± 12% +22.5% 769882 ± 8% sched_debug.cpu#1.avg_idle 123795 ± 7% -13.6% 106992 ± 9% sched_debug.cpu#32.ttwu_count 10875 ± 4% -16.5% 9083 ± 8% sched_debug.cfs_rq[35]:/.min_vruntime 5103 ± 9% -16.2% 4277 ± 10% sched_debug.cfs_rq[40]:/.min_vruntime 86 ± 6% -13.7% 74 ± 11% sched_debug.cpu#44.ttwu_local 538474 ± 13% +27.6% 686910 ± 7% sched_debug.cpu#15.avg_idle 223 ± 4% +16.4% 260 ± 6% sched_debug.cpu#28.ttwu_local 33784 ± 5% -15.1% 28679 ± 11% cpuidle.C1E-IVT.usage 2764 ± 6% -20.6% 2193 ± 20% sched_debug.cfs_rq[20]:/.min_vruntime 681 ± 19% -19.1% 551 ± 6% cpuidle.POLL.usage 18925 ± 9% +15.6% 21877 ± 3% sched_debug.cfs_rq[0]:/.exec_clock 559454 ± 13% +21.3% 678413 ± 6% sched_debug.cpu#27.avg_idle 49536 ± 3% -10.2% 44495 ± 1% sched_debug.cpu#15.nr_load_updates 17570 ± 6% -17.5% 14492 ± 10% sched_debug.cfs_rq[11]:/.min_vruntime 57206 ± 1% -7.6% 52840 ± 2% sched_debug.cpu#7.nr_load_updates 51547 ± 1% -8.0% 47418 ± 3% sched_debug.cpu#26.nr_load_updates 43519 ± 1% -9.2% 39535 ± 1% sched_debug.cpu#43.nr_load_updates 50591 ± 1% -8.6% 46252 ± 2% sched_debug.cpu#35.nr_load_updates 45642 ± 1% -10.1% 41051 ± 2% sched_debug.cpu#23.nr_load_updates 46023 ± 2% -9.0% 41872 ± 1% sched_debug.cpu#19.nr_load_updates 3.42 ± 1% +9.8% 3.75 ± 2% turbostat.RAM_W 58859 ± 3% +5.9% 62353 ± 1% vmstat.system.cs 269 ± 2% +3.8% 279 ± 0% time.system_time 93 ± 1% +3.5% 96 ± 0% time.percent_of_cpu_this_job_got ivb42: Ivytown Ivy Bridge-EP Memory: 64G thrulay.throughput 44000 ++-*----------------------------------------------------------------+ |..: | 42000 *+ : .*..*. .*. | | : *.*. *..*. *..* | | :.. + *. | 40000 ++ * *.. + *.. * | | + *.*.. .. : | 38000 ++ * * : .*.. | | *. .*..*.* | 36000 ++ O * | | O O O O O O O O O O O O O O O O O O | 34000 ++ O O O O O | | O O | 32000 ++-------------------O----------------------------------------------+ [*] bisect-good sample [O] bisect-bad sample To reproduce: apt-get install ruby ruby-oj git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git cd lkp-tests bin/setup-local job.yaml # the job file attached in this email bin/run-local job.yaml 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. Thanks, Huang, Ying --=-rA/T2kpl1mnz9Vq2/58p Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="job.yaml" Content-Transfer-Encoding: 7bit --- testcase: thrulay default_monitors: wait: pre-test uptime: iostat: vmstat: numa-numastat: numa-vmstat: numa-meminfo: proc-vmstat: proc-stat: meminfo: slabinfo: interrupts: lock_stat: latency_stats: softirqs: bdi_dev_mapping: diskstats: cpuidle: cpufreq: turbostat: sched_debug: interval: 10 pmeter: default_watchdogs: watch-oom: watchdog: cpufreq_governor: - performance commit: b2776bf7149bddd1f4161f14f79520f17fc1d71d model: Ivytown Ivy Bridge-EP nr_cpu: 48 memory: 64G rootfs: debian-x86_64.cgz runtime: 300s thrulay: testbox: ivb42 tbox_group: ivb42 kconfig: x86_64-rhel enqueue_time: 2014-12-08 05:18:17.151038272 +08:00 head_commit: d273c3193b966e6ecdc5948b3d86efb8514ee335 base_commit: 009d0431c3914de64666bec0d350e54fdd59df6a branch: internal-eywa/master kernel: "/kernel/x86_64-rhel/b2776bf7149bddd1f4161f14f79520f17fc1d71d/vmlinuz-3.18.0-gb2776bf" user: lkp queue: cyclic result_root: "/result/ivb42/thrulay/performance-300s/debian-x86_64.cgz/x86_64-rhel/b2776bf7149bddd1f4161f14f79520f17fc1d71d/0" job_file: "/lkp/scheduled/ivb42/cyclic_thrulay-performance-300s-debian-x86_64.cgz-x86_64-rhel-BASE-b2776bf7149bddd1f4161f14f79520f17fc1d71d-0.yaml" dequeue_time: 2014-12-09 09:16:04.465533630 +08:00 job_state: finished loadavg: 1.11 0.89 0.42 1/410 10159 start_time: '1418087801' end_time: '1418088102' version: "/lkp/lkp/.src-20141206-060219" --=-rA/T2kpl1mnz9Vq2/58p Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="reproduce" Content-Transfer-Encoding: 7bit echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu1/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu10/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu11/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu12/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu13/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu14/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu15/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu16/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu17/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu18/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu19/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu2/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu20/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu21/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu22/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu23/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu24/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu25/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu26/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu27/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu28/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu29/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu3/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu30/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu31/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu32/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu33/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu34/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu35/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu36/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu37/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu38/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu39/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu4/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu40/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu41/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu42/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu43/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu44/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu45/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu46/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu47/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu5/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu6/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu7/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu8/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu9/cpufreq/scaling_governor thrulayd thrulay -t 300 127.0.0.1 --=-rA/T2kpl1mnz9Vq2/58p Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable _______________________________________________ LKP mailing list LKP@linux.intel.com =0D --=-rA/T2kpl1mnz9Vq2/58p-- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/