All of lore.kernel.org
 help / color / mirror / Atom feed
From: Fengguang Wu <fengguang.wu@intel.com>
To: lkp@lists.01.org
Subject: [sched/balance] 815296e0446: -71.2% cpuidle.C3-SNB.time
Date: Tue, 04 Mar 2014 09:58:45 +0800	[thread overview]
Message-ID: <20140304015845.GA12265@localhost> (raw)

[-- Attachment #1: Type: text/plain, Size: 8298 bytes --]

Alex,

FYI, we noticed the below changes on commit

https://github.com/alexshi/power-scheduling.git single-balance
815296e0446ff6c405ef647082024ce3d8183e10 ("sched: unify imbalance bias for target group")

test case: lkp-snb01/micro/aim7/compute

bf0607d57b0b3ef  815296e0446ff6c405ef64708  
---------------  -------------------------  
    465050 ~ 9%     -71.2%     134141 ~16%   cpuidle.C3-SNB.time
     10109 ~33%     -63.0%       3743 ~25%   sched_debug.cfs_rq[20]:/.min_vruntime
      7163 ~31%     -63.2%       2638 ~22%   sched_debug.cfs_rq[20]:/.MIN_vruntime
      7166 ~31%     -63.1%       2641 ~22%   sched_debug.cfs_rq[20]:/.max_vruntime
      1722 ~10%     -34.7%       1124 ~27%   sched_debug.cfs_rq[13]:/.MIN_vruntime
      1725 ~10%     -34.6%       1127 ~27%   sched_debug.cfs_rq[13]:/.max_vruntime
      7774 ~18%     +47.0%      11430 ~22%   sched_debug.cfs_rq[9]:/.runnable_load_avg
      8117 ~18%     +47.2%      11946 ~20%   sched_debug.cfs_rq[9]:/.load
      8106 ~18%     +47.4%      11946 ~20%   sched_debug.cpu#9.load
      7787 ~18%     +47.1%      11457 ~22%   sched_debug.cpu#9.cpu_load
      7319 ~23%     +42.4%      10420 ~21%   sched_debug.cpu#30.cpu_load
      7287 ~23%     +42.8%      10404 ~21%   sched_debug.cfs_rq[30]:/.runnable_load_avg
      7757 ~19%     +58.1%      12268 ~31%   sched_debug.cfs_rq[26]:/.tg_load_contrib
      7821 ~21%     +52.2%      11904 ~24%   sched_debug.cpu#11.cpu_load
      7956 ~18%     +49.0%      11856 ~24%   sched_debug.cfs_rq[11]:/.runnable_load_avg
      1722 ~16%     -42.6%        989 ~24%   sched_debug.cfs_rq[6]:/.MIN_vruntime
      1726 ~16%     -42.5%        991 ~24%   sched_debug.cfs_rq[6]:/.max_vruntime
      8357 ~15%     +44.4%      12068 ~19%   sched_debug.cfs_rq[9]:/.tg_load_contrib
      8513 ~15%     +48.6%      12648 ~22%   sched_debug.cfs_rq[11]:/.tg_load_contrib
      2050 ~19%     -34.7%       1339 ~24%   sched_debug.cfs_rq[6]:/.min_vruntime
      7278 ~16%     +46.6%      10667 ~21%   sched_debug.cpu#25.cpu_load
         7 ~20%     +48.6%         11 ~19%   sched_debug.cpu#9.nr_running
         7 ~20%     +48.6%         11 ~19%   sched_debug.cfs_rq[9]:/.nr_running
      7285 ~16%     +46.0%      10639 ~21%   sched_debug.cfs_rq[25]:/.runnable_load_avg
      8495 ~18%     +35.5%      11513 ~19%   sched_debug.cpu#14.load
      8489 ~18%     +35.6%      11513 ~19%   sched_debug.cfs_rq[14]:/.load
      7985 ~24%     +37.9%      11015 ~19%   sched_debug.cpu#12.cpu_load
      7983 ~25%     +38.3%      11043 ~20%   sched_debug.cfs_rq[12]:/.runnable_load_avg
      7123 ~15%     +52.4%      10853 ~22%   sched_debug.cfs_rq[24]:/.load
      1671 ~10%     -36.6%       1059 ~24%   sched_debug.cfs_rq[7]:/.MIN_vruntime
      7128 ~15%     +52.2%      10853 ~22%   sched_debug.cpu#24.load
      1674 ~10%     -36.6%       1062 ~24%   sched_debug.cfs_rq[7]:/.max_vruntime
      7997 ~13%     +48.2%      11852 ~20%   sched_debug.cfs_rq[8]:/.tg_load_contrib
      2039 ~15%     -31.0%       1408 ~19%   sched_debug.cfs_rq[7]:/.min_vruntime
      8556 ~22%     +38.2%      11821 ~18%   sched_debug.cfs_rq[12]:/.tg_load_contrib
       952 ~12%     +59.6%       1520 ~ 6%   cpuidle.C1E-SNB.usage
      7553 ~14%     +49.0%      11253 ~21%   sched_debug.cfs_rq[24]:/.tg_load_contrib
      2013 ~11%     -27.5%       1459 ~17%   sched_debug.cfs_rq[13]:/.min_vruntime
       431 ~21%     +68.8%        727 ~26%   sched_debug.cfs_rq[6]:/.blocked_load_avg
      8512 ~10%     +31.5%      11197 ~14%   sched_debug.cfs_rq[16]:/.tg_load_contrib
      9269 ~18%     +21.2%      11234 ~12%   sched_debug.cfs_rq[6]:/.tg_load_contrib
      7816 ~ 9%     +29.7%      10139 ~15%   sched_debug.cpu#22.cpu_load
      8023 ~ 5%     +38.9%      11146 ~12%   sched_debug.cfs_rq[7]:/.runnable_load_avg
      8054 ~ 6%     +38.5%      11156 ~11%   sched_debug.cpu#7.cpu_load
      2255 ~35%     -44.4%       1253 ~28%   sched_debug.cfs_rq[3]:/.MIN_vruntime
      3.46 ~ 9%     -24.4%       2.61 ~ 9%   sched_debug.cfs_rq[6]:/.spread
      2258 ~34%     -44.4%       1256 ~28%   sched_debug.cfs_rq[3]:/.max_vruntime
      7752 ~ 9%     +30.2%      10091 ~15%   sched_debug.cfs_rq[22]:/.runnable_load_avg
      8579 ~ 6%     +37.4%      11791 ~11%   sched_debug.cfs_rq[7]:/.tg_load_contrib
      9337 ~18%     +17.7%      10992 ~13%   sched_debug.cpu#6.load
      9337 ~18%     +17.7%      10992 ~13%   sched_debug.cfs_rq[6]:/.load
      8499 ~ 6%     +37.1%      11654 ~10%   sched_debug.cpu#7.load
      8499 ~ 6%     +37.1%      11654 ~10%   sched_debug.cfs_rq[7]:/.load
         7 ~ 5%     +38.5%         10 ~10%   sched_debug.cpu#7.nr_running
         7 ~ 5%     +38.5%         10 ~10%   sched_debug.cfs_rq[7]:/.nr_running
        45 ~23%     -38.4%         28 ~33%   sched_debug.cpu#13.nr_uninterruptible
    122137 ~10%     +15.0%     140407 ~11%   numa-vmstat.node1.nr_active_anon
    121019 ~10%     +14.8%     138944 ~11%   numa-vmstat.node1.nr_anon_pages
    545505 ~ 9%     +14.4%     623974 ~11%   numa-meminfo.node1.Active
      4788 ~ 6%     +24.6%       5967 ~12%   sched_debug.cpu#19.nr_switches
   1183156 ~10%      +7.8%    1276020 ~10%   numa-meminfo.node1.MemUsed
      8845 ~ 8%     +27.6%      11285 ~ 7%   sched_debug.cfs_rq[23]:/.tg_load_contrib
      8338 ~ 8%     +43.9%      11997 ~20%   sched_debug.cpu#23.load
      8322 ~ 8%     +44.2%      11997 ~20%   sched_debug.cfs_rq[23]:/.load
         7 ~10%     +51.4%         11 ~22%   sched_debug.cfs_rq[23]:/.nr_running
         7 ~10%     +51.4%         11 ~22%   sched_debug.cpu#23.nr_running
      5982 ~11%     -18.4%       4878 ~ 5%   sched_debug.cpu#20.nr_switches
      5145 ~ 4%     -15.7%       4335 ~ 7%   sched_debug.cpu#13.nr_switches
     10354 ~15%     +24.9%      12936 ~ 9%   sched_debug.cfs_rq[25]:/.tg_load_contrib
      3.20 ~ 4%     -15.2%       2.72 ~ 3%   sched_debug.cfs_rq[23]:/.spread
      6547 ~ 7%     -15.9%       5509 ~ 5%   slabinfo.shmem_inode_cache.num_objs
    250366 ~ 3%     +12.9%     282665 ~ 4%   proc-vmstat.nr_active_anon
    248251 ~ 3%     +12.6%     279447 ~ 4%   proc-vmstat.nr_anon_pages
   1011621 ~ 2%     +11.6%    1128719 ~ 4%   meminfo.Active(anon)
      6506 ~ 7%     -15.4%       5507 ~ 5%   slabinfo.shmem_inode_cache.active_objs
   1003281 ~ 2%     +11.2%    1116144 ~ 3%   meminfo.AnonPages
      4011 ~ 4%     +10.3%       4424 ~ 6%   sched_debug.cpu#7.nr_switches
   1132480 ~ 2%     +10.3%    1249495 ~ 3%   meminfo.Active
      6293 ~ 4%      +8.9%       6852 ~ 5%   slabinfo.kmalloc-128.active_objs
      3.29 ~ 6%      -8.4%       3.01 ~ 7%   sched_debug.cfs_rq[27]:/.spread
      4272 ~ 2%      -8.0%       3928 ~ 3%   sched_debug.cpu#8.curr->pid
      6421 ~ 3%      +7.3%       6891 ~ 4%   slabinfo.kmalloc-128.num_objs
     14672 ~ 1%     +19.0%      17462 ~ 3%   time.voluntary_context_switches
      6073 ~ 2%      +5.2%       6387 ~ 3%   vmstat.system.cs
     22.49 ~ 0%      +0.7%      22.65 ~ 0%   boottime.dhcp

                           time.voluntary_context_switches

   22000 ++-----------------------------------------------------------------+
         O           O                                                      |
   21000 ++                  O  O                 O     O                   |
   20000 ++    O  O                O  O  O                                  |
         |  O             O                    O     O                      |
   19000 ++             O                   O                               |
         |                                                               O  |
   18000 ++                                                O                O
         |                                                   O     O        |
   17000 ++                                                           O     |
   16000 ++                                                     O           |
         |                                                                  |
   15000 ++                  *..            *..                             |
         *..*..*..*..*..*. ..   *..*..*.. ..   *..*..*..*                   |
   14000 ++---------------*--------------*----------------------------------+

Thanks,
Fengguang

WARNING: multiple messages have this Message-ID (diff)
From: Fengguang Wu <fengguang.wu@intel.com>
To: Alex Shi <alex.shi@linaro.org>
Cc: LKML <linux-kernel@vger.kernel.org>, lkp@01.org
Subject: [sched/balance] 815296e0446: -71.2% cpuidle.C3-SNB.time
Date: Tue, 4 Mar 2014 09:58:45 +0800	[thread overview]
Message-ID: <20140304015845.GA12265@localhost> (raw)

Alex,

FYI, we noticed the below changes on commit

https://github.com/alexshi/power-scheduling.git single-balance
815296e0446ff6c405ef647082024ce3d8183e10 ("sched: unify imbalance bias for target group")

test case: lkp-snb01/micro/aim7/compute

bf0607d57b0b3ef  815296e0446ff6c405ef64708  
---------------  -------------------------  
    465050 ~ 9%     -71.2%     134141 ~16%   cpuidle.C3-SNB.time
     10109 ~33%     -63.0%       3743 ~25%   sched_debug.cfs_rq[20]:/.min_vruntime
      7163 ~31%     -63.2%       2638 ~22%   sched_debug.cfs_rq[20]:/.MIN_vruntime
      7166 ~31%     -63.1%       2641 ~22%   sched_debug.cfs_rq[20]:/.max_vruntime
      1722 ~10%     -34.7%       1124 ~27%   sched_debug.cfs_rq[13]:/.MIN_vruntime
      1725 ~10%     -34.6%       1127 ~27%   sched_debug.cfs_rq[13]:/.max_vruntime
      7774 ~18%     +47.0%      11430 ~22%   sched_debug.cfs_rq[9]:/.runnable_load_avg
      8117 ~18%     +47.2%      11946 ~20%   sched_debug.cfs_rq[9]:/.load
      8106 ~18%     +47.4%      11946 ~20%   sched_debug.cpu#9.load
      7787 ~18%     +47.1%      11457 ~22%   sched_debug.cpu#9.cpu_load
      7319 ~23%     +42.4%      10420 ~21%   sched_debug.cpu#30.cpu_load
      7287 ~23%     +42.8%      10404 ~21%   sched_debug.cfs_rq[30]:/.runnable_load_avg
      7757 ~19%     +58.1%      12268 ~31%   sched_debug.cfs_rq[26]:/.tg_load_contrib
      7821 ~21%     +52.2%      11904 ~24%   sched_debug.cpu#11.cpu_load
      7956 ~18%     +49.0%      11856 ~24%   sched_debug.cfs_rq[11]:/.runnable_load_avg
      1722 ~16%     -42.6%        989 ~24%   sched_debug.cfs_rq[6]:/.MIN_vruntime
      1726 ~16%     -42.5%        991 ~24%   sched_debug.cfs_rq[6]:/.max_vruntime
      8357 ~15%     +44.4%      12068 ~19%   sched_debug.cfs_rq[9]:/.tg_load_contrib
      8513 ~15%     +48.6%      12648 ~22%   sched_debug.cfs_rq[11]:/.tg_load_contrib
      2050 ~19%     -34.7%       1339 ~24%   sched_debug.cfs_rq[6]:/.min_vruntime
      7278 ~16%     +46.6%      10667 ~21%   sched_debug.cpu#25.cpu_load
         7 ~20%     +48.6%         11 ~19%   sched_debug.cpu#9.nr_running
         7 ~20%     +48.6%         11 ~19%   sched_debug.cfs_rq[9]:/.nr_running
      7285 ~16%     +46.0%      10639 ~21%   sched_debug.cfs_rq[25]:/.runnable_load_avg
      8495 ~18%     +35.5%      11513 ~19%   sched_debug.cpu#14.load
      8489 ~18%     +35.6%      11513 ~19%   sched_debug.cfs_rq[14]:/.load
      7985 ~24%     +37.9%      11015 ~19%   sched_debug.cpu#12.cpu_load
      7983 ~25%     +38.3%      11043 ~20%   sched_debug.cfs_rq[12]:/.runnable_load_avg
      7123 ~15%     +52.4%      10853 ~22%   sched_debug.cfs_rq[24]:/.load
      1671 ~10%     -36.6%       1059 ~24%   sched_debug.cfs_rq[7]:/.MIN_vruntime
      7128 ~15%     +52.2%      10853 ~22%   sched_debug.cpu#24.load
      1674 ~10%     -36.6%       1062 ~24%   sched_debug.cfs_rq[7]:/.max_vruntime
      7997 ~13%     +48.2%      11852 ~20%   sched_debug.cfs_rq[8]:/.tg_load_contrib
      2039 ~15%     -31.0%       1408 ~19%   sched_debug.cfs_rq[7]:/.min_vruntime
      8556 ~22%     +38.2%      11821 ~18%   sched_debug.cfs_rq[12]:/.tg_load_contrib
       952 ~12%     +59.6%       1520 ~ 6%   cpuidle.C1E-SNB.usage
      7553 ~14%     +49.0%      11253 ~21%   sched_debug.cfs_rq[24]:/.tg_load_contrib
      2013 ~11%     -27.5%       1459 ~17%   sched_debug.cfs_rq[13]:/.min_vruntime
       431 ~21%     +68.8%        727 ~26%   sched_debug.cfs_rq[6]:/.blocked_load_avg
      8512 ~10%     +31.5%      11197 ~14%   sched_debug.cfs_rq[16]:/.tg_load_contrib
      9269 ~18%     +21.2%      11234 ~12%   sched_debug.cfs_rq[6]:/.tg_load_contrib
      7816 ~ 9%     +29.7%      10139 ~15%   sched_debug.cpu#22.cpu_load
      8023 ~ 5%     +38.9%      11146 ~12%   sched_debug.cfs_rq[7]:/.runnable_load_avg
      8054 ~ 6%     +38.5%      11156 ~11%   sched_debug.cpu#7.cpu_load
      2255 ~35%     -44.4%       1253 ~28%   sched_debug.cfs_rq[3]:/.MIN_vruntime
      3.46 ~ 9%     -24.4%       2.61 ~ 9%   sched_debug.cfs_rq[6]:/.spread
      2258 ~34%     -44.4%       1256 ~28%   sched_debug.cfs_rq[3]:/.max_vruntime
      7752 ~ 9%     +30.2%      10091 ~15%   sched_debug.cfs_rq[22]:/.runnable_load_avg
      8579 ~ 6%     +37.4%      11791 ~11%   sched_debug.cfs_rq[7]:/.tg_load_contrib
      9337 ~18%     +17.7%      10992 ~13%   sched_debug.cpu#6.load
      9337 ~18%     +17.7%      10992 ~13%   sched_debug.cfs_rq[6]:/.load
      8499 ~ 6%     +37.1%      11654 ~10%   sched_debug.cpu#7.load
      8499 ~ 6%     +37.1%      11654 ~10%   sched_debug.cfs_rq[7]:/.load
         7 ~ 5%     +38.5%         10 ~10%   sched_debug.cpu#7.nr_running
         7 ~ 5%     +38.5%         10 ~10%   sched_debug.cfs_rq[7]:/.nr_running
        45 ~23%     -38.4%         28 ~33%   sched_debug.cpu#13.nr_uninterruptible
    122137 ~10%     +15.0%     140407 ~11%   numa-vmstat.node1.nr_active_anon
    121019 ~10%     +14.8%     138944 ~11%   numa-vmstat.node1.nr_anon_pages
    545505 ~ 9%     +14.4%     623974 ~11%   numa-meminfo.node1.Active
      4788 ~ 6%     +24.6%       5967 ~12%   sched_debug.cpu#19.nr_switches
   1183156 ~10%      +7.8%    1276020 ~10%   numa-meminfo.node1.MemUsed
      8845 ~ 8%     +27.6%      11285 ~ 7%   sched_debug.cfs_rq[23]:/.tg_load_contrib
      8338 ~ 8%     +43.9%      11997 ~20%   sched_debug.cpu#23.load
      8322 ~ 8%     +44.2%      11997 ~20%   sched_debug.cfs_rq[23]:/.load
         7 ~10%     +51.4%         11 ~22%   sched_debug.cfs_rq[23]:/.nr_running
         7 ~10%     +51.4%         11 ~22%   sched_debug.cpu#23.nr_running
      5982 ~11%     -18.4%       4878 ~ 5%   sched_debug.cpu#20.nr_switches
      5145 ~ 4%     -15.7%       4335 ~ 7%   sched_debug.cpu#13.nr_switches
     10354 ~15%     +24.9%      12936 ~ 9%   sched_debug.cfs_rq[25]:/.tg_load_contrib
      3.20 ~ 4%     -15.2%       2.72 ~ 3%   sched_debug.cfs_rq[23]:/.spread
      6547 ~ 7%     -15.9%       5509 ~ 5%   slabinfo.shmem_inode_cache.num_objs
    250366 ~ 3%     +12.9%     282665 ~ 4%   proc-vmstat.nr_active_anon
    248251 ~ 3%     +12.6%     279447 ~ 4%   proc-vmstat.nr_anon_pages
   1011621 ~ 2%     +11.6%    1128719 ~ 4%   meminfo.Active(anon)
      6506 ~ 7%     -15.4%       5507 ~ 5%   slabinfo.shmem_inode_cache.active_objs
   1003281 ~ 2%     +11.2%    1116144 ~ 3%   meminfo.AnonPages
      4011 ~ 4%     +10.3%       4424 ~ 6%   sched_debug.cpu#7.nr_switches
   1132480 ~ 2%     +10.3%    1249495 ~ 3%   meminfo.Active
      6293 ~ 4%      +8.9%       6852 ~ 5%   slabinfo.kmalloc-128.active_objs
      3.29 ~ 6%      -8.4%       3.01 ~ 7%   sched_debug.cfs_rq[27]:/.spread
      4272 ~ 2%      -8.0%       3928 ~ 3%   sched_debug.cpu#8.curr->pid
      6421 ~ 3%      +7.3%       6891 ~ 4%   slabinfo.kmalloc-128.num_objs
     14672 ~ 1%     +19.0%      17462 ~ 3%   time.voluntary_context_switches
      6073 ~ 2%      +5.2%       6387 ~ 3%   vmstat.system.cs
     22.49 ~ 0%      +0.7%      22.65 ~ 0%   boottime.dhcp

                           time.voluntary_context_switches

   22000 ++-----------------------------------------------------------------+
         O           O                                                      |
   21000 ++                  O  O                 O     O                   |
   20000 ++    O  O                O  O  O                                  |
         |  O             O                    O     O                      |
   19000 ++             O                   O                               |
         |                                                               O  |
   18000 ++                                                O                O
         |                                                   O     O        |
   17000 ++                                                           O     |
   16000 ++                                                     O           |
         |                                                                  |
   15000 ++                  *..            *..                             |
         *..*..*..*..*..*. ..   *..*..*.. ..   *..*..*..*                   |
   14000 ++---------------*--------------*----------------------------------+

Thanks,
Fengguang

             reply	other threads:[~2014-03-04  1:58 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-03-04  1:58 Fengguang Wu [this message]
2014-03-04  1:58 ` [sched/balance] 815296e0446: -71.2% cpuidle.C3-SNB.time Fengguang Wu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140304015845.GA12265@localhost \
    --to=fengguang.wu@intel.com \
    --cc=lkp@lists.01.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.