All of lore.kernel.org
 help / color / mirror / Atom feed
* [libata/ahci] 8a4aeec8d2d: +138.4% perf-stat.dTLB-store-misses, +37.2% perf-stat.dTLB-load-misses
@ 2014-04-21  7:29 ` Jet Chen
  0 siblings, 0 replies; 6+ messages in thread
From: Jet Chen @ 2014-04-21  7:29 UTC (permalink / raw)
  To: Dan Williams; +Cc: Tejun Heo, LKML, lkp, Fengguang Wu

[-- Attachment #1: Type: text/plain, Size: 2874 bytes --]

HI Dan,

we noticed the below changes on

git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata for-next
commit 8a4aeec8d2d6a3edeffbdfae451cdf05cbf0fefd ("libata/ahci: accommodate tag ordered controllers")

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4
---------------  -------------------------
     88694337 ~39%    +138.4%  2.115e+08 ~46%  TOTAL perf-stat.dTLB-store-misses
       217057 ~ 0%     -31.3%     149221 ~ 3%  TOTAL interrupts.46:PCI-MSI-edge.ahci
    6.995e+08 ~20%     +37.2%  9.598e+08 ~25%  TOTAL perf-stat.dTLB-load-misses
       110302 ~ 0%     -28.9%      78402 ~ 2%  TOTAL interrupts.CAL
    3.168e+08 ~ 9%     +14.5%  3.627e+08 ~10%  TOTAL perf-stat.L1-dcache-prefetches
    2.553e+09 ~12%     +26.5%  3.228e+09 ~11%  TOTAL perf-stat.LLC-loads
    5.815e+08 ~ 6%     +27.3%  7.403e+08 ~11%  TOTAL perf-stat.LLC-stores
    3.662e+09 ~11%     +22.9%  4.501e+09 ~10%  TOTAL perf-stat.L1-dcache-load-misses
    2.155e+10 ~ 1%      +8.3%  2.333e+10 ~ 1%  TOTAL perf-stat.L1-dcache-store-misses
    3.619e+10 ~ 1%      +5.9%  3.832e+10 ~ 2%  TOTAL perf-stat.cache-references
    1.605e+10 ~ 1%      +4.3%  1.674e+10 ~ 1%  TOTAL perf-stat.L1-icache-load-misses
       239691 ~ 7%      -8.4%     219537 ~ 1%  TOTAL interrupts.RES
         3483 ~ 0%      -5.4%       3297 ~ 0%  TOTAL vmstat.system.in
    2.748e+08 ~ 1%      +4.3%  2.865e+08 ~ 0%  TOTAL perf-stat.cache-misses
     98935369 ~ 0%      +4.9%  1.038e+08 ~ 0%  TOTAL perf-stat.LLC-store-misses
          699 ~ 1%      -3.7%        673 ~ 1%  TOTAL iostat.sda.w_await
          698 ~ 1%      -3.7%        672 ~ 1%  TOTAL iostat.sda.await
       203893 ~ 0%      +3.7%     211474 ~ 0%  TOTAL iostat.sda.wkB/s
       203972 ~ 0%      +3.7%     211488 ~ 0%  TOTAL vmstat.io.bo
       618082 ~ 4%      -4.6%     589619 ~ 1%  TOTAL perf-stat.context-switches
    1.432e+12 ~ 1%      +3.0%  1.475e+12 ~ 0%  TOTAL perf-stat.L1-icache-loads
     3.35e+11 ~ 0%      +3.2%  3.456e+11 ~ 0%  TOTAL perf-stat.L1-dcache-stores
    1.486e+12 ~ 0%      +2.8%  1.527e+12 ~ 0%  TOTAL perf-stat.iTLB-loads
    3.006e+11 ~ 0%      +2.6%  3.084e+11 ~ 0%  TOTAL perf-stat.branch-instructions
    1.793e+12 ~ 0%      +2.8%  1.843e+12 ~ 0%  TOTAL perf-stat.cpu-cycles
    3.352e+11 ~ 1%      +2.9%  3.451e+11 ~ 0%  TOTAL perf-stat.dTLB-stores
    2.994e+11 ~ 1%      +3.1%  3.087e+11 ~ 0%  TOTAL perf-stat.branch-loads
     1.49e+12 ~ 0%      +2.9%  1.533e+12 ~ 0%  TOTAL perf-stat.instructions
     5.48e+11 ~ 0%      +2.8%  5.633e+11 ~ 0%  TOTAL perf-stat.dTLB-loads
    2.028e+11 ~ 1%      +2.9%  2.086e+11 ~ 1%  TOTAL perf-stat.bus-cycles
    5.484e+11 ~ 0%      +2.9%  5.644e+11 ~ 0%  TOTAL perf-stat.L1-dcache-loads
    1.829e+12 ~ 0%      +2.7%  1.877e+12 ~ 1%  TOTAL perf-stat.ref-cycles

Legend:
	~XX%    - stddev percent
	[+-]XX% - change percent

Attach full stats changes entries for reference.

Thanks,
Jet





[-- Attachment #2: reproduce --]
[-- Type: text/plain, Size: 453 bytes --]

mkfs -t ext4 -q /dev/sda1
echo 1 > /sys/kernel/debug/tracing/events/writeback/balance_dirty_pages/enable
echo 1 > /sys/kernel/debug/tracing/events/writeback/bdi_dirty_ratelimit/enable
echo 1 > /sys/kernel/debug/tracing/events/writeback/global_dirty_state/enable
echo 1 > /sys/kernel/debug/tracing/events/writeback/writeback_single_inode/enable
mount -t ext4 /dev/sda1 /fs/sda1
dd  if=/dev/zero of=/fs/sda1/zero-1 status=none &
sleep 600
killall -9 dd



[-- Attachment #3: stats_changes --]
[-- Type: text/plain, Size: 11813 bytes --]

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      1.23 ~ 8%     -30.0%       0.86 ~15%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      1.23 ~ 8%     -30.0%       0.86 ~15%  TOTAL perf-profile.cpu-cycles.jbd2_journal_add_journal_head.jbd2_journal_get_write_access.__ext4_journal_get_write_access.ext4_reserve_inode_write.ext4_mark_inode_dirty

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
     56347 ~ 0%     -26.3%      41535 ~ 5%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
     56543 ~ 0%     -32.9%      37934 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    112890 ~ 0%     -29.6%      79469 ~ 2%  TOTAL softirqs.BLOCK

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      0.95 ~12%     -26.0%       0.70 ~ 7%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      0.95 ~12%     -26.0%       0.70 ~ 7%  TOTAL perf-profile.cpu-cycles.jbd2_journal_put_journal_head.__ext4_handle_dirty_metadata.ext4_mark_iloc_dirty.ext4_mark_inode_dirty.ext4_dirty_inode

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      0.95 ~ 5%     -18.2%       0.77 ~24%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      0.95 ~ 5%     -18.2%       0.77 ~24%  TOTAL perf-profile.cpu-cycles.generic_file_aio_write.ext4_file_write.do_sync_write.vfs_write.sys_write

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      2468 ~ 3%     +19.5%       2949 ~ 6%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      2468 ~ 3%     +19.5%       2949 ~ 6%  TOTAL proc-vmstat.kswapd_high_wmark_hit_quickly

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      1.52 ~15%     +18.6%       1.80 ~ 6%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
      1.52 ~15%     +18.6%       1.80 ~ 6%  TOTAL perf-profile.cpu-cycles.write

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
     74703 ~ 3%     +10.8%      82758 ~ 6%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
     74703 ~ 3%     +10.8%      82758 ~ 6%  TOTAL ftrace.balance_dirty_pages.sda.task_ratelimit

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
     71536 ~ 1%     +10.1%      78793 ~ 4%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
     71536 ~ 1%     +10.1%      78793 ~ 4%  TOTAL ftrace.bdi_dirty_ratelimit.sda.task_ratelimit

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
  88694337 ~39%    +138.4%  2.115e+08 ~46%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
  88694337 ~39%    +138.4%  2.115e+08 ~46%  TOTAL perf-stat.dTLB-store-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    108743 ~ 0%     -27.7%      78635 ~ 6%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
    108313 ~ 0%     -34.8%      70585 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    217057 ~ 0%     -31.3%     149221 ~ 3%  TOTAL interrupts.46:PCI-MSI-edge.ahci

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 6.995e+08 ~20%     +37.2%  9.598e+08 ~25%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.995e+08 ~20%     +37.2%  9.598e+08 ~25%  TOTAL perf-stat.dTLB-load-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
     55103 ~ 0%     -25.1%      41273 ~ 4%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
     55198 ~ 0%     -32.7%      37128 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    110302 ~ 0%     -28.9%      78402 ~ 2%  TOTAL interrupts.CAL

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 3.168e+08 ~ 9%     +14.5%  3.627e+08 ~10%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 3.168e+08 ~ 9%     +14.5%  3.627e+08 ~10%  TOTAL perf-stat.L1-dcache-prefetches

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 2.553e+09 ~12%     +26.5%  3.228e+09 ~11%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 2.553e+09 ~12%     +26.5%  3.228e+09 ~11%  TOTAL perf-stat.LLC-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 5.815e+08 ~ 6%     +27.3%  7.403e+08 ~11%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 5.815e+08 ~ 6%     +27.3%  7.403e+08 ~11%  TOTAL perf-stat.LLC-stores

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 3.662e+09 ~11%     +22.9%  4.501e+09 ~10%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 3.662e+09 ~11%     +22.9%  4.501e+09 ~10%  TOTAL perf-stat.L1-dcache-load-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.153e+10 ~ 2%     +12.4%  1.296e+10 ~ 2%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.002e+10 ~ 0%      +3.5%  1.037e+10 ~ 1%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 2.155e+10 ~ 1%      +8.3%  2.333e+10 ~ 1%  TOTAL perf-stat.L1-dcache-store-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 3.619e+10 ~ 1%      +5.9%  3.832e+10 ~ 2%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 3.619e+10 ~ 1%      +5.9%  3.832e+10 ~ 2%  TOTAL perf-stat.cache-references

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.605e+10 ~ 1%      +4.3%  1.674e+10 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.605e+10 ~ 1%      +4.3%  1.674e+10 ~ 1%  TOTAL perf-stat.L1-icache-load-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    102668 ~ 1%      -4.3%      98275 ~ 2%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
    137022 ~10%     -11.5%     121262 ~ 1%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    239691 ~ 7%      -8.4%     219537 ~ 1%  TOTAL interrupts.RES

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      1727 ~ 0%      -4.2%       1654 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      1756 ~ 1%      -6.5%       1642 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
      3483 ~ 0%      -5.4%       3297 ~ 0%  TOTAL vmstat.system.in

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 2.748e+08 ~ 1%      +4.3%  2.865e+08 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 2.748e+08 ~ 1%      +4.3%  2.865e+08 ~ 0%  TOTAL perf-stat.cache-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
  98935369 ~ 0%      +4.9%  1.038e+08 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
  98935369 ~ 0%      +4.9%  1.038e+08 ~ 0%  TOTAL perf-stat.LLC-store-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
       699 ~ 1%      -3.7%        673 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
       699 ~ 1%      -3.7%        673 ~ 1%  TOTAL iostat.sda.w_await

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
       698 ~ 1%      -3.7%        672 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
       698 ~ 1%      -3.7%        672 ~ 1%  TOTAL iostat.sda.await

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    101176 ~ 0%      +3.4%     104666 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
    102716 ~ 0%      +4.0%     106808 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    203893 ~ 0%      +3.7%     211474 ~ 0%  TOTAL iostat.sda.wkB/s

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    101269 ~ 0%      +3.4%     104694 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
    102702 ~ 0%      +4.0%     106793 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    203972 ~ 0%      +3.7%     211488 ~ 0%  TOTAL vmstat.io.bo

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    618082 ~ 4%      -4.6%     589619 ~ 1%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    618082 ~ 4%      -4.6%     589619 ~ 1%  TOTAL perf-stat.context-switches

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 8.267e+11 ~ 1%      +2.5%  8.472e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.053e+11 ~ 0%      +3.8%  6.281e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 1.432e+12 ~ 1%      +3.0%  1.475e+12 ~ 0%  TOTAL perf-stat.L1-icache-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.947e+11 ~ 1%      +2.8%  2.002e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.403e+11 ~ 0%      +3.7%  1.454e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
  3.35e+11 ~ 0%      +3.2%  3.456e+11 ~ 0%  TOTAL perf-stat.L1-dcache-stores

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 8.763e+11 ~ 0%      +2.3%  8.967e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.098e+11 ~ 0%      +3.4%  6.305e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 1.486e+12 ~ 0%      +2.8%  1.527e+12 ~ 0%  TOTAL perf-stat.iTLB-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.778e+11 ~ 0%      +1.7%  1.809e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.228e+11 ~ 0%      +3.9%  1.276e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 3.006e+11 ~ 0%      +2.6%  3.084e+11 ~ 0%  TOTAL perf-stat.branch-instructions

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.117e+12 ~ 0%      +2.7%  1.148e+12 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.754e+11 ~ 0%      +2.9%  6.948e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 1.793e+12 ~ 0%      +2.8%  1.843e+12 ~ 0%  TOTAL perf-stat.cpu-cycles

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.949e+11 ~ 1%      +2.3%  1.994e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.403e+11 ~ 0%      +3.9%  1.457e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 3.352e+11 ~ 1%      +2.9%  3.451e+11 ~ 0%  TOTAL perf-stat.dTLB-stores

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.765e+11 ~ 1%      +2.6%  1.811e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.229e+11 ~ 0%      +3.8%  1.276e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 2.994e+11 ~ 1%      +3.1%  3.087e+11 ~ 0%  TOTAL perf-stat.branch-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 8.788e+11 ~ 0%      +2.3%  8.988e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.114e+11 ~ 0%      +3.8%  6.345e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
  1.49e+12 ~ 0%      +2.9%  1.533e+12 ~ 0%  TOTAL perf-stat.instructions

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 3.279e+11 ~ 0%      +2.5%   3.36e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 2.201e+11 ~ 0%      +3.3%  2.274e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
  5.48e+11 ~ 0%      +2.8%  5.633e+11 ~ 0%  TOTAL perf-stat.dTLB-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.256e+11 ~ 1%      +2.5%  1.287e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
  7.72e+10 ~ 0%      +3.4%  7.984e+10 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 2.028e+11 ~ 1%      +2.9%  2.086e+11 ~ 1%  TOTAL perf-stat.bus-cycles

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
  3.28e+11 ~ 0%      +2.4%   3.36e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 2.204e+11 ~ 0%      +3.6%  2.284e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 5.484e+11 ~ 0%      +2.9%  5.644e+11 ~ 0%  TOTAL perf-stat.L1-dcache-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.132e+12 ~ 1%      +2.4%   1.16e+12 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.962e+11 ~ 0%      +3.0%  7.173e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 1.829e+12 ~ 0%      +2.7%  1.877e+12 ~ 1%  TOTAL perf-stat.ref-cycles


^ permalink raw reply	[flat|nested] 6+ messages in thread

* [libata/ahci] 8a4aeec8d2d: +138.4% perf-stat.dTLB-store-misses, +37.2% perf-stat.dTLB-load-misses
@ 2014-04-21  7:29 ` Jet Chen
  0 siblings, 0 replies; 6+ messages in thread
From: Jet Chen @ 2014-04-21  7:29 UTC (permalink / raw)
  To: lkp

[-- Attachment #1: Type: text/plain, Size: 2928 bytes --]

HI Dan,

we noticed the below changes on

git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata for-next
commit 8a4aeec8d2d6a3edeffbdfae451cdf05cbf0fefd ("libata/ahci: accommodate tag ordered controllers")

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4
---------------  -------------------------
     88694337 ~39%    +138.4%  2.115e+08 ~46%  TOTAL perf-stat.dTLB-store-misses
       217057 ~ 0%     -31.3%     149221 ~ 3%  TOTAL interrupts.46:PCI-MSI-edge.ahci
    6.995e+08 ~20%     +37.2%  9.598e+08 ~25%  TOTAL perf-stat.dTLB-load-misses
       110302 ~ 0%     -28.9%      78402 ~ 2%  TOTAL interrupts.CAL
    3.168e+08 ~ 9%     +14.5%  3.627e+08 ~10%  TOTAL perf-stat.L1-dcache-prefetches
    2.553e+09 ~12%     +26.5%  3.228e+09 ~11%  TOTAL perf-stat.LLC-loads
    5.815e+08 ~ 6%     +27.3%  7.403e+08 ~11%  TOTAL perf-stat.LLC-stores
    3.662e+09 ~11%     +22.9%  4.501e+09 ~10%  TOTAL perf-stat.L1-dcache-load-misses
    2.155e+10 ~ 1%      +8.3%  2.333e+10 ~ 1%  TOTAL perf-stat.L1-dcache-store-misses
    3.619e+10 ~ 1%      +5.9%  3.832e+10 ~ 2%  TOTAL perf-stat.cache-references
    1.605e+10 ~ 1%      +4.3%  1.674e+10 ~ 1%  TOTAL perf-stat.L1-icache-load-misses
       239691 ~ 7%      -8.4%     219537 ~ 1%  TOTAL interrupts.RES
         3483 ~ 0%      -5.4%       3297 ~ 0%  TOTAL vmstat.system.in
    2.748e+08 ~ 1%      +4.3%  2.865e+08 ~ 0%  TOTAL perf-stat.cache-misses
     98935369 ~ 0%      +4.9%  1.038e+08 ~ 0%  TOTAL perf-stat.LLC-store-misses
          699 ~ 1%      -3.7%        673 ~ 1%  TOTAL iostat.sda.w_await
          698 ~ 1%      -3.7%        672 ~ 1%  TOTAL iostat.sda.await
       203893 ~ 0%      +3.7%     211474 ~ 0%  TOTAL iostat.sda.wkB/s
       203972 ~ 0%      +3.7%     211488 ~ 0%  TOTAL vmstat.io.bo
       618082 ~ 4%      -4.6%     589619 ~ 1%  TOTAL perf-stat.context-switches
    1.432e+12 ~ 1%      +3.0%  1.475e+12 ~ 0%  TOTAL perf-stat.L1-icache-loads
     3.35e+11 ~ 0%      +3.2%  3.456e+11 ~ 0%  TOTAL perf-stat.L1-dcache-stores
    1.486e+12 ~ 0%      +2.8%  1.527e+12 ~ 0%  TOTAL perf-stat.iTLB-loads
    3.006e+11 ~ 0%      +2.6%  3.084e+11 ~ 0%  TOTAL perf-stat.branch-instructions
    1.793e+12 ~ 0%      +2.8%  1.843e+12 ~ 0%  TOTAL perf-stat.cpu-cycles
    3.352e+11 ~ 1%      +2.9%  3.451e+11 ~ 0%  TOTAL perf-stat.dTLB-stores
    2.994e+11 ~ 1%      +3.1%  3.087e+11 ~ 0%  TOTAL perf-stat.branch-loads
     1.49e+12 ~ 0%      +2.9%  1.533e+12 ~ 0%  TOTAL perf-stat.instructions
     5.48e+11 ~ 0%      +2.8%  5.633e+11 ~ 0%  TOTAL perf-stat.dTLB-loads
    2.028e+11 ~ 1%      +2.9%  2.086e+11 ~ 1%  TOTAL perf-stat.bus-cycles
    5.484e+11 ~ 0%      +2.9%  5.644e+11 ~ 0%  TOTAL perf-stat.L1-dcache-loads
    1.829e+12 ~ 0%      +2.7%  1.877e+12 ~ 1%  TOTAL perf-stat.ref-cycles

Legend:
	~XX%    - stddev percent
	[+-]XX% - change percent

Attach full stats changes entries for reference.

Thanks,
Jet





[-- Attachment #2: reproduce.ksh --]
[-- Type: text/plain, Size: 453 bytes --]

mkfs -t ext4 -q /dev/sda1
echo 1 > /sys/kernel/debug/tracing/events/writeback/balance_dirty_pages/enable
echo 1 > /sys/kernel/debug/tracing/events/writeback/bdi_dirty_ratelimit/enable
echo 1 > /sys/kernel/debug/tracing/events/writeback/global_dirty_state/enable
echo 1 > /sys/kernel/debug/tracing/events/writeback/writeback_single_inode/enable
mount -t ext4 /dev/sda1 /fs/sda1
dd  if=/dev/zero of=/fs/sda1/zero-1 status=none &
sleep 600
killall -9 dd



[-- Attachment #3: stats_changes.ksh --]
[-- Type: text/plain, Size: 11813 bytes --]

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      1.23 ~ 8%     -30.0%       0.86 ~15%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      1.23 ~ 8%     -30.0%       0.86 ~15%  TOTAL perf-profile.cpu-cycles.jbd2_journal_add_journal_head.jbd2_journal_get_write_access.__ext4_journal_get_write_access.ext4_reserve_inode_write.ext4_mark_inode_dirty

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
     56347 ~ 0%     -26.3%      41535 ~ 5%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
     56543 ~ 0%     -32.9%      37934 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    112890 ~ 0%     -29.6%      79469 ~ 2%  TOTAL softirqs.BLOCK

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      0.95 ~12%     -26.0%       0.70 ~ 7%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      0.95 ~12%     -26.0%       0.70 ~ 7%  TOTAL perf-profile.cpu-cycles.jbd2_journal_put_journal_head.__ext4_handle_dirty_metadata.ext4_mark_iloc_dirty.ext4_mark_inode_dirty.ext4_dirty_inode

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      0.95 ~ 5%     -18.2%       0.77 ~24%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      0.95 ~ 5%     -18.2%       0.77 ~24%  TOTAL perf-profile.cpu-cycles.generic_file_aio_write.ext4_file_write.do_sync_write.vfs_write.sys_write

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      2468 ~ 3%     +19.5%       2949 ~ 6%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      2468 ~ 3%     +19.5%       2949 ~ 6%  TOTAL proc-vmstat.kswapd_high_wmark_hit_quickly

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      1.52 ~15%     +18.6%       1.80 ~ 6%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
      1.52 ~15%     +18.6%       1.80 ~ 6%  TOTAL perf-profile.cpu-cycles.write

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
     74703 ~ 3%     +10.8%      82758 ~ 6%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
     74703 ~ 3%     +10.8%      82758 ~ 6%  TOTAL ftrace.balance_dirty_pages.sda.task_ratelimit

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
     71536 ~ 1%     +10.1%      78793 ~ 4%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
     71536 ~ 1%     +10.1%      78793 ~ 4%  TOTAL ftrace.bdi_dirty_ratelimit.sda.task_ratelimit

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
  88694337 ~39%    +138.4%  2.115e+08 ~46%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
  88694337 ~39%    +138.4%  2.115e+08 ~46%  TOTAL perf-stat.dTLB-store-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    108743 ~ 0%     -27.7%      78635 ~ 6%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
    108313 ~ 0%     -34.8%      70585 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    217057 ~ 0%     -31.3%     149221 ~ 3%  TOTAL interrupts.46:PCI-MSI-edge.ahci

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 6.995e+08 ~20%     +37.2%  9.598e+08 ~25%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.995e+08 ~20%     +37.2%  9.598e+08 ~25%  TOTAL perf-stat.dTLB-load-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
     55103 ~ 0%     -25.1%      41273 ~ 4%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
     55198 ~ 0%     -32.7%      37128 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    110302 ~ 0%     -28.9%      78402 ~ 2%  TOTAL interrupts.CAL

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 3.168e+08 ~ 9%     +14.5%  3.627e+08 ~10%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 3.168e+08 ~ 9%     +14.5%  3.627e+08 ~10%  TOTAL perf-stat.L1-dcache-prefetches

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 2.553e+09 ~12%     +26.5%  3.228e+09 ~11%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 2.553e+09 ~12%     +26.5%  3.228e+09 ~11%  TOTAL perf-stat.LLC-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 5.815e+08 ~ 6%     +27.3%  7.403e+08 ~11%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 5.815e+08 ~ 6%     +27.3%  7.403e+08 ~11%  TOTAL perf-stat.LLC-stores

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 3.662e+09 ~11%     +22.9%  4.501e+09 ~10%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 3.662e+09 ~11%     +22.9%  4.501e+09 ~10%  TOTAL perf-stat.L1-dcache-load-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.153e+10 ~ 2%     +12.4%  1.296e+10 ~ 2%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.002e+10 ~ 0%      +3.5%  1.037e+10 ~ 1%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 2.155e+10 ~ 1%      +8.3%  2.333e+10 ~ 1%  TOTAL perf-stat.L1-dcache-store-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 3.619e+10 ~ 1%      +5.9%  3.832e+10 ~ 2%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 3.619e+10 ~ 1%      +5.9%  3.832e+10 ~ 2%  TOTAL perf-stat.cache-references

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.605e+10 ~ 1%      +4.3%  1.674e+10 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.605e+10 ~ 1%      +4.3%  1.674e+10 ~ 1%  TOTAL perf-stat.L1-icache-load-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    102668 ~ 1%      -4.3%      98275 ~ 2%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
    137022 ~10%     -11.5%     121262 ~ 1%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    239691 ~ 7%      -8.4%     219537 ~ 1%  TOTAL interrupts.RES

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
      1727 ~ 0%      -4.2%       1654 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
      1756 ~ 1%      -6.5%       1642 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
      3483 ~ 0%      -5.4%       3297 ~ 0%  TOTAL vmstat.system.in

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 2.748e+08 ~ 1%      +4.3%  2.865e+08 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 2.748e+08 ~ 1%      +4.3%  2.865e+08 ~ 0%  TOTAL perf-stat.cache-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
  98935369 ~ 0%      +4.9%  1.038e+08 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
  98935369 ~ 0%      +4.9%  1.038e+08 ~ 0%  TOTAL perf-stat.LLC-store-misses

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
       699 ~ 1%      -3.7%        673 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
       699 ~ 1%      -3.7%        673 ~ 1%  TOTAL iostat.sda.w_await

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
       698 ~ 1%      -3.7%        672 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
       698 ~ 1%      -3.7%        672 ~ 1%  TOTAL iostat.sda.await

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    101176 ~ 0%      +3.4%     104666 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
    102716 ~ 0%      +4.0%     106808 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    203893 ~ 0%      +3.7%     211474 ~ 0%  TOTAL iostat.sda.wkB/s

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    101269 ~ 0%      +3.4%     104694 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
    102702 ~ 0%      +4.0%     106793 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    203972 ~ 0%      +3.7%     211488 ~ 0%  TOTAL vmstat.io.bo

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
    618082 ~ 4%      -4.6%     589619 ~ 1%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
    618082 ~ 4%      -4.6%     589619 ~ 1%  TOTAL perf-stat.context-switches

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 8.267e+11 ~ 1%      +2.5%  8.472e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.053e+11 ~ 0%      +3.8%  6.281e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 1.432e+12 ~ 1%      +3.0%  1.475e+12 ~ 0%  TOTAL perf-stat.L1-icache-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.947e+11 ~ 1%      +2.8%  2.002e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.403e+11 ~ 0%      +3.7%  1.454e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
  3.35e+11 ~ 0%      +3.2%  3.456e+11 ~ 0%  TOTAL perf-stat.L1-dcache-stores

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 8.763e+11 ~ 0%      +2.3%  8.967e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.098e+11 ~ 0%      +3.4%  6.305e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 1.486e+12 ~ 0%      +2.8%  1.527e+12 ~ 0%  TOTAL perf-stat.iTLB-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.778e+11 ~ 0%      +1.7%  1.809e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.228e+11 ~ 0%      +3.9%  1.276e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 3.006e+11 ~ 0%      +2.6%  3.084e+11 ~ 0%  TOTAL perf-stat.branch-instructions

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.117e+12 ~ 0%      +2.7%  1.148e+12 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.754e+11 ~ 0%      +2.9%  6.948e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 1.793e+12 ~ 0%      +2.8%  1.843e+12 ~ 0%  TOTAL perf-stat.cpu-cycles

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.949e+11 ~ 1%      +2.3%  1.994e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.403e+11 ~ 0%      +3.9%  1.457e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 3.352e+11 ~ 1%      +2.9%  3.451e+11 ~ 0%  TOTAL perf-stat.dTLB-stores

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.765e+11 ~ 1%      +2.6%  1.811e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 1.229e+11 ~ 0%      +3.8%  1.276e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 2.994e+11 ~ 1%      +3.1%  3.087e+11 ~ 0%  TOTAL perf-stat.branch-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 8.788e+11 ~ 0%      +2.3%  8.988e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.114e+11 ~ 0%      +3.8%  6.345e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
  1.49e+12 ~ 0%      +2.9%  1.533e+12 ~ 0%  TOTAL perf-stat.instructions

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 3.279e+11 ~ 0%      +2.5%   3.36e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 2.201e+11 ~ 0%      +3.3%  2.274e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
  5.48e+11 ~ 0%      +2.8%  5.633e+11 ~ 0%  TOTAL perf-stat.dTLB-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.256e+11 ~ 1%      +2.5%  1.287e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
  7.72e+10 ~ 0%      +3.4%  7.984e+10 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 2.028e+11 ~ 1%      +2.9%  2.086e+11 ~ 1%  TOTAL perf-stat.bus-cycles

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
  3.28e+11 ~ 0%      +2.4%   3.36e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 2.204e+11 ~ 0%      +3.6%  2.284e+11 ~ 0%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 5.484e+11 ~ 0%      +2.9%  5.644e+11 ~ 0%  TOTAL perf-stat.L1-dcache-loads

2cf532f5e67c0cf  8a4aeec8d2d6a3edeffbdfae4  
---------------  -------------------------  
 1.132e+12 ~ 1%      +2.4%   1.16e+12 ~ 1%  bay/micro/dd-write/1HDD-cfq-ext4-1dd
 6.962e+11 ~ 0%      +3.0%  7.173e+11 ~ 1%  bay/micro/dd-write/1HDD-cfq-xfs-1dd
 1.829e+12 ~ 0%      +2.7%  1.877e+12 ~ 1%  TOTAL perf-stat.ref-cycles


^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [libata/ahci] 8a4aeec8d2d: +138.4% perf-stat.dTLB-store-misses, +37.2% perf-stat.dTLB-load-misses
  2014-04-21  7:29 ` Jet Chen
@ 2014-04-22 17:11   ` Dan Williams
  -1 siblings, 0 replies; 6+ messages in thread
From: Dan Williams @ 2014-04-22 17:11 UTC (permalink / raw)
  To: Jet Chen; +Cc: Tejun Heo, LKML, lkp, Fengguang Wu

On Mon, Apr 21, 2014 at 12:29 AM, Jet Chen <jet.chen@intel.com> wrote:
> HI Dan,
>
> we noticed the below changes on
>
> git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata for-next
> commit 8a4aeec8d2d6a3edeffbdfae451cdf05cbf0fefd ("libata/ahci: accommodate
> tag ordered controllers")

Hi, was this on simulated hardware or a real AHCI controller and disk?

It does appear this test noticed increased throughput:

    203893 ~ 0%      +3.7%     211474 ~ 0%  TOTAL iostat.sda.wkB/s

I wonder if ap->last_tag can be moved to a hotter cacheline, but if
throughput goes up I can imagine it throws off the cpu statistics
quite a bit.

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [libata/ahci] 8a4aeec8d2d: +138.4% perf-stat.dTLB-store-misses, +37.2% perf-stat.dTLB-load-misses
@ 2014-04-22 17:11   ` Dan Williams
  0 siblings, 0 replies; 6+ messages in thread
From: Dan Williams @ 2014-04-22 17:11 UTC (permalink / raw)
  To: lkp

[-- Attachment #1: Type: text/plain, Size: 653 bytes --]

On Mon, Apr 21, 2014 at 12:29 AM, Jet Chen <jet.chen@intel.com> wrote:
> HI Dan,
>
> we noticed the below changes on
>
> git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata for-next
> commit 8a4aeec8d2d6a3edeffbdfae451cdf05cbf0fefd ("libata/ahci: accommodate
> tag ordered controllers")

Hi, was this on simulated hardware or a real AHCI controller and disk?

It does appear this test noticed increased throughput:

    203893 ~ 0%      +3.7%     211474 ~ 0%  TOTAL iostat.sda.wkB/s

I wonder if ap->last_tag can be moved to a hotter cacheline, but if
throughput goes up I can imagine it throws off the cpu statistics
quite a bit.

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [libata/ahci] 8a4aeec8d2d: +138.4% perf-stat.dTLB-store-misses, +37.2% perf-stat.dTLB-load-misses
  2014-04-22 17:11   ` Dan Williams
@ 2014-04-23  8:21     ` Jet Chen
  -1 siblings, 0 replies; 6+ messages in thread
From: Jet Chen @ 2014-04-23  8:21 UTC (permalink / raw)
  To: Dan Williams; +Cc: Tejun Heo, LKML, lkp, Fengguang Wu

On 04/23/2014 01:11 AM, Dan Williams wrote:
> On Mon, Apr 21, 2014 at 12:29 AM, Jet Chen <jet.chen@intel.com> wrote:
>> HI Dan,
>>
>> we noticed the below changes on
>>
>> git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata for-next
>> commit 8a4aeec8d2d6a3edeffbdfae451cdf05cbf0fefd ("libata/ahci: accommodate
>> tag ordered controllers")
> 
> Hi, was this on simulated hardware or a real AHCI controller and disk?
> 

Testing was on a physical machine with a real AHCI controller.

root@bay ~# lspci | grep AHCI
00:1f.2 SATA controller: Intel Corporation 82801IR/IO/IH (ICH9R/DO/DH) 6 port SATA Controller [AHCI mode] (rev 02)

> It does appear this test noticed increased throughput:
> 
>     203893 ~ 0%      +3.7%     211474 ~ 0%  TOTAL iostat.sda.wkB/s
> 
> I wonder if ap->last_tag can be moved to a hotter cacheline, but if
> throughput goes up I can imagine it throws off the cpu statistics
> quite a bit.
> 

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [libata/ahci] 8a4aeec8d2d: +138.4% perf-stat.dTLB-store-misses, +37.2% perf-stat.dTLB-load-misses
@ 2014-04-23  8:21     ` Jet Chen
  0 siblings, 0 replies; 6+ messages in thread
From: Jet Chen @ 2014-04-23  8:21 UTC (permalink / raw)
  To: lkp

[-- Attachment #1: Type: text/plain, Size: 950 bytes --]

On 04/23/2014 01:11 AM, Dan Williams wrote:
> On Mon, Apr 21, 2014 at 12:29 AM, Jet Chen <jet.chen@intel.com> wrote:
>> HI Dan,
>>
>> we noticed the below changes on
>>
>> git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata for-next
>> commit 8a4aeec8d2d6a3edeffbdfae451cdf05cbf0fefd ("libata/ahci: accommodate
>> tag ordered controllers")
> 
> Hi, was this on simulated hardware or a real AHCI controller and disk?
> 

Testing was on a physical machine with a real AHCI controller.

root(a)bay ~# lspci | grep AHCI
00:1f.2 SATA controller: Intel Corporation 82801IR/IO/IH (ICH9R/DO/DH) 6 port SATA Controller [AHCI mode] (rev 02)

> It does appear this test noticed increased throughput:
> 
>     203893 ~ 0%      +3.7%     211474 ~ 0%  TOTAL iostat.sda.wkB/s
> 
> I wonder if ap->last_tag can be moved to a hotter cacheline, but if
> throughput goes up I can imagine it throws off the cpu statistics
> quite a bit.
> 

^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2014-04-23  8:21 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-04-21  7:29 [libata/ahci] 8a4aeec8d2d: +138.4% perf-stat.dTLB-store-misses, +37.2% perf-stat.dTLB-load-misses Jet Chen
2014-04-21  7:29 ` Jet Chen
2014-04-22 17:11 ` Dan Williams
2014-04-22 17:11   ` Dan Williams
2014-04-23  8:21   ` Jet Chen
2014-04-23  8:21     ` Jet Chen

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.