Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1221860

[lkp] [fs/file.c] 8a81252b77: 14.2% will-it-scale.per_thread_ops

Show all headers | View raw

[Multipart message — attachments visible in raw view] - view raw

FYI, we noticed the below changes on

https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
commit 8a81252b774b53e628a8a0fe18e2b8fc236d92cc ("fs/file.c: don't acquire files->file_lock in fd_install()")


=========================================================================================
tbox_group/testcase/rootfs/kconfig/compiler/cpufreq_governor/test:
  xps/will-it-scale/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/performance/open1

commit: 
  1af95de6f0119d5bde02d3a811a9f3a3661e954e
  8a81252b774b53e628a8a0fe18e2b8fc236d92cc

1af95de6f0119d5b 8a81252b774b53e628a8a0fe18 
---------------- -------------------------- 
         %stddev     %change         %stddev
             \          |                \  
    581483 ±  2%     +14.2%     663787 ±  2%  will-it-scale.per_thread_ops
    689.96 ±  0%      -2.7%     671.31 ±  0%  will-it-scale.time.system_time
     17.86 ±  1%     +59.8%      28.55 ±  0%  will-it-scale.time.user_time
      3521 ±  6%     -11.2%       3125 ±  3%  slabinfo.kmalloc-192.active_objs
     17.86 ±  1%     +59.8%      28.55 ±  0%  time.user_time
      8.75 ± 16%     -51.4%       4.25 ± 50%  sched_debug.cfs_rq[1]:/.nr_spread_over
      5.50 ± 20%     +95.5%      10.75 ± 35%  sched_debug.cfs_rq[3]:/.nr_spread_over
    473.25 ± 23%     +45.7%     689.50 ± 25%  sched_debug.cfs_rq[7]:/.utilization_load_avg
    811992 ± 10%     +11.6%     906272 ±  3%  sched_debug.cpu#0.avg_idle
     80.00 ± 17%     +61.6%     129.25 ± 33%  sched_debug.cpu#7.cpu_load[0]
      1372 ± 19%     +50.6%       2066 ± 13%  sched_debug.cpu#7.curr->pid
     20835 ± 26%     +40.7%      29308 ± 18%  sched_debug.cpu#7.ttwu_count
      2.15 ±  2%     +34.2%       2.88 ±  2%  perf-profile.cpu-cycles.__alloc_fd.get_unused_fd_flags.do_sys_open.sys_open.system_call_fastpath
      1.40 ±  3%      -8.7%       1.28 ±  3%  perf-profile.cpu-cycles.__slab_alloc.kmem_cache_alloc.get_empty_filp.path_openat.do_filp_open
      0.96 ±  4%      -8.4%       0.88 ±  2%  perf-profile.cpu-cycles.dput.__fput.____fput.task_work_run.do_notify_resume
      2.55 ±  4%     +42.7%       3.63 ±  2%  perf-profile.cpu-cycles.get_unused_fd_flags.do_sys_open.sys_open.system_call_fastpath
      3.67 ±  4%      -9.1%       3.34 ±  3%  perf-profile.cpu-cycles.getname.do_sys_open.sys_open.system_call_fastpath
      1.02 ±  7%     +16.4%       1.19 ±  5%  perf-profile.cpu-cycles.kmem_cache_free.putname.do_sys_open.sys_open.system_call_fastpath
      1.45 ±  6%     +22.8%       1.78 ±  5%  perf-profile.cpu-cycles.path_init.path_openat.do_filp_open.do_sys_open.sys_open
      1.19 ±  6%     +25.4%       1.49 ±  4%  perf-profile.cpu-cycles.putname.do_sys_open.sys_open.system_call_fastpath
      1.71 ±  7%     -14.0%       1.47 ±  4%  perf-profile.cpu-cycles.security_file_free.__fput.____fput.task_work_run.do_notify_resume


xps: Nehalem
Memory: 4G




                          will-it-scale.time.user_time

  35 ++---------------------------------------------------------------------+
     O                     O O  O O  O O                                    |
  30 ++O    O    O  O O  O                O O  O O  O                       |
     |                                                O O  O O  O           |
  25 ++                                                                     |
     |             .*.*..*.*.*..*.*..*.*..*.*..*                            |
  20 *+*..*.*..*.*.                             +                           |
     |                                           *..*.*.*..*.*..*.*..*.*..*.*
  15 ++                                                                     |
     |                                                                      |
  10 ++                                                                     |
     |                                                                      |
   5 ++                                                                     |
     |                                                                      |
   0 ++---O----O------------------------------------------------------------+


	[*] bisect-good sample
	[O] bisect-bad  sample

To reproduce:

        git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
        cd lkp-tests
        bin/lkp install job.yaml  # job file is attached in this email
        bin/lkp run     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,
Ying Huang

Back to linux.kernel | Previous | Next | Find similar | Unroll thread

Thread

[lkp] [fs/file.c] 8a81252b77: 14.2% will-it-scale.per_thread_ops kernel test robot <ying.huang@intel.com> - 2015-09-10 04:40 +0200

csiph-web