lkml.org 
[lkml]   [2009]   [Aug]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [UPDATED][PATCH][mmotm] Help Root Memory Cgroup Resource Counters Scale Better (v5)

    * Balbir Singh <balbir@linux.vnet.ibm.com> wrote:

    > * Ingo Molnar <mingo@elte.hu> [2009-08-13 10:35:24]:
    >
    > >
    > > * Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
    > >
    > > > Without Patch
    > > >
    > > > Performance counter stats for '/home/balbir/parallel_pagefault':
    > > >
    > > > 5826093739340 cycles # 809.989 M/sec
    > > > 408883496292 instructions # 0.070 IPC
    > > > 7057079452 cache-references # 0.981 M/sec
    > > > 3036086243 cache-misses # 0.422 M/sec
    > >
    > > > With this patch applied
    > > >
    > > > Performance counter stats for '/home/balbir/parallel_pagefault':
    > > >
    > > > 5957054385619 cycles # 828.333 M/sec
    > > > 1058117350365 instructions # 0.178 IPC
    > > > 9161776218 cache-references # 1.274 M/sec
    > > > 1920494280 cache-misses # 0.267 M/sec
    > >
    > > Nice how the instruction count and the IPC value incraesed, and the
    > > cache-miss count decreased.
    > >
    > > Btw., a 'perf stat' suggestion: you can also make use of built-in
    > > error bars via repeating parallel_pagefault N times:
    > >
    > > aldebaran:~> perf stat --repeat 3 /bin/ls
    >
    > Ingo, with the repeat experiements I see
    >
    > 7192354.545647 task-clock-msecs # 23.955 CPUs ( +- 0.002% )
    > 425627 context-switches # 0.000 M/sec ( +- 0.333% )
    > 155 CPU-migrations # 0.000 M/sec ( +- 10.897% )
    > 95336481 page-faults # 0.013 M/sec ( +- 0.085% )
    > 5951929070187 cycles # 827.536 M/sec ( +- 0.009% )
    > 1058312583796 instructions # 0.178 IPC ( +- 0.076% )
    > 9616609083 cache-references # 1.337 M/sec ( +- 2.536% )
    > 1952367514 cache-misses # 0.271 M/sec ( +- 0.156% )
    >
    > 300.246532761 seconds time elapsed ( +- 0.002% )
    >
    > Except for the CPU migrations and the cache references, all the
    > other parameters seem to be well within an acceptable error range.

    Yeah, nice!

    Ingo


    \
     
     \ /
      Last update: 2009-08-15 16:29    [W:0.046 / U:0.924 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site