lkml.org 
[lkml]   [2008]   [Oct]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [PATCH 0/4] Reclaim page capture v4
    On Fri, Oct 3, 2008 at 3:48 PM, KOSAKI Motohiro
    <kosaki.motohiro@jp.fujitsu.com> wrote:
    >> Hi, Andy.
    >>
    >> I tested your patch in my desktop.
    >> The test is just kernel compile with single thread.
    >> My system environment is as follows.
    >>
    >> model name : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
    >> MemTotal: 2065856 kB
    >>
    >> When I tested vanilla, compile time is as follows.
    >>
    >> 2433.53user 187.96system 42:05.99elapsed 103%CPU (0avgtext+0avgdata
    >> 0maxresident)k
    >> 588752inputs+4503408outputs (127major+55456246minor)pagefaults 0swaps
    >>
    >> When I tested your patch, as follows.
    >>
    >> 2489.63user 202.41system 44:47.71elapsed 100%CPU (0avgtext+0avgdata
    >> 0maxresident)k
    >> 538608inputs+4503928outputs (130major+55531561minor)pagefaults 0swaps
    >>
    >> Regresstion almost is above 2 minutes.
    >> Do you think It is a trivial?
    >
    > Ooops.
    > this is definitly significant regression.
    >
    >
    >> I know your patch is good to allocate hugepage.
    >> But, I think many users don't need it, including embedded system and
    >> desktop users yet.
    >>
    >> So I suggest you made it enable optionally.
    >
    > No.
    > if the patch has this significant regression,
    > nobody turn on its option.
    >
    > We should fix that.

    I have been tested it.
    But I can't reproduce such as regression.
    I don't know why such regression happed at that time.

    Sorry for confusing.
    Please ignore my test result at that time.

    This is new test result.

    before

    2346.24user 191.44system 42:07.28elapsed 100%CPU (0avgtext+0avgdata
    0maxresident)k
    458624inputs+4262728outputs (183major+52299730minor)pagefaults 0swaps


    after

    2349.75user 195.72system 42:16.36elapsed 100%CPU (0avgtext+0avgdata
    0maxresident)k
    475632inputs+4265208outputs (183major+52308969minor)pagefaults 0swaps

    I think we can ignore some time gap.
    Sometime, after is faster than before.

    I could conclude it doesn't have any regressions in my desktop machine.

    Tested-by: MinChan Kim <minchan.kim@gmail.com>

    --
    Kinds regards,
    MinChan Kim


    \
     
     \ /
      Last update: 2008-10-07 06:31    [W:0.030 / U:1.908 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site