[lkml]   [2009]   [Sep]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [PATCH 3/8] writeback: switch to per-bdi threads for flushing data
    On Tue, Sep 08 2009, Daniel Walker wrote:
    > On Tue, 2009-09-08 at 11:23 +0200, Jens Axboe wrote:
    > > This gets rid of pdflush for bdi writeout and kupdated style cleaning.
    > > pdflush writeout suffers from lack of locality and also requires more
    > > threads to handle the same workload, since it has to work in a
    > > non-blocking fashion against each queue. This also introduces lumpy
    > > behaviour and potential request starvation, since pdflush can be starved
    > > for queue access if others are accessing it. A sample ffsb workload that
    > > does random writes to files is about 8% faster here on a simple SATA drive
    > > during the benchmark phase. File layout also seems a LOT more smooth in
    > > vmstat:
    > This patch has a checkpatch error, and couple of warnings.. Here's one
    > of the warnings which I though was concerning..
    > WARNING: trailing semicolon indicates no statements, indent implies
    > otherwise
    > #388: FILE: fs/fs-writeback.c:177:
    > + } else if (wb->task);
    > + wake_up_process(wb->task);
    > I suppose that could be a defect .. btw, patch 7 of 8 also has a few
    > trivial warnings.

    Oops yes, that was added between -v18 and -19 with the moving of that
    code. Will fix that up, thanks for spotting that.

    I'll check the series for checkpatch cleanliness. I did at some point,
    but that was a few revisions ago.

    Jens Axboe

     \ /
      Last update: 2009-09-08 16:23    [W:0.019 / U:27.656 seconds]
    ©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site