lkml.org 
[lkml]   [2004]   [May]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: dentry bloat.
    Hi,

    The following is the output of dcachebench run on the 4 kernels:

    Environment - 2-way P4 Xeon 2.4MHz SMP box with 4.5GB RAM.
    Tests were run for 10 iterations to calculate the milliseconds/iteration
    and then mean and deviation were calculated.


    Kernel version Mean Standard Deviation
    --------------- ---- ------------------

    2.6.6-rc3(baseline) 10578 221

    2.6.6 10280 110

    2.6.6-bk 10862 30

    2.6.6-mm1 10626 36

    To find out if the huge performance dip between the 2.6.6
    and 2.6.6-bk is because of the hash changes, I removed the hash patch
    from 2.6.6-bk and applied it to 2.6.6.

    2.6.6-bk with old hash 10685 34

    2.6.6 with new hash 10496 125

    Looks like the new hashing function has brought down the performance.
    Also some code outside dcache.c and inode.c seems to have pushed down
    the performance in 2.6.6-bk.

    Raghav



    On Tue, May 11, 2004 at 01:22:05PM -0700, Andrew Morton wrote:
    > Maneesh Soni <maneesh@in.ibm.com> wrote:
    > >
    > > We can see this happening in the following numbers taken using dcachebench*
    > > gathered on 2-way P4 Xeon 2.4MHz SMP box with 4.5GB RAM. The benchmark was run
    > > with the following parameters and averaged over 10 runs.
    > > ./dcachebench -p 32 -b testdir
    > >
    > > Average microseconds/iterations Std. Deviation
    > > (lesser is better)
    > > 2.6.6 10204 161.5
    > > 2.6.6-mm1 10571 51.5
    > >
    >
    > Well.. this could be anything. If the hash is any good -mm shouldn't be
    > doing significantly more locked operations. (I think - didn't check very
    > closely).
    >
    > Also the inode and dentry hash algorithms were changed in -mm. You can
    > evaluate the effect of that by comparing 2.6.6 with current Linus -bk.
    >
    > If we compare 2.6.6-bk with 2.6.6-mm1 and see a slowdown on SMP and no
    > slowdown on UP then yup, it might be due to additional locking.
    >
    > But we should evaluate the hash changes separately.
    >
    > Summary:
    >
    > 2.6.6-rc3: baseline
    > 2.6.6: dentry size+alignment changes
    > 2.6.6-bk: dentry size+alignment changes, hash changes
    > 2.6.6-mm1: dentry size+alignment changes, hash changes, lots of other stuff.
    > -
    > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    > the body of a message to majordomo@vger.kernel.org
    > More majordomo info at http://vger.kernel.org/majordomo-info.html
    > Please read the FAQ at http://www.tux.org/lkml/
    >
    >
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

    \
     
     \ /
      Last update: 2005-03-22 14:03    [W:4.163 / U:0.180 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site