[lkml]   [2007]   [Dec]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: Major regression on hackbench with SLUB (more numbers)

    * Christoph Lameter <> wrote:

    > Hmmmm... Some tests here on an 8p 8G machine:

    > In an extreme case (boot with slub_min_order=9 to get huge page sized
    > slabs) SLUB can win against SLAB:
    > N=10 Time: 0.338 Minimally faster
    > N=20 Time: 0.560 10% faster
    > N=50 Time: 1.353 15% faster

    what's up with this regression? There's been absolutely no activity
    about it in the last 8 days: upstream still regresses, -mm still
    regresses and there are no patches posted for testing.

    being able to utilize order-0 pages was supposed to be one of the big
    plusses of SLUB, so booting with _2MB_ sized slabs cannot be seriously
    the "fix", right?


     \ /
      Last update: 2007-12-21 13:15    [W:0.021 / U:3.384 seconds]
    ©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site