[lkml]   [2009]   [Feb]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [patch] SLQB slab allocator
    On Thursday 05 February 2009 07:09:15 Christoph Lameter wrote:
    > On Wed, 4 Feb 2009, Nick Piggin wrote:
    > > That's very true, and we touched on this earlier. It is I guess
    > > you can say a downside of queueing. But an analogous situation
    > > in SLUB would be that lots of pages on the partial list with
    > > very few free objects, or freeing objects to pages with few
    > > objects in them. Basically SLUB will have to do the extra work
    > > in the fastpath.
    > But these are pages with mostly allocated objects and just a few objects
    > free. The SLAB case is far worse: You have N objects on a queue and they
    > are keeping possibly N pages away from the page allocator and in those
    > pages *nothing* is used.

    Periodic queue trimming should prevent this from becoming a big problem.
    It will trim away those objects, and so subsequent allocations will come
    from new pages and be densely packed. I don't think I've seen a problem
    in SLAB reported from this phenomenon, so I'm not too concerned about it
    at the moment.

     \ /
      Last update: 2009-02-05 04:21    [W:0.029 / U:147.996 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site