lkml.org 
[lkml]   [2001]   [Sep]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    SubjectRe: Purpose of the mm/slab.c changes
    Date
    >
    > it provides lifo allocations from both partial and unused slabs.
    >

    lifo/fifo for unused slabs is obviously superflous - free is free, it
    doesn't matter which free page is used first/last.
    The partial slabs are already lifo: if a slab goes from full to partial,
    it's added to the head of the partial list.

    > You
    > should benchmark it with a real load, not with dummy
    > allocations/freeing.
    >
    Did you run any benchmarks? If yes, could you post them?

    What I did was checking the number of branches in the hot path
    (increased), the code length (increased) and execution time with dummy
    loads (slower).

    --
    Manfred



    -
    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 13:03    [W:0.021 / U:31.280 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site