[lkml]   [2011]   [Oct]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [PATCH v2 6/6] slub: only preallocate cpus_with_slabs if offstack
    On Sun, 23 Oct 2011, Gilad Ben-Yossef wrote:

    > We need a cpumask to track cpus with per cpu cache pages
    > to know which cpu to whack during flush_all. For
    > CONFIG_CPUMASK_OFFSTACK=n we allocate the mask on stack.
    > For CONFIG_CPUMASK_OFFSTACK=y we don't want to call kmalloc
    > on the flush_all path, so we preallocate per kmem_cache
    > on cache creation and use it in flush_all.

    I think the on stack alloc should be the default because we can then avoid
    the field in kmem_cache and the associated logic with managing the field.
    Can we do a GFP_ATOMIC allocation in flush_all()? If the alloc
    fails then you can still fallback to send an IPI to all cpus.

     \ /
      Last update: 2011-10-28 06:09    [W:0.027 / U:56.528 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site