[lkml]   [2012]   [Jul]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 3/3] slub: release a lock if freeing object with a lock is failed in __slab_free()
On Sat, 23 Jun 2012, Joonsoo Kim wrote:

> In some case of __slab_free(), we need a lock for manipulating partial list.
> If freeing object with a lock is failed, a lock doesn't needed anymore
> for some reasons.
> Case 1. prior is NULL, kmem_cache_debug(s) is true
> In this case, another free is occured before our free is succeed.
> When slab is full(prior is NULL), only possible operation is slab_free().
> So in this case, we guess another free is occured.
> It may make a slab frozen, so lock is not needed anymore.

A free cannot freeze the slab without taking the lock. The taken lock
makes sure that the thread that first enters slab_free() will be able to
hold back the thread that wants to freeze the slab.

> Case 2. inuse is NULL
> In this case, acquire_slab() is occured before out free is succeed.
> We have a last object for slab, so other operation for this slab is
> not possible except acquire_slab().
> Acquire_slab() makes a slab frozen, so lock is not needed anymore.

acquire_slab() also requires lock acquisition and would be held of by
slab_free holding the lock.

> This also make logic somehow simple that 'was_frozen with a lock' case
> is never occured. Remove it.

That is actually interesting and would be a good optimization.

 \ /
  Last update: 2012-07-05 17:01    [W:0.132 / U:6.848 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site