On Wed, May 18, 2011 at 10:47:18AM +0100, Mel Gorman wrote:

As we are aggressively shrinking slab, we can reach the stage where
we scan the requested number of objects and reclaim none of them
potentially setting zone->all_unreclaimable to 1 if a lot of scanning
has also taken place recently without pages being freed. Once this
happens, kswapd isn't even trying to reclaim pages and is instead stuck
in shrink_slab until a page is freed clearing zone->all_unreclaimable
and zone->pages-scanned.

Isn't this completely broken then? We can have slabs with lots of
objects but none are reclaimable - e.g. dirty inodes are not even on
the inode LRU and require IO to get there, so repeatedly scanning
the slab trying to free inodes is completely pointless.

If the shrinkers are not freeing anything, then it should be backing
off and giving thme some time to clean objects is a much more
efficient use of CPU time than spinning madly. Indeed, if you back
off, you can do another pass over the LRU and see if there are more
pages that can be reclaimed, too, so you're not dependent on the
shrinkers actually making progress to break the livelock....

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com