Re: [patch 0/9] mm: thrash detection-based file cache sizing v3

2013-08-12 Thread Johannes Weiner
On Fri, Aug 09, 2013 at 03:53:09PM -0700, Andrew Morton wrote: > On Tue, 6 Aug 2013 18:44:01 -0400 Johannes Weiner wrote: > > > This series solves the problem by maintaining a history of pages > > evicted from the inactive list, enabling the VM to tell streaming IO > > from thrashing and

Re: [patch 0/9] mm: thrash detection-based file cache sizing v3

2013-08-12 Thread Johannes Weiner
On Fri, Aug 09, 2013 at 03:53:09PM -0700, Andrew Morton wrote: On Tue, 6 Aug 2013 18:44:01 -0400 Johannes Weiner han...@cmpxchg.org wrote: This series solves the problem by maintaining a history of pages evicted from the inactive list, enabling the VM to tell streaming IO from thrashing

Re: [patch 0/9] mm: thrash detection-based file cache sizing v3

2013-08-09 Thread Andrew Morton
On Tue, 6 Aug 2013 18:44:01 -0400 Johannes Weiner wrote: > This series solves the problem by maintaining a history of pages > evicted from the inactive list, enabling the VM to tell streaming IO > from thrashing and rebalance the page cache lists when appropriate. Looks nice. The lack of

Re: [patch 0/9] mm: thrash detection-based file cache sizing v3

2013-08-09 Thread Andrew Morton
On Tue, 6 Aug 2013 18:44:01 -0400 Johannes Weiner han...@cmpxchg.org wrote: This series solves the problem by maintaining a history of pages evicted from the inactive list, enabling the VM to tell streaming IO from thrashing and rebalance the page cache lists when appropriate. Looks nice.

[patch 0/9] mm: thrash detection-based file cache sizing v3

2013-08-06 Thread Johannes Weiner
[ My apologies for the double send, I screwed up one of the recipient addresses the first time around and it got dropped by some MTAs. ] Changes in version 3: o Lazily remove inodes without shadow entries from the global list to reduce modifications of said list to an absolute minimum.

[patch 0/9] mm: thrash detection-based file cache sizing v3

2013-08-06 Thread Johannes Weiner
[ My apologies for the double send, I screwed up one of the recipient addresses the first time around and it got dropped by some MTAs. ] Changes in version 3: o Lazily remove inodes without shadow entries from the global list to reduce modifications of said list to an absolute minimum.