[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-12 Thread Greg Thelen
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com writes: On Mon, 11 Oct 2010 17:24:21 -0700 Greg Thelen gthe...@google.com wrote: Is your motivation to increase performance with the same functionality? If so, then would a 'static inline' be performance equivalent to a preprocessor macro

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-12 Thread KAMEZAWA Hiroyuki
On Tue, 12 Oct 2010 00:32:33 -0700 Greg Thelen gthe...@google.com wrote: KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com writes: What are the cases where current-mm-owner-cgroups != current-cgroups? In that case, assume group A and B. thread(1) - belongs to cgroup A (thread(1)

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-11 Thread Greg Thelen
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com writes: On Wed, 06 Oct 2010 17:27:13 -0700 Greg Thelen gthe...@google.com wrote: KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com writes: On Tue, 05 Oct 2010 12:00:17 -0700 Greg Thelen gthe...@google.com wrote: Andrea Righi

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-11 Thread KAMEZAWA Hiroyuki
On Mon, 11 Oct 2010 17:24:21 -0700 Greg Thelen gthe...@google.com wrote: Is your motivation to increase performance with the same functionality? If so, then would a 'static inline' be performance equivalent to a preprocessor macro yet be safer to use? Ah, if lockdep finds this as bug,

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-06 Thread KAMEZAWA Hiroyuki
On Tue, 05 Oct 2010 12:00:17 -0700 Greg Thelen gthe...@google.com wrote: Andrea Righi ari...@develer.com writes: On Sun, Oct 03, 2010 at 11:58:02PM -0700, Greg Thelen wrote: Extend mem_cgroup to contain dirty page limits. Also add routines allowing the kernel to query the dirty usage of

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-06 Thread Greg Thelen
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com writes: On Tue, 05 Oct 2010 12:00:17 -0700 Greg Thelen gthe...@google.com wrote: Andrea Righi ari...@develer.com writes: On Sun, Oct 03, 2010 at 11:58:02PM -0700, Greg Thelen wrote: Extend mem_cgroup to contain dirty page limits. Also

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-06 Thread KAMEZAWA Hiroyuki
On Wed, 06 Oct 2010 17:27:13 -0700 Greg Thelen gthe...@google.com wrote: KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com writes: On Tue, 05 Oct 2010 12:00:17 -0700 Greg Thelen gthe...@google.com wrote: Andrea Righi ari...@develer.com writes: On Sun, Oct 03, 2010 at 11:58:02PM

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-05 Thread KAMEZAWA Hiroyuki
On Sun, 3 Oct 2010 23:58:02 -0700 Greg Thelen gthe...@google.com wrote: Extend mem_cgroup to contain dirty page limits. Also add routines allowing the kernel to query the dirty usage of a memcg. These interfaces not used by the kernel yet. A subsequent commit will add kernel calls to

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-05 Thread Andrea Righi
On Sun, Oct 03, 2010 at 11:58:02PM -0700, Greg Thelen wrote: Extend mem_cgroup to contain dirty page limits. Also add routines allowing the kernel to query the dirty usage of a memcg. These interfaces not used by the kernel yet. A subsequent commit will add kernel calls to utilize these

[Devel] Re: [PATCH 07/10] memcg: add dirty limits to mem_cgroup

2010-10-05 Thread Greg Thelen
Andrea Righi ari...@develer.com writes: On Sun, Oct 03, 2010 at 11:58:02PM -0700, Greg Thelen wrote: Extend mem_cgroup to contain dirty page limits. Also add routines allowing the kernel to query the dirty usage of a memcg. These interfaces not used by the kernel yet. A subsequent commit