Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled

2012-11-28 Thread Hugh Dickins
On Wed, 21 Nov 2012, Michal Hocko wrote: > On Tue 20-11-12 13:49:32, Andrew Morton wrote: > > On Mon, 19 Nov 2012 17:44:34 -0800 (PST) > > David Rientjes wrote: > > > > > While profiling numa/core v16 with cgroup_disable=memory on the command > > > line, I noticed mem_cgroup_count_vm_event() sti

Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled

2012-11-21 Thread Michal Hocko
On Tue 20-11-12 13:49:32, Andrew Morton wrote: > On Mon, 19 Nov 2012 17:44:34 -0800 (PST) > David Rientjes wrote: > > > While profiling numa/core v16 with cgroup_disable=memory on the command > > line, I noticed mem_cgroup_count_vm_event() still showed up as high as > > 0.60% in perftop. > > >

Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled fix

2012-11-20 Thread Kamezawa Hiroyuki
(2012/11/21 11:48), David Rientjes wrote: Move the check for !mm out of line as suggested by Andrew. Signed-off-by: David Rientjes Thank you very much ! Acked-by: KAMEZAWA Hiroyuki --- include/linux/memcontrol.h |2 +- mm/memcontrol.c|3 +++ 2 files changed, 4 ins

Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled

2012-11-20 Thread Kamezawa Hiroyuki
(2012/11/21 6:49), Andrew Morton wrote: On Mon, 19 Nov 2012 17:44:34 -0800 (PST) David Rientjes wrote: While profiling numa/core v16 with cgroup_disable=memory on the command line, I noticed mem_cgroup_count_vm_event() still showed up as high as 0.60% in perftop. This occurs because the funct

Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled

2012-11-20 Thread Andrew Morton
On Mon, 19 Nov 2012 17:44:34 -0800 (PST) David Rientjes wrote: > While profiling numa/core v16 with cgroup_disable=memory on the command > line, I noticed mem_cgroup_count_vm_event() still showed up as high as > 0.60% in perftop. > > This occurs because the function is called extremely often e

Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled

2012-11-20 Thread Johannes Weiner
On Mon, Nov 19, 2012 at 05:44:34PM -0800, David Rientjes wrote: > While profiling numa/core v16 with cgroup_disable=memory on the command > line, I noticed mem_cgroup_count_vm_event() still showed up as high as > 0.60% in perftop. > > This occurs because the function is called extremely often ev

Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled

2012-11-20 Thread Glauber Costa
On 11/20/2012 08:23 AM, Kamezawa Hiroyuki wrote: > (2012/11/20 10:44), David Rientjes wrote: >> While profiling numa/core v16 with cgroup_disable=memory on the command >> line, I noticed mem_cgroup_count_vm_event() still showed up as high as >> 0.60% in perftop. >> >> This occurs because the functi

Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled

2012-11-19 Thread Michal Hocko
On Mon 19-11-12 17:44:34, David Rientjes wrote: > While profiling numa/core v16 with cgroup_disable=memory on the command > line, I noticed mem_cgroup_count_vm_event() still showed up as high as > 0.60% in perftop. > > This occurs because the function is called extremely often even when memcg >

Re: [patch] mm, memcg: avoid unnecessary function call when memcg is disabled

2012-11-19 Thread Kamezawa Hiroyuki
(2012/11/20 10:44), David Rientjes wrote: While profiling numa/core v16 with cgroup_disable=memory on the command line, I noticed mem_cgroup_count_vm_event() still showed up as high as 0.60% in perftop. This occurs because the function is called extremely often even when memcg is disabled. To f