Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Mel Gorman
On Wed, Feb 03, 2016 at 01:32:46PM +, Mel Gorman wrote: > > Yes, but the question is, are there true cross-CPU cache-misses? I.e. are > > there > > any 'global' (or per node) counters that we keep touching and which keep > > generating cache-misses? > > > > I haven't specifically

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Mel Gorman
On Wed, Feb 03, 2016 at 01:49:21PM +0100, Ingo Molnar wrote: > > * Mel Gorman wrote: > > > On Wed, Feb 03, 2016 at 12:28:49PM +0100, Ingo Molnar wrote: > > > > > > * Mel Gorman wrote: > > > > > > > Changelog since v3 > > > > o Force enable stats during profiling and latencytop > > > > > > >

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Ingo Molnar
* Mel Gorman wrote: > On Wed, Feb 03, 2016 at 12:28:49PM +0100, Ingo Molnar wrote: > > > > * Mel Gorman wrote: > > > > > Changelog since v3 > > > o Force enable stats during profiling and latencytop > > > > > > Changelog since V2 > > > o Print stats that are not related to schedstat > > > o

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Srikar Dronamraju
> Changelog since v3 > o Force enable stats during profiling and latencytop > > Changelog since V2 > o Print stats that are not related to schedstat > o Reintroduce a static inline for update_stats_dequeue > > Changelog since V1 > o Introduce schedstat_enabled and address Ingo's feedback > o

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Mel Gorman
On Wed, Feb 03, 2016 at 12:28:49PM +0100, Ingo Molnar wrote: > > * Mel Gorman wrote: > > > Changelog since v3 > > o Force enable stats during profiling and latencytop > > > > Changelog since V2 > > o Print stats that are not related to schedstat > > o Reintroduce a static inline for

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Ingo Molnar
* Mel Gorman wrote: > Changelog since v3 > o Force enable stats during profiling and latencytop > > Changelog since V2 > o Print stats that are not related to schedstat > o Reintroduce a static inline for update_stats_dequeue > > Changelog since V1 > o Introduce schedstat_enabled and address

[PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Mel Gorman
Changelog since v3 o Force enable stats during profiling and latencytop Changelog since V2 o Print stats that are not related to schedstat o Reintroduce a static inline for update_stats_dequeue Changelog since V1 o Introduce schedstat_enabled and address Ingo's feedback o More schedstat-only

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Ingo Molnar
* Mel Gorman wrote: > Changelog since v3 > o Force enable stats during profiling and latencytop > > Changelog since V2 > o Print stats that are not related to schedstat > o Reintroduce a static inline for update_stats_dequeue > > Changelog since V1 > o Introduce

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Mel Gorman
On Wed, Feb 03, 2016 at 01:49:21PM +0100, Ingo Molnar wrote: > > * Mel Gorman wrote: > > > On Wed, Feb 03, 2016 at 12:28:49PM +0100, Ingo Molnar wrote: > > > > > > * Mel Gorman wrote: > > > > > > > Changelog since v3 > > > > o Force

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Srikar Dronamraju
> Changelog since v3 > o Force enable stats during profiling and latencytop > > Changelog since V2 > o Print stats that are not related to schedstat > o Reintroduce a static inline for update_stats_dequeue > > Changelog since V1 > o Introduce schedstat_enabled and address Ingo's feedback > o

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Mel Gorman
On Wed, Feb 03, 2016 at 12:28:49PM +0100, Ingo Molnar wrote: > > * Mel Gorman wrote: > > > Changelog since v3 > > o Force enable stats during profiling and latencytop > > > > Changelog since V2 > > o Print stats that are not related to schedstat > > o Reintroduce a

[PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Mel Gorman
Changelog since v3 o Force enable stats during profiling and latencytop Changelog since V2 o Print stats that are not related to schedstat o Reintroduce a static inline for update_stats_dequeue Changelog since V1 o Introduce schedstat_enabled and address Ingo's feedback o More schedstat-only

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Mel Gorman
On Wed, Feb 03, 2016 at 01:32:46PM +, Mel Gorman wrote: > > Yes, but the question is, are there true cross-CPU cache-misses? I.e. are > > there > > any 'global' (or per node) counters that we keep touching and which keep > > generating cache-misses? > > > > I haven't specifically

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v4

2016-02-03 Thread Ingo Molnar
* Mel Gorman wrote: > On Wed, Feb 03, 2016 at 12:28:49PM +0100, Ingo Molnar wrote: > > > > * Mel Gorman wrote: > > > > > Changelog since v3 > > > o Force enable stats during profiling and latencytop > > > > > > Changelog since V2 > >