2014-06-20 18:49:41

by Max Asbock

Subject: [Patch] tracing: tell mm_migrate_pages event about numa_misplaced

The mm_migrate_pages trace event reports a reason for the migration, typically as a
symbolic string. The exception is the reason MR_NUMA_MISPLACED for which it just displays
the numeric value:
mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=0x5

This patch makes the output consistent by introducing a string value for MR_NUMA_MISPLACED.
The event is then reported as:
mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=numa_misplaced

Signed-off-by: Max Asbock <[email protected]>

migrate.h | 1 +
1 file changed, 1 insertion(+)


--- linux-3.16-rc1/include/trace/events/migrate.h.orig 2014-06-20 10:00:26.768410407 -0700
+++ linux-3.16-rc1/include/trace/events/migrate.h 2014-06-20 10:01:55.432410334 -0700
@@ -17,6 +17,7 @@
{MR_MEMORY_HOTPLUG, "memory_hotplug"}, \
{MR_SYSCALL, "syscall_or_cpuset"}, \
{MR_MEMPOLICY_MBIND, "mempolicy_mbind"}, \
+ {MR_NUMA_MISPLACED, "numa_misplaced"}, \
{MR_CMA, "cma"}

TRACE_EVENT(mm_migrate_pages,

2014-06-23 14:22:05

by Mel Gorman

Subject: Re: [Patch] tracing: tell mm_migrate_pages event about numa_misplaced

On Fri, Jun 20, 2014 at 11:49:16AM -0700, Max Asbock wrote:
>
> The mm_migrate_pages trace event reports a reason for the migration, typically as a
> symbolic string. The exception is the reason MR_NUMA_MISPLACED for which it just displays
> the numeric value:
> mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=0x5
>
> This patch makes the output consistent by introducing a string value for MR_NUMA_MISPLACED.
> The event is then reported as:
> mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=numa_misplaced
>
> Signed-off-by: Max Asbock <[email protected]>

Acked-by: Mel Gorman <[email protected]>

--
Mel Gorman
SUSE Labs

2014-06-23 14:31:17

by Steven Rostedt

Subject: Re: [Patch] tracing: tell mm_migrate_pages event about numa_misplaced

On Mon, 23 Jun 2014 15:21:59 +0100
Mel Gorman <[email protected]> wrote:

> On Fri, Jun 20, 2014 at 11:49:16AM -0700, Max Asbock wrote:
> >
> > The mm_migrate_pages trace event reports a reason for the migration, typically as a
> > symbolic string. The exception is the reason MR_NUMA_MISPLACED for which it just displays
> > the numeric value:
> > mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=0x5
> >
> > This patch makes the output consistent by introducing a string value for MR_NUMA_MISPLACED.
> > The event is then reported as:
> > mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=numa_misplaced
> >
> > Signed-off-by: Max Asbock <[email protected]>
>
> Acked-by: Mel Gorman <[email protected]>
>

Would you like to take this? Or Andrew?

You can add my Acked-by: Steven Rostedt <[email protected]>


-- Steve

2014-06-23 14:56:37

by Mel Gorman

Subject: Re: [Patch] tracing: tell mm_migrate_pages event about numa_misplaced

On Mon, Jun 23, 2014 at 10:31:11AM -0400, Steven Rostedt wrote:
> On Mon, 23 Jun 2014 15:21:59 +0100
> Mel Gorman <[email protected]> wrote:
>
> > On Fri, Jun 20, 2014 at 11:49:16AM -0700, Max Asbock wrote:
> > >
> > > The mm_migrate_pages trace event reports a reason for the migration, typically as a
> > > symbolic string. The exception is the reason MR_NUMA_MISPLACED for which it just displays
> > > the numeric value:
> > > mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=0x5
> > >
> > > This patch makes the output consistent by introducing a string value for MR_NUMA_MISPLACED.
> > > The event is then reported as:
> > > mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=numa_misplaced
> > >
> > > Signed-off-by: Max Asbock <[email protected]>
> >
> > Acked-by: Mel Gorman <[email protected]>
> >
>
> Would you like to take this? Or Andrew?
>

I expect Andrew will pick it up.

--
Mel Gorman
SUSE Labs