[PATCH 0/5] OOM analysis helper patch series v2

[KOSAKI Motohiro]

> On Thu, 9 Jul 2009, KOSAKI Motohiro wrote:
>
> > Subject: [PATCH] add isolate pages vmstat
> >
> > If the system have plenty threads or processes, concurrent reclaim can
> > isolate very much pages.
> > Unfortunately, current /proc/meminfo and OOM log can't show it.
>
> "
> If the system is running a heavy load of processes then concurrent reclaim
> can isolate a large numbe of pages from the LRU. /proc/meminfo and the
> output generated for an OOM do not show how many pages were isolated.
> "
>
> > This patch provide the way of showing this information.
>
> "
> This patch shows the information about isolated pages.
> "
>
>
> Page migration can also isolate a large number of pages from the LRU. But
> the new counters are not used there.

Correct. Will fix.

Plus, current reclaim logic depend on the system have enough much pages on LRU.
Maybe we don't only need to limit #-of-reclaimer, but also need to limit #-of-migrator.
I think we can use similar logic.




--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[Christoph Lameter-7]

On Fri, 10 Jul 2009, KOSAKI Motohiro wrote:

> Plus, current reclaim logic depend on the system have enough much pages on LRU.
> Maybe we don't only need to limit #-of-reclaimer, but also need to limit #-of-migrator.
> I think we can use similar logic.

I think your isolate pages counters can be used in both locations.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[KOSAKI Motohiro]

> On Fri, 10 Jul 2009, KOSAKI Motohiro wrote:
>
> > Plus, current reclaim logic depend on the system have enough much pages on LRU.
> > Maybe we don't only need to limit #-of-reclaimer, but also need to limit #-of-migrator.
> > I think we can use similar logic.
>
> I think your isolate pages counters can be used in both locations.
>

I totally agree this :)




--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/