linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
* about profiling and stats info for pagecache/buffercache
@ 2001-05-06 18:02 Alexey Zhuravlev
  2001-05-06 19:42 ` Rik van Riel
  0 siblings, 1 reply; 3+ messages in thread
From: Alexey Zhuravlev @ 2001-05-06 18:02 UTC (permalink / raw)
  To: linux-mm

Hello!

As far as I understand, now Linux have no facility to collect stats info
for pagecache/buffercache. For example, it'd be fine if we can see how 
many requests were submited to pagecache/buffercache and how many of 
these requests was serviced from cache without I/O. Moreover, it'd be fine
to have some profiling info on requests for pagecache/buffercache...


--
poka, lexa
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux.eu.org/Linux-MM/

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: about profiling and stats info for pagecache/buffercache
  2001-05-06 18:02 about profiling and stats info for pagecache/buffercache Alexey Zhuravlev
@ 2001-05-06 19:42 ` Rik van Riel
  2001-05-07 18:10   ` Stephen C. Tweedie
  0 siblings, 1 reply; 3+ messages in thread
From: Rik van Riel @ 2001-05-06 19:42 UTC (permalink / raw)
  To: Alexey Zhuravlev; +Cc: linux-mm

On Sun, 6 May 2001, Alexey Zhuravlev wrote:

> As far as I understand, now Linux have no facility to collect stats info
> for pagecache/buffercache. For example, it'd be fine if we can see how 
> many requests were submited to pagecache/buffercache and how many of 
> these requests was serviced from cache without I/O. Moreover, it'd be fine
> to have some profiling info on requests for pagecache/buffercache...

OK, so you want:

pagecache	nr_requests	hit	mis	
buffercache	nr_requests	hit	mis

I'd like to see a few other statistics as well, mainly for the
pageout code...

- nr pages scannned
- nr pages moved to the inactive_clean list
- nr pages "rescued" from the inactive_clean list
- nr pages evicted
- nr pages deactivated by pageout scanning
- nr pages deactivated by drop-behind

Are there any more ideas for statistics people would like to
see?

regards,

Rik
--
Virtual memory is like a game you can't win;
However, without VM there's truly nothing to lose...

http://www.surriel.com/		http://distro.conectiva.com/

Send all your spam to aardvark@nl.linux.org (spam digging piggy)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux.eu.org/Linux-MM/

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: about profiling and stats info for pagecache/buffercache
  2001-05-06 19:42 ` Rik van Riel
@ 2001-05-07 18:10   ` Stephen C. Tweedie
  0 siblings, 0 replies; 3+ messages in thread
From: Stephen C. Tweedie @ 2001-05-07 18:10 UTC (permalink / raw)
  To: Rik van Riel; +Cc: Alexey Zhuravlev, linux-mm

Hi,

On Sun, May 06, 2001 at 04:42:04PM -0300, Rik van Riel wrote:
> 
> I'd like to see a few other statistics as well, mainly for the
> pageout code...
> 
> - nr pages scannned
> - nr pages moved to the inactive_clean list
> - nr pages "rescued" from the inactive_clean list
> - nr pages evicted
> - nr pages deactivated by pageout scanning
> - nr pages deactivated by drop-behind
> 
> Are there any more ideas for statistics people would like to
> see?

As long as that's per-zone, and includes failed scans as well as
successes, fine.

--Stephen
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux.eu.org/Linux-MM/

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2001-05-07 18:10 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2001-05-06 18:02 about profiling and stats info for pagecache/buffercache Alexey Zhuravlev
2001-05-06 19:42 ` Rik van Riel
2001-05-07 18:10   ` Stephen C. Tweedie

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox