linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Frans Pop <elendil@planet.nl>
To: Mel Gorman <mel@csn.ul.ie>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	stable@kernel.org, linux-kernel@vger.kernel.org,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	Jiri Kosina <jkosina@suse.cz>,
	Sven Geggus <lists@fuchsschwanzdomain.de>,
	Karol Lewandowski <karol.k.lewandowski@gmail.com>,
	Tobias Oetiker <tobi@oetiker.ch>,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Pekka Enberg <penberg@cs.helsinki.fi>,
	Rik van Riel <riel@redhat.com>,
	Christoph Lameter <cl@linux-foundation.org>,
	Stephan von Krawczynski <skraw@ithnet.com>,
	Kernel Testers List <kernel-testers@vger.kernel.org>
Subject: Re: [PATCH 3/3] vmscan: Force kswapd to take notice faster when high-order watermarks are being hit
Date: Wed, 4 Nov 2009 01:01:46 +0100	[thread overview]
Message-ID: <200911040101.50194.elendil@planet.nl> (raw)
In-Reply-To: <20091103220808.GF22046@csn.ul.ie>

[-- Attachment #1: Type: text/plain, Size: 1675 bytes --]

On Tuesday 03 November 2009, you wrote:
> > With a representative test I get 0 for kswapd_slept_prematurely.
> > Tested with .32-rc6 + patches 1-3 + this patch.
>
> Assuming the problem actually reproduced, can you still retest with the

Yes, it does.

> patch I posted as a follow-up and see if fast or slow premature sleeps
> are happening and if the problem still occurs please? It's still
> possible with the patch as-is could be timing related. After I posted
> this patch, I continued testing and found I could get counts fairly
> reliably if kswapd was calling printk() before making the premature
> check so the window appears to be very small.

Tested with .32-rc6 and .31.1. With that follow-up patch I still get 
freezes and SKB allocation errors. And I don't get anywhere near the fast, 
smooth and reliable behavior I get when I do the congestion_wait() 
reverts.

The new case does trigger as you can see below, but I'm afraid I don't see 
it making any significant difference for my test. Hope the data is still 
useful for you.

From vmstat for .32-rc6:
kswapd_highorder_rewakeup 8
kswapd_slept_prematurely_fast 329
kswapd_slept_prematurely_slow 55

From vmstat for .31.1:
kswapd_highorder_rewakeup 20
kswapd_slept_prematurely_fast 307
kswapd_slept_prematurely_slow 105

If you'd like me to test with the congestion_wait() revert on top of this 
for comparison, please let me know.

Cheers,
FJP

P.S. Your follow-up patch did not apply cleanly on top of the debug one as 
you seem to have made some changes between posting them (dropped kswapd_ 
from the sleeping_prematurely() function name and added a comment).


[-- Attachment #2: vmstat.32 --]
[-- Type: text/plain, Size: 1451 bytes --]

nr_free_pages 4798
nr_inactive_anon 102550
nr_active_anon 305242
nr_inactive_file 17876
nr_active_file 13213
nr_unevictable 400
nr_mlock 400
nr_anon_pages 376898
nr_mapped 2769
nr_file_pages 63678
nr_dirty 18
nr_writeback 0
nr_slab_reclaimable 2236
nr_slab_unreclaimable 3984
nr_page_table_pages 3996
nr_kernel_stack 173
nr_unstable 0
nr_bounce 0
nr_vmscan_write 215582
nr_writeback_temp 0
nr_isolated_anon 0
nr_isolated_file 0
nr_shmem 17
pgpgin 607186
pgpgout 872956
pswpin 9397
pswpout 215580
pgalloc_dma 2128
pgalloc_dma32 1922180
pgalloc_normal 0
pgalloc_movable 0
pgfree 1929319
pgactivate 122493
pgdeactivate 383992
pgfault 2210388
pgmajfault 6625
pgrefill_dma 1792
pgrefill_dma32 386511
pgrefill_normal 0
pgrefill_movable 0
pgsteal_dma 41
pgsteal_dma32 295511
pgsteal_normal 0
pgsteal_movable 0
pgscan_kswapd_dma 64
pgscan_kswapd_dma32 379687
pgscan_kswapd_normal 0
pgscan_kswapd_movable 0
pgscan_direct_dma 36768
pgscan_direct_dma32 5233523
pgscan_direct_normal 0
pgscan_direct_movable 0
pginodesteal 2416
slabs_scanned 42240
kswapd_steal 241253
kswapd_inodesteal 6252
kswapd_highorder_rewakeup 20
kswapd_slept_prematurely_fast 307
kswapd_slept_prematurely_slow 105
pageoutrun 3394
allocstall 964
pgrotated 215342
unevictable_pgs_culled 4247
unevictable_pgs_scanned 0
unevictable_pgs_rescued 33344
unevictable_pgs_mlocked 43192
unevictable_pgs_munlocked 42780
unevictable_pgs_cleared 2
unevictable_pgs_stranded 0
unevictable_pgs_mlockfreed 0

[-- Attachment #3: vmstat.31 --]
[-- Type: text/plain, Size: 1375 bytes --]

nr_free_pages 5730
nr_inactive_anon 101680
nr_active_anon 304236
nr_inactive_file 18296
nr_active_file 14717
nr_unevictable 408
nr_mlock 408
nr_anon_pages 347177
nr_mapped 2751
nr_file_pages 93394
nr_dirty 8
nr_writeback 0
nr_slab_reclaimable 2218
nr_slab_unreclaimable 3670
nr_page_table_pages 3976
nr_unstable 0
nr_bounce 0
nr_vmscan_write 238631
nr_writeback_temp 0
pgpgin 594630
pgpgout 964231
pswpin 8629
pswpout 238627
pgalloc_dma 2169
pgalloc_dma32 1869092
pgalloc_normal 0
pgalloc_movable 0
pgfree 1877147
pgactivate 116309
pgdeactivate 372861
pgfault 2152528
pgmajfault 6806
pgrefill_dma 1410
pgrefill_dma32 375616
pgrefill_normal 0
pgrefill_movable 0
pgsteal_dma 54
pgsteal_dma32 285950
pgsteal_normal 0
pgsteal_movable 0
pgscan_kswapd_dma 96
pgscan_kswapd_dma32 564994
pgscan_kswapd_normal 0
pgscan_kswapd_movable 0
pgscan_direct_dma 448
pgscan_direct_dma32 268795
pgscan_direct_normal 0
pgscan_direct_movable 0
pginodesteal 2411
slabs_scanned 41600
kswapd_steal 247394
kswapd_inodesteal 6479
kswapd_highorder_rewakeup 8
kswapd_slept_prematurely_fast 329
kswapd_slept_prematurely_slow 55
pageoutrun 3525
allocstall 686
pgrotated 238322
unevictable_pgs_culled 4254
unevictable_pgs_scanned 0
unevictable_pgs_rescued 33336
unevictable_pgs_mlocked 43192
unevictable_pgs_munlocked 42772
unevictable_pgs_cleared 2
unevictable_pgs_stranded 0
unevictable_pgs_mlockfreed 0

  reply	other threads:[~2009-11-04  0:01 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-10-27 13:40 [PATCH 0/3] Reduce GFP_ATOMIC allocation failures, partial fix V3 Mel Gorman
2009-10-27 13:40 ` [PATCH 1/3] page allocator: Always wake kswapd when restarting an allocation attempt after direct reclaim failed Mel Gorman
2009-10-27 13:40 ` [PATCH 2/3] page allocator: Do not allow interrupts to use ALLOC_HARDER Mel Gorman
     [not found]   ` <1256650833-15516-3-git-send-email-mel-wPRd99KPJ+uzQB+pC5nmwQ@public.gmane.org>
2009-10-27 20:09     ` Andrew Morton
2009-10-27 21:12       ` David Rientjes
2009-10-31 18:40         ` Pavel Machek
2009-10-31 19:51           ` David Rientjes
2009-10-31 20:11             ` Pavel Machek
2009-10-31 21:19               ` David Rientjes
2009-10-31 22:29                 ` Pavel Machek
2009-10-31 22:55                   ` Rik van Riel
2009-11-01  7:35                     ` Pavel Machek
2009-11-01 12:37                       ` KOSAKI Motohiro
2009-11-01 14:44                       ` Rik van Riel
2009-11-01 19:32                         ` Pavel Machek
2009-11-02 16:38                         ` Christoph Lameter
2009-10-31 23:59               ` Rik van Riel
2009-11-02 16:42                 ` Christoph Lameter
2009-11-02 20:53                   ` David Rientjes
2009-11-03 17:10                     ` Christoph Lameter
2009-11-04  1:46                       ` David Rientjes
2009-11-04  9:01                         ` Pavel Machek
2009-11-09 10:11                           ` Mel Gorman
2009-10-28 10:24       ` Mel Gorman
2009-10-27 13:40 ` [PATCH 3/3] vmscan: Force kswapd to take notice faster when high-order watermarks are being hit Mel Gorman
2009-10-27 18:18   ` Rik van Riel
2009-10-27 20:19   ` Andrew Morton
2009-10-28  3:54     ` KOSAKI Motohiro
2009-10-28 10:29     ` Mel Gorman
2009-10-28 19:47       ` Andrew Morton
2009-11-02 16:05         ` Mel Gorman
2009-11-02 17:32           ` Frans Pop
2009-11-02 17:38             ` Mel Gorman
2009-11-02 20:36               ` Mel Gorman
2009-11-03 22:01               ` Frans Pop
2009-11-03 22:08                 ` Mel Gorman
2009-11-04  0:01                   ` Frans Pop [this message]
2009-11-04  1:18                     ` Mel Gorman
2009-11-04  2:05                       ` Frans Pop
2009-11-04  2:08                         ` Frans Pop
2009-11-04 15:48                         ` Mel Gorman
2009-11-04 20:57                           ` Frans Pop
2009-11-05 16:48                             ` [PATCH 3/3] vmscan: Force kswapd to take notice faster when high-order watermarks are being hit (data on latencies available) Mel Gorman
2009-11-12 11:36                               ` Frans Pop
2009-11-04  2:08                       ` [PATCH 3/3] vmscan: Force kswapd to take notice faster when high-order watermarks are being hit Mel Gorman
2009-10-28 13:02 ` [PATCH 0/3] Reduce GFP_ATOMIC allocation failures, partial fix V3 Karol Lewandowski

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=200911040101.50194.elendil@planet.nl \
    --to=elendil@planet.nl \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux-foundation.org \
    --cc=jkosina@suse.cz \
    --cc=karol.k.lewandowski@gmail.com \
    --cc=kernel-testers@vger.kernel.org \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lists@fuchsschwanzdomain.de \
    --cc=mel@csn.ul.ie \
    --cc=penberg@cs.helsinki.fi \
    --cc=riel@redhat.com \
    --cc=skraw@ithnet.com \
    --cc=stable@kernel.org \
    --cc=tobi@oetiker.ch \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox