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
next prev parent reply other threads:[~2009-11-04 0:01 UTC|newest]
Thread overview: 115+ 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 ` Mel Gorman
2009-10-27 13:40 ` [PATCH 2/3] page allocator: Do not allow interrupts to use ALLOC_HARDER Mel Gorman
2009-10-27 13:40 ` 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 20:09 ` Andrew Morton
2009-10-27 20:09 ` Andrew Morton
[not found] ` <20091027130924.fa903f5a.akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2009-10-27 21:12 ` David Rientjes
2009-10-27 21:12 ` David Rientjes
2009-10-27 21:12 ` David Rientjes
[not found] ` <alpine.DEB.2.00.0910271411530.9183-X6Q0R45D7oAcqpCFd4KODRPsWskHk0ljAL8bYrjMMd8@public.gmane.org>
2009-10-31 18:40 ` Pavel Machek
2009-10-31 18:40 ` Pavel Machek
2009-10-31 18:40 ` Pavel Machek
2009-10-31 19:51 ` David Rientjes
2009-10-31 19:51 ` David Rientjes
2009-10-31 20:11 ` Pavel Machek
2009-10-31 20:11 ` Pavel Machek
[not found] ` <20091031201158.GB29536-I/5MKhXcvmPrBKCeMvbIDA@public.gmane.org>
2009-10-31 21:19 ` David Rientjes
2009-10-31 21:19 ` David Rientjes
2009-10-31 21:19 ` David Rientjes
2009-10-31 22:29 ` Pavel Machek
2009-10-31 22:29 ` Pavel Machek
2009-10-31 22:55 ` Rik van Riel
2009-10-31 22:55 ` Rik van Riel
[not found] ` <4AECC04B.9060808-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2009-11-01 7:35 ` Pavel Machek
2009-11-01 7:35 ` Pavel Machek
2009-11-01 7:35 ` Pavel Machek
[not found] ` <20091101073527.GB32720-I/5MKhXcvmPrBKCeMvbIDA@public.gmane.org>
2009-11-01 12:37 ` KOSAKI Motohiro
2009-11-01 12:37 ` KOSAKI Motohiro
2009-11-01 12:37 ` KOSAKI Motohiro
2009-11-01 14:44 ` Rik van Riel
2009-11-01 14:44 ` Rik van Riel
[not found] ` <4AED9EB4.5080601-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2009-11-01 19:32 ` Pavel Machek
2009-11-01 19:32 ` Pavel Machek
2009-11-01 19:32 ` Pavel Machek
2009-11-02 16:38 ` Christoph Lameter
2009-11-02 16:38 ` Christoph Lameter
2009-10-31 23:59 ` Rik van Riel
2009-10-31 23:59 ` Rik van Riel
2009-11-02 16:42 ` Christoph Lameter
2009-11-02 16:42 ` Christoph Lameter
2009-11-02 20:53 ` David Rientjes
2009-11-02 20:53 ` David Rientjes
2009-11-02 20:53 ` David Rientjes
2009-11-03 17:10 ` Christoph Lameter
2009-11-03 17:10 ` Christoph Lameter
2009-11-04 1:46 ` David Rientjes
2009-11-04 1:46 ` David Rientjes
2009-11-04 1:46 ` David Rientjes
[not found] ` <alpine.DEB.2.00.0911031739380.1187-X6Q0R45D7oAcqpCFd4KODRPsWskHk0ljAL8bYrjMMd8@public.gmane.org>
2009-11-04 9:01 ` Pavel Machek
2009-11-04 9:01 ` Pavel Machek
2009-11-04 9:01 ` Pavel Machek
[not found] ` <20091104090140.GA14694-I/5MKhXcvmPrBKCeMvbIDA@public.gmane.org>
2009-11-09 10:11 ` Mel Gorman
2009-11-09 10:11 ` Mel Gorman
2009-11-09 10:11 ` Mel Gorman
2009-10-28 10:24 ` 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 13:40 ` Mel Gorman
2009-10-27 18:18 ` Rik van Riel
2009-10-27 18:18 ` Rik van Riel
[not found] ` <1256650833-15516-4-git-send-email-mel-wPRd99KPJ+uzQB+pC5nmwQ@public.gmane.org>
2009-10-27 18:18 ` Rik van Riel
2009-10-27 20:19 ` Andrew Morton
2009-10-27 20:19 ` Andrew Morton
[not found] ` <20091027131905.410ec04a.akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2009-10-28 3:54 ` KOSAKI Motohiro
2009-10-28 3:54 ` KOSAKI Motohiro
2009-10-28 3:54 ` KOSAKI Motohiro
2009-10-28 10:29 ` Mel Gorman
2009-10-28 10:29 ` Mel Gorman
2009-10-28 10:29 ` Mel Gorman
2009-10-28 19:47 ` Andrew Morton
2009-10-28 19:47 ` Andrew Morton
[not found] ` <20091028124756.7af44b6b.akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2009-11-02 16:05 ` Mel Gorman
2009-11-02 16:05 ` Mel Gorman
2009-11-02 16:05 ` Mel Gorman
2009-11-02 17:32 ` Frans Pop
2009-11-02 17:32 ` Frans Pop
[not found] ` <200911021832.59035.elendil-EIBgga6/0yRmR6Xm/wNWPw@public.gmane.org>
2009-11-02 17:38 ` Mel Gorman
2009-11-02 17:38 ` Mel Gorman
2009-11-02 17:38 ` Mel Gorman
2009-11-02 20:36 ` Mel Gorman
2009-11-02 20:36 ` Mel Gorman
2009-11-03 22:01 ` Frans Pop
[not found] ` <200911032301.59662.elendil-EIBgga6/0yRmR6Xm/wNWPw@public.gmane.org>
2009-11-03 22:08 ` Mel Gorman
2009-11-03 22:08 ` Mel Gorman
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 1:18 ` Mel Gorman
[not found] ` <20091104011811.GG22046-wPRd99KPJ+uzQB+pC5nmwQ@public.gmane.org>
2009-11-04 2:05 ` Frans Pop
2009-11-04 2:05 ` Frans Pop
2009-11-04 2:05 ` Frans Pop
2009-11-04 2:08 ` Frans Pop
2009-11-04 2:08 ` Frans Pop
[not found] ` <200911040305.59352.elendil-EIBgga6/0yRmR6Xm/wNWPw@public.gmane.org>
2009-11-04 15:48 ` Mel Gorman
2009-11-04 15:48 ` Mel Gorman
2009-11-04 15:48 ` Mel Gorman
[not found] ` <20091104154853.GM22046-wPRd99KPJ+uzQB+pC5nmwQ@public.gmane.org>
2009-11-04 20:57 ` Frans Pop
2009-11-04 20:57 ` Frans Pop
2009-11-04 20:57 ` Frans Pop
[not found] ` <200911042157.25020.elendil-EIBgga6/0yRmR6Xm/wNWPw@public.gmane.org>
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
2009-11-05 16:48 ` Mel Gorman
2009-11-05 16:48 ` Mel Gorman
[not found] ` <20091105164832.GB25926-wPRd99KPJ+uzQB+pC5nmwQ@public.gmane.org>
2009-11-12 11:36 ` Frans Pop
2009-11-12 11:36 ` Frans Pop
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
2009-11-04 2:08 ` Mel Gorman
2009-11-04 2:08 ` Mel Gorman
[not found] ` <1256650833-15516-1-git-send-email-mel-wPRd99KPJ+uzQB+pC5nmwQ@public.gmane.org>
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 ` Mel Gorman
2009-10-27 13:40 ` Mel Gorman
2009-10-28 13:02 ` [PATCH 0/3] Reduce GFP_ATOMIC allocation failures, partial fix V3 Karol Lewandowski
2009-10-28 13:02 ` Karol Lewandowski
2009-10-28 13:02 ` 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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.