From: Johannes Stezenbach <js@sig21.net>
To: Hillf Danton <dhillf@gmail.com>
Cc: "Toralf Förster" <toralf.foerster@gmx.de>,
linux-kernel@vger.kernel.org, "Rik van Riel" <riel@redhat.com>,
linux-mm@kvack.org
Subject: Re: swap storm since kernel 3.2.x
Date: Thu, 9 Feb 2012 14:21:55 +0100 [thread overview]
Message-ID: <20120209132155.GA15147@sig21.net> (raw)
In-Reply-To: <CAJd=RBDzUpUgZLVU+WSfb8grzMAbi3fcyyZkpX8qpaxu6zYe1g@mail.gmail.com>
On Thu, Feb 09, 2012 at 08:02:20PM +0800, Hillf Danton wrote:
> On Thu, Feb 9, 2012 at 7:36 PM, Johannes Stezenbach <js@sig21.net> wrote:
> > On Wed, Feb 08, 2012 at 08:34:14PM +0800, Hillf Danton wrote:
> >> And I want to ask kswapd to do less work, the attached diff is
> >> based on 3.2.5, mind to test it with CONFIG_DEBUG_OBJECTS enabled?
> >
> > Sorry, for slow reply. The patch does not apply to 3.2.4
> > (3.2.5 only has the ASPM change which I don't want to
> > try atm). Is the patch below correct?
> >
>
> It is fine;)
Hm, with 3.2.4 + patch +
CONFIG_DEBUG_OBJECTS=y
# CONFIG_DEBUG_OBJECTS_SELFTEST is not set
# CONFIG_DEBUG_OBJECTS_FREE is not set
CONFIG_DEBUG_OBJECTS_TIMERS=y
CONFIG_DEBUG_OBJECTS_WORK=y
CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
it looks good. Neither do I get the huge debug_objects_cache
nor does it swap, after running a crosstool-ng toolchain build.
Well, last time I also had one kvm -m 1G instance running. I'll
try if that triggers the issue. So far:
OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME
689249 689235 99% 0.36K 31334 22 250672K debug_objects_cache
625185 609295 97% 0.42K 34735 18 277880K buffer_head
103834 103393 99% 1.74K 7245 18 231840K ext3_inode_cache
84348 82351 97% 0.58K 3124 27 49984K dentry
MemTotal: 3938800 kB
MemFree: 77136 kB
Buffers: 68892 kB
Cached: 2686376 kB
SwapCached: 8 kB
Active: 1343464 kB
Inactive: 1584476 kB
Active(anon): 78712 kB
Inactive(anon): 145220 kB
Active(file): 1264752 kB
Inactive(file): 1439256 kB
Unevictable: 0 kB
Mlocked: 0 kB
SwapTotal: 3903484 kB
SwapFree: 3903248 kB
Dirty: 64 kB
Writeback: 0 kB
AnonPages: 172676 kB
Mapped: 41868 kB
Shmem: 51260 kB
Slab: 872400 kB
SReclaimable: 549904 kB
SUnreclaim: 322496 kB
KernelStack: 1432 kB
PageTables: 3172 kB
NFS_Unstable: 0 kB
Bounce: 0 kB
WritebackTmp: 0 kB
CommitLimit: 5872884 kB
Committed_AS: 474604 kB
VmallocTotal: 34359738367 kB
VmallocUsed: 345800 kB
VmallocChunk: 34359386531 kB
DirectMap4k: 12288 kB
DirectMap2M: 4098048 kB
Thanks,
Johannes
--
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-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Johannes Stezenbach <js@sig21.net>
To: Hillf Danton <dhillf@gmail.com>
Cc: "Toralf Förster" <toralf.foerster@gmx.de>,
linux-kernel@vger.kernel.org, "Rik van Riel" <riel@redhat.com>,
linux-mm@kvack.org
Subject: Re: swap storm since kernel 3.2.x
Date: Thu, 9 Feb 2012 14:21:55 +0100 [thread overview]
Message-ID: <20120209132155.GA15147@sig21.net> (raw)
In-Reply-To: <CAJd=RBDzUpUgZLVU+WSfb8grzMAbi3fcyyZkpX8qpaxu6zYe1g@mail.gmail.com>
On Thu, Feb 09, 2012 at 08:02:20PM +0800, Hillf Danton wrote:
> On Thu, Feb 9, 2012 at 7:36 PM, Johannes Stezenbach <js@sig21.net> wrote:
> > On Wed, Feb 08, 2012 at 08:34:14PM +0800, Hillf Danton wrote:
> >> And I want to ask kswapd to do less work, the attached diff is
> >> based on 3.2.5, mind to test it with CONFIG_DEBUG_OBJECTS enabled?
> >
> > Sorry, for slow reply. The patch does not apply to 3.2.4
> > (3.2.5 only has the ASPM change which I don't want to
> > try atm). Is the patch below correct?
> >
>
> It is fine;)
Hm, with 3.2.4 + patch +
CONFIG_DEBUG_OBJECTS=y
# CONFIG_DEBUG_OBJECTS_SELFTEST is not set
# CONFIG_DEBUG_OBJECTS_FREE is not set
CONFIG_DEBUG_OBJECTS_TIMERS=y
CONFIG_DEBUG_OBJECTS_WORK=y
CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
it looks good. Neither do I get the huge debug_objects_cache
nor does it swap, after running a crosstool-ng toolchain build.
Well, last time I also had one kvm -m 1G instance running. I'll
try if that triggers the issue. So far:
OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME
689249 689235 99% 0.36K 31334 22 250672K debug_objects_cache
625185 609295 97% 0.42K 34735 18 277880K buffer_head
103834 103393 99% 1.74K 7245 18 231840K ext3_inode_cache
84348 82351 97% 0.58K 3124 27 49984K dentry
MemTotal: 3938800 kB
MemFree: 77136 kB
Buffers: 68892 kB
Cached: 2686376 kB
SwapCached: 8 kB
Active: 1343464 kB
Inactive: 1584476 kB
Active(anon): 78712 kB
Inactive(anon): 145220 kB
Active(file): 1264752 kB
Inactive(file): 1439256 kB
Unevictable: 0 kB
Mlocked: 0 kB
SwapTotal: 3903484 kB
SwapFree: 3903248 kB
Dirty: 64 kB
Writeback: 0 kB
AnonPages: 172676 kB
Mapped: 41868 kB
Shmem: 51260 kB
Slab: 872400 kB
SReclaimable: 549904 kB
SUnreclaim: 322496 kB
KernelStack: 1432 kB
PageTables: 3172 kB
NFS_Unstable: 0 kB
Bounce: 0 kB
WritebackTmp: 0 kB
CommitLimit: 5872884 kB
Committed_AS: 474604 kB
VmallocTotal: 34359738367 kB
VmallocUsed: 345800 kB
VmallocChunk: 34359386531 kB
DirectMap4k: 12288 kB
DirectMap2M: 4098048 kB
Thanks,
Johannes
next prev parent reply other threads:[~2012-02-09 13:22 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-02-04 10:09 swap storm since kernel 3.2.x Toralf Förster
2012-02-04 13:33 ` Johannes Stezenbach
2012-02-04 14:36 ` Toralf Förster
2012-02-05 4:45 ` Hillf Danton
2012-02-05 4:45 ` Hillf Danton
2012-02-05 10:07 ` Toralf Förster
2012-02-05 10:07 ` Toralf Förster
2012-02-05 11:38 ` Hillf Danton
2012-02-05 11:38 ` Hillf Danton
2012-02-08 8:56 ` Toralf Förster
2012-02-08 8:56 ` Toralf Förster
2012-02-08 11:52 ` Johannes Stezenbach
2012-02-08 11:52 ` Johannes Stezenbach
2012-02-08 12:34 ` Hillf Danton
2012-02-08 12:34 ` Hillf Danton
2012-02-09 11:36 ` Johannes Stezenbach
2012-02-09 11:36 ` Johannes Stezenbach
2012-02-09 12:02 ` Hillf Danton
2012-02-09 12:02 ` Hillf Danton
2012-02-09 13:21 ` Johannes Stezenbach [this message]
2012-02-09 13:21 ` Johannes Stezenbach
2012-02-09 13:54 ` Johannes Stezenbach
2012-02-09 13:54 ` Johannes Stezenbach
2012-02-09 14:06 ` Rik van Riel
2012-02-09 14:06 ` Rik van Riel
2012-02-10 12:36 ` Hillf Danton
2012-02-10 12:36 ` Hillf Danton
2012-02-09 13:04 ` Toralf Förster
2012-02-09 13:04 ` Toralf Förster
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=20120209132155.GA15147@sig21.net \
--to=js@sig21.net \
--cc=dhillf@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=riel@redhat.com \
--cc=toralf.foerster@gmx.de \
/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.