linux/Documentation/sysctl
Mel Gorman 90afa5de6f vmscan: properly account for the number of page cache pages zone_reclaim() can reclaim
A bug was brought to my attention against a distro kernel but it affects
mainline and I believe problems like this have been reported in various
guises on the mailing lists although I don't have specific examples at the
moment.

The reported problem was that malloc() stalled for a long time (minutes in
some cases) if a large tmpfs mount was occupying a large percentage of
memory overall.  The pages did not get cleaned or reclaimed by
zone_reclaim() because the zone_reclaim_mode was unsuitable, but the lists
are uselessly scanned frequencly making the CPU spin at near 100%.

This patchset intends to address that bug and bring the behaviour of
zone_reclaim() more in line with expectations which were noticed during
investigation.  It is based on top of mmotm and takes advantage of
Kosaki's work with respect to zone_reclaim().

Patch 1 fixes the heuristics that zone_reclaim() uses to determine if the
	scan should go ahead. The broken heuristic is what was causing the
	malloc() stall as it uselessly scanned the LRU constantly. Currently,
	zone_reclaim is assuming zone_reclaim_mode is 1 and historically it
	could not deal with tmpfs pages at all. This fixes up the heuristic so
	that an unnecessary scan is more likely to be correctly avoided.

Patch 2 notes that zone_reclaim() returning a failure automatically means
	the zone is marked full. This is not always true. It could have
	failed because the GFP mask or zone_reclaim_mode were unsuitable.

Patch 3 introduces a counter zreclaim_failed that will increment each
	time the zone_reclaim scan-avoidance heuristics fail. If that
	counter is rapidly increasing, then zone_reclaim_mode should be
	set to 0 as a temporarily resolution and a bug reported because
	the scan-avoidance heuristic is still broken.

This patch:

On NUMA machines, the administrator can configure zone_reclaim_mode that
is a more targetted form of direct reclaim.  On machines with large NUMA
distances for example, a zone_reclaim_mode defaults to 1 meaning that
clean unmapped pages will be reclaimed if the zone watermarks are not
being met.

There is a heuristic that determines if the scan is worthwhile but the
problem is that the heuristic is not being properly applied and is
basically assuming zone_reclaim_mode is 1 if it is enabled.  The lack of
proper detection can manfiest as high CPU usage as the LRU list is scanned
uselessly.

Historically, once enabled it was depending on NR_FILE_PAGES which may
include swapcache pages that the reclaim_mode cannot deal with.  Patch
vmscan-change-the-number-of-the-unmapped-files-in-zone-reclaim.patch by
Kosaki Motohiro noted that zone_page_state(zone, NR_FILE_PAGES) included
pages that were not file-backed such as swapcache and made a calculation
based on the inactive, active and mapped files.  This is far superior when
zone_reclaim==1 but if RECLAIM_SWAP is set, then NR_FILE_PAGES is a
reasonable starting figure.

This patch alters how zone_reclaim() works out how many pages it might be
able to reclaim given the current reclaim_mode.  If RECLAIM_SWAP is set in
the reclaim_mode it will either consider NR_FILE_PAGES as potential
candidates or else use NR_{IN}ACTIVE}_PAGES-NR_FILE_MAPPED to discount
swapcache and other non-file-backed pages.  If RECLAIM_WRITE is not set,
then NR_FILE_DIRTY number of pages are not candidates.  If RECLAIM_SWAP is
not set, then NR_FILE_MAPPED are not.

[kosaki.motohiro@jp.fujitsu.com: Estimate unmapped pages minus tmpfs pages]
[fengguang.wu@intel.com: Fix underflow problem in Kosaki's estimate]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-16 19:47:45 -07:00
..
00-INDEX documentation: update Documentation/filesystem/proc.txt and Documentation/sysctls 2009-04-02 19:04:53 -07:00
abi.txt
ctl_unnumbered.txt
fs.txt documentation: update Documentation/filesystem/proc.txt and Documentation/sysctls 2009-04-02 19:04:53 -07:00
kernel.txt Merge branch 'master' into next 2009-05-08 17:56:47 +10:00
net.txt Documentation/sysctl/net.txt: fix a typo 2009-04-13 15:04:28 -07:00
README
sunrpc.txt
vm.txt vmscan: properly account for the number of page cache pages zone_reclaim() can reclaim 2009-06-16 19:47:45 -07:00

Documentation for /proc/sys/		kernel version 2.2.10
	(c) 1998, 1999,  Rik van Riel <riel@nl.linux.org>

'Why', I hear you ask, 'would anyone even _want_ documentation
for them sysctl files? If anybody really needs it, it's all in
the source...'

Well, this documentation is written because some people either
don't know they need to tweak something, or because they don't
have the time or knowledge to read the source code.

Furthermore, the programmers who built sysctl have built it to
be actually used, not just for the fun of programming it :-)

==============================================================

Legal blurb:

As usual, there are two main things to consider:
1. you get what you pay for
2. it's free

The consequences are that I won't guarantee the correctness of
this document, and if you come to me complaining about how you
screwed up your system because of wrong documentation, I won't
feel sorry for you. I might even laugh at you...

But of course, if you _do_ manage to screw up your system using
only the sysctl options used in this file, I'd like to hear of
it. Not only to have a great laugh, but also to make sure that
you're the last RTFMing person to screw up.

In short, e-mail your suggestions, corrections and / or horror
stories to: <riel@nl.linux.org>

Rik van Riel.

==============================================================

Introduction:

Sysctl is a means of configuring certain aspects of the kernel
at run-time, and the /proc/sys/ directory is there so that you
don't even need special tools to do it!
In fact, there are only four things needed to use these config
facilities:
- a running Linux system
- root access
- common sense (this is especially hard to come by these days)
- knowledge of what all those values mean

As a quick 'ls /proc/sys' will show, the directory consists of
several (arch-dependent?) subdirs. Each subdir is mainly about
one part of the kernel, so you can do configuration on a piece
by piece basis, or just some 'thematic frobbing'.

The subdirs are about:
abi/		execution domains & personalities
debug/		<empty>
dev/		device specific information (eg dev/cdrom/info)
fs/		specific filesystems
		filehandle, inode, dentry and quota tuning
		binfmt_misc <Documentation/binfmt_misc.txt>
kernel/		global kernel info / tuning
		miscellaneous stuff
net/		networking stuff, for documentation look in:
		<Documentation/networking/>
proc/		<empty>
sunrpc/		SUN Remote Procedure Call (NFS)
vm/		memory management tuning
		buffer and cache management

These are the subdirs I have on my system. There might be more
or other subdirs in another setup. If you see another dir, I'd
really like to hear about it :-)