From: Mel Gorman <mel@csn.ul.ie>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>,
Christoph Lameter <cl@linux-foundation.org>,
Adam Litke <agl@us.ibm.com>, Avi Kivity <avi@redhat.com>,
David Rientjes <rientjes@google.com>,
Minchan Kim <minchan.kim@gmail.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Rik van Riel <riel@redhat.com>, Mel Gorman <mel@csn.ul.ie>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH 13/14] mm,compaction: Add a tunable that decides when memory should be compacted and when it should be reclaimed
Date: Tue, 20 Apr 2010 22:01:15 +0100 [thread overview]
Message-ID: <1271797276-31358-14-git-send-email-mel@csn.ul.ie> (raw)
In-Reply-To: <1271797276-31358-1-git-send-email-mel@csn.ul.ie>
The kernel applies some heuristics when deciding if memory should be
compacted or reclaimed to satisfy a high-order allocation. One of these
is based on the fragmentation. If the index is below 500, memory will not
be compacted. This choice is arbitrary and not based on data. To help
optimise the system and set a sensible default for this value, this patch
adds a sysctl extfrag_threshold. The kernel will only compact memory if
the fragmentation index is above the extfrag_threshold.
[randy.dunlap@oracle.com: Fix build errors when proc fs is not configured]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
---
Documentation/sysctl/vm.txt | 16 +++++++++++++++-
include/linux/compaction.h | 3 +++
kernel/sysctl.c | 15 +++++++++++++++
mm/compaction.c | 12 +++++++++++-
4 files changed, 44 insertions(+), 2 deletions(-)
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 3b3fa1b..6274970 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -27,6 +27,7 @@ Currently, these files are in /proc/sys/vm:
- dirty_ratio
- dirty_writeback_centisecs
- drop_caches
+- extfrag_threshold
- hugepages_treat_as_movable
- hugetlb_shm_group
- laptop_mode
@@ -149,6 +149,20 @@ user should run `sync' first.
==============================================================
+extfrag_threshold
+
+This parameter affects whether the kernel will compact memory or direct
+reclaim to satisfy a high-order allocation. /proc/extfrag_index shows what
+the fragmentation index for each order is in each zone in the system. Values
+tending towards 0 imply allocations would fail due to lack of memory,
+values towards 1000 imply failures are due to fragmentation and -1 implies
+that the allocation will succeed as long as watermarks are met.
+
+The kernel will not compact memory in a zone if the
+fragmentation index is <= extfrag_threshold. The default value is 500.
+
+==============================================================
+
hugepages_treat_as_movable
This parameter is only useful when kernelcore= is specified at boot time to
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index eed40ec..3719325 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -15,6 +15,9 @@
extern int sysctl_compact_memory;
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos);
+extern int sysctl_extfrag_threshold;
+extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *length, loff_t *ppos);
extern int fragmentation_index(struct zone *zone, unsigned int order);
extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 987d6cf..43dc29d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -262,6 +262,11 @@ static int min_sched_shares_ratelimit = 100000; /* 100 usec */
static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */
#endif
+#ifdef CONFIG_COMPACTION
+static int min_extfrag_threshold;
+static int max_extfrag_threshold = 1000;
+#endif
+
static struct ctl_table kern_table[] = {
{
.procname = "sched_child_runs_first",
@@ -1130,6 +1135,16 @@ static struct ctl_table vm_table[] = {
.mode = 0200,
.proc_handler = sysctl_compaction_handler,
},
+ {
+ .procname = "extfrag_threshold",
+ .data = &sysctl_extfrag_threshold,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = sysctl_extfrag_handler,
+ .extra1 = &min_extfrag_threshold,
+ .extra2 = &max_extfrag_threshold,
+ },
+
#endif /* CONFIG_COMPACTION */
{
.procname = "min_free_kbytes",
diff --git a/mm/compaction.c b/mm/compaction.c
index 06aed42..bd13560 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -433,6 +433,8 @@ static unsigned long compact_zone_order(struct zone *zone,
return compact_zone(zone, &cc);
}
+int sysctl_extfrag_threshold = 500;
+
/**
* try_to_compact_pages - Direct compact to satisfy a high-order allocation
* @zonelist: The zonelist used for the current allocation
@@ -491,7 +493,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
* Only compact if a failure would be due to fragmentation.
*/
fragindex = fragmentation_index(zone, order);
- if (fragindex >= 0 && fragindex <= 500)
+ if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
continue;
if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) {
@@ -572,6 +574,14 @@ int sysctl_compaction_handler(struct ctl_table *table, int write,
return 0;
}
+int sysctl_extfrag_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *length, loff_t *ppos)
+{
+ proc_dointvec_minmax(table, write, buffer, length, ppos);
+
+ return 0;
+}
+
#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
ssize_t sysfs_compact_node(struct sys_device *dev,
struct sysdev_attribute *attr,
--
1.6.5
--
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/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2010-04-20 21:02 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-20 21:01 [PATCH 0/14] Memory Compaction v8 Mel Gorman
2010-04-20 21:01 ` [PATCH 01/14] mm,migration: Take a reference to the anon_vma before migrating Mel Gorman
2010-04-21 2:49 ` KAMEZAWA Hiroyuki
2010-04-20 21:01 ` [PATCH 02/14] mm,migration: Share the anon_vma ref counts between KSM and page migration Mel Gorman
2010-04-20 21:01 ` [PATCH 03/14] mm,migration: Do not try to migrate unmapped anonymous pages Mel Gorman
2010-04-20 21:01 ` [PATCH 04/14] mm,migration: Allow the migration of PageSwapCache pages Mel Gorman
2010-04-21 14:30 ` Christoph Lameter
2010-04-21 15:00 ` Mel Gorman
2010-04-21 15:05 ` Christoph Lameter
2010-04-21 15:14 ` Mel Gorman
2010-04-21 15:31 ` Christoph Lameter
2010-04-21 15:34 ` Mel Gorman
2010-04-21 15:46 ` Christoph Lameter
2010-04-22 9:28 ` Mel Gorman
2010-04-22 9:46 ` KAMEZAWA Hiroyuki
2010-04-22 10:13 ` Minchan Kim
2010-04-22 10:31 ` KAMEZAWA Hiroyuki
2010-04-22 10:51 ` KAMEZAWA Hiroyuki
2010-04-22 14:14 ` Mel Gorman
2010-04-22 14:18 ` Minchan Kim
2010-04-22 15:40 ` Mel Gorman
2010-04-22 16:13 ` Mel Gorman
2010-04-22 19:29 ` Mel Gorman
2010-04-22 19:40 ` Christoph Lameter
2010-04-22 23:52 ` KAMEZAWA Hiroyuki
2010-04-23 9:03 ` Mel Gorman
2010-04-22 14:23 ` Minchan Kim
2010-04-22 14:40 ` Minchan Kim
2010-04-22 15:44 ` Mel Gorman
2010-04-23 18:31 ` Andrea Arcangeli
2010-04-23 19:23 ` Mel Gorman
2010-04-23 19:39 ` Andrea Arcangeli
2010-04-23 21:35 ` Andrea Arcangeli
2010-04-24 10:52 ` Mel Gorman
2010-04-24 11:13 ` Andrea Arcangeli
2010-04-24 11:59 ` Mel Gorman
2010-04-24 14:30 ` Andrea Arcangeli
2010-04-26 21:54 ` Rik van Riel
2010-04-26 22:11 ` Mel Gorman
2010-04-26 22:26 ` Andrea Arcangeli
2010-04-25 14:41 ` Andrea Arcangeli
2010-04-27 9:40 ` Mel Gorman
2010-04-27 10:41 ` KAMEZAWA Hiroyuki
2010-04-27 11:12 ` Mel Gorman
2010-04-27 15:42 ` Andrea Arcangeli
2010-04-24 10:50 ` Mel Gorman
2010-04-22 15:14 ` Christoph Lameter
2010-04-23 3:39 ` Paul E. McKenney
2010-04-23 4:55 ` Minchan Kim
2010-04-21 23:59 ` KAMEZAWA Hiroyuki
2010-04-22 0:11 ` Minchan Kim
2010-04-20 21:01 ` [PATCH 05/14] mm: Allow CONFIG_MIGRATION to be set without CONFIG_NUMA or memory hot-remove Mel Gorman
2010-04-20 21:01 ` [PATCH 06/14] mm: Export unusable free space index via debugfs Mel Gorman
2010-04-20 21:01 ` [PATCH 07/14] mm: Export fragmentation " Mel Gorman
2010-04-20 21:01 ` [PATCH 08/14] mm: Move definition for LRU isolation modes to a header Mel Gorman
2010-04-20 21:01 ` [PATCH 09/14] mm,compaction: Memory compaction core Mel Gorman
2010-04-20 21:01 ` [PATCH 10/14] mm,compaction: Add /proc trigger for memory compaction Mel Gorman
2010-04-20 21:01 ` [PATCH 11/14] mm,compaction: Add /sys trigger for per-node " Mel Gorman
2010-04-20 21:01 ` [PATCH 12/14] mm,compaction: Direct compact when a high-order allocation fails Mel Gorman
2010-05-05 12:19 ` [PATCH] fix count_vm_event preempt in memory compaction direct reclaim Andrea Arcangeli
2010-05-05 12:51 ` Mel Gorman
2010-05-05 13:11 ` Andrea Arcangeli
2010-05-05 13:55 ` Mel Gorman
2010-05-05 14:48 ` Andrea Arcangeli
2010-05-05 15:14 ` Mel Gorman
2010-05-05 15:25 ` Andrea Arcangeli
2010-05-05 15:32 ` Mel Gorman
2010-04-20 21:01 ` Mel Gorman [this message]
2010-04-20 21:01 ` [PATCH 14/14] mm,compaction: Defer compaction using an exponential backoff when compaction fails Mel Gorman
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=1271797276-31358-14-git-send-email-mel@csn.ul.ie \
--to=mel@csn.ul.ie \
--cc=aarcange@redhat.com \
--cc=agl@us.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=avi@redhat.com \
--cc=cl@linux-foundation.org \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan.kim@gmail.com \
--cc=riel@redhat.com \
--cc=rientjes@google.com \
/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;
as well as URLs for NNTP newsgroup(s).