[PATCH] ZVC/zone_reclaim: Leave 1% of unmapped pagecache pages for file I/O

It turns out that it is advantageous to leave a small portion of unmapped file
backed pages if all of a zone's pages (or almost all pages) are allocated and
so the page allocator has to go off-node.

This allows recently used file I/O buffers to stay on the node and
reduces the times that zone reclaim is invoked if file I/O occurs
when we run out of memory in a zone.

The problem is that zone reclaim runs too frequently when the page cache is
used for file I/O (read write and therefore unmapped pages!) alone and we have
almost all pages of the zone allocated.  Zone reclaim may remove 32 unmapped
pages.  File I/O will use these pages for the next read/write requests and the
unmapped pages increase.  After the zone has filled up again zone reclaim will
remove it again after only 32 pages.  This cycle is too inefficient and there
are potentially too many zone reclaim cycles.

With the 1% boundary we may still remove all unmapped pages for file I/O in
zone reclaim pass.  However.  it will take a large number of read and writes
to get back to 1% again where we trigger zone reclaim again.

The zone reclaim 2.6.16/17 does not show this behavior because we have a 30
second timeout.

[akpm@osdl.org: rename the /proc file and the variable]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 8 insertions, 1 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 27e748eb72b0..656b588a9f96 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -150,6 +150,10 @@ struct zone {
 	unsigned long		lowmem_reserve[MAX_NR_ZONES];
 
 #ifdef CONFIG_NUMA
+	/*
+	 * zone reclaim becomes active if more unmapped pages exist.
+	 */
+	unsigned long		min_unmapped_ratio;
 	struct per_cpu_pageset	*pageset[NR_CPUS];
 #else
 	struct per_cpu_pageset	pageset[NR_CPUS];
@@ -414,6 +418,8 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *,
 					void __user *, size_t *, loff_t *);
 int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *,
 					void __user *, size_t *, loff_t *);
+int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
+			struct file *, void __user *, size_t *, loff_t *);
 
 #include <linux/topology.h>
 /* Returns the number of the current Node. */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index cf6ca6e377bd..5e59184c9096 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -189,6 +189,7 @@ extern long vm_total_pages;
 
 #ifdef CONFIG_NUMA
 extern int zone_reclaim_mode;
+extern int sysctl_min_unmapped_ratio;
 extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
 #else
 #define zone_reclaim_mode 0
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 46e4d8f2771f..e4b1a4d4dcf3 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -188,7 +188,7 @@ enum
 	VM_DROP_PAGECACHE=29,	/* int: nuke lots of pagecache */
 	VM_PERCPU_PAGELIST_FRACTION=30,/* int: fraction of pages in each percpu_pagelist */
 	VM_ZONE_RECLAIM_MODE=31, /* reclaim local zone memory before going off node */
-	VM_ZONE_RECLAIM_INTERVAL=32, /* time period to wait after reclaim failure */
+	VM_MIN_UNMAPPED=32,	/* Set min percent of unmapped pages */
 	VM_PANIC_ON_OOM=33,	/* panic at out-of-memory */
 	VM_VDSO_ENABLED=34,	/* map VDSO into new processes? */
 };