aboutsummaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorMartin Hicks <mort@sgi.com>2005-06-21 17:14:41 -0700
committerLinus Torvalds <torvalds@ppc970.osdl.org>2005-06-21 18:46:14 -0700
commit753ee728964e5afb80c17659cc6c3a6fd0a42fe0 (patch)
tree41c9a7700d0858c1f77c5bdaba97e5b636f69b06 /include
parentbfbb38fb808ac23ef44472d05d9bb36edfb49ed0 (diff)
[PATCH] VM: early zone reclaim
This is the core of the (much simplified) early reclaim. The goal of this patch is to reclaim some easily-freed pages from a zone before falling back onto another zone. One of the major uses of this is NUMA machines. With the default allocator behavior the allocator would look for memory in another zone, which might be off-node, before trying to reclaim from the current zone. This adds a zone tuneable to enable early zone reclaim. It is selected on a per-zone basis and is turned on/off via syscall. Adding some extra throttling on the reclaim was also required (patch 4/4). Without the machine would grind to a crawl when doing a "make -j" kernel build. Even with this patch the System Time is higher on average, but it seems tolerable. Here are some numbers for kernbench runs on a 2-node, 4cpu, 8Gig RAM Altix in the "make -j" run: wall user sys %cpu ctx sw. sleeps ---- ---- --- ---- ------ ------ No patch 1009 1384 847 258 298170 504402 w/patch, no reclaim 880 1376 667 288 254064 396745 w/patch & reclaim 1079 1385 926 252 291625 548873 These numbers are the average of 2 runs of 3 "make -j" runs done right after system boot. Run-to-run variability for "make -j" is huge, so these numbers aren't terribly useful except to seee that with reclaim the benchmark still finishes in a reasonable amount of time. I also looked at the NUMA hit/miss stats for the "make -j" runs and the reclaim doesn't make any difference when the machine is thrashing away. Doing a "make -j8" on a single node that is filled with page cache pages takes 700 seconds with reclaim turned on and 735 seconds without reclaim (due to remote memory accesses). The simple zone_reclaim syscall program is at http://www.bork.org/~mort/sgi/zone_reclaim.c Signed-off-by: Martin Hicks <mort@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'include')
-rw-r--r--include/asm-i386/unistd.h2
-rw-r--r--include/asm-ia64/unistd.h1
-rw-r--r--include/linux/mmzone.h6
-rw-r--r--include/linux/swap.h1
4 files changed, 9 insertions, 1 deletions
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index 61bcc1b1e3f..176413fb9ae 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -256,7 +256,7 @@
#define __NR_io_submit 248
#define __NR_io_cancel 249
#define __NR_fadvise64 250
-
+#define __NR_set_zone_reclaim 251
#define __NR_exit_group 252
#define __NR_lookup_dcookie 253
#define __NR_epoll_create 254
diff --git a/include/asm-ia64/unistd.h b/include/asm-ia64/unistd.h
index 33e26c557c5..f7f43ec2483 100644
--- a/include/asm-ia64/unistd.h
+++ b/include/asm-ia64/unistd.h
@@ -263,6 +263,7 @@
#define __NR_add_key 1271
#define __NR_request_key 1272
#define __NR_keyctl 1273
+#define __NR_set_zone_reclaim 1276
#ifdef __KERNEL__
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index beacd931b60..dfc2452ccb1 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -145,6 +145,12 @@ struct zone {
int all_unreclaimable; /* All pages pinned */
/*
+ * Does the allocator try to reclaim pages from the zone as soon
+ * as it fails a watermark_ok() in __alloc_pages?
+ */
+ int reclaim_pages;
+
+ /*
* prev_priority holds the scanning priority for this zone. It is
* defined as the scanning priority at which we achieved our reclaim
* target at the previous try_to_free_pages() or balance_pgdat()
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3bbc41be9bd..0d21e682d99 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -173,6 +173,7 @@ extern void swap_setup(void);
/* linux/mm/vmscan.c */
extern int try_to_free_pages(struct zone **, unsigned int, unsigned int);
+extern int zone_reclaim(struct zone *, unsigned int, unsigned int);
extern int shrink_all_memory(int);
extern int vm_swappiness;