summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/sysctl/vm.txt17
-rw-r--r--arch/ia64/include/asm/topology.h3
-rw-r--r--arch/powerpc/include/asm/topology.h8
-rw-r--r--include/linux/topology.h3
-rw-r--r--mm/page_alloc.c2
5 files changed, 15 insertions, 18 deletions
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index dd9d0e33b443..5b6da0fb5fbf 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -772,16 +772,17 @@ This is value ORed together of
2 = Zone reclaim writes dirty pages out
4 = Zone reclaim swaps pages
-zone_reclaim_mode is set during bootup to 1 if it is determined that pages
-from remote zones will cause a measurable performance reduction. The
-page allocator will then reclaim easily reusable pages (those page
-cache pages that are currently not used) before allocating off node pages.
-
-It may be beneficial to switch off zone reclaim if the system is
-used for a file server and all of memory should be used for caching files
-from disk. In that case the caching effect is more important than
+zone_reclaim_mode is disabled by default. For file servers or workloads
+that benefit from having their data cached, zone_reclaim_mode should be
+left disabled as the caching effect is likely to be more important than
data locality.
+zone_reclaim may be enabled if it's known that the workload is partitioned
+such that each partition fits within a NUMA node and that accessing remote
+memory would cause a measurable performance reduction. The page allocator
+will then reclaim easily reusable pages (those page cache pages that are
+currently not used) before allocating off node pages.
+
Allowing zone reclaim to write out pages stops processes that are
writing large amounts of data from dirtying pages on other nodes. Zone
reclaim will write out dirty pages if a zone fills up and so effectively
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 3202aa74e0d6..6437ca21f61b 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -21,7 +21,8 @@
#define PENALTY_FOR_NODE_WITH_CPUS 255
/*
- * Distance above which we begin to use zone reclaim
+ * Nodes within this distance are eligible for reclaim by zone_reclaim() when
+ * zone_reclaim_mode is enabled.
*/
#define RECLAIM_DISTANCE 15
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index c9202151079f..6c8a8c5a37a1 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -9,12 +9,8 @@ struct device_node;
#ifdef CONFIG_NUMA
/*
- * Before going off node we want the VM to try and reclaim from the local
- * node. It does this if the remote distance is larger than RECLAIM_DISTANCE.
- * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of
- * 20, we never reclaim and go off node straight away.
- *
- * To fix this we choose a smaller value of RECLAIM_DISTANCE.
+ * If zone_reclaim_mode is enabled, a RECLAIM_DISTANCE of 10 will mean that
+ * all zones on all nodes will be eligible for zone_reclaim().
*/
#define RECLAIM_DISTANCE 10
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 973671ff9e7d..dda6ee521e74 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -58,7 +58,8 @@ int arch_update_cpu_topology(void);
/*
* If the distance between nodes in a system is larger than RECLAIM_DISTANCE
* (in whatever arch specific measurement units returned by node_distance())
- * then switch on zone reclaim on boot.
+ * and zone_reclaim_mode is enabled then the VM will only call zone_reclaim()
+ * on nodes within this distance.
*/
#define RECLAIM_DISTANCE 30
#endif
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7cfdcd808f52..dfe954fbb48a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1860,8 +1860,6 @@ static void __paginginit init_zone_allows_reclaim(int nid)
for_each_node_state(i, N_MEMORY)
if (node_distance(nid, i) <= RECLAIM_DISTANCE)
node_set(i, NODE_DATA(nid)->reclaim_nodes);
- else
- zone_reclaim_mode = 1;
}
#else /* CONFIG_NUMA */