summaryrefslogtreecommitdiff
path: root/include/linux/shrinker.h
diff options
context:
space:
mode:
authorGlauber Costa <glommer@openvz.org>2013-08-28 10:18:04 +1000
committerAl Viro <viro@zeniv.linux.org.uk>2013-09-10 18:56:31 -0400
commit1d3d4437eae1bb2963faab427f65f90663c64aa1 (patch)
tree1a5aa2be9b9f260fcd5dbd70b5c4e540b177b3f3 /include/linux/shrinker.h
parent0ce3d74450815500e31f16a0b65f6bab687985c3 (diff)
vmscan: per-node deferred work
The list_lru infrastructure already keeps per-node LRU lists in its node-specific list_lru_node arrays and provide us with a per-node API, and the shrinkers are properly equiped with node information. This means that we can now focus our shrinking effort in a single node, but the work that is deferred from one run to another is kept global at nr_in_batch. Work can be deferred, for instance, during direct reclaim under a GFP_NOFS allocation, where situation, all the filesystem shrinkers will be prevented from running and accumulate in nr_in_batch the amount of work they should have done, but could not. This creates an impedance problem, where upon node pressure, work deferred will accumulate and end up being flushed in other nodes. The problem we describe is particularly harmful in big machines, where many nodes can accumulate at the same time, all adding to the global counter nr_in_batch. As we accumulate more and more, we start to ask for the caches to flush even bigger numbers. The result is that the caches are depleted and do not stabilize. To achieve stable steady state behavior, we need to tackle it differently. In this patch we keep the deferred count per-node, in the new array nr_deferred[] (the name is also a bit more descriptive) and will never accumulate that to other nodes. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Diffstat (limited to 'include/linux/shrinker.h')
-rw-r--r--include/linux/shrinker.h14
1 files changed, 12 insertions, 2 deletions
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 76f520c4c394..8f80f243fed9 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -19,6 +19,8 @@ struct shrink_control {
/* shrink from these nodes */
nodemask_t nodes_to_scan;
+ /* current node being shrunk (for NUMA aware shrinkers) */
+ int nid;
};
#define SHRINK_STOP (~0UL)
@@ -44,6 +46,8 @@ struct shrink_control {
* due to potential deadlocks. If SHRINK_STOP is returned, then no further
* attempts to call the @scan_objects will be made from the current reclaim
* context.
+ *
+ * @flags determine the shrinker abilities, like numa awareness
*/
struct shrinker {
int (*shrink)(struct shrinker *, struct shrink_control *sc);
@@ -54,12 +58,18 @@ struct shrinker {
int seeks; /* seeks to recreate an obj */
long batch; /* reclaim batch size, 0 = default */
+ unsigned long flags;
/* These are for internal use */
struct list_head list;
- atomic_long_t nr_in_batch; /* objs pending delete */
+ /* objs pending delete, per node */
+ atomic_long_t *nr_deferred;
};
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
-extern void register_shrinker(struct shrinker *);
+
+/* Flags */
+#define SHRINKER_NUMA_AWARE (1 << 0)
+
+extern int register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);
#endif