summaryrefslogtreecommitdiffstats
path: root/mm
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 /mm
parent0ce3d74450815500e31f16a0b65f6bab687985c3 (diff)
downloadlinux-stable-1d3d4437eae1bb2963faab427f65f90663c64aa1.tar.gz
linux-stable-1d3d4437eae1bb2963faab427f65f90663c64aa1.tar.bz2
linux-stable-1d3d4437eae1bb2963faab427f65f90663c64aa1.zip
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 'mm')
-rw-r--r--mm/vmscan.c241
1 files changed, 140 insertions, 101 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fe0d5c458440..799ebceeb4f7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -155,14 +155,31 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
}
/*
- * Add a shrinker callback to be called from the vm
+ * Add a shrinker callback to be called from the vm.
*/
-void register_shrinker(struct shrinker *shrinker)
+int register_shrinker(struct shrinker *shrinker)
{
- atomic_long_set(&shrinker->nr_in_batch, 0);
+ size_t size = sizeof(*shrinker->nr_deferred);
+
+ /*
+ * If we only have one possible node in the system anyway, save
+ * ourselves the trouble and disable NUMA aware behavior. This way we
+ * will save memory and some small loop time later.
+ */
+ if (nr_node_ids == 1)
+ shrinker->flags &= ~SHRINKER_NUMA_AWARE;
+
+ if (shrinker->flags & SHRINKER_NUMA_AWARE)
+ size *= nr_node_ids;
+
+ shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
+ if (!shrinker->nr_deferred)
+ return -ENOMEM;
+
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
up_write(&shrinker_rwsem);
+ return 0;
}
EXPORT_SYMBOL(register_shrinker);
@@ -186,6 +203,118 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker,
}
#define SHRINK_BATCH 128
+
+static unsigned long
+shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
+ unsigned long nr_pages_scanned, unsigned long lru_pages)
+{
+ unsigned long freed = 0;
+ unsigned long long delta;
+ long total_scan;
+ long max_pass;
+ long nr;
+ long new_nr;
+ int nid = shrinkctl->nid;
+ long batch_size = shrinker->batch ? shrinker->batch
+ : SHRINK_BATCH;
+
+ if (shrinker->count_objects)
+ max_pass = shrinker->count_objects(shrinker, shrinkctl);
+ else
+ max_pass = do_shrinker_shrink(shrinker, shrinkctl, 0);
+ if (max_pass == 0)
+ return 0;
+
+ /*
+ * copy the current shrinker scan count into a local variable
+ * and zero it so that other concurrent shrinker invocations
+ * don't also do this scanning work.
+ */
+ nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
+
+ total_scan = nr;
+ delta = (4 * nr_pages_scanned) / shrinker->seeks;
+ delta *= max_pass;
+ do_div(delta, lru_pages + 1);
+ total_scan += delta;
+ if (total_scan < 0) {
+ printk(KERN_ERR
+ "shrink_slab: %pF negative objects to delete nr=%ld\n",
+ shrinker->shrink, total_scan);
+ total_scan = max_pass;
+ }
+
+ /*
+ * We need to avoid excessive windup on filesystem shrinkers
+ * due to large numbers of GFP_NOFS allocations causing the
+ * shrinkers to return -1 all the time. This results in a large
+ * nr being built up so when a shrink that can do some work
+ * comes along it empties the entire cache due to nr >>>
+ * max_pass. This is bad for sustaining a working set in
+ * memory.
+ *
+ * Hence only allow the shrinker to scan the entire cache when
+ * a large delta change is calculated directly.
+ */
+ if (delta < max_pass / 4)
+ total_scan = min(total_scan, max_pass / 2);
+
+ /*
+ * Avoid risking looping forever due to too large nr value:
+ * never try to free more than twice the estimate number of
+ * freeable entries.
+ */
+ if (total_scan > max_pass * 2)
+ total_scan = max_pass * 2;
+
+ trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
+ nr_pages_scanned, lru_pages,
+ max_pass, delta, total_scan);
+
+ while (total_scan >= batch_size) {
+
+ if (shrinker->scan_objects) {
+ unsigned long ret;
+ shrinkctl->nr_to_scan = batch_size;
+ ret = shrinker->scan_objects(shrinker, shrinkctl);
+
+ if (ret == SHRINK_STOP)
+ break;
+ freed += ret;
+ } else {
+ int nr_before;
+ long ret;
+
+ nr_before = do_shrinker_shrink(shrinker, shrinkctl, 0);
+ ret = do_shrinker_shrink(shrinker, shrinkctl,
+ batch_size);
+ if (ret == -1)
+ break;
+ if (ret < nr_before)
+ freed += nr_before - ret;
+ }
+
+ count_vm_events(SLABS_SCANNED, batch_size);
+ total_scan -= batch_size;
+
+ cond_resched();
+ }
+
+ /*
+ * move the unused scan count back into the shrinker in a
+ * manner that handles concurrent updates. If we exhausted the
+ * scan, there is no need to do an update.
+ */
+ if (total_scan > 0)
+ new_nr = atomic_long_add_return(total_scan,
+ &shrinker->nr_deferred[nid]);
+ else
+ new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
+
+ trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
+ return freed;
+}
+
/*
* Call the shrink functions to age shrinkable caches
*
@@ -227,108 +356,18 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl,
}
list_for_each_entry(shrinker, &shrinker_list, list) {
- unsigned long long delta;
- long total_scan;
- long max_pass;
- long nr;
- long new_nr;
- long batch_size = shrinker->batch ? shrinker->batch
- : SHRINK_BATCH;
-
- if (shrinker->count_objects)
- max_pass = shrinker->count_objects(shrinker, shrinkctl);
- else
- max_pass = do_shrinker_shrink(shrinker, shrinkctl, 0);
- if (max_pass == 0)
- continue;
-
- /*
- * copy the current shrinker scan count into a local variable
- * and zero it so that other concurrent shrinker invocations
- * don't also do this scanning work.
- */
- nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
-
- total_scan = nr;
- delta = (4 * nr_pages_scanned) / shrinker->seeks;
- delta *= max_pass;
- do_div(delta, lru_pages + 1);
- total_scan += delta;
- if (total_scan < 0) {
- printk(KERN_ERR
- "shrink_slab: %pF negative objects to delete nr=%ld\n",
- shrinker->shrink, total_scan);
- total_scan = max_pass;
- }
-
- /*
- * We need to avoid excessive windup on filesystem shrinkers
- * due to large numbers of GFP_NOFS allocations causing the
- * shrinkers to return -1 all the time. This results in a large
- * nr being built up so when a shrink that can do some work
- * comes along it empties the entire cache due to nr >>>
- * max_pass. This is bad for sustaining a working set in
- * memory.
- *
- * Hence only allow the shrinker to scan the entire cache when
- * a large delta change is calculated directly.
- */
- if (delta < max_pass / 4)
- total_scan = min(total_scan, max_pass / 2);
-
- /*
- * Avoid risking looping forever due to too large nr value:
- * never try to free more than twice the estimate number of
- * freeable entries.
- */
- if (total_scan > max_pass * 2)
- total_scan = max_pass * 2;
-
- trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
- nr_pages_scanned, lru_pages,
- max_pass, delta, total_scan);
-
- while (total_scan >= batch_size) {
-
- if (shrinker->scan_objects) {
- unsigned long ret;
- shrinkctl->nr_to_scan = batch_size;
- ret = shrinker->scan_objects(shrinker, shrinkctl);
+ for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
+ if (!node_online(shrinkctl->nid))
+ continue;
- if (ret == SHRINK_STOP)
- break;
- freed += ret;
- } else {
- int nr_before;
- long ret;
-
- nr_before = do_shrinker_shrink(shrinker, shrinkctl, 0);
- ret = do_shrinker_shrink(shrinker, shrinkctl,
- batch_size);
- if (ret == -1)
- break;
- if (ret < nr_before)
- freed += nr_before - ret;
- }
+ if (!(shrinker->flags & SHRINKER_NUMA_AWARE) &&
+ (shrinkctl->nid != 0))
+ break;
- count_vm_events(SLABS_SCANNED, batch_size);
- total_scan -= batch_size;
+ freed += shrink_slab_node(shrinkctl, shrinker,
+ nr_pages_scanned, lru_pages);
- cond_resched();
}
-
- /*
- * move the unused scan count back into the shrinker in a
- * manner that handles concurrent updates. If we exhausted the
- * scan, there is no need to do an update.
- */
- if (total_scan > 0)
- new_nr = atomic_long_add_return(total_scan,
- &shrinker->nr_in_batch);
- else
- new_nr = atomic_long_read(&shrinker->nr_in_batch);
-
- trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
}
up_read(&shrinker_rwsem);
out: