fallback_alloc is called on kmalloc if the preferred node doesn't have
free or partial slabs and there's no pages on the node's free list
(GFP_THISNODE allocations fail). Before invoking the reclaimer it tries
to locate a free or partial slab on other allowed nodes' lists. While
iterating over the preferred node's zonelist it skips those zones which
cpuset_zone_allowed_hardwall returns false for. That means that for a
task bound to a specific node using cpusets fallback_alloc will always
ignore free slabs on other nodes and go directly to the reclaimer,
which, however, may allocate from other nodes if cpuset.mem_hardwall is
unset (default). As a result, we may get lists of free slabs grow
without bounds on other nodes, which is bad, because inactive slabs are
only evicted by cache_reap at a very slow rate and cannot be dropped
forcefully.
To reproduce the issue, run a process that will walk over a directory
tree with lots of files inside a cpuset bound to a node that constantly
experiences memory pressure. Look at num_slabs vs active_slabs growth as
reported by /proc/slabinfo.
We should use cpuset_zone_allowed_softwall in fallback_alloc. Since it
can sleep, we only call it on __GFP_WAIT allocations. For atomic
allocations we simply ignore cpusets, which is in agreement with the
cpuset documenation (see the comment to __cpuset_node_allowed_softwall).
Signed-off-by: Vladimir Davydov <vdavy...@parallels.com>
Cc: Christoph Lameter <c...@linux.com>
Cc: Pekka Enberg <penb...@kernel.org>
Cc: David Rientjes <rient...@google.com>
Cc: Joonsoo Kim <iamjoonsoo....@lge.com>
---
mm/slab.c | 23 ++++++++++++++++-------
1 file changed, 16 insertions(+), 7 deletions(-)
diff --git a/mm/slab.c b/mm/slab.c
index 2e60bf3dedbb..1d77a4df7ee1 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3049,14 +3049,23 @@ retry:
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
nid = zone_to_nid(zone);
- if (cpuset_zone_allowed_hardwall(zone, flags) &&
- get_node(cache, nid) &&
- get_node(cache, nid)->free_objects) {
- obj = ____cache_alloc_node(cache,
- flags | GFP_THISNODE, nid);
- if (obj)
- break;
+ if (!get_node(cache, nid) ||
+ !get_node(cache, nid)->free_objects)
+ continue;
+
+ if (local_flags & __GFP_WAIT) {
+ bool allowed;
+
+ local_irq_enable();
+ allowed = cpuset_zone_allowed_softwall(zone, flags);
+ local_irq_disable();
+ if (!allowed)
+ continue;
}
+
+ obj = ____cache_alloc_node(cache, flags | GFP_THISNODE, nid);
+ if (obj)
+ break;
}
if (!obj) {
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
