From 6b4e3181d7bd5ca5ab6f45929e4a5ffa7ab4ab7f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 1 Sep 2016 16:14:41 -0700 Subject: mm, oom: prevent premature OOM killer invocation for high order request There have been several reports about pre-mature OOM killer invocation in 4.7 kernel when order-2 allocation request (for the kernel stack) invoked OOM killer even during basic workloads (light IO or even kernel compile on some filesystems). In all reported cases the memory is fragmented and there are no order-2+ pages available. There is usually a large amount of slab memory (usually dentries/inodes) and further debugging has shown that there are way too many unmovable blocks which are skipped during the compaction. Multiple reporters have confirmed that the current linux-next which includes [1] and [2] helped and OOMs are not reproducible anymore. A simpler fix for the late rc and stable is to simply ignore the compaction feedback and retry as long as there is a reclaim progress and we are not getting OOM for order-0 pages. We already do that for CONFING_COMPACTION=n so let's reuse the same code when compaction is enabled as well. [1] http://lkml.kernel.org/r/20160810091226.6709-1-vbabka@suse.cz [2] http://lkml.kernel.org/r/f7a9ea9d-bb88-bfd6-e340-3a933559305a@suse.cz Fixes: 0a0337e0d1d1 ("mm, oom: rework oom detection") Link: http://lkml.kernel.org/r/20160823074339.GB23577@dhcp22.suse.cz Signed-off-by: Michal Hocko Tested-by: Olaf Hering Tested-by: Ralf-Peter Rohbeck Cc: Markus Trippelsdorf Cc: Arkadiusz Miskiewicz Cc: Ralf-Peter Rohbeck Cc: Jiri Slaby Cc: Vlastimil Babka Cc: Joonsoo Kim Cc: Tetsuo Handa Cc: David Rientjes Cc: [4.7.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 51 ++------------------------------------------------- 1 file changed, 2 insertions(+), 49 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3fbe73a6fe4b..7791a03f8deb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3137,54 +3137,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; } -static inline bool -should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, - enum compact_result compact_result, - enum compact_priority *compact_priority, - int compaction_retries) -{ - int max_retries = MAX_COMPACT_RETRIES; - - if (!order) - return false; - - /* - * compaction considers all the zone as desperately out of memory - * so it doesn't really make much sense to retry except when the - * failure could be caused by insufficient priority - */ - if (compaction_failed(compact_result)) { - if (*compact_priority > MIN_COMPACT_PRIORITY) { - (*compact_priority)--; - return true; - } - return false; - } - - /* - * make sure the compaction wasn't deferred or didn't bail out early - * due to locks contention before we declare that we should give up. - * But do not retry if the given zonelist is not suitable for - * compaction. - */ - if (compaction_withdrawn(compact_result)) - return compaction_zonelist_suitable(ac, order, alloc_flags); - - /* - * !costly requests are much more important than __GFP_REPEAT - * costly ones because they are de facto nofail and invoke OOM - * killer to move on while costly can fail and users are ready - * to cope with that. 1/4 retries is rather arbitrary but we - * would need much more detailed feedback from compaction to - * make a better decision. - */ - if (order > PAGE_ALLOC_COSTLY_ORDER) - max_retries /= 4; - if (compaction_retries <= max_retries) - return true; - - return false; -} #else static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, @@ -3195,6 +3147,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; } +#endif /* CONFIG_COMPACTION */ + static inline bool should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags, enum compact_result compact_result, @@ -3221,7 +3175,6 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla } return false; } -#endif /* CONFIG_COMPACTION */ /* Perform direct synchronous page reclaim */ static int -- cgit v1.2.3 From 6aa303defb7454a2520c4ddcdf6b081f62a15890 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 1 Sep 2016 16:14:55 -0700 Subject: mm, vmscan: only allocate and reclaim from zones with pages managed by the buddy allocator Firmware Assisted Dump (FA_DUMP) on ppc64 reserves substantial amounts of memory when booting a secondary kernel. Srikar Dronamraju reported that multiple nodes may have no memory managed by the buddy allocator but still return true for populated_zone(). Commit 1d82de618ddd ("mm, vmscan: make kswapd reclaim in terms of nodes") was reported to cause kswapd to spin at 100% CPU usage when fadump was enabled. The old code happened to deal with the situation of a populated node with zero free pages by co-incidence but the current code tries to reclaim populated zones without realising that is impossible. We cannot just convert populated_zone() as many existing users really need to check for present_pages. This patch introduces a managed_zone() helper and uses it in the few cases where it is critical that the check is made for managed pages -- zonelist construction and page reclaim. Link: http://lkml.kernel.org/r/20160831195104.GB8119@techsingularity.net Signed-off-by: Mel Gorman Reported-by: Srikar Dronamraju Tested-by: Srikar Dronamraju Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7791a03f8deb..a2214c64ed3c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4360,7 +4360,7 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, do { zone_type--; zone = pgdat->node_zones + zone_type; - if (populated_zone(zone)) { + if (managed_zone(zone)) { zoneref_set_zone(zone, &zonelist->_zonerefs[nr_zones++]); check_highest_zone(zone_type); @@ -4598,7 +4598,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) for (j = 0; j < nr_nodes; j++) { node = node_order[j]; z = &NODE_DATA(node)->node_zones[zone_type]; - if (populated_zone(z)) { + if (managed_zone(z)) { zoneref_set_zone(z, &zonelist->_zonerefs[pos++]); check_highest_zone(zone_type); -- cgit v1.2.3