diff options
author | Mel Gorman <mgorman@techsingularity.net> | 2016-07-28 15:47:31 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-07-28 16:07:41 -0700 |
commit | 5a1c84b404a7176b8b36e2a0041b6f0adb3151a3 (patch) | |
tree | ff98e242c5d4d3a24ca49f6ddc707028aeb938f9 /mm/page_alloc.c | |
parent | bb4cc2bea6df7854d629bff114ca03237cc718d6 (diff) | |
download | lwn-5a1c84b404a7176b8b36e2a0041b6f0adb3151a3.tar.gz lwn-5a1c84b404a7176b8b36e2a0041b6f0adb3151a3.zip |
mm: remove reclaim and compaction retry approximations
If per-zone LRU accounting is available then there is no point
approximating whether reclaim and compaction should retry based on pgdat
statistics. This is effectively a revert of "mm, vmstat: remove zone
and node double accounting by approximating retries" with the difference
that inactive/active stats are still available. This preserves the
history of why the approximation was retried and why it had to be
reverted to handle OOM kills on 32-bit systems.
Link: http://lkml.kernel.org/r/1469110261-7365-4-git-send-email-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r-- | mm/page_alloc.c | 49 |
1 files changed, 10 insertions, 39 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 759cfa8cbbeb..dfdb608f7b3d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3402,7 +3402,6 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, { struct zone *zone; struct zoneref *z; - pg_data_t *current_pgdat = NULL; /* * Make sure we converge to OOM if we cannot make any progress @@ -3412,15 +3411,6 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, return false; /* - * Blindly retry lowmem allocation requests that are often ignored by - * the OOM killer up to MAX_RECLAIM_RETRIES as we not have a reliable - * and fast means of calculating reclaimable, dirty and writeback pages - * in eligible zones. - */ - if (ac->high_zoneidx < ZONE_NORMAL) - goto out; - - /* * Keep reclaiming pages while there is a chance this will lead * somewhere. If none of the target zones can satisfy our allocation * request even if all reclaimable pages are considered then we are @@ -3430,38 +3420,18 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, ac->nodemask) { unsigned long available; unsigned long reclaimable; - int zid; - if (current_pgdat == zone->zone_pgdat) - continue; - - current_pgdat = zone->zone_pgdat; - available = reclaimable = pgdat_reclaimable_pages(current_pgdat); + available = reclaimable = zone_reclaimable_pages(zone); available -= DIV_ROUND_UP(no_progress_loops * available, MAX_RECLAIM_RETRIES); - - /* Account for all free pages on eligible zones */ - for (zid = 0; zid <= zone_idx(zone); zid++) { - struct zone *acct_zone = ¤t_pgdat->node_zones[zid]; - - available += zone_page_state_snapshot(acct_zone, NR_FREE_PAGES); - } + available += zone_page_state_snapshot(zone, NR_FREE_PAGES); /* * Would the allocation succeed if we reclaimed the whole - * available? This is approximate because there is no - * accurate count of reclaimable pages per zone. + * available? */ - for (zid = 0; zid <= zone_idx(zone); zid++) { - struct zone *check_zone = ¤t_pgdat->node_zones[zid]; - unsigned long estimate; - - estimate = min(check_zone->managed_pages, available); - if (!__zone_watermark_ok(check_zone, order, - min_wmark_pages(check_zone), ac_classzone_idx(ac), - alloc_flags, estimate)) - continue; - + if (__zone_watermark_ok(zone, order, min_wmark_pages(zone), + ac_classzone_idx(ac), alloc_flags, available)) { /* * If we didn't make any progress and have a lot of * dirty + writeback pages then we should wait for @@ -3471,16 +3441,15 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, if (!did_some_progress) { unsigned long write_pending; - write_pending = - node_page_state(current_pgdat, NR_WRITEBACK) + - node_page_state(current_pgdat, NR_FILE_DIRTY); + write_pending = zone_page_state_snapshot(zone, + NR_ZONE_WRITE_PENDING); if (2 * write_pending > reclaimable) { congestion_wait(BLK_RW_ASYNC, HZ/10); return true; } } -out: + /* * Memory allocation/reclaim might be called from a WQ * context and the current implementation of the WQ @@ -4361,6 +4330,7 @@ void show_free_areas(unsigned int filter) " active_file:%lukB" " inactive_file:%lukB" " unevictable:%lukB" + " writepending:%lukB" " present:%lukB" " managed:%lukB" " mlocked:%lukB" @@ -4383,6 +4353,7 @@ void show_free_areas(unsigned int filter) K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)), K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)), K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)), + K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)), K(zone->present_pages), K(zone->managed_pages), K(zone_page_state(zone, NR_MLOCK)), |