The patch titled
Subject: mm: vmscan: rework compaction-ready signaling in direct reclaim
has been added to the -mm tree. Its filename is
mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: mm: vmscan: rework compaction-ready signaling in direct reclaim
Page reclaim for a higher-order page runs until compaction is ready, then
aborts and signals this situation through the return value of
shrink_zones(). This is an oddly specific signal to encode in the return
value of shrink_zones(), though, and can be quite confusing.
Introduce sc->compaction_ready and signal the compactability of the zones
out-of-band to free up the return value of shrink_zones() for actual zone
reclaimability.
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmscan.c | 67 +++++++++++++++++++++++---------------------------
1 file changed, 31 insertions(+), 36 deletions(-)
diff -puN mm/vmscan.c~mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim mm/vmscan.c
--- a/mm/vmscan.c~mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim
+++ a/mm/vmscan.c
@@ -65,6 +65,9 @@ struct scan_control {
/* Number of pages freed so far during a call to shrink_zones() */
unsigned long nr_reclaimed;
+ /* One of the zones is ready for compaction */
+ int compaction_ready;
+
/* How many pages shrink_list() should reclaim */
unsigned long nr_to_reclaim;
@@ -2298,15 +2301,11 @@ static void shrink_zone(struct zone *zon
}
/* Returns true if compaction should go ahead for a high-order request */
-static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
+static inline bool compaction_ready(struct zone *zone, int order)
{
unsigned long balance_gap, watermark;
bool watermark_ok;
- /* Do not consider compaction for orders reclaim is meant to satisfy */
- if (sc->order <= PAGE_ALLOC_COSTLY_ORDER)
- return false;
-
/*
* Compaction takes time to run and there are potentially other
* callers using the pages just freed. Continue reclaiming until
@@ -2315,18 +2314,18 @@ static inline bool compaction_ready(stru
*/
balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP(
zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO));
- watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
+ watermark = high_wmark_pages(zone) + balance_gap + (2UL << order);
watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);
/*
* If compaction is deferred, reclaim up to a point where
* compaction will have a chance of success when re-enabled
*/
- if (compaction_deferred(zone, sc->order))
+ if (compaction_deferred(zone, order))
return watermark_ok;
/* If compaction is not ready to start, keep reclaiming */
- if (!compaction_suitable(zone, sc->order))
+ if (!compaction_suitable(zone, order))
return false;
return watermark_ok;
@@ -2347,20 +2346,14 @@ static inline bool compaction_ready(stru
*
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
- *
- * This function returns true if a zone is being reclaimed for a costly
- * high-order allocation and compaction is ready to begin. This indicates to
- * the caller that it should consider retrying the allocation instead of
- * further reclaim.
*/
-static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
+static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
{
struct zoneref *z;
struct zone *zone;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
unsigned long lru_pages = 0;
- bool aborted_reclaim = false;
struct reclaim_state *reclaim_state = current->reclaim_state;
gfp_t orig_mask;
struct shrink_control shrink = {
@@ -2397,22 +2390,24 @@ static bool shrink_zones(struct zonelist
if (sc->priority != DEF_PRIORITY &&
!zone_reclaimable(zone))
continue; /* Let kswapd poll it */
- if (IS_ENABLED(CONFIG_COMPACTION)) {
- /*
- * If we already have plenty of memory free for
- * compaction in this zone, don't free any more.
- * Even though compaction is invoked for any
- * non-zero order, only frequent costly order
- * reclamation is disruptive enough to become a
- * noticeable problem, like transparent huge
- * page allocations.
- */
- if ((zonelist_zone_idx(z) <= requested_highidx)
- && compaction_ready(zone, sc)) {
- aborted_reclaim = true;
- continue;
- }
+
+ /*
+ * If we already have plenty of memory free for
+ * compaction in this zone, don't free any more.
+ * Even though compaction is invoked for any
+ * non-zero order, only frequent costly order
+ * reclamation is disruptive enough to become a
+ * noticeable problem, like transparent huge
+ * page allocations.
+ */
+ if (IS_ENABLED(CONFIG_COMPACTION) &&
+ sc->order > PAGE_ALLOC_COSTLY_ORDER &&
+ zonelist_zone_idx(z) <= requested_highidx &&
+ compaction_ready(zone, sc->order)) {
+ sc->compaction_ready = true;
+ continue;
}
+
/*
* This steals pages from memory cgroups over softlimit
* and returns the number of reclaimed pages and
@@ -2450,8 +2445,6 @@ static bool shrink_zones(struct zonelist
* promoted it to __GFP_HIGHMEM.
*/
sc->gfp_mask = orig_mask;
-
- return aborted_reclaim;
}
/* All zones in zonelist are unreclaimable? */
@@ -2495,7 +2488,6 @@ static unsigned long do_try_to_free_page
{
unsigned long total_scanned = 0;
unsigned long writeback_threshold;
- bool aborted_reclaim;
delayacct_freepages_start();
@@ -2506,12 +2498,15 @@ static unsigned long do_try_to_free_page
vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
sc->priority);
sc->nr_scanned = 0;
- aborted_reclaim = shrink_zones(zonelist, sc);
+ shrink_zones(zonelist, sc);
total_scanned += sc->nr_scanned;
if (sc->nr_reclaimed >= sc->nr_to_reclaim)
goto out;
+ if (sc->compaction_ready)
+ goto out;
+
/*
* If we're getting trouble reclaiming, start doing
* writepage even in laptop mode.
@@ -2532,7 +2527,7 @@ static unsigned long do_try_to_free_page
WB_REASON_TRY_TO_FREE_PAGES);
sc->may_writepage = 1;
}
- } while (--sc->priority >= 0 && !aborted_reclaim);
+ } while (--sc->priority >= 0);
out:
delayacct_freepages_end();
@@ -2541,7 +2536,7 @@ out:
return sc->nr_reclaimed;
/* Aborted reclaim to try compaction? don't OOM, then */
- if (aborted_reclaim)
+ if (sc->compaction_ready)
return 1;
/* top priority shrink_zones still had more to do? don't OOM, then */
_
Patches currently in -mm which might be from hannes@xxxxxxxxxxx are
vmalloc-use-rcu-list-iterator-to-reduce-vmap_area_lock-contention.patch
memcg-cleanup-memcg_cache_params-refcnt-usage.patch
memcg-destroy-kmem-caches-when-last-slab-is-freed.patch
memcg-mark-caches-that-belong-to-offline-memcgs-as-dead.patch
slub-dont-fail-kmem_cache_shrink-if-slab-placement-optimization-fails.patch
slub-make-slab_free-non-preemptable.patch
memcg-wait-for-kfrees-to-finish-before-destroying-cache.patch
slub-make-dead-memcg-caches-discard-free-slabs-immediately.patch
slab-do-not-keep-free-objects-slabs-on-dead-memcg-caches.patch
mm-page-flags-clean-up-the-page-flag-test-set-clear-macros.patch
mm-memcontrol-fold-mem_cgroup_do_charge.patch
mm-memcontrol-rearrange-charging-fast-path.patch
mm-memcontrol-reclaim-at-least-once-for-__gfp_noretry.patch
mm-huge_memory-use-gfp_transhuge-when-charging-huge-pages.patch
mm-memcontrol-retry-reclaim-for-oom-disabled-and-__gfp_nofail-charges.patch
mm-memcontrol-remove-explicit-oom-parameter-in-charge-path.patch
mm-memcontrol-simplify-move-precharge-function.patch
mm-memcontrol-catch-root-bypass-in-move-precharge.patch
mm-memcontrol-use-root_mem_cgroup-res_counter.patch
mm-memcontrol-remove-ordering-between-pc-mem_cgroup-and-pagecgroupused.patch
mm-memcontrol-do-not-acquire-page_cgroup-lock-for-kmem-pages.patch
mm-memcontrol-rewrite-charge-api.patch
mm-memcontrol-rewrite-charge-api-fix-3.patch
mm-memcontrol-rewrite-uncharge-api.patch
mm-memcontrol-rewrite-uncharge-api-fix-2.patch
memcg-remove-lookup_cgroup_page-prototype.patch
mm-vmscan-remove-remains-of-kswapd-managed-zone-all_unreclaimable.patch
mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim.patch
mm-vmscan-remove-all_unreclaimable.patch
mm-vmscan-move-swappiness-out-of-scan_control.patch
memcg-deprecate-memoryforce_empty-knob.patch
memcg-deprecate-memoryforce_empty-knob-fix.patch
debugging-keep-track-of-page-owners.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
