The patch titled
Subject: mm, vmscan: begin reclaiming pages on a per-node basis
has been added to the -mm tree. Its filename is
mm-vmscan-begin-reclaiming-pages-on-a-per-node-basis.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-vmscan-begin-reclaiming-pages-on-a-per-node-basis.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-vmscan-begin-reclaiming-pages-on-a-per-node-basis.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: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Subject: mm, vmscan: begin reclaiming pages on a per-node basis
This patch makes reclaim decisions on a per-node basis. A reclaimer knows
what zone is required by the allocation request and skips pages from
higher zones. In many cases this will be ok because it's a GFP_HIGHMEM
request of some description. On 64-bit, ZONE_DMA32 requests will cause
some problems but 32-bit devices on 64-bit platforms are increasingly
rare. Historically it would have been a major problem on 32-bit with big
Highmem:Lowmem ratios but such configurations are also now rare and even
where they exist, they are not encouraged. If it really becomes a
problem, it'll manifest as very low reclaim efficiencies.
Link: http://lkml.kernel.org/r/1466518566-30034-5-git-send-email-mgorman@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmscan.c | 78 +++++++++++++++++++++++++++++++++-----------------
1 file changed, 53 insertions(+), 25 deletions(-)
diff -puN mm/vmscan.c~mm-vmscan-begin-reclaiming-pages-on-a-per-node-basis mm/vmscan.c
--- a/mm/vmscan.c~mm-vmscan-begin-reclaiming-pages-on-a-per-node-basis
+++ a/mm/vmscan.c
@@ -84,6 +84,9 @@ struct scan_control {
/* Scan (total_size >> priority) pages at once */
int priority;
+ /* The highest zone to isolate pages for reclaim from */
+ enum zone_type reclaim_idx;
+
unsigned int may_writepage:1;
/* Can mapped pages be reclaimed? */
@@ -1392,6 +1395,7 @@ static unsigned long isolate_lru_pages(u
unsigned long nr_taken = 0;
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
unsigned long scan, nr_pages;
+ LIST_HEAD(pages_skipped);
for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
!list_empty(src); scan++) {
@@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(u
VM_BUG_ON_PAGE(!PageLRU(page), page);
+ if (page_zonenum(page) > sc->reclaim_idx) {
+ list_move(&page->lru, &pages_skipped);
+ continue;
+ }
+
switch (__isolate_lru_page(page, mode)) {
case 0:
nr_pages = hpage_nr_pages(page);
@@ -1420,6 +1429,15 @@ static unsigned long isolate_lru_pages(u
}
}
+ /*
+ * Splice any skipped pages to the start of the LRU list. Note that
+ * this disrupts the LRU order when reclaiming for lower zones but
+ * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
+ * scanning would soon rescan the same pages to skip and put the
+ * system at risk of premature OOM.
+ */
+ if (!list_empty(&pages_skipped))
+ list_splice(&pages_skipped, src);
*nr_scanned = scan;
trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
@@ -1589,7 +1607,7 @@ static int current_may_throttle(void)
}
/*
- * shrink_inactive_list() is a helper for shrink_zone(). It returns the number
+ * shrink_inactive_list() is a helper for shrink_node(). It returns the number
* of reclaimed pages
*/
static noinline_for_stack unsigned long
@@ -2401,12 +2419,13 @@ static inline bool should_continue_recla
}
}
-static bool shrink_zone(struct zone *zone, struct scan_control *sc,
- bool is_classzone)
+static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
+ enum zone_type classzone_idx)
{
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
bool reclaimable = false;
+ struct zone *zone = &pgdat->node_zones[classzone_idx];
do {
struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2438,7 +2457,7 @@ static bool shrink_zone(struct zone *zon
shrink_zone_memcg(zone, memcg, sc, &lru_pages);
zone_lru_pages += lru_pages;
- if (memcg && is_classzone)
+ if (!global_reclaim(sc) && sc->reclaim_idx == classzone_idx)
shrink_slab(sc->gfp_mask, zone_to_nid(zone),
memcg, sc->nr_scanned - scanned,
lru_pages);
@@ -2469,7 +2488,7 @@ static bool shrink_zone(struct zone *zon
* Shrink the slab caches in the same proportion that
* the eligible LRU pages were scanned.
*/
- if (global_reclaim(sc) && is_classzone)
+ if (global_reclaim(sc) && sc->reclaim_idx == classzone_idx)
shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
sc->nr_scanned - nr_scanned,
zone_lru_pages);
@@ -2546,14 +2565,14 @@ 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.
*/
-static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
+static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc,
+ enum zone_type classzone_idx)
{
struct zoneref *z;
struct zone *zone;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
gfp_t orig_mask;
- enum zone_type requested_highidx = gfp_zone(sc->gfp_mask);
/*
* If the number of buffer_heads in the machine exceeds the maximum
@@ -2566,15 +2585,20 @@ static void shrink_zones(struct zonelist
for_each_zone_zonelist_nodemask(zone, z, zonelist,
gfp_zone(sc->gfp_mask), sc->nodemask) {
- enum zone_type classzone_idx;
-
if (!populated_zone(zone))
continue;
- classzone_idx = requested_highidx;
+ /*
+ * Note that reclaim_idx does not change as it is the highest
+ * zone reclaimed from which for empty zones is a no-op but
+ * classzone_idx is used by shrink_node to test if the slabs
+ * should be shrunk on a given node.
+ */
while (!populated_zone(zone->zone_pgdat->node_zones +
- classzone_idx))
+ classzone_idx)) {
classzone_idx--;
+ continue;
+ }
/*
* Take care memory controller reclaiming has small influence
@@ -2600,8 +2624,8 @@ static void shrink_zones(struct zonelist
*/
if (IS_ENABLED(CONFIG_COMPACTION) &&
sc->order > PAGE_ALLOC_COSTLY_ORDER &&
- zonelist_zone_idx(z) <= requested_highidx &&
- compaction_ready(zone, sc->order, requested_highidx)) {
+ zonelist_zone_idx(z) <= classzone_idx &&
+ compaction_ready(zone, sc->order, classzone_idx)) {
sc->compaction_ready = true;
continue;
}
@@ -2621,7 +2645,7 @@ static void shrink_zones(struct zonelist
/* need some check for avoid more shrink_zone() */
}
- shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
+ shrink_node(zone->zone_pgdat, sc, classzone_idx);
}
/*
@@ -2653,6 +2677,7 @@ static unsigned long do_try_to_free_page
int initial_priority = sc->priority;
unsigned long total_scanned = 0;
unsigned long writeback_threshold;
+ enum zone_type classzone_idx = sc->reclaim_idx;
retry:
delayacct_freepages_start();
@@ -2663,7 +2688,7 @@ retry:
vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
sc->priority);
sc->nr_scanned = 0;
- shrink_zones(zonelist, sc);
+ shrink_zones(zonelist, sc, classzone_idx);
total_scanned += sc->nr_scanned;
if (sc->nr_reclaimed >= sc->nr_to_reclaim)
@@ -2847,6 +2872,7 @@ unsigned long try_to_free_pages(struct z
struct scan_control sc = {
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
+ .reclaim_idx = gfp_zone(gfp_mask),
.order = order,
.nodemask = nodemask,
.priority = DEF_PRIORITY,
@@ -3118,7 +3144,7 @@ static bool kswapd_shrink_zone(struct zo
balance_gap, classzone_idx))
return true;
- shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
+ shrink_node(zone->zone_pgdat, sc, classzone_idx);
/* TODO: ANOMALY */
clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
@@ -3167,6 +3193,7 @@ static int balance_pgdat(pg_data_t *pgda
unsigned long nr_soft_scanned;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
+ .reclaim_idx = MAX_NR_ZONES - 1,
.order = order,
.priority = DEF_PRIORITY,
.may_writepage = !laptop_mode,
@@ -3237,15 +3264,14 @@ static int balance_pgdat(pg_data_t *pgda
sc.may_writepage = 1;
/*
- * Now scan the zone in the dma->highmem direction, stopping
- * at the last zone which needs scanning.
- *
- * We do this because the page allocator works in the opposite
- * direction. This prevents the page allocator from allocating
- * pages behind kswapd's direction of progress, which would
- * cause too much scanning of the lower zones.
+ * Continue scanning in the highmem->dma direction stopping at
+ * the last zone which needs scanning. This may reclaim lowmem
+ * pages that are not necessary for zone balancing but it
+ * preserves LRU ordering. It is assumed that the bulk of
+ * allocation requests can use arbitrary zones with the
+ * possible exception of big highmem:lowmem configurations.
*/
- for (i = 0; i <= end_zone; i++) {
+ for (i = end_zone; i >= 0; i--) {
struct zone *zone = pgdat->node_zones + i;
if (!populated_zone(zone))
@@ -3256,6 +3282,7 @@ static int balance_pgdat(pg_data_t *pgda
continue;
sc.nr_scanned = 0;
+ sc.reclaim_idx = i;
nr_soft_scanned = 0;
/*
@@ -3704,6 +3731,7 @@ static int __zone_reclaim(struct zone *z
.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP),
.may_swap = 1,
+ .reclaim_idx = zone_idx(zone),
};
cond_resched();
@@ -3723,7 +3751,7 @@ static int __zone_reclaim(struct zone *z
* priorities until we have enough memory freed.
*/
do {
- shrink_zone(zone, &sc, true);
+ shrink_node(zone->zone_pgdat, &sc, zone_idx(zone));
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
}
_
Patches currently in -mm which might be from mgorman@xxxxxxxxxxxxxxxxxxx are
mm-slaub-add-__gfp_atomic-to-the-gfp-reclaim-mask.patch
mm-vmstat-add-infrastructure-for-per-node-vmstats.patch
mm-vmscan-move-lru_lock-to-the-node.patch
mm-vmscan-move-lru-lists-to-node.patch
mm-vmscan-begin-reclaiming-pages-on-a-per-node-basis.patch
mm-vmscan-have-kswapd-only-scan-based-on-the-highest-requested-zone.patch
mm-vmscan-make-kswapd-reclaim-in-terms-of-nodes.patch
mm-vmscan-remove-balance-gap.patch
mm-vmscan-simplify-the-logic-deciding-whether-kswapd-sleeps.patch
mm-vmscan-by-default-have-direct-reclaim-only-shrink-once-per-node.patch
mm-vmscan-remove-duplicate-logic-clearing-node-congestion-and-dirty-state.patch
mm-vmscan-do-not-reclaim-from-kswapd-if-there-is-any-eligible-zone.patch
mm-vmscan-make-shrink_node-decisions-more-node-centric.patch
mm-memcg-move-memcg-limit-enforcement-from-zones-to-nodes.patch
mm-workingset-make-working-set-detection-node-aware.patch
mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes.patch
mm-move-page-mapped-accounting-to-the-node.patch
mm-rename-nr_anon_pages-to-nr_anon_mapped.patch
mm-move-most-file-based-accounting-to-the-node.patch
mm-move-vmscan-writes-and-file-write-accounting-to-the-node.patch
mm-vmscan-update-classzone_idx-if-buffer_heads_over_limit.patch
mm-vmscan-only-wakeup-kswapd-once-per-node-for-the-requested-classzone.patch
mm-convert-zone_reclaim-to-node_reclaim.patch
mm-vmscan-add-classzone-information-to-tracepoints.patch
mm-page_alloc-remove-fair-zone-allocation-policy.patch
mm-page_alloc-cache-the-last-node-whose-dirty-limit-is-reached.patch
mm-vmstat-replace-__count_zone_vm_events-with-a-zone-id-equivalent.patch
mm-vmstat-account-per-zone-stalls-and-pages-skipped-during-reclaim.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
