The patch titled
Subject: mm, vmscan: cleanup lru size claculations
has been added to the -mm tree. Its filename is
mm-vmscan-cleanup-lru-size-claculations.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-vmscan-cleanup-lru-size-claculations.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-vmscan-cleanup-lru-size-claculations.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: Michal Hocko <mhocko@xxxxxxxx>
Subject: mm, vmscan: cleanup lru size claculations
lruvec_lru_size returns the full size of the LRU list while we sometimes
need a value reduced only to eligible zones (e.g. for lowmem requests).
inactive_list_is_low is one such user. Later patches will add more of
them. Add a new parameter to lruvec_lru_size and allow it filter out
zones which are not eligible for the given context.
Link: http://lkml.kernel.org/r/20170117103702.28542-2-mhocko@xxxxxxxxxx
Signed-off-by: Michal Hocko <mhocko@xxxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Acked-by: Hillf Danton <hillf.zj@xxxxxxxxxxxxxxx>
Acked-by: Minchan Kim <minchan@xxxxxxxxxx>
Acked-by: Mel Gorman <mgorman@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mmzone.h | 2
mm/vmscan.c | 89 +++++++++++++++++++--------------------
mm/workingset.c | 2
3 files changed, 46 insertions(+), 47 deletions(-)
diff -puN include/linux/mmzone.h~mm-vmscan-cleanup-lru-size-claculations include/linux/mmzone.h
--- a/include/linux/mmzone.h~mm-vmscan-cleanup-lru-size-claculations
+++ a/include/linux/mmzone.h
@@ -780,7 +780,7 @@ static inline struct pglist_data *lruvec
#endif
}
-extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru);
+extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx);
#ifdef CONFIG_HAVE_MEMORY_PRESENT
void memory_present(int nid, unsigned long start, unsigned long end);
diff -puN mm/vmscan.c~mm-vmscan-cleanup-lru-size-claculations mm/vmscan.c
--- a/mm/vmscan.c~mm-vmscan-cleanup-lru-size-claculations
+++ a/mm/vmscan.c
@@ -234,22 +234,39 @@ bool pgdat_reclaimable(struct pglist_dat
pgdat_reclaimable_pages(pgdat) * 6;
}
-unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
+/**
+ * lruvec_lru_size - Returns the number of pages on the given LRU list.
+ * @lruvec: lru vector
+ * @lru: lru to use
+ * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list)
+ */
+unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
{
+ unsigned long lru_size;
+ int zid;
+
if (!mem_cgroup_disabled())
- return mem_cgroup_get_lru_size(lruvec, lru);
+ lru_size = mem_cgroup_get_lru_size(lruvec, lru);
+ else
+ lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
- return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
-}
+ for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
+ struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
+ unsigned long size;
-unsigned long lruvec_zone_lru_size(struct lruvec *lruvec, enum lru_list lru,
- int zone_idx)
-{
- if (!mem_cgroup_disabled())
- return mem_cgroup_get_zone_lru_size(lruvec, lru, zone_idx);
+ if (!managed_zone(zone))
+ continue;
+
+ if (!mem_cgroup_disabled())
+ size = mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
+ else
+ size = zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zid],
+ NR_ZONE_LRU_BASE + lru);
+ lru_size -= min(size, lru_size);
+ }
+
+ return lru_size;
- return zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zone_idx],
- NR_ZONE_LRU_BASE + lru);
}
/*
@@ -2049,11 +2066,10 @@ static bool inactive_list_is_low(struct
struct scan_control *sc, bool trace)
{
unsigned long inactive_ratio;
- unsigned long total_inactive, inactive;
- unsigned long total_active, active;
+ unsigned long inactive, active;
+ enum lru_list inactive_lru = file * LRU_FILE;
+ enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
unsigned long gb;
- struct pglist_data *pgdat = lruvec_pgdat(lruvec);
- int zid;
/*
* If we don't have swap space, anonymous page deactivation
@@ -2062,27 +2078,8 @@ static bool inactive_list_is_low(struct
if (!file && !total_swap_pages)
return false;
- total_inactive = inactive = lruvec_lru_size(lruvec, file * LRU_FILE);
- total_active = active = lruvec_lru_size(lruvec, file * LRU_FILE + LRU_ACTIVE);
-
- /*
- * For zone-constrained allocations, it is necessary to check if
- * deactivations are required for lowmem to be reclaimed. This
- * calculates the inactive/active pages available in eligible zones.
- */
- for (zid = sc->reclaim_idx + 1; zid < MAX_NR_ZONES; zid++) {
- struct zone *zone = &pgdat->node_zones[zid];
- unsigned long inactive_zone, active_zone;
-
- if (!managed_zone(zone))
- continue;
-
- inactive_zone = lruvec_zone_lru_size(lruvec, file * LRU_FILE, zid);
- active_zone = lruvec_zone_lru_size(lruvec, (file * LRU_FILE) + LRU_ACTIVE, zid);
-
- inactive -= min(inactive, inactive_zone);
- active -= min(active, active_zone);
- }
+ inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
+ active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
gb = (inactive + active) >> (30 - PAGE_SHIFT);
if (gb)
@@ -2091,10 +2088,12 @@ static bool inactive_list_is_low(struct
inactive_ratio = 1;
if (trace)
- trace_mm_vmscan_inactive_list_is_low(pgdat->node_id,
+ trace_mm_vmscan_inactive_list_is_low(lruvec_pgdat(lruvec)->node_id,
sc->reclaim_idx,
- total_inactive, inactive,
- total_active, active, inactive_ratio, file);
+ lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive,
+ lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active,
+ inactive_ratio, file);
+
return inactive * inactive_ratio < active;
}
@@ -2234,7 +2233,7 @@ static void get_scan_count(struct lruvec
* system is under heavy pressure.
*/
if (!inactive_list_is_low(lruvec, true, sc, false) &&
- lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
+ lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES) >> sc->priority) {
scan_balance = SCAN_FILE;
goto out;
}
@@ -2260,10 +2259,10 @@ static void get_scan_count(struct lruvec
* anon in [0], file in [1]
*/
- anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON) +
- lruvec_lru_size(lruvec, LRU_INACTIVE_ANON);
- file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
- lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
+ anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
+ lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
+ file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
+ lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
spin_lock_irq(&pgdat->lru_lock);
if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
@@ -2301,7 +2300,7 @@ out:
unsigned long size;
unsigned long scan;
- size = lruvec_lru_size(lruvec, lru);
+ size = lruvec_lru_size(lruvec, lru, MAX_NR_ZONES);
scan = size >> sc->priority;
if (!scan && pass && force_scan)
diff -puN mm/workingset.c~mm-vmscan-cleanup-lru-size-claculations mm/workingset.c
--- a/mm/workingset.c~mm-vmscan-cleanup-lru-size-claculations
+++ a/mm/workingset.c
@@ -267,7 +267,7 @@ bool workingset_refault(void *shadow)
}
lruvec = mem_cgroup_lruvec(pgdat, memcg);
refault = atomic_long_read(&lruvec->inactive_age);
- active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
+ active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
rcu_read_unlock();
/*
_
Patches currently in -mm which might be from mhocko@xxxxxxxx are
mm-throttle-show_mem-from-warn_alloc.patch
mm-trace-extract-compaction_status-and-zone_type-to-a-common-header.patch
oom-trace-add-oom-detection-tracepoints.patch
oom-trace-add-compaction-retry-tracepoint.patch
mm-vmscan-remove-unused-mm_vmscan_memcg_isolate.patch
mm-vmscan-add-active-list-aging-tracepoint.patch
mm-vmscan-add-active-list-aging-tracepoint-update.patch
mm-vmscan-show-the-number-of-skipped-pages-in-mm_vmscan_lru_isolate.patch
mm-vmscan-show-lru-name-in-mm_vmscan_lru_isolate-tracepoint.patch
mm-vmscan-extract-shrink_page_list-reclaim-counters-into-a-struct.patch
mm-vmscan-enhance-mm_vmscan_lru_shrink_inactive-tracepoint.patch
mm-vmscan-add-mm_vmscan_inactive_list_is_low-tracepoint.patch
trace-vmscan-postprocess-sync-with-tracepoints-updates.patch
mm-vmscan-do-not-count-freed-pages-as-pgdeactivate.patch
mm-vmscan-cleanup-lru-size-claculations.patch
mm-vmscan-consider-eligible-zones-in-get_scan_count.patch
revert-mm-bail-out-in-shrink_inactive_list.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
