@@ -1006,6 +1006,7 @@ enum zone_flags {
* Cleared when kswapd is woken.
*/
ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */
+ ZONE_BELOW_HIGH, /* zone is below high watermark. */
};
static inline unsigned long zone_managed_pages(struct zone *zone)
@@ -2409,7 +2409,13 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone,
return min(batch << 2, pcp->high);
}
- if (pcp->count >= high && high_min != high_max) {
+ if (high_min == high_max)
+ return high;
+
+ if (test_bit(ZONE_BELOW_HIGH, &zone->flags)) {
+ pcp->high = max(high - (batch << pcp->free_factor), high_min);
+ high = max(pcp->count, high_min);
+ } else if (pcp->count >= high) {
int need_high = (batch << pcp->free_factor) + batch;
/* pcp->high should be large enough to hold batch freed pages */
@@ -2459,6 +2465,10 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
if (pcp->count >= high) {
free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high),
pcp, pindex);
+ if (test_bit(ZONE_BELOW_HIGH, &zone->flags) &&
+ zone_watermark_ok(zone, 0, high_wmark_pages(zone),
+ ZONE_MOVABLE, 0))
+ clear_bit(ZONE_BELOW_HIGH, &zone->flags);
}
}
@@ -2765,7 +2775,7 @@ static int nr_pcp_alloc(struct per_cpu_pages *pcp, struct zone *zone, int order)
* If we had larger pcp->high, we could avoid to allocate from
* zone.
*/
- if (high_min != high_max && !test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags))
+ if (high_min != high_max && !test_bit(ZONE_BELOW_HIGH, &zone->flags))
high = pcp->high = min(high + batch, high_max);
if (!order) {
@@ -3226,6 +3236,14 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
}
}
+ mark = high_wmark_pages(zone);
+ if (zone_watermark_fast(zone, order, mark,
+ ac->highest_zoneidx, alloc_flags,
+ gfp_mask))
+ goto try_this_zone;
+ else if (!test_bit(ZONE_BELOW_HIGH, &zone->flags))
+ set_bit(ZONE_BELOW_HIGH, &zone->flags);
+
mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
if (!zone_watermark_fast(zone, order, mark,
ac->highest_zoneidx, alloc_flags,
One target of PCP is to minimize pages in PCP if the system free pages is too few. To reach that target, when page reclaiming is active for the zone (ZONE_RECLAIM_ACTIVE), we will stop increasing PCP high in allocating path, decrease PCP high and free some pages in freeing path. But this may be too late because the background page reclaiming may introduce latency for some workloads. So, in this patch, during page allocation we will detect whether the number of free pages of the zone is below high watermark. If so, we will stop increasing PCP high in allocating path, decrease PCP high and free some pages in freeing path. With this, we can reduce the possibility of the premature background page reclaiming caused by too large PCP. The high watermark checking is done in allocating path to reduce the overhead in hotter freeing path. Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: David Hildenbrand <david@redhat.com> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Christoph Lameter <cl@linux.com> --- include/linux/mmzone.h | 1 + mm/page_alloc.c | 22 ++++++++++++++++++++-- 2 files changed, 21 insertions(+), 2 deletions(-)