diff mbox series

[152/200] mm: don't wake kswapd prematurely when watermark boosting is disabled

Message ID 20201215031215.ZzmH0glWr%akpm@linux-foundation.org (mailing list archive)
State New, archived
Headers show
Series [001/200] kthread: add kthread_work tracepoints | expand

Commit Message

Andrew Morton Dec. 15, 2020, 3:12 a.m. UTC
From: Johannes Weiner <hannes@cmpxchg.org>
Subject: mm: don't wake kswapd prematurely when watermark boosting is disabled

On 2-node NUMA hosts we see bursts of kswapd reclaim and subsequent
pressure spikes and stalls from cache refaults while there is plenty of
free memory in the system.

Usually, kswapd is woken up when all eligible nodes in an allocation are
full.  But the code related to watermark boosting can wake kswapd on one
full node while the other one is mostly empty.  This may be justified to
fight fragmentation, but is currently unconditionally done whether
watermark boosting is occurring or not.

In our case, many of our workloads' throughput scales with available
memory, and pure utilization is a more tangible concern than trends around
longer-term fragmentation.  As a result we generally disable watermark

Wake kswapd only woken when watermark boosting is requested.

Link: https://lkml.kernel.org/r/20201020175833.397286-1-hannes@cmpxchg.org
Fixes: 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

 mm/page_alloc.c |   13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)
diff mbox series


--- a/mm/page_alloc.c~mm-dont-wake-kswapd-prematurely-when-watermark-boosting-is-disabled
+++ a/mm/page_alloc.c
@@ -2482,12 +2482,12 @@  static bool can_steal_fallback(unsigned
 	return false;
-static inline void boost_watermark(struct zone *zone)
+static inline bool boost_watermark(struct zone *zone)
 	unsigned long max_boost;
 	if (!watermark_boost_factor)
-		return;
+		return false;
 	 * Don't bother in zones that are unlikely to produce results.
 	 * On small machines, including kdump capture kernels running
@@ -2495,7 +2495,7 @@  static inline void boost_watermark(struc
 	 * memory situation immediately.
 	if ((pageblock_nr_pages * 4) > zone_managed_pages(zone))
-		return;
+		return false;
 	max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
 			watermark_boost_factor, 10000);
@@ -2509,12 +2509,14 @@  static inline void boost_watermark(struc
 	 * boosted watermark resulting in a hang.
 	if (!max_boost)
-		return;
+		return false;
 	max_boost = max(pageblock_nr_pages, max_boost);
 	zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
+	return true;
@@ -2552,8 +2554,7 @@  static void steal_suitable_fallback(stru
 	 * likelihood of future fallbacks. Wake kswapd now as the node
 	 * may be balanced overall and kswapd will not wake naturally.
-	boost_watermark(zone);
-	if (alloc_flags & ALLOC_KSWAPD)
+	if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD))
 		set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
 	/* We are not allowed to try stealing from the whole block */