mm/page_alloc: introduce vm.percpu_pagelist_high_fraction

This introduces a new sysctl vm.percpu_pagelist_high_fraction.  It is
similar to the old vm.percpu_pagelist_fraction.  The old sysctl increased
both pcp->batch and pcp->high with the higher pcp->high potentially
reducing zone->lock contention.  However, the higher pcp->batch value also
potentially increased allocation latency while the PCP was refilled.  This
sysctl only adjusts pcp->high so that zone->lock contention is potentially
reduced but allocation latency during a PCP refill remains the same.

  # grep -E "high:|batch" /proc/zoneinfo | tail -2
              high:  649
              batch: 63

  # sysctl vm.percpu_pagelist_high_fraction=8
  # grep -E "high:|batch" /proc/zoneinfo | tail -2
              high:  35071
              batch: 63

  # sysctl vm.percpu_pagelist_high_fraction=64
              high:  4383
              batch: 63

  # sysctl vm.percpu_pagelist_high_fraction=0
              high:  649
              batch: 63

[mgorman@techsingularity.net: fix documentation]
  Link: https://lkml.kernel.org/r/20210528151010.GQ30378@techsingularity.net

Link: https://lkml.kernel.org/r/20210525080119.5455-7-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 62 insertions, 7 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index adf35ccfd8e5..cfc4071310fb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -120,6 +120,7 @@ typedef int __bitwise fpi_t;
 
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
+#define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)
 
 struct pagesets {
 	local_lock_t lock;
@@ -192,6 +193,7 @@ EXPORT_SYMBOL(_totalram_pages);
 unsigned long totalreserve_pages __read_mostly;
 unsigned long totalcma_pages __read_mostly;
 
+int percpu_pagelist_high_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
 DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
 EXPORT_SYMBOL(init_on_alloc);
@@ -6725,17 +6727,32 @@ static int zone_highsize(struct zone *zone, int batch, int cpu_online)
 #ifdef CONFIG_MMU
 	int high;
 	int nr_local_cpus;
+	unsigned long total_pages;
+
+	if (!percpu_pagelist_high_fraction) {
+		/*
+		 * By default, the high value of the pcp is based on the zone
+		 * low watermark so that if they are full then background
+		 * reclaim will not be started prematurely.
+		 */
+		total_pages = low_wmark_pages(zone);
+	} else {
+		/*
+		 * If percpu_pagelist_high_fraction is configured, the high
+		 * value is based on a fraction of the managed pages in the
+		 * zone.
+		 */
+		total_pages = zone_managed_pages(zone) / percpu_pagelist_high_fraction;
+	}
 
 	/*
-	 * The high value of the pcp is based on the zone low watermark
-	 * so that if they are full then background reclaim will not be
-	 * started prematurely. The value is split across all online CPUs
-	 * local to the zone. Note that early in boot that CPUs may not be
-	 * online yet and that during CPU hotplug that the cpumask is not
-	 * yet updated when a CPU is being onlined.
+	 * Split the high value across all online CPUs local to the zone. Note
+	 * that early in boot that CPUs may not be online yet and that during
+	 * CPU hotplug that the cpumask is not yet updated when a CPU is being
+	 * onlined.
 	 */
 	nr_local_cpus = max(1U, cpumask_weight(cpumask_of_node(zone_to_nid(zone)))) + cpu_online;
-	high = low_wmark_pages(zone) / nr_local_cpus;
+	high = total_pages / nr_local_cpus;
 
 	/*
 	 * Ensure high is at least batch*4. The multiple is based on the
@@ -8500,6 +8517,44 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write,
 	return 0;
 }
 
+/*
+ * percpu_pagelist_high_fraction - changes the pcp->high for each zone on each
+ * cpu. It is the fraction of total pages in each zone that a hot per cpu
+ * pagelist can have before it gets flushed back to buddy allocator.
+ */
+int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table,
+		int write, void *buffer, size_t *length, loff_t *ppos)
+{
+	struct zone *zone;
+	int old_percpu_pagelist_high_fraction;
+	int ret;
+
+	mutex_lock(&pcp_batch_high_lock);
+	old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction;
+
+	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
+	if (!write || ret < 0)
+		goto out;
+
+	/* Sanity checking to avoid pcp imbalance */
+	if (percpu_pagelist_high_fraction &&
+	    percpu_pagelist_high_fraction < MIN_PERCPU_PAGELIST_HIGH_FRACTION) {
+		percpu_pagelist_high_fraction = old_percpu_pagelist_high_fraction;
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* No change? */
+	if (percpu_pagelist_high_fraction == old_percpu_pagelist_high_fraction)
+		goto out;
+
+	for_each_populated_zone(zone)
+		zone_set_pageset_high_and_batch(zone, 0);
+out:
+	mutex_unlock(&pcp_batch_high_lock);
+	return ret;
+}
+
 #ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES
 /*
  * Returns the number of pages that arch has reserved but