@@ -943,6 +943,7 @@ static int cacheinfo_cpu_online(unsigned int cpu)
if (rc)
goto err;
update_data_cache_size(true, cpu);
+ setup_pcp_cacheinfo();
return 0;
err:
free_cache_attributes(cpu);
@@ -956,6 +957,7 @@ static int cacheinfo_cpu_pre_down(unsigned int cpu)
free_cache_attributes(cpu);
update_data_cache_size(false, cpu);
+ setup_pcp_cacheinfo();
return 0;
}
@@ -325,6 +325,7 @@ void drain_all_pages(struct zone *zone);
void drain_local_pages(struct zone *zone);
void page_alloc_init_late(void);
+void setup_pcp_cacheinfo(void);
/*
* gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
@@ -677,6 +677,7 @@ enum zone_watermarks {
#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost)
#define PCPF_PREV_FREE_HIGH_ORDER 0x01
+#define PCPF_FREE_HIGH_BATCH 0x02
struct per_cpu_pages {
spinlock_t lock; /* Protects lists field */
@@ -52,6 +52,7 @@
#include <linux/psi.h>
#include <linux/khugepaged.h>
#include <linux/delayacct.h>
+#include <linux/cacheinfo.h>
#include <asm/div64.h>
#include "internal.h"
#include "shuffle.h"
@@ -2385,7 +2386,9 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
*/
if (order && order <= PAGE_ALLOC_COSTLY_ORDER) {
free_high = (pcp->free_factor &&
- (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER));
+ (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) &&
+ (!(pcp->flags & PCPF_FREE_HIGH_BATCH) ||
+ pcp->count >= READ_ONCE(pcp->batch)));
pcp->flags |= PCPF_PREV_FREE_HIGH_ORDER;
} else if (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) {
pcp->flags &= ~PCPF_PREV_FREE_HIGH_ORDER;
@@ -5418,6 +5421,38 @@ static void zone_pcp_update(struct zone *zone, int cpu_online)
mutex_unlock(&pcp_batch_high_lock);
}
+static void zone_pcp_update_cacheinfo(struct zone *zone)
+{
+ int cpu;
+ struct per_cpu_pages *pcp;
+ struct cpu_cacheinfo *cci;
+
+ for_each_online_cpu(cpu) {
+ pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
+ cci = get_cpu_cacheinfo(cpu);
+ /*
+ * If per-CPU data cache is large enough, up to
+ * "batch" high-order pages can be cached in PCP for
+ * consecutive freeing. This can reduce zone lock
+ * contention without hurting cache-hot pages sharing.
+ */
+ spin_lock(&pcp->lock);
+ if ((cci->size_data >> PAGE_SHIFT) > 4 * pcp->batch)
+ pcp->flags |= PCPF_FREE_HIGH_BATCH;
+ else
+ pcp->flags &= ~PCPF_FREE_HIGH_BATCH;
+ spin_unlock(&pcp->lock);
+ }
+}
+
+void setup_pcp_cacheinfo(void)
+{
+ struct zone *zone;
+
+ for_each_populated_zone(zone)
+ zone_pcp_update_cacheinfo(zone);
+}
+
/*
* Allocate per cpu pagesets and initialize them.
* Before this call only boot pagesets were available.
In commit f26b3fa04611 ("mm/page_alloc: limit number of high-order pages on PCP during bulk free"), the PCP (Per-CPU Pageset) will be drained when PCP is mostly used for high-order pages freeing to improve the cache-hot pages reusing between page allocating and freeing CPUs. On system with small per-CPU data cache, pages shouldn't be cached before draining to guarantee cache-hot. But on a system with large per-CPU data cache, more pages can be cached before draining to reduce zone lock contention. So, in this patch, instead of draining without any caching, "batch" pages will be cached in PCP before draining if the per-CPU data cache size is more than "4 * batch". On a 2-socket Intel server with 128 logical CPU, with the patch, the network bandwidth of the UNIX (AF_UNIX) test case of lmbench test suite with 16-pair processes increase 72.2%. The cycles% of the spinlock contention (mostly for zone lock) decreases from 45.8% to 21.2%. The number of PCP draining for high order pages freeing (free_high) decreases 89.8%. The cache miss rate keeps 0.3%. 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> --- drivers/base/cacheinfo.c | 2 ++ include/linux/gfp.h | 1 + include/linux/mmzone.h | 1 + mm/page_alloc.c | 37 ++++++++++++++++++++++++++++++++++++- 4 files changed, 40 insertions(+), 1 deletion(-)