aboutsummaryrefslogtreecommitdiffstats
path: root/mm/swap.c
diff options
context:
space:
mode:
authorShaohua Li <shaohua.li@intel.com>2011-05-24 17:12:55 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-05-25 08:39:37 -0700
commiteb709b0d062efd653a61183af8e27b2711c3cf5c (patch)
treeea0b4139854c2e713acab7ac679fa368ef9187ef /mm/swap.c
parentf68aa5b445fd00b67588ade611a4efb1a34dadb4 (diff)
downloadkernel_goldelico_gta04-eb709b0d062efd653a61183af8e27b2711c3cf5c.zip
kernel_goldelico_gta04-eb709b0d062efd653a61183af8e27b2711c3cf5c.tar.gz
kernel_goldelico_gta04-eb709b0d062efd653a61183af8e27b2711c3cf5c.tar.bz2
mm: batch activate_page() to reduce lock contention
The zone->lru_lock is heavily contented in workload where activate_page() is frequently used. We could do batch activate_page() to reduce the lock contention. The batched pages will be added into zone list when the pool is full or page reclaim is trying to drain them. For example, in a 4 socket 64 CPU system, create a sparse file and 64 processes, processes shared map to the file. Each process read access the whole file and then exit. The process exit will do unmap_vmas() and cause a lot of activate_page() call. In such workload, we saw about 58% total time reduction with below patch. Other workloads with a lot of activate_page also benefits a lot too. Andrew Morton suggested activate_page() and putback_lru_pages() should follow the same path to active pages, but this is hard to implement (see commit 7a608572a282a ("Revert "mm: batch activate_page() to reduce lock contention")). On the other hand, do we really need putback_lru_pages() to follow the same path? I tested several FIO/FFSB benchmark (about 20 scripts for each benchmark) in 3 machines here from 2 sockets to 4 sockets. My test doesn't show anything significant with/without below patch (there is slight difference but mostly some noise which we found even without below patch before). Below patch basically returns to the same as my first post. I tested some microbenchmarks: case-anon-cow-rand-mt 0.58% case-anon-cow-rand -3.30% case-anon-cow-seq-mt -0.51% case-anon-cow-seq -5.68% case-anon-r-rand-mt 0.23% case-anon-r-rand 0.81% case-anon-r-seq-mt -0.71% case-anon-r-seq -1.99% case-anon-rx-rand-mt 2.11% case-anon-rx-seq-mt 3.46% case-anon-w-rand-mt -0.03% case-anon-w-rand -0.50% case-anon-w-seq-mt -1.08% case-anon-w-seq -0.12% case-anon-wx-rand-mt -5.02% case-anon-wx-seq-mt -1.43% case-fork 1.65% case-fork-sleep -0.07% case-fork-withmem 1.39% case-hugetlb -0.59% case-lru-file-mmap-read-mt -0.54% case-lru-file-mmap-read 0.61% case-lru-file-mmap-read-rand -2.24% case-lru-file-readonce -0.64% case-lru-file-readtwice -11.69% case-lru-memcg -1.35% case-mmap-pread-rand-mt 1.88% case-mmap-pread-rand -15.26% case-mmap-pread-seq-mt 0.89% case-mmap-pread-seq -69.72% case-mmap-xread-rand-mt 0.71% case-mmap-xread-seq-mt 0.38% The most significent are: case-lru-file-readtwice -11.69% case-mmap-pread-rand -15.26% case-mmap-pread-seq -69.72% which use activate_page a lot. others are basically variations because each run has slightly difference. In UP case, 'size mm/swap.o' before the two patches: text data bss dec hex filename 6466 896 4 7366 1cc6 mm/swap.o after the two patches: text data bss dec hex filename 6343 896 4 7243 1c4b mm/swap.o Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hiroyuki Kamezawa <kamezawa.hiroyuki@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/swap.c')
-rw-r--r--mm/swap.c45
1 files changed, 40 insertions, 5 deletions
diff --git a/mm/swap.c b/mm/swap.c
index 2f365d1..3a442f1 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -272,14 +272,10 @@ static void update_page_reclaim_stat(struct zone *zone, struct page *page,
memcg_reclaim_stat->recent_rotated[file]++;
}
-/*
- * FIXME: speed this up?
- */
-void activate_page(struct page *page)
+static void __activate_page(struct page *page, void *arg)
{
struct zone *zone = page_zone(page);
- spin_lock_irq(&zone->lru_lock);
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
int file = page_is_file_cache(page);
int lru = page_lru_base_type(page);
@@ -292,8 +288,45 @@ void activate_page(struct page *page)
update_page_reclaim_stat(zone, page, file, 1);
}
+}
+
+#ifdef CONFIG_SMP
+static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
+
+static void activate_page_drain(int cpu)
+{
+ struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);
+
+ if (pagevec_count(pvec))
+ pagevec_lru_move_fn(pvec, __activate_page, NULL);
+}
+
+void activate_page(struct page *page)
+{
+ if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+ struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+
+ page_cache_get(page);
+ if (!pagevec_add(pvec, page))
+ pagevec_lru_move_fn(pvec, __activate_page, NULL);
+ put_cpu_var(activate_page_pvecs);
+ }
+}
+
+#else
+static inline void activate_page_drain(int cpu)
+{
+}
+
+void activate_page(struct page *page)
+{
+ struct zone *zone = page_zone(page);
+
+ spin_lock_irq(&zone->lru_lock);
+ __activate_page(page, NULL);
spin_unlock_irq(&zone->lru_lock);
}
+#endif
/*
* Mark a page as having seen activity.
@@ -464,6 +497,8 @@ static void drain_cpu_pagevecs(int cpu)
pvec = &per_cpu(lru_deactivate_pvecs, cpu);
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+
+ activate_page_drain(cpu);
}
/**