vmscan: separate sc.swap_cluster_max and sc.nr_max_reclaim
Currently, sc.scap_cluster_max has double meanings.
1) reclaim batch size as isolate_lru_pages()'s argument
2) reclaim baling out thresolds
The two meanings pretty unrelated. Thus, Let's separate it.
this patch doesn't change any behavior.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/vmscan.c b/mm/vmscan.c
index cb69f71..7b0d5c7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -55,6 +55,9 @@
/* Number of pages freed so far during a call to shrink_zones() */
unsigned long nr_reclaimed;
+ /* How many pages shrink_list() should reclaim */
+ unsigned long nr_to_reclaim;
+
/* This context's GFP mask */
gfp_t gfp_mask;
@@ -1595,6 +1598,7 @@
enum lru_list l;
unsigned long nr_reclaimed = sc->nr_reclaimed;
unsigned long swap_cluster_max = sc->swap_cluster_max;
+ unsigned long nr_to_reclaim = sc->nr_to_reclaim;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
int noswap = 0;
@@ -1639,8 +1643,7 @@
* with multiple processes reclaiming pages, the total
* freeing target can get unreasonably large.
*/
- if (nr_reclaimed > swap_cluster_max &&
- priority < DEF_PRIORITY && !current_is_kswapd())
+ if (nr_reclaimed > nr_to_reclaim && priority < DEF_PRIORITY)
break;
}
@@ -1738,6 +1741,7 @@
struct zoneref *z;
struct zone *zone;
enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
+ unsigned long writeback_threshold;
delayacct_freepages_start();
@@ -1773,7 +1777,7 @@
}
}
total_scanned += sc->nr_scanned;
- if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+ if (sc->nr_reclaimed >= sc->nr_to_reclaim) {
ret = sc->nr_reclaimed;
goto out;
}
@@ -1785,8 +1789,8 @@
* that's undesirable in laptop mode, where we *want* lumpy
* writeout. So in laptop mode, write out the whole world.
*/
- if (total_scanned > sc->swap_cluster_max +
- sc->swap_cluster_max / 2) {
+ writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
+ if (total_scanned > writeback_threshold) {
wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
sc->may_writepage = 1;
}
@@ -1832,6 +1836,7 @@
.gfp_mask = gfp_mask,
.may_writepage = !laptop_mode,
.swap_cluster_max = SWAP_CLUSTER_MAX,
+ .nr_to_reclaim = SWAP_CLUSTER_MAX,
.may_unmap = 1,
.may_swap = 1,
.swappiness = vm_swappiness,
@@ -1890,6 +1895,7 @@
.may_unmap = 1,
.may_swap = !noswap,
.swap_cluster_max = SWAP_CLUSTER_MAX,
+ .nr_to_reclaim = SWAP_CLUSTER_MAX,
.swappiness = swappiness,
.order = 0,
.mem_cgroup = mem_cont,
@@ -1961,6 +1967,11 @@
.may_unmap = 1,
.may_swap = 1,
.swap_cluster_max = SWAP_CLUSTER_MAX,
+ /*
+ * kswapd doesn't want to be bailed out while reclaim. because
+ * we want to put equal scanning pressure on each zone.
+ */
+ .nr_to_reclaim = ULONG_MAX,
.swappiness = vm_swappiness,
.order = order,
.mem_cgroup = NULL,
@@ -2630,7 +2641,9 @@
.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
.may_swap = 1,
.swap_cluster_max = max_t(unsigned long, nr_pages,
- SWAP_CLUSTER_MAX),
+ SWAP_CLUSTER_MAX),
+ .nr_to_reclaim = max_t(unsigned long, nr_pages,
+ SWAP_CLUSTER_MAX),
.gfp_mask = gfp_mask,
.swappiness = vm_swappiness,
.order = order,