summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorHugh Dickins <hugh@veritas.com>2009-01-06 14:39:55 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-01-06 15:59:06 -0800
commitc60aa176c6de82703f064082b909496fc4fee956 (patch)
tree2a6e58bda416af2c87f470023041f7049dcf1167
parent20137a490f397d9c01fc9fadd83a8d198bda4477 (diff)
downloadlinux-c60aa176c6de82703f064082b909496fc4fee956.tar.gz
linux-c60aa176c6de82703f064082b909496fc4fee956.tar.bz2
linux-c60aa176c6de82703f064082b909496fc4fee956.zip
swapfile: swap allocation cycle if nonrot
Though attempting to find free clusters (Andrea), swap allocation has always restarted its searches from the beginning of the swap area (sct), to reduce seek times between swap pages, by not scattering them all over the partition. But on a solidstate swap device, seeks are cheap, and block remapping to level the wear may be limited by zones: in that case it's better to cycle around the whole partition. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Joern Engel <joern@logfs.org> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Donjun Shin <djshin90@gmail.com> Cc: Tejun Heo <teheo@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/swapfile.c50
1 files changed, 46 insertions, 4 deletions
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b0f56603b9be..763210732b5f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -169,6 +169,7 @@ static int wait_for_discard(void *word)
static inline unsigned long scan_swap_map(struct swap_info_struct *si)
{
unsigned long offset;
+ unsigned long scan_base;
unsigned long last_in_cluster = 0;
int latency_ration = LATENCY_LIMIT;
int found_free_cluster = 0;
@@ -181,10 +182,11 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si)
* all over the entire swap partition, so that we reduce
* overall disk seek times between swap pages. -- sct
* But we do now try to find an empty cluster. -Andrea
+ * And we let swap pages go all over an SSD partition. Hugh
*/
si->flags += SWP_SCANNING;
- offset = si->cluster_next;
+ scan_base = offset = si->cluster_next;
if (unlikely(!si->cluster_nr--)) {
if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
@@ -206,7 +208,16 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si)
}
spin_unlock(&swap_lock);
- offset = si->lowest_bit;
+ /*
+ * If seek is expensive, start searching for new cluster from
+ * start of partition, to minimize the span of allocated swap.
+ * But if seek is cheap, search from our current position, so
+ * that swap is allocated from all over the partition: if the
+ * Flash Translation Layer only remaps within limited zones,
+ * we don't want to wear out the first zone too quickly.
+ */
+ if (!(si->flags & SWP_SOLIDSTATE))
+ scan_base = offset = si->lowest_bit;
last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
/* Locate the first empty (unaligned) cluster */
@@ -228,6 +239,27 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si)
}
offset = si->lowest_bit;
+ last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
+
+ /* Locate the first empty (unaligned) cluster */
+ for (; last_in_cluster < scan_base; offset++) {
+ if (si->swap_map[offset])
+ last_in_cluster = offset + SWAPFILE_CLUSTER;
+ else if (offset == last_in_cluster) {
+ spin_lock(&swap_lock);
+ offset -= SWAPFILE_CLUSTER - 1;
+ si->cluster_next = offset;
+ si->cluster_nr = SWAPFILE_CLUSTER - 1;
+ found_free_cluster = 1;
+ goto checks;
+ }
+ if (unlikely(--latency_ration < 0)) {
+ cond_resched();
+ latency_ration = LATENCY_LIMIT;
+ }
+ }
+
+ offset = scan_base;
spin_lock(&swap_lock);
si->cluster_nr = SWAPFILE_CLUSTER - 1;
si->lowest_alloc = 0;
@@ -239,7 +271,7 @@ checks:
if (!si->highest_bit)
goto no_page;
if (offset > si->highest_bit)
- offset = si->lowest_bit;
+ scan_base = offset = si->lowest_bit;
if (si->swap_map[offset])
goto scan;
@@ -323,8 +355,18 @@ scan:
latency_ration = LATENCY_LIMIT;
}
}
+ offset = si->lowest_bit;
+ while (++offset < scan_base) {
+ if (!si->swap_map[offset]) {
+ spin_lock(&swap_lock);
+ goto checks;
+ }
+ if (unlikely(--latency_ration < 0)) {
+ cond_resched();
+ latency_ration = LATENCY_LIMIT;
+ }
+ }
spin_lock(&swap_lock);
- goto checks;
no_page:
si->flags -= SWP_SCANNING;