The patch titled
vmscan: add some sanity checks to get_scan_ratio
has been added to the -mm tree. Its filename is
vmscan-add-some-sanity-checks-to-get_scan_ratio.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: vmscan: add some sanity checks to get_scan_ratio
From: Rik van Riel <riel@xxxxxxxxxx>
The access ratio based scan rate determination in get_scan_ratio
works ok in most situations, but needs to be corrected in some
corner cases:
- if we run out of swap space, do not bother scanning the anon LRUs
- if we have already freed all of the page cache, we need to scan
the anon LRUs
- restore the *actual* access ratio based scan rate algorithm, the
previous versions of this patch series had the wrong version
- scale the number of pages added to zone->nr_scan[l]
Signed-off-by: Rik van Riel <riel@xxxxxxxxxx>
---
include/linux/mmzone.h | 2
Index: linux-2.6.26-rc2-mm1/mm/vmscan.c
===================================================================
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mmzone.h | 2
mm/page_alloc.c | 3 -
mm/swap.c | 13 ++++
mm/vmscan.c | 104 ++++++++++++++++++++++++++-------------
4 files changed, 85 insertions(+), 37 deletions(-)
diff -puN include/linux/mmzone.h~add-some-sanity-checks-to-get_scan_ratio include/linux/mmzone.h
--- a/include/linux/mmzone.h~add-some-sanity-checks-to-get_scan_ratio
+++ a/include/linux/mmzone.h
@@ -289,6 +289,8 @@ struct zone {
unsigned long recent_rotated_anon;
unsigned long recent_rotated_file;
+ unsigned long recent_scanned_anon;
+ unsigned long recent_scanned_file;
unsigned long pages_scanned; /* since last reclaim */
unsigned long flags; /* zone flags, see below */
diff -puN mm/page_alloc.c~add-some-sanity-checks-to-get_scan_ratio mm/page_alloc.c
--- a/mm/page_alloc.c~add-some-sanity-checks-to-get_scan_ratio
+++ a/mm/page_alloc.c
@@ -3436,7 +3436,8 @@ static void __paginginit free_area_init_
}
zone->recent_rotated_anon = 0;
zone->recent_rotated_file = 0;
-//TODO recent_scanned_* ???
+ zone->recent_scanned_anon = 0;
+ zone->recent_scanned_file = 0;
zap_zone_vm_stats(zone);
zone->flags = 0;
if (!size)
diff -puN mm/swap.c~add-some-sanity-checks-to-get_scan_ratio mm/swap.c
--- a/mm/swap.c~add-some-sanity-checks-to-get_scan_ratio
+++ a/mm/swap.c
@@ -176,8 +176,8 @@ void activate_page(struct page *page)
spin_lock_irq(&zone->lru_lock);
if (PageLRU(page) && !PageActive(page)) {
- int lru = LRU_BASE;
- lru += page_file_cache(page);
+ int file = page_file_cache(page);
+ int lru = LRU_BASE + file;
del_page_from_lru_list(zone, page, lru);
SetPageActive(page);
@@ -185,6 +185,15 @@ void activate_page(struct page *page)
add_page_to_lru_list(zone, page, lru);
__count_vm_event(PGACTIVATE);
mem_cgroup_move_lists(page, true);
+
+ if (file) {
+ zone->recent_scanned_file++;
+ zone->recent_rotated_file++;
+ } else {
+ /* Can this happen? Maybe through tmpfs... */
+ zone->recent_scanned_anon++;
+ zone->recent_rotated_anon++;
+ }
}
spin_unlock_irq(&zone->lru_lock);
}
diff -puN mm/vmscan.c~add-some-sanity-checks-to-get_scan_ratio mm/vmscan.c
--- a/mm/vmscan.c~add-some-sanity-checks-to-get_scan_ratio
+++ a/mm/vmscan.c
@@ -911,8 +911,13 @@ static unsigned long shrink_inactive_lis
__mod_zone_page_state(zone, NR_INACTIVE_ANON,
-count[LRU_INACTIVE_ANON]);
- if (scan_global_lru(sc))
+ if (scan_global_lru(sc)) {
zone->pages_scanned += nr_scan;
+ zone->recent_scanned_anon += count[LRU_ACTIVE_ANON] +
+ count[LRU_INACTIVE_ANON];
+ zone->recent_scanned_file += count[LRU_ACTIVE_FILE] +
+ count[LRU_INACTIVE_FILE];
+ }
spin_unlock_irq(&zone->lru_lock);
nr_scanned += nr_scan;
@@ -962,11 +967,13 @@ static unsigned long shrink_inactive_lis
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
list_del(&page->lru);
- if (page_file_cache(page)) {
+ if (page_file_cache(page))
lru += LRU_FILE;
- zone->recent_rotated_file++;
- } else {
- zone->recent_rotated_anon++;
+ if (scan_global_lru(sc)) {
+ if (page_file_cache(page))
+ zone->recent_rotated_file++;
+ else
+ zone->recent_rotated_anon++;
}
if (PageActive(page))
lru += LRU_ACTIVE;
@@ -1045,8 +1052,13 @@ static void shrink_active_list(unsigned
* zone->pages_scanned is used for detect zone's oom
* mem_cgroup remembers nr_scan by itself.
*/
- if (scan_global_lru(sc))
+ if (scan_global_lru(sc)) {
zone->pages_scanned += pgscanned;
+ if (file)
+ zone->recent_scanned_file += pgscanned;
+ else
+ zone->recent_scanned_anon += pgscanned;
+ }
if (file)
__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
@@ -1188,9 +1200,8 @@ static unsigned long shrink_list(enum lr
static void get_scan_ratio(struct zone *zone, struct scan_control * sc,
unsigned long *percent)
{
- unsigned long anon, file;
+ unsigned long anon, file, free;
unsigned long anon_prio, file_prio;
- unsigned long rotate_sum;
unsigned long ap, fp;
anon = zone_page_state(zone, NR_ACTIVE_ANON) +
@@ -1198,15 +1209,19 @@ static void get_scan_ratio(struct zone *
file = zone_page_state(zone, NR_ACTIVE_FILE) +
zone_page_state(zone, NR_INACTIVE_FILE);
- rotate_sum = zone->recent_rotated_file + zone->recent_rotated_anon;
-
/* Keep a floating average of RECENT references. */
- if (unlikely(rotate_sum > min(anon, file))) {
+ if (unlikely(zone->recent_scanned_anon > anon / zone->inactive_ratio)) {
spin_lock_irq(&zone->lru_lock);
- zone->recent_rotated_file /= 2;
+ zone->recent_scanned_anon /= 2;
zone->recent_rotated_anon /= 2;
spin_unlock_irq(&zone->lru_lock);
- rotate_sum /= 2;
+ }
+
+ if (unlikely(zone->recent_scanned_file > file / 4)) {
+ spin_lock_irq(&zone->lru_lock);
+ zone->recent_scanned_file /= 2;
+ zone->recent_rotated_file /= 2;
+ spin_unlock_irq(&zone->lru_lock);
}
/*
@@ -1219,23 +1234,33 @@ static void get_scan_ratio(struct zone *
/*
* anon recent_rotated_anon
* %anon = 100 * ----------- / ------------------- * IO cost
- * anon + file rotate_sum
+ * anon + file recent_scanned_anon
*/
- ap = (anon_prio * anon) / (anon + file + 1);
- ap *= rotate_sum / (zone->recent_rotated_anon + 1);
- if (ap == 0)
- ap = 1;
- else if (ap > 100)
- ap = 100;
- percent[0] = ap;
-
- fp = (file_prio * file) / (anon + file + 1);
- fp *= rotate_sum / (zone->recent_rotated_file + 1);
- if (fp == 0)
- fp = 1;
- else if (fp > 100)
- fp = 100;
- percent[1] = fp;
+ ap = (anon_prio + 1) * (zone->recent_scanned_anon + 1);
+ ap /= zone->recent_rotated_anon + 1;
+
+ fp = (file_prio + 1) * (zone->recent_scanned_file + 1);
+ fp /= zone->recent_rotated_file + 1;
+
+ /* Normalize to percentages */
+ percent[0] = 100 * ap / (ap + fp + 1);
+ percent[1] = 100 - percent[0];
+
+ free = zone_page_state(zone, NR_FREE_PAGES);
+
+ /*
+ * If we have no swap space, do not bother scanning anon pages.
+ */
+ if (nr_swap_pages <= 0) {
+ percent[0] = 0;
+ percent[1] = 100;
+ }
+ /*
+ * If we already freed most file pages, scan the anon pages
+ * regardless of the page access ratios or swappiness setting.
+ */
+ else if (file + free <= zone->pages_high)
+ percent[0] = 100;
}
@@ -1256,13 +1281,17 @@ static unsigned long shrink_zone(int pri
for_each_lru(l) {
if (scan_global_lru(sc)) {
int file = is_file_lru(l);
+ int scan;
/*
* Add one to nr_to_scan just to make sure that the
- * kernel will slowly sift through the active list.
+ * kernel will slowly sift through each list.
*/
- zone->nr_scan[l] += (zone_page_state(zone,
- NR_INACTIVE_ANON + l) >> priority) + 1;
- nr[l] = zone->nr_scan[l] * percent[file] / 100;
+ scan = zone_page_state(zone, NR_INACTIVE_ANON + l);
+ scan >>= priority;
+ scan = (scan * percent[file]) / 100;
+
+ zone->nr_scan[l] += scan + 1;
+ nr[l] = zone->nr_scan[l];
if (nr[l] >= sc->swap_cluster_max)
zone->nr_scan[l] = 0;
else
@@ -1279,7 +1308,7 @@ static unsigned long shrink_zone(int pri
}
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
- nr[LRU_INACTIVE_FILE]) {
+ nr[LRU_INACTIVE_FILE]) {
for_each_lru(l) {
if (nr[l]) {
nr_to_scan = min(nr[l],
@@ -1292,6 +1321,13 @@ static unsigned long shrink_zone(int pri
}
}
+ /*
+ * Even if we did not try to evict anon pages at all, we want to
+ * rebalance the anon lru active/inactive ratio.
+ */
+ if (scan_global_lru(sc) && inactive_anon_low(zone))
+ shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
+
throttle_vm_writeout(sc->gfp_mask);
return nr_reclaimed;
}
_
Patches currently in -mm which might be from riel@xxxxxxxxxx are
ntp-let-update_persistent_clock-sleep.patch
access_process_vm-device-memory-infrastructure.patch
access_process_vm-device-memory-infrastructure-fix.patch
use-generic_access_phys-for-dev-mem-mappings.patch
use-generic_access_phys-for-dev-mem-mappings-fix.patch
use-generic_access_phys-for-pci-mmap-on-x86.patch
powerpc-ioremap_prot.patch
spufs-use-the-new-vm_ops-access.patch
spufs-use-the-new-vm_ops-access-fix.patch
page-flags-record-page-flag-overlays-explicitly.patch
page-flags-record-page-flag-overlays-explicitly-xen.patch
slub-record-page-flag-overlays-explicitly.patch
slob-record-page-flag-overlays-explicitly.patch
vmscan-give-referenced-active-and-unmapped-pages-a-second-trip-around-the-lru.patch
idr-change-the-idr-structure.patch
idr-rename-some-of-the-idr-apis-internal-routines.patch
idr-fix-a-printk-call.patch
idr-error-checking-factorization.patch
idr-make-idr_get_new-rcu-safe.patch
idr-make-idr_get_new-rcu-safe-fix.patch
idr-make-idr_find-rcu-safe.patch
idr-make-idr_remove-rcu-safe.patch
ipc-call-idr_find-without-locking-in-ipc_lock.patch
ipc-get-rid-of-ipc_lock_down.patch
vmscan-move-isolate_lru_page-to-vmscanc.patch
vmscan-use-an-indexed-array-for-lru-variables.patch
vmscan-use-an-array-for-the-lru-pagevecs.patch
vmscan-free-swap-space-on-swap-in-activation.patch
vmscan-define-page_file_cache-function.patch
vmscan-split-lru-lists-into-anon-file-sets.patch
vmscan-second-chance-replacement-for-anonymous-pages.patch
vmscan-add-some-sanity-checks-to-get_scan_ratio.patch
vmscan-fix-pagecache-reclaim-referenced-bit-check.patch
vmscan-add-newly-swapped-in-pages-to-the-inactive-list.patch
vmscan-more-aggressively-use-lumpy-reclaim.patch
vmscan-pageflag-helpers-for-configed-out-flags.patch
vmscan-noreclaim-lru-infrastructure.patch
vmscan-noreclaim-lru-page-statistics.patch
vmscan-ramfs-and-ram-disk-pages-are-non-reclaimable.patch
vmscan-shm_locked-pages-are-non-reclaimable.patch
vmscan-mlocked-pages-are-non-reclaimable.patch
vmscan-downgrade-mmap-sem-while-populating-mlocked-regions.patch
vmscan-handle-mlocked-pages-during-map-remap-unmap.patch
vmscan-mlocked-pages-statistics.patch
vmscan-cull-non-reclaimable-pages-in-fault-path.patch
vmscan-noreclaim-and-mlocked-pages-vm-events.patch
mm-only-vmscan-noreclaim-lru-scan-sysctl.patch
vmscan-mlocked-pages-count-attempts-to-free-mlocked-page.patch
vmscan-noreclaim-lru-and-mlocked-pages-documentation.patch
make-mm-rmapc-anon_vma_cachep-static.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
