vmscan: prevent get_scan_ratio() rounding errors

get_scan_ratio() calculates percentage and if the percentage is < 1%, it
will round percentage down to 0% and cause we completely ignore scanning
anon/file pages to reclaim memory even the total anon/file pages are very
big.

To avoid underflow, we don't use percentage, instead we directly calculate
how many pages should be scaned.  In this way, we should get several
scanned pages for < 1% percent.

This has some benefits:

1. increase our calculation precision

2.  making our scan more smoothly.  Without this, if percent[x] is
   underflow, shrink_zone() doesn't scan any pages and suddenly it scans
   all pages when priority is zero.  With this, even priority isn't zero,
   shrink_zone() gets chance to scan some pages.

Note, this patch doesn't really change logics, but just increase
precision.  For system with a lot of memory, this might slightly changes
behavior.  For example, in a sequential file read workload, without the
patch, we don't swap any anon pages.  With it, if anon memory size is
bigger than 16G, we will see one anon page swapped.  The 16G is calculated
as PAGE_SIZE * priority(4096) * (fp/ap).  fp/ap is assumed to be 1024
which is common in this workload.  So the impact sounds not a big deal.

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
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 25b0202c60df66234ccb103ed1cb285c6badf105..8e1d72333e8a514de62c1041703a9f04540e746c 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1513,22 +1513,53 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
        return shrink_inactive_list(nr_to_scan, zone, sc, priority, file);
 }
 
+/*
+ * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
+ * until we collected @swap_cluster_max pages to scan.
+ */
+static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
+                                      unsigned long *nr_saved_scan)
+{
+       unsigned long nr;
+
+       *nr_saved_scan += nr_to_scan;
+       nr = *nr_saved_scan;
+
+       if (nr >= SWAP_CLUSTER_MAX)
+               *nr_saved_scan = 0;
+       else
+               nr = 0;
+
+       return nr;
+}
+
 /*
  * Determine how aggressively the anon and file LRU lists should be
  * scanned.  The relative value of each set of LRU lists is determined
  * by looking at the fraction of the pages scanned we did rotate back
  * onto the active list instead of evict.
  *
- * percent[0] specifies how much pressure to put on ram/swap backed
- * memory, while percent[1] determines pressure on the file LRUs.
+ * nr[0] = anon pages to scan; nr[1] = file pages to scan
  */
-static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
-                                       unsigned long *percent)
+static void get_scan_count(struct zone *zone, struct scan_control *sc,
+                                       unsigned long *nr, int priority)
 {
        unsigned long anon, file, free;
        unsigned long anon_prio, file_prio;
        unsigned long ap, fp;
        struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+       u64 fraction[2], denominator;
+       enum lru_list l;
+       int noswap = 0;
+
+       /* If we have no swap space, do not bother scanning anon pages. */
+       if (!sc->may_swap || (nr_swap_pages <= 0)) {
+               noswap = 1;
+               fraction[0] = 0;
+               fraction[1] = 1;
+               denominator = 1;
+               goto out;
+       }
 
        anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
                zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
@@ -1540,9 +1571,10 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
                /* If we have very few page cache pages,
                   force-scan anon pages. */
                if (unlikely(file + free <= high_wmark_pages(zone))) {
-                       percent[0] = 100;
-                       percent[1] = 0;
-                       return;
+                       fraction[0] = 1;
+                       fraction[1] = 0;
+                       denominator = 1;
+                       goto out;
                }
        }
 
@@ -1589,29 +1621,22 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
        fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
        fp /= reclaim_stat->recent_rotated[1] + 1;
 
-       /* Normalize to percentages */
-       percent[0] = 100 * ap / (ap + fp + 1);
-       percent[1] = 100 - percent[0];
-}
-
-/*
- * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
- * until we collected @swap_cluster_max pages to scan.
- */
-static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
-                                      unsigned long *nr_saved_scan)
-{
-       unsigned long nr;
-
-       *nr_saved_scan += nr_to_scan;
-       nr = *nr_saved_scan;
-
-       if (nr >= SWAP_CLUSTER_MAX)
-               *nr_saved_scan = 0;
-       else
-               nr = 0;
+       fraction[0] = ap;
+       fraction[1] = fp;
+       denominator = ap + fp + 1;
+out:
+       for_each_evictable_lru(l) {
+               int file = is_file_lru(l);
+               unsigned long scan;
 
-       return nr;
+               scan = zone_nr_lru_pages(zone, sc, l);
+               if (priority || noswap) {
+                       scan >>= priority;
+                       scan = div64_u64(scan * fraction[file], denominator);
+               }
+               nr[l] = nr_scan_try_batch(scan,
+                                         &reclaim_stat->nr_saved_scan[l]);
+       }
 }
 
 /*
@@ -1622,33 +1647,11 @@ static void shrink_zone(int priority, struct zone *zone,
 {
        unsigned long nr[NR_LRU_LISTS];
        unsigned long nr_to_scan;
-       unsigned long percent[2];       /* anon @ 0; file @ 1 */
        enum lru_list l;
        unsigned long nr_reclaimed = sc->nr_reclaimed;
        unsigned long nr_to_reclaim = sc->nr_to_reclaim;
-       struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
-       int noswap = 0;
-
-       /* If we have no swap space, do not bother scanning anon pages. */
-       if (!sc->may_swap || (nr_swap_pages <= 0)) {
-               noswap = 1;
-               percent[0] = 0;
-               percent[1] = 100;
-       } else
-               get_scan_ratio(zone, sc, percent);
 
-       for_each_evictable_lru(l) {
-               int file = is_file_lru(l);
-               unsigned long scan;
-
-               scan = zone_nr_lru_pages(zone, sc, l);
-               if (priority || noswap) {
-                       scan >>= priority;
-                       scan = (scan * percent[file]) / 100;
-               }
-               nr[l] = nr_scan_try_batch(scan,
-                                         &reclaim_stat->nr_saved_scan[l]);
-       }
+       get_scan_count(zone, sc, nr, priority);
 
        while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
                                        nr[LRU_INACTIVE_FILE]) {