return mem_cgroup_swappiness(sc->target_mem_cgroup);
}
+enum scan_balance {
+ SCAN_EQUAL,
+ SCAN_FRACT,
+ SCAN_ANON,
+ SCAN_FILE,
+};
+
/*
* Determine how aggressively the anon and file LRU lists should be
* scanned. The relative value of each set of LRU lists is determined
static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
unsigned long *nr)
{
- unsigned long anon, file, free;
+ struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
+ u64 fraction[2];
+ u64 denominator = 0; /* gcc */
+ struct zone *zone = lruvec_zone(lruvec);
unsigned long anon_prio, file_prio;
+ enum scan_balance scan_balance;
+ unsigned long anon, file, free;
+ bool force_scan = false;
unsigned long ap, fp;
- struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
- u64 fraction[2], denominator;
enum lru_list lru;
- int noswap = 0;
- bool force_scan = false;
- struct zone *zone = lruvec_zone(lruvec);
/*
* If the zone or memcg is small, nr[l] can be 0. This
/* 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;
+ scan_balance = SCAN_FILE;
+ goto out;
+ }
+
+ /*
+ * Global reclaim will swap to prevent OOM even with no
+ * swappiness, but memcg users want to use this knob to
+ * disable swapping for individual groups completely when
+ * using the memory controller's swap limit feature would be
+ * too expensive.
+ */
+ if (!global_reclaim(sc) && !vmscan_swappiness(sc)) {
+ scan_balance = SCAN_FILE;
+ goto out;
+ }
+
+ /*
+ * Do not apply any pressure balancing cleverness when the
+ * system is close to OOM, scan both anon and file equally
+ * (unless the swappiness setting disagrees with swapping).
+ */
+ if (!sc->priority && vmscan_swappiness(sc)) {
+ scan_balance = SCAN_EQUAL;
goto out;
}
file = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
get_lru_size(lruvec, LRU_INACTIVE_FILE);
+ /*
+ * If it's foreseeable that reclaiming the file cache won't be
+ * enough to get the zone back into a desirable shape, we have
+ * to swap. Better start now and leave the - probably heavily
+ * thrashing - remaining file pages alone.
+ */
if (global_reclaim(sc)) {
- free = zone_page_state(zone, NR_FREE_PAGES);
+ free = zone_page_state(zone, NR_FREE_PAGES);
if (unlikely(file + free <= high_wmark_pages(zone))) {
- /*
- * If we have very few page cache pages, force-scan
- * anon pages.
- */
- fraction[0] = 1;
- fraction[1] = 0;
- denominator = 1;
- goto out;
- } else if (!inactive_file_is_low_global(zone)) {
- /*
- * There is enough inactive page cache, do not
- * reclaim anything from the working set right now.
- */
- fraction[0] = 0;
- fraction[1] = 1;
- denominator = 1;
+ scan_balance = SCAN_ANON;
goto out;
}
}
+ /*
+ * There is enough inactive page cache, do not reclaim
+ * anything from the anonymous working set right now.
+ */
+ if (!inactive_file_is_low(lruvec)) {
+ scan_balance = SCAN_FILE;
+ goto out;
+ }
+
+ scan_balance = SCAN_FRACT;
+
/*
* With swappiness at 100, anonymous and file have the same priority.
* This scanning priority is essentially the inverse of IO cost.
out:
for_each_evictable_lru(lru) {
int file = is_file_lru(lru);
+ unsigned long size;
unsigned long scan;
- scan = get_lru_size(lruvec, lru);
- if (sc->priority || noswap || !vmscan_swappiness(sc)) {
- scan >>= sc->priority;
- if (!scan && force_scan)
- scan = SWAP_CLUSTER_MAX;
+ size = get_lru_size(lruvec, lru);
+ scan = size >> sc->priority;
+
+ if (!scan && force_scan)
+ scan = min(size, SWAP_CLUSTER_MAX);
+
+ switch (scan_balance) {
+ case SCAN_EQUAL:
+ /* Scan lists relative to size */
+ break;
+ case SCAN_FRACT:
+ /*
+ * Scan types proportional to swappiness and
+ * their relative recent reclaim efficiency.
+ */
scan = div64_u64(scan * fraction[file], denominator);
+ break;
+ case SCAN_FILE:
+ case SCAN_ANON:
+ /* Scan one type exclusively */
+ if ((scan_balance == SCAN_FILE) != file)
+ scan = 0;
+ break;
+ default:
+ /* Look ma, no brain */
+ BUG();
}
nr[lru] = scan;
}