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;
}
}
+/*
+ * This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
+ */
+static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+{
+ unsigned long nr[NR_LRU_LISTS];
+ unsigned long nr_to_scan;
+ enum lru_list lru;
+ unsigned long nr_reclaimed = 0;
+ unsigned long nr_to_reclaim = sc->nr_to_reclaim;
+ struct blk_plug plug;
+
+ get_scan_count(lruvec, sc, nr);
+
+ blk_start_plug(&plug);
+ while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
+ nr[LRU_INACTIVE_FILE]) {
+ for_each_evictable_lru(lru) {
+ if (nr[lru]) {
+ nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX);
+ nr[lru] -= nr_to_scan;
+
+ nr_reclaimed += shrink_list(lru, nr_to_scan,
+ lruvec, sc);
+ }
+ }
+ /*
+ * On large memory systems, scan >> priority can become
+ * really large. This is fine for the starting priority;
+ * we want to put equal scanning pressure on each zone.
+ * However, if the VM has a harder time of freeing pages,
+ * with multiple processes reclaiming pages, the total
+ * freeing target can get unreasonably large.
+ */
+ if (nr_reclaimed >= nr_to_reclaim &&
+ sc->priority < DEF_PRIORITY)
+ break;
+ }
+ blk_finish_plug(&plug);
+ sc->nr_reclaimed += nr_reclaimed;
+
+ /*
+ * Even if we did not try to evict anon pages at all, we want to
+ * rebalance the anon lru active/inactive ratio.
+ */
+ if (inactive_anon_is_low(lruvec))
+ shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
+ sc, LRU_ACTIVE_ANON);
+
+ throttle_vm_writeout(sc->gfp_mask);
+}
+
/* Use reclaim/compaction for costly allocs or under memory pressure */
static bool in_reclaim_compaction(struct scan_control *sc)
{
* calls try_to_compact_zone() that it will have enough free pages to succeed.
* It will give up earlier than that if there is difficulty reclaiming pages.
*/
-static inline bool should_continue_reclaim(struct lruvec *lruvec,
+static inline bool should_continue_reclaim(struct zone *zone,
unsigned long nr_reclaimed,
unsigned long nr_scanned,
struct scan_control *sc)
* inactive lists are large enough, continue reclaiming
*/
pages_for_compaction = (2UL << sc->order);
- inactive_lru_pages = get_lru_size(lruvec, LRU_INACTIVE_FILE);
+ inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE);
if (nr_swap_pages > 0)
- inactive_lru_pages += get_lru_size(lruvec, LRU_INACTIVE_ANON);
+ inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON);
if (sc->nr_reclaimed < pages_for_compaction &&
inactive_lru_pages > pages_for_compaction)
return true;
/* If compaction would go ahead or the allocation would succeed, stop */
- switch (compaction_suitable(lruvec_zone(lruvec), sc->order)) {
+ switch (compaction_suitable(zone, sc->order)) {
case COMPACT_PARTIAL:
case COMPACT_CONTINUE:
return false;
}
}
-/*
- * This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
- */
-static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
{
- unsigned long nr[NR_LRU_LISTS];
- unsigned long nr_to_scan;
- enum lru_list lru;
unsigned long nr_reclaimed, nr_scanned;
- unsigned long nr_to_reclaim = sc->nr_to_reclaim;
- struct blk_plug plug;
-
-restart:
- nr_reclaimed = 0;
- nr_scanned = sc->nr_scanned;
- get_scan_count(lruvec, sc, nr);
-
- blk_start_plug(&plug);
- while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
- nr[LRU_INACTIVE_FILE]) {
- for_each_evictable_lru(lru) {
- if (nr[lru]) {
- nr_to_scan = min_t(unsigned long,
- nr[lru], SWAP_CLUSTER_MAX);
- nr[lru] -= nr_to_scan;
-
- nr_reclaimed += shrink_list(lru, nr_to_scan,
- lruvec, sc);
- }
- }
- /*
- * On large memory systems, scan >> priority can become
- * really large. This is fine for the starting priority;
- * we want to put equal scanning pressure on each zone.
- * However, if the VM has a harder time of freeing pages,
- * with multiple processes reclaiming pages, the total
- * freeing target can get unreasonably large.
- */
- if (nr_reclaimed >= nr_to_reclaim &&
- sc->priority < DEF_PRIORITY)
- break;
- }
- blk_finish_plug(&plug);
- sc->nr_reclaimed += nr_reclaimed;
- /*
- * Even if we did not try to evict anon pages at all, we want to
- * rebalance the anon lru active/inactive ratio.
- */
- if (inactive_anon_is_low(lruvec))
- shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
- sc, LRU_ACTIVE_ANON);
-
- /* reclaim/compaction might need reclaim to continue */
- if (should_continue_reclaim(lruvec, nr_reclaimed,
- sc->nr_scanned - nr_scanned, sc))
- goto restart;
+ do {
+ struct mem_cgroup *root = sc->target_mem_cgroup;
+ struct mem_cgroup_reclaim_cookie reclaim = {
+ .zone = zone,
+ .priority = sc->priority,
+ };
+ struct mem_cgroup *memcg;
- throttle_vm_writeout(sc->gfp_mask);
-}
+ nr_reclaimed = sc->nr_reclaimed;
+ nr_scanned = sc->nr_scanned;
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
-{
- struct mem_cgroup *root = sc->target_mem_cgroup;
- struct mem_cgroup_reclaim_cookie reclaim = {
- .zone = zone,
- .priority = sc->priority,
- };
- struct mem_cgroup *memcg;
+ memcg = mem_cgroup_iter(root, NULL, &reclaim);
+ do {
+ struct lruvec *lruvec;
- memcg = mem_cgroup_iter(root, NULL, &reclaim);
- do {
- struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+ lruvec = mem_cgroup_zone_lruvec(zone, memcg);
- shrink_lruvec(lruvec, sc);
+ shrink_lruvec(lruvec, sc);
- /*
- * Limit reclaim has historically picked one memcg and
- * scanned it with decreasing priority levels until
- * nr_to_reclaim had been reclaimed. This priority
- * cycle is thus over after a single memcg.
- *
- * Direct reclaim and kswapd, on the other hand, have
- * to scan all memory cgroups to fulfill the overall
- * scan target for the zone.
- */
- if (!global_reclaim(sc)) {
- mem_cgroup_iter_break(root, memcg);
- break;
- }
- memcg = mem_cgroup_iter(root, memcg, &reclaim);
- } while (memcg);
+ /*
+ * Direct reclaim and kswapd have to scan all memory
+ * cgroups to fulfill the overall scan target for the
+ * zone.
+ *
+ * Limit reclaim, on the other hand, only cares about
+ * nr_to_reclaim pages to be reclaimed and it will
+ * retry with decreasing priority if one round over the
+ * whole hierarchy is not sufficient.
+ */
+ if (!global_reclaim(sc) &&
+ sc->nr_reclaimed >= sc->nr_to_reclaim) {
+ mem_cgroup_iter_break(root, memcg);
+ break;
+ }
+ memcg = mem_cgroup_iter(root, memcg, &reclaim);
+ } while (memcg);
+ } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
+ sc->nr_scanned - nr_scanned, sc));
}
/* Returns true if compaction should go ahead for a high-order request */
.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
.may_swap = 1,
- .nr_to_reclaim = max_t(unsigned long, nr_pages,
- SWAP_CLUSTER_MAX),
+ .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
.gfp_mask = gfp_mask,
.order = order,
.priority = ZONE_RECLAIM_PRIORITY,