}
/*
- * Are there way too many processes in the direct reclaim path already?
+ * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
+ * then get resheduled. When there are massive number of tasks doing page
+ * allocation, such sleeping direct reclaimers may keep piling up on each CPU,
+ * the LRU list will go small and be scanned faster than necessary, leading to
+ * unnecessary swapping, thrashing and OOM.
*/
static int too_many_isolated(struct zone *zone, int file,
struct scan_control *sc)
isolated = zone_page_state(zone, NR_ISOLATED_ANON);
}
+ /*
+ * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
+ * won't get blocked by normal direct-reclaimers, forming a circular
+ * deadlock.
+ */
+ if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS)
+ inactive >>= 3;
+
return isolated > inactive;
}
}
/*
- * pgdat_balanced is used when checking if a node is balanced for high-order
- * allocations. Only zones that meet watermarks and are in a zone allowed
- * by the callers classzone_idx are added to balanced_pages. The total of
- * balanced pages must be at least 25% of the zones allowed by classzone_idx
- * for the node to be considered balanced. Forcing all zones to be balanced
- * for high orders can cause excessive reclaim when there are imbalanced zones.
+ * pgdat_balanced() is used when checking if a node is balanced.
+ *
+ * For order-0, all zones must be balanced!
+ *
+ * For high-order allocations only zones that meet watermarks and are in a
+ * zone allowed by the callers classzone_idx are added to balanced_pages. The
+ * total of balanced pages must be at least 25% of the zones allowed by
+ * classzone_idx for the node to be considered balanced. Forcing all zones to
+ * be balanced for high orders can cause excessive reclaim when there are
+ * imbalanced zones.
* The choice of 25% is due to
* o a 16M DMA zone that is balanced will not balance a zone on any
* reasonable sized machine
* Similarly, on x86-64 the Normal zone would need to be at least 1G
* to balance a node on its own. These seemed like reasonable ratios.
*/
-static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages,
- int classzone_idx)
+static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
{
unsigned long present_pages = 0;
+ unsigned long balanced_pages = 0;
int i;
- for (i = 0; i <= classzone_idx; i++)
- present_pages += pgdat->node_zones[i].present_pages;
+ /* Check the watermark levels */
+ for (i = 0; i <= classzone_idx; i++) {
+ struct zone *zone = pgdat->node_zones + i;
+
+ if (!populated_zone(zone))
+ continue;
- /* A special case here: if zone has no page, we think it's balanced */
- return balanced_pages >= (present_pages >> 2);
+ present_pages += zone->present_pages;
+
+ /*
+ * A special case here:
+ *
+ * balance_pgdat() skips over all_unreclaimable after
+ * DEF_PRIORITY. Effectively, it considers them balanced so
+ * they must be considered balanced here as well!
+ */
+ if (zone->all_unreclaimable) {
+ balanced_pages += zone->present_pages;
+ continue;
+ }
+
+ if (zone_balanced(zone, order, 0, i))
+ balanced_pages += zone->present_pages;
+ else if (!order)
+ return false;
+ }
+
+ if (order)
+ return balanced_pages >= (present_pages >> 2);
+ else
+ return true;
}
/*
static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
int classzone_idx)
{
- int i;
- unsigned long balanced = 0;
- bool all_zones_ok = true;
-
/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
if (remaining)
return false;
return false;
}
- /* Check the watermark levels */
- for (i = 0; i <= classzone_idx; i++) {
- struct zone *zone = pgdat->node_zones + i;
-
- if (!populated_zone(zone))
- continue;
-
- /*
- * balance_pgdat() skips over all_unreclaimable after
- * DEF_PRIORITY. Effectively, it considers them balanced so
- * they must be considered balanced here as well if kswapd
- * is to sleep
- */
- if (zone->all_unreclaimable) {
- balanced += zone->present_pages;
- continue;
- }
-
- if (!zone_balanced(zone, order, 0, i))
- all_zones_ok = false;
- else
- balanced += zone->present_pages;
- }
-
- /*
- * For high-order requests, the balanced zones must contain at least
- * 25% of the nodes pages for kswapd to sleep. For order-0, all zones
- * must be balanced
- */
- if (order)
- return pgdat_balanced(pgdat, balanced, classzone_idx);
- else
- return all_zones_ok;
+ return pgdat_balanced(pgdat, order, classzone_idx);
}
/*
static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
int *classzone_idx)
{
- int all_zones_ok;
- unsigned long balanced;
+ struct zone *unbalanced_zone;
int i;
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
unsigned long total_scanned;
unsigned long lru_pages = 0;
int has_under_min_watermark_zone = 0;
- all_zones_ok = 1;
- balanced = 0;
+ unbalanced_zone = NULL;
/*
* Scan in the highmem->dma direction for the highest
}
if (!zone_balanced(zone, testorder, 0, end_zone)) {
- all_zones_ok = 0;
+ unbalanced_zone = zone;
/*
* We are still under min water mark. This
* means that we have a GFP_ATOMIC allocation
* speculatively avoid congestion waits
*/
zone_clear_flag(zone, ZONE_CONGESTED);
- if (i <= *classzone_idx)
- balanced += zone->present_pages;
}
}
pfmemalloc_watermark_ok(pgdat))
wake_up(&pgdat->pfmemalloc_wait);
- if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
+ if (pgdat_balanced(pgdat, order, *classzone_idx))
break; /* kswapd: all done */
/*
* OK, kswapd is getting into trouble. Take a nap, then take
if (total_scanned && (sc.priority < DEF_PRIORITY - 2)) {
if (has_under_min_watermark_zone)
count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
- else
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ else if (unbalanced_zone)
+ wait_iff_congested(unbalanced_zone, BLK_RW_ASYNC, HZ/10);
}
/*
} while (--sc.priority >= 0);
out:
- /*
- * order-0: All zones must meet high watermark for a balanced node
- * high-order: Balanced zones must make up at least 25% of the node
- * for the node to be balanced
- */
- if (!(all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))) {
+ if (!pgdat_balanced(pgdat, order, *classzone_idx)) {
cond_resched();
try_to_freeze();
projects / karo-tx-linux.git / blobdiff