Skip to contentSkip to conversation

Fix: hash table growth (for small tables) should be limited (v2)

PATCH New Mathieu Desnoyers 2 participants 2 messages Aug 27, 2013 – Aug 29, 2013 2 messages not in the archive

lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): 20130827220142.GA13424@Krystal

#1 lore raw

PATCH 1/1 Fix: hash table growth (for small tables) should be limited (v2)

Buckets with many entries encountered in a hash table could cause it to grow to a large size, beyond the scope for which this mechanism is expected to play a role when node accounting is available. Indeed, when the hash table grows to larger size, split-counter node accounting is expected to deal with resize/shrink rather than relying on an heuristic based on the largest bucket size.

This is fixing an issue where we see hash tables sometimes reaching 65k entries index (65536*8 = 524288 bytes) for a workload limited to adding 1000 entries and then removing all of them, done in a loop (random keys).

---

src/common/hashtable/rculfhash.c +26 -3
index b430a3d..ebdc4ff 100644
@@ -726,9 +726,32 @@ void check_resize(struct cds_lfht *ht, unsigned long size, uint32_t chain_len)
 	if (chain_len > 100)
 		dbg_printf("WARNING: large chain length: %u.\n",
 			   chain_len);
-	if (chain_len >= CHAIN_LEN_RESIZE_THRESHOLD)
-		cds_lfht_resize_lazy_grow(ht, size,
-			cds_lfht_get_count_order_u32(chain_len - (CHAIN_LEN_TARGET - 1)));
+	if (chain_len >= CHAIN_LEN_RESIZE_THRESHOLD) {
+		int growth;
+
+		/*
+		 * Ideal growth calculated based on chain length.
+		 */
+		growth = cds_lfht_get_count_order_u32(chain_len
+				- (CHAIN_LEN_TARGET - 1));
+		if ((ht->flags & CDS_LFHT_ACCOUNTING)
+				&& (size << growth) >= (1UL << COUNT_COMMIT_ORDER)) {
+			/*
+			 * If ideal growth expands the hash table size
+			 * beyond the "small hash table" sizes, use the
+			 * maximum small hash table size to attempt
+			 * expanding the hash table. This only applies
+			 * when node accounting is available, otherwise
+			 * the chain length is used to expand the hash
+			 * table in every case.
+			 */
+			growth = COUNT_COMMIT_ORDER -
+				cds_lfht_get_count_order_u32(size);
+			if (growth <= 0)
+				return;
+		}
+		cds_lfht_resize_lazy_grow(ht, size, growth);
+	}
 }
 
 static
Signature · 3 lines
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com

A message that is not in the archive (sent off-list or not yet received): 20130827221104.GA13930@Krystal

#3 lore raw

Merged!

Mathieu Desnoyers:

Quoted 55 lines

Buckets with many entries encountered in a hash table could cause it to grow to a large size, beyond the scope for which this mechanism is expected to play a role when node accounting is available. Indeed, when the hash table grows to larger size, split-counter node accounting is expected to deal with resize/shrink rather than relying on an heuristic based on the largest bucket size.

This is fixing an issue where we see hash tables sometimes reaching 65k entries index (65536*8 = 524288 bytes) for a workload limited to adding 1000 entries and then removing all of them, done in a loop (random keys).

---

src/common/hashtable/rculfhash.c +26 -3
index b430a3d..ebdc4ff 100644
@@ -726,9 +726,32 @@ void check_resize(struct cds_lfht *ht, unsigned long size, uint32_t chain_len)
 	if (chain_len > 100)
 		dbg_printf("WARNING: large chain length: %u.\n",
 			   chain_len);
-	if (chain_len >= CHAIN_LEN_RESIZE_THRESHOLD)
-		cds_lfht_resize_lazy_grow(ht, size,
-			cds_lfht_get_count_order_u32(chain_len - (CHAIN_LEN_TARGET - 1)));
+	if (chain_len >= CHAIN_LEN_RESIZE_THRESHOLD) {
+		int growth;
+
+		/*
+		 * Ideal growth calculated based on chain length.
+		 */
+		growth = cds_lfht_get_count_order_u32(chain_len
+				- (CHAIN_LEN_TARGET - 1));
+		if ((ht->flags & CDS_LFHT_ACCOUNTING)
+				&& (size << growth) >= (1UL << COUNT_COMMIT_ORDER)) {
+			/*
+			 * If ideal growth expands the hash table size
+			 * beyond the "small hash table" sizes, use the
+			 * maximum small hash table size to attempt
+			 * expanding the hash table. This only applies
+			 * when node accounting is available, otherwise
+			 * the chain length is used to expand the hash
+			 * table in every case.
+			 */
+			growth = COUNT_COMMIT_ORDER -
+				cds_lfht_get_count_order_u32(size);
+			if (growth <= 0)
+				return;
+		}
+		cds_lfht_resize_lazy_grow(ht, size, growth);
+	}
 }
 
 static