summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndres Freund2018-01-29 19:02:09 +0000
committerAndres Freund2018-01-29 19:24:57 +0000
commitab9f2c429d8fbd3580cd2ae5f2054ba6956b1f60 (patch)
treeb75c0239b09ce35238ffb00b3533d8f4171add30
parentc068f87723ca9cded1f2aceb956ede49de651690 (diff)
Prevent growth of simplehash tables when they're "too empty".
In cases where simplehash tables where filled with either a lot of conflicting hash-values, or values that hash to consecutive values (i.e. build "chains") the growth heuristics in d4c62a6b623d6eef88218158e9fa3cf974c6c7e5 could trigger rather explosively. To fix that, address some of the reasons (see previous commit) of why the growth heuristics where needed, and only allow growth when the table isn't too empty. While that means there's a few cases of bad input that can be slower, that seems a lot better than running very quickly out of memory. Author: Tomas Vondra and Andres Freund, with additional input by Thomas Munro, Tom Lane Todd A. Cook Reported-By: Todd A. Cook, Tomas Vondra, Thomas Munro Discussion: https://postgr.es/m/[email protected] Backpatch: 10, where simplehash was introduced
-rw-r--r--src/include/lib/simplehash.h19
1 files changed, 15 insertions, 4 deletions
diff --git a/src/include/lib/simplehash.h b/src/include/lib/simplehash.h
index c5af5b96a7..5273d49460 100644
--- a/src/include/lib/simplehash.h
+++ b/src/include/lib/simplehash.h
@@ -174,6 +174,10 @@ SH_SCOPE void SH_STAT(SH_TYPE * tb);
#ifndef SH_GROW_MAX_MOVE
#define SH_GROW_MAX_MOVE 150
#endif
+#ifndef SH_GROW_MIN_FILLFACTOR
+/* but do not grow due to SH_GROW_MAX_* if below */
+#define SH_GROW_MIN_FILLFACTOR 0.1
+#endif
#ifdef SH_STORE_HASH
#define SH_COMPARE_KEYS(tb, ahash, akey, b) (ahash == SH_GET_HASH(tb, b) && SH_EQUAL(tb, b->SH_KEY, akey))
@@ -574,9 +578,12 @@ restart:
* hashtables, grow the hashtable if collisions would require
* us to move a lot of entries. The most likely cause of such
* imbalance is filling a (currently) small table, from a
- * currently big one, in hash-table order.
+ * currently big one, in hash-table order. Don't grow if the
+ * hashtable would be too empty, to prevent quick space
+ * explosion for some weird edge cases.
*/
- if (++emptydist > SH_GROW_MAX_MOVE)
+ if (unlikely(++emptydist > SH_GROW_MAX_MOVE) &&
+ ((double) tb->members / tb->size) >= SH_GROW_MIN_FILLFACTOR)
{
tb->grow_threshold = 0;
goto restart;
@@ -621,9 +628,12 @@ restart:
* To avoid negative consequences from overly imbalanced hashtables,
* grow the hashtable if collisions lead to large runs. The most
* likely cause of such imbalance is filling a (currently) small
- * table, from a currently big one, in hash-table order.
+ * table, from a currently big one, in hash-table order. Don't grow
+ * if the hashtable would be too empty, to prevent quick space
+ * explosion for some weird edge cases.
*/
- if (insertdist > SH_GROW_MAX_DIB)
+ if (unlikely(insertdist > SH_GROW_MAX_DIB) &&
+ ((double) tb->members / tb->size) >= SH_GROW_MIN_FILLFACTOR)
{
tb->grow_threshold = 0;
goto restart;
@@ -923,6 +933,7 @@ SH_STAT(SH_TYPE * tb)
#undef SH_MAX_FILLFACTOR
#undef SH_GROW_MAX_DIB
#undef SH_GROW_MAX_MOVE
+#undef SH_GROW_MIN_FILLFACTOR
#undef SH_MAX_SIZE
/* types */