Fix: hash table growth (for small tables) should be limited
authorMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Tue, 27 Aug 2013 21:58:22 +0000 (17:58 -0400)
committerMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fri, 30 Aug 2013 18:24:34 +0000 (14:24 -0400)
commite53ab1eb49ad61eddcc9481bd6a6fbaf1b257439
treec72e29e998394c420760a9aa8bd07ea85f55cf97
parent223c9ed052d32fd078df0fcd48ce7732cdbe0165
Fix: hash table growth (for small tables) should be limited

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).

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
rculfhash.c
This page took 0.032877 seconds and 4 git commands to generate.