config, dht: reduce default msb ignore bits to 4

With the default value of 12, a node's range is partitioned into
4096 * smp::count sub-ranges which are queried sequentually for a range
scan.  If the number of rows in the table is smaller than the required
result size, we will query all of them.  This can take so long that we
time out.

A better fix is to query multiple sub-ranges in parallel and merge them,
but for that we need to resurrect the non-sequential merger.
This commit is contained in:
Avi Kivity
2016-11-23 21:22:08 +02:00
parent c526a9f0be
commit b81a57e8eb

View File

@@ -737,7 +737,7 @@ public:
val(prometheus_port, uint16_t, 9180, Used, "Prometheus port, set to zero to disable") \
val(prometheus_address, sstring, "0.0.0.0", Used, "Prometheus listening address") \
val(abort_on_lsa_bad_alloc, bool, false, Used, "Abort when allocation in LSA region fails") \
val(murmur3_partitioner_ignore_msb_bits, unsigned, 12, Used, "Number of most siginificant token bits to ignore in murmur3 partitioner; increase for very large clusters") \
val(murmur3_partitioner_ignore_msb_bits, unsigned, 4, Used, "Number of most siginificant token bits to ignore in murmur3 partitioner; increase for very large clusters") \
/* done! */
#define _make_value_member(name, type, deflt, status, desc, ...) \