database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-02 09:02:37 +03:00
Code Activity

Fixes for Disk-based Hash Aggregation.

Browse Source 
Justin Pryzby raised a couple issues with commit 1f39bce0. Fixed.

Also, tweak the way the size of a hash entry is estimated and the
number of buckets is estimated when calling BuildTupleHashTableExt().

Discussion: https://www.postgresql.org/message-id/20200319064222.GR26184@telsasoft.com
This commit is contained in:
Jeff Davis
2020-03-23 13:56:28 -07:00
parent 0830d21f5b
commit 64fe602279
2 changed files with 8 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/backend/commands/explain.c
View File

@ -2778,7 +2778,7 @@ static void
show_hashagg_info(AggState *aggstate, ExplainState *es) show_hashagg_info(AggState *aggstate, ExplainState *es)
{ {
Agg *agg = (Agg *)aggstate->ss.ps.plan; Agg *agg = (Agg *)aggstate->ss.ps.plan;
long memPeakKb = (aggstate->hash_mem_peak + 1023) / 1024; int64 memPeakKb = (aggstate->hash_mem_peak + 1023) / 1024;
Assert(IsA(aggstate, AggState)); Assert(IsA(aggstate, AggState));

19
src/backend/executor/nodeAgg.c
View File

@ -1873,17 +1873,12 @@ hash_agg_update_metrics(AggState *aggstate, bool from_tape, int npartitions)
aggstate->hash_disk_used = disk_used; aggstate->hash_disk_used = disk_used;
} }
/* /* update hashentrysize estimate based on contents */
* Update hashentrysize estimate based on contents. Don't include meta_mem
* in the memory used, because empty buckets would inflate the per-entry
* cost. An underestimate of the per-entry size is better than an
* overestimate, because an overestimate could compound with each level of
* recursion.
*/
if (aggstate->hash_ngroups_current > 0) if (aggstate->hash_ngroups_current > 0)
{ {
aggstate->hashentrysize = aggstate->hashentrysize =
hash_mem / (double)aggstate->hash_ngroups_current; sizeof(TupleHashEntryData) +
(hash_mem / (double)aggstate->hash_ngroups_current);
} }
} }
@ -1899,10 +1894,10 @@ hash_choose_num_buckets(double hashentrysize, long ngroups, Size memory)
max_nbuckets = memory / hashentrysize; max_nbuckets = memory / hashentrysize;
/* /*
* Leave room for slop to avoid a case where the initial hash table size * Underestimating is better than overestimating. Too many buckets crowd
* exceeds the memory limit (though that may still happen in edge cases). * out space for group keys and transition state values.
*/ */
max_nbuckets *= 0.75; max_nbuckets >>= 1;
if (nbuckets > max_nbuckets) if (nbuckets > max_nbuckets)
nbuckets = max_nbuckets; nbuckets = max_nbuckets;
@ -3548,7 +3543,7 @@ ExecInitAgg(Agg *node, EState *estate, int eflags)
* reasonable. * reasonable.
*/ */
for (i = 0; i < aggstate->num_hashes; i++) for (i = 0; i < aggstate->num_hashes; i++)
totalGroups = aggstate->perhash[i].aggnode->numGroups; totalGroups += aggstate->perhash[i].aggnode->numGroups;
hash_agg_set_limits(aggstate->hashentrysize, totalGroups, 0, hash_agg_set_limits(aggstate->hashentrysize, totalGroups, 0,
&aggstate->hash_mem_limit, &aggstate->hash_mem_limit,