diff options
author | Andres Freund <andres@anarazel.de> | 2017-12-05 10:55:56 -0800 |
---|---|---|
committer | Andres Freund <andres@anarazel.de> | 2017-12-05 10:55:56 -0800 |
commit | 5bcf389ecfd40daf92238e1abbff4fc4d3f18b33 (patch) | |
tree | 085fae86ad5cb6cd155e4a9e2612d56fcae19f97 /src/backend/commands/explain.c | |
parent | 82c5c533d1f55dfbf3eacc61aff64fedc8915d78 (diff) | |
download | postgresql-5bcf389ecfd40daf92238e1abbff4fc4d3f18b33.tar.gz postgresql-5bcf389ecfd40daf92238e1abbff4fc4d3f18b33.zip |
Fix EXPLAIN ANALYZE of hash join when the leader doesn't participate.
If a hash join appears in a parallel query, there may be no hash table
available for explain.c to inspect even though a hash table may have
been built in other processes. This could happen either because
parallel_leader_participation was set to off or because the leader
happened to hit the end of the outer relation immediately (even though
the complete relation is not empty) and decided not to build the hash
table.
Commit bf11e7ee introduced a way for workers to exchange
instrumentation via the DSM segment for Sort nodes even though they
are not parallel-aware. This commit does the same for Hash nodes, so
that explain.c has a way to find instrumentation data from an
arbitrary participant that actually built the hash table.
Author: Thomas Munro
Reviewed-By: Andres Freund
Discussion: https://postgr.es/m/CAEepm%3D3DUQC2-z252N55eOcZBer6DPdM%3DFzrxH9dZc5vYLsjaA%40mail.gmail.com
Diffstat (limited to 'src/backend/commands/explain.c')
-rw-r--r-- | src/backend/commands/explain.c | 60 |
1 files changed, 44 insertions, 16 deletions
diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c index 447f69d044e..7e4fbafc535 100644 --- a/src/backend/commands/explain.c +++ b/src/backend/commands/explain.c @@ -19,7 +19,7 @@ #include "commands/createas.h" #include "commands/defrem.h" #include "commands/prepare.h" -#include "executor/hashjoin.h" +#include "executor/nodeHash.h" #include "foreign/fdwapi.h" #include "nodes/extensible.h" #include "nodes/nodeFuncs.h" @@ -2379,34 +2379,62 @@ show_sort_info(SortState *sortstate, ExplainState *es) static void show_hash_info(HashState *hashstate, ExplainState *es) { - HashJoinTable hashtable; + HashInstrumentation *hinstrument = NULL; - hashtable = hashstate->hashtable; + /* + * In a parallel query, the leader process may or may not have run the + * hash join, and even if it did it may not have built a hash table due to + * timing (if it started late it might have seen no tuples in the outer + * relation and skipped building the hash table). Therefore we have to be + * prepared to get instrumentation data from a worker if there is no hash + * table. + */ + if (hashstate->hashtable) + { + hinstrument = (HashInstrumentation *) + palloc(sizeof(HashInstrumentation)); + ExecHashGetInstrumentation(hinstrument, hashstate->hashtable); + } + else if (hashstate->shared_info) + { + SharedHashInfo *shared_info = hashstate->shared_info; + int i; + + /* Find the first worker that built a hash table. */ + for (i = 0; i < shared_info->num_workers; ++i) + { + if (shared_info->hinstrument[i].nbatch > 0) + { + hinstrument = &shared_info->hinstrument[i]; + break; + } + } + } - if (hashtable) + if (hinstrument) { - long spacePeakKb = (hashtable->spacePeak + 1023) / 1024; + long spacePeakKb = (hinstrument->space_peak + 1023) / 1024; if (es->format != EXPLAIN_FORMAT_TEXT) { - ExplainPropertyLong("Hash Buckets", hashtable->nbuckets, es); + ExplainPropertyLong("Hash Buckets", hinstrument->nbuckets, es); ExplainPropertyLong("Original Hash Buckets", - hashtable->nbuckets_original, es); - ExplainPropertyLong("Hash Batches", hashtable->nbatch, es); + hinstrument->nbuckets_original, es); + ExplainPropertyLong("Hash Batches", hinstrument->nbatch, es); ExplainPropertyLong("Original Hash Batches", - hashtable->nbatch_original, es); + hinstrument->nbatch_original, es); ExplainPropertyLong("Peak Memory Usage", spacePeakKb, es); } - else if (hashtable->nbatch_original != hashtable->nbatch || - hashtable->nbuckets_original != hashtable->nbuckets) + else if (hinstrument->nbatch_original != hinstrument->nbatch || + hinstrument->nbuckets_original != hinstrument->nbuckets) { appendStringInfoSpaces(es->str, es->indent * 2); appendStringInfo(es->str, "Buckets: %d (originally %d) Batches: %d (originally %d) Memory Usage: %ldkB\n", - hashtable->nbuckets, - hashtable->nbuckets_original, - hashtable->nbatch, - hashtable->nbatch_original, + hinstrument->nbuckets, + hinstrument->nbuckets_original, + hinstrument->nbatch, + hinstrument->nbatch_original, spacePeakKb); } else @@ -2414,7 +2442,7 @@ show_hash_info(HashState *hashstate, ExplainState *es) appendStringInfoSpaces(es->str, es->indent * 2); appendStringInfo(es->str, "Buckets: %d Batches: %d Memory Usage: %ldkB\n", - hashtable->nbuckets, hashtable->nbatch, + hinstrument->nbuckets, hinstrument->nbatch, spacePeakKb); } } |