open-dsi
/
postgres
mirror of https://github.com/postgres/postgres
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Show index search count in EXPLAIN ANALYZE, take 2.

Browse Source 
Expose the count of index searches/index descents in EXPLAIN ANALYZE's
output for index scan/index-only scan/bitmap index scan nodes.  This
information is particularly useful with scans that use ScalarArrayOp
quals, where the number of index searches can be unpredictable due to
implementation details that interact with physical index characteristics
(at least with nbtree SAOP scans, since Postgres 17 commit 5bf748b8).
The information shown also provides useful context when EXPLAIN ANALYZE
runs a plan with an index scan node that successfully applied the skip
scan optimization (set to be added to nbtree by an upcoming patch).

The instrumentation works by teaching all index AMs to increment a new
nsearches counter whenever a new index search begins.  The counter is
incremented at exactly the same point that index AMs already increment
the pg_stat_*_indexes.idx_scan counter (we're counting the same event,
but at the scan level rather than the relation level).  Parallel queries
have workers copy their local counter struct into shared memory when an
index scan node ends -- even when it isn't a parallel aware scan node.
An earlier version of this patch that only worked with parallel aware
scans became commit 5ead85fb (though that was quickly reverted by commit
d00107cd following "debug_parallel_query=regress" buildfarm failures).

Our approach doesn't match the approach used when tracking other index
scan related costs (e.g., "Rows Removed by Filter:").  It is comparable
to the approach used in similar cases involving costs that are only
readily accessible inside an access method, not from the executor proper
(e.g., "Heap Blocks:" output for a Bitmap Heap Scan, which was recently
enhanced to show per-worker costs by commit 5a1e6df3, using essentially
the same scheme as the one used here).  It is necessary for index AMs to
have direct responsibility for maintaining the new counter, since the
counter might need to be incremented multiple times per amgettuple call
(or per amgetbitmap call).  But it is also necessary for the executor
proper to manage the shared memory now used to transfer each worker's
counter struct to the leader.

Author: Peter Geoghegan <pg@bowt.ie>
Reviewed-By: Robert Haas <robertmhaas@gmail.com>
Reviewed-By: Tomas Vondra <tomas@vondra.me>
Reviewed-By: Masahiro Ikeda <ikedamsh@oss.nttdata.com>
Reviewed-By: Matthias van de Meent <boekewurm+postgres@gmail.com>
Discussion: https://postgr.es/m/CAH2-WzkRqvaqR2CTNqTZP0z6FuL4-3ED6eQB0yx38XBNj1v-4Q@mail.gmail.com
Discussion: https://postgr.es/m/CAH2-Wz=PKR6rB7qbx+Vnd7eqeB5VTcrW=iJvAsTsKbdG+kW_UA@mail.gmail.com
pull/207/head
Peter Geoghegan 4 months ago
parent 12c5f797ea
commit 0fbceae841
37 changed files with 797 additions and 98 deletions
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Show Stats Download Patch File Download Diff File
  1. 2
      contrib/bloom/blscan.c
  2. 7
      doc/src/sgml/bloom.sgml
  3. 28
      doc/src/sgml/monitoring.sgml
  4. 60
      doc/src/sgml/perform.sgml
  5. 3
      doc/src/sgml/ref/explain.sgml
  6. 2
      doc/src/sgml/rules.sgml
  7. 2
      src/backend/access/brin/brin.c
  8. 2
      src/backend/access/gin/ginscan.c
  9. 4
      src/backend/access/gist/gistget.c
  10. 2
      src/backend/access/hash/hashsearch.c
  11. 2
      src/backend/access/heap/heapam_handler.c
  12. 5
      src/backend/access/index/genam.c
  13. 70
      src/backend/access/index/indexam.c
  14. 10
      src/backend/access/nbtree/nbtree.c
  15. 2
      src/backend/access/nbtree/nbtsearch.c
  16. 2
      src/backend/access/spgist/spgscan.c
  17. 63
      src/backend/commands/explain.c
  18. 2
      src/backend/executor/execIndexing.c
  19. 59
      src/backend/executor/execParallel.c
  20. 2
      src/backend/executor/execReplication.c
  21. 116
      src/backend/executor/nodeBitmapIndexscan.c
  22. 96
      src/backend/executor/nodeIndexonlyscan.c
  23. 97
      src/backend/executor/nodeIndexscan.c
  24. 2
      src/backend/utils/adt/selfuncs.c
  25. 34
      src/include/access/genam.h
  26. 11
      src/include/access/relscan.h
  27. 6
      src/include/executor/nodeBitmapIndexscan.h
  28. 1
      src/include/executor/nodeIndexonlyscan.h
  29. 1
      src/include/executor/nodeIndexscan.h
  30. 12
      src/include/nodes/execnodes.h
  31. 27
      src/test/regress/expected/brin_multi.out
  32. 49
      src/test/regress/expected/memoize.out
  33. 100
      src/test/regress/expected/partition_prune.out
  34. 3
      src/test/regress/expected/select.out
  35. 5
      src/test/regress/sql/memoize.sql
  36. 4
      src/test/regress/sql/partition_prune.sql
  37. 2
      src/tools/pgindent/typedefs.list

2
contrib/bloom/blscan.c
Unescape View File

@ -116,6 +116,8 @@ blgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
bas = GetAccessStrategy(BAS_BULKREAD);
npages = RelationGetNumberOfBlocks(scan->indexRelation);
pgstat_count_index_scan(scan->indexRelation);
if (scan->instrument)
scan->instrument->nsearches++;
for (blkno = BLOOM_HEAD_BLKNO; blkno < npages; blkno++)
{

7
doc/src/sgml/bloom.sgml
Unescape View File

@ -173,10 +173,11 @@ CREATE INDEX
Buffers: shared hit=21864
-&gt; Bitmap Index Scan on bloomidx (cost=0.00..178436.00 rows=1 width=0) (actual time=20.005..20.005 rows=2300.00 loops=1)
Index Cond: ((i2 = 898732) AND (i5 = 123451))
Index Searches: 1
Buffers: shared hit=19608
Planning Time: 0.099 ms
Execution Time: 22.632 ms
(10 rows)
(11 rows)
</programlisting>
</para>
@ -208,13 +209,15 @@ CREATE INDEX
Buffers: shared hit=6
-&gt; Bitmap Index Scan on btreeidx5 (cost=0.00..4.52 rows=11 width=0) (actual time=0.026..0.026 rows=7.00 loops=1)
Index Cond: (i5 = 123451)
Index Searches: 1
Buffers: shared hit=3
-&gt; Bitmap Index Scan on btreeidx2 (cost=0.00..4.52 rows=11 width=0) (actual time=0.007..0.007 rows=8.00 loops=1)
Index Cond: (i2 = 898732)
Index Searches: 1
Buffers: shared hit=3
Planning Time: 0.264 ms
Execution Time: 0.047 ms
(13 rows)
(15 rows)
</programlisting>
Although this query runs much faster than with either of the single
indexes, we pay a penalty in index size. Each of the single-column

28
doc/src/sgml/monitoring.sgml
Unescape View File

@ -4234,16 +4234,32 @@ description | Waiting for a newly initialized WAL file to reach durable storage
<note>
<para>
Queries that use certain <acronym>SQL</acronym> constructs to search for
rows matching any value out of a list or array of multiple scalar values
(see <xref linkend="functions-comparisons"/>) perform multiple
<quote>primitive</quote> index scans (up to one primitive scan per scalar
value) during query execution. Each internal primitive index scan
increments <structname>pg_stat_all_indexes</structname>.<structfield>idx_scan</structfield>,
Index scans may sometimes perform multiple index searches per execution.
Each index search increments <structname>pg_stat_all_indexes</structname>.<structfield>idx_scan</structfield>,
so it's possible for the count of index scans to significantly exceed the
total number of index scan executor node executions.
</para>
<para>
This can happen with queries that use certain <acronym>SQL</acronym>
constructs to search for rows matching any value out of a list or array of
multiple scalar values (see <xref linkend="functions-comparisons"/>). It
can also happen to queries with a
<literal><replaceable>column_name</replaceable> =
<replaceable>value1</replaceable> OR
<replaceable>column_name</replaceable> =
<replaceable>value2</replaceable> ...</literal> construct, though only
when the optimizer transforms the construct into an equivalent
multi-valued array representation.
</para>
</note>
<tip>
<para>
<command>EXPLAIN ANALYZE</command> outputs the total number of index
searches performed by each index scan node. See
<xref linkend="using-explain-analyze"/> for an example demonstrating how
this works.
</para>
</tip>
</sect2>

60
doc/src/sgml/perform.sgml
Unescape View File

@ -729,9 +729,11 @@ WHERE t1.unique1 &lt; 10 AND t1.unique2 = t2.unique2;
Buffers: shared hit=3 read=5 written=4
-&gt; Bitmap Index Scan on tenk1_unique1 (cost=0.00..4.36 rows=10 width=0) (actual time=0.004..0.004 rows=10.00 loops=1)
Index Cond: (unique1 &lt; 10)
Index Searches: 1
Buffers: shared hit=2
-&gt; Index Scan using tenk2_unique2 on tenk2 t2 (cost=0.29..7.90 rows=1 width=244) (actual time=0.003..0.003 rows=1.00 loops=10)
Index Cond: (unique2 = t1.unique2)
Index Searches: 10
Buffers: shared hit=24 read=6
Planning:
Buffers: shared hit=15 dirtied=9
@ -790,6 +792,7 @@ WHERE t1.unique1 &lt; 100 AND t1.unique2 = t2.unique2 ORDER BY t1.fivethous;
Buffers: shared hit=92
-&gt; Bitmap Index Scan on tenk1_unique1 (cost=0.00..5.04 rows=100 width=0) (actual time=0.013..0.013 rows=100.00 loops=1)
Index Cond: (unique1 &lt; 100)
Index Searches: 1
Buffers: shared hit=2
Planning:
Buffers: shared hit=12
@ -805,6 +808,58 @@ WHERE t1.unique1 &lt; 100 AND t1.unique2 = t2.unique2 ORDER BY t1.fivethous;
shown.)
</para>
<para>
Index Scan nodes (as well as Bitmap Index Scan and Index-Only Scan nodes)
show an <quote>Index Searches</quote> line that reports the total number
of searches across <emphasis>all</emphasis> node
executions/<literal>loops</literal>:
<screen>
EXPLAIN ANALYZE SELECT * FROM tenk1 WHERE thousand IN (1, 500, 700, 999);
QUERY PLAN
-------------------------------------------------------------------&zwsp;---------------------------------------------------------------
Bitmap Heap Scan on tenk1 (cost=9.45..73.44 rows=40 width=244) (actual time=0.012..0.028 rows=40.00 loops=1)
Recheck Cond: (thousand = ANY ('{1,500,700,999}'::integer[]))
Heap Blocks: exact=39
Buffers: shared hit=47
-> Bitmap Index Scan on tenk1_thous_tenthous (cost=0.00..9.44 rows=40 width=0) (actual time=0.009..0.009 rows=40.00 loops=1)
Index Cond: (thousand = ANY ('{1,500,700,999}'::integer[]))
Index Searches: 4
Buffers: shared hit=8
Planning Time: 0.029 ms
Execution Time: 0.034 ms
</screen>
Here we see a Bitmap Index Scan node that needed 4 separate index
searches. The scan had to search the index from the
<structname>tenk1_thous_tenthous</structname> index root page once per
<type>integer</type> value from the predicate's <literal>IN</literal>
construct. However, the number of index searches often won't have such a
simple correspondence to the query predicate:
<screen>
EXPLAIN ANALYZE SELECT * FROM tenk1 WHERE thousand IN (1, 2, 3, 4);
QUERY PLAN
--------------------------------------------------------------------&zwsp;--------------------------------------------------------------
Bitmap Heap Scan on tenk1 (cost=9.45..73.44 rows=40 width=244) (actual time=0.009..0.019 rows=40.00 loops=1)
Recheck Cond: (thousand = ANY ('{1,2,3,4}'::integer[]))
Heap Blocks: exact=38
Buffers: shared hit=40
-> Bitmap Index Scan on tenk1_thous_tenthous (cost=0.00..9.44 rows=40 width=0) (actual time=0.005..0.005 rows=40.00 loops=1)
Index Cond: (thousand = ANY ('{1,2,3,4}'::integer[]))
Index Searches: 1
Buffers: shared hit=2
Planning Time: 0.029 ms
Execution Time: 0.026 ms
</screen>
This variant of our <literal>IN</literal> query performed only 1 index
search. It spent less time traversing the index (compared to the original
query) because its <literal>IN</literal> construct uses values matching
index tuples stored next to each other, on the same
<structname>tenk1_thous_tenthous</structname> index leaf page.
</para>
<para>
Another type of extra information is the number of rows removed by a
filter condition:
@ -861,6 +916,7 @@ EXPLAIN ANALYZE SELECT * FROM polygon_tbl WHERE f1 @&gt; polygon '(0.5,2.0)';
Index Scan using gpolygonind on polygon_tbl (cost=0.13..8.15 rows=1 width=85) (actual time=0.074..0.074 rows=0.00 loops=1)
Index Cond: (f1 @&gt; '((0.5,2))'::polygon)
Rows Removed by Index Recheck: 1
Index Searches: 1
Buffers: shared hit=1
Planning Time: 0.039 ms
Execution Time: 0.098 ms
@ -894,8 +950,10 @@ EXPLAIN (ANALYZE, BUFFERS OFF) SELECT * FROM tenk1 WHERE unique1 &lt; 100 AND un
-&gt; BitmapAnd (cost=25.07..25.07 rows=10 width=0) (actual time=0.100..0.101 rows=0.00 loops=1)
-&gt; Bitmap Index Scan on tenk1_unique1 (cost=0.00..5.04 rows=100 width=0) (actual time=0.027..0.027 rows=100.00 loops=1)
Index Cond: (unique1 &lt; 100)
Index Searches: 1
-&gt; Bitmap Index Scan on tenk1_unique2 (cost=0.00..19.78 rows=999 width=0) (actual time=0.070..0.070 rows=999.00 loops=1)
Index Cond: (unique2 &gt; 9000)
Index Searches: 1
Planning Time: 0.162 ms
Execution Time: 0.143 ms
</screen>
@ -923,6 +981,7 @@ EXPLAIN ANALYZE UPDATE tenk1 SET hundred = hundred + 1 WHERE unique1 &lt; 100;
Buffers: shared hit=4 read=2
-&gt; Bitmap Index Scan on tenk1_unique1 (cost=0.00..5.04 rows=100 width=0) (actual time=0.031..0.031 rows=100.00 loops=1)
Index Cond: (unique1 &lt; 100)
Index Searches: 1
Buffers: shared read=2
Planning Time: 0.151 ms
Execution Time: 1.856 ms
@ -1061,6 +1120,7 @@ EXPLAIN ANALYZE SELECT * FROM tenk1 WHERE unique1 &lt; 100 AND unique2 &gt; 9000
Index Cond: (unique2 &gt; 9000)
Filter: (unique1 &lt; 100)
Rows Removed by Filter: 287
Index Searches: 1
Buffers: shared hit=16
Planning Time: 0.077 ms
Execution Time: 0.086 ms

3
doc/src/sgml/ref/explain.sgml
Unescape View File

@ -506,10 +506,11 @@ EXPLAIN ANALYZE EXECUTE query(100, 200);
Buffers: shared hit=4
-&gt; Index Scan using test_pkey on test (cost=0.29..10.27 rows=99 width=8) (actual time=0.009..0.025 rows=99.00 loops=1)
Index Cond: ((id &gt; 100) AND (id &lt; 200))
Index Searches: 1
Buffers: shared hit=4
Planning Time: 0.244 ms
Execution Time: 0.073 ms
(9 rows)
(10 rows)
</programlisting>
</para>

2
doc/src/sgml/rules.sgml
Unescape View File

@ -1046,6 +1046,7 @@ SELECT count(*) FROM words WHERE word = 'caterpiler';
-&gt; Index Only Scan using wrd_word on wrd (cost=0.42..4.44 rows=1 width=0) (actual time=0.039..0.039 rows=0.00 loops=1)
Index Cond: (word = 'caterpiler'::text)
Heap Fetches: 0
Index Searches: 1
Planning time: 0.164 ms
Execution time: 0.117 ms
</programlisting>
@ -1090,6 +1091,7 @@ SELECT word FROM words ORDER BY word &lt;-&gt; 'caterpiler' LIMIT 10;
Limit (cost=0.29..1.06 rows=10 width=10) (actual time=187.222..188.257 rows=10.00 loops=1)
-&gt; Index Scan using wrd_trgm on wrd (cost=0.29..37020.87 rows=479829 width=10) (actual time=187.219..188.252 rows=10.00 loops=1)
Order By: (word &lt;-&gt; 'caterpiler'::text)
Index Searches: 1
Planning time: 0.196 ms
Execution time: 198.640 ms
</programlisting>

2
src/backend/access/brin/brin.c
Unescape View File

@ -592,6 +592,8 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
opaque = (BrinOpaque *) scan->opaque;
bdesc = opaque->bo_bdesc;
pgstat_count_index_scan(idxRel);
if (scan->instrument)
scan->instrument->nsearches++;
/*
* We need to know the size of the table so that we know how long to

2
src/backend/access/gin/ginscan.c
Unescape View File

@ -442,6 +442,8 @@ ginNewScanKey(IndexScanDesc scan)
MemoryContextSwitchTo(oldCtx);
pgstat_count_index_scan(scan->indexRelation);
if (scan->instrument)
scan->instrument->nsearches++;
}
void

4
src/backend/access/gist/gistget.c
Unescape View File

@ -625,6 +625,8 @@ gistgettuple(IndexScanDesc scan, ScanDirection dir)
GISTSearchItem fakeItem;
pgstat_count_index_scan(scan->indexRelation);
if (scan->instrument)
scan->instrument->nsearches++;
so->firstCall = false;
so->curPageData = so->nPageData = 0;
@ -750,6 +752,8 @@ gistgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
return 0;
pgstat_count_index_scan(scan->indexRelation);
if (scan->instrument)
scan->instrument->nsearches++;
/* Begin the scan by processing the root page */
so->curPageData = so->nPageData = 0;

2
src/backend/access/hash/hashsearch.c
Unescape View File

@ -298,6 +298,8 @@ _hash_first(IndexScanDesc scan, ScanDirection dir)
HashScanPosItem *currItem;
pgstat_count_index_scan(rel);
if (scan->instrument)
scan->instrument->nsearches++;
/*
* We do not support hash scans with no index qualification, because we

2
src/backend/access/heap/heapam_handler.c
Unescape View File

@ -749,7 +749,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
tableScan = NULL;
heapScan = NULL;
indexScan = index_beginscan(OldHeap, OldIndex, SnapshotAny, 0, 0);
indexScan = index_beginscan(OldHeap, OldIndex, SnapshotAny, NULL, 0, 0);
index_rescan(indexScan, NULL, 0, NULL, 0);
}
else

5
src/backend/access/index/genam.c
Unescape View File

@ -119,6 +119,7 @@ RelationGetIndexScan(Relation indexRelation, int nkeys, int norderbys)
scan->ignore_killed_tuples = !scan->xactStartedInRecovery;
scan->opaque = NULL;
scan->instrument = NULL;
scan->xs_itup = NULL;
scan->xs_itupdesc = NULL;
@ -446,7 +447,7 @@ systable_beginscan(Relation heapRelation,
}
sysscan->iscan = index_beginscan(heapRelation, irel,
snapshot, nkeys, 0);
snapshot, NULL, nkeys, 0);
index_rescan(sysscan->iscan, idxkey, nkeys, NULL, 0);
sysscan->scan = NULL;
@ -711,7 +712,7 @@ systable_beginscan_ordered(Relation heapRelation,
}
sysscan->iscan = index_beginscan(heapRelation, indexRelation,
snapshot, nkeys, 0);
snapshot, NULL, nkeys, 0);
index_rescan(sysscan->iscan, idxkey, nkeys, NULL, 0);
sysscan->scan = NULL;

70
src/backend/access/index/indexam.c
Unescape View File

@ -256,6 +256,7 @@ IndexScanDesc
index_beginscan(Relation heapRelation,
Relation indexRelation,
Snapshot snapshot,
IndexScanInstrumentation *instrument,
int nkeys, int norderbys)
{
IndexScanDesc scan;
@ -270,6 +271,7 @@ index_beginscan(Relation heapRelation,
*/
scan->heapRelation = heapRelation;
scan->xs_snapshot = snapshot;
scan->instrument = instrument;
/* prepare to fetch index matches from table */
scan->xs_heapfetch = table_index_fetch_begin(heapRelation);
@ -286,6 +288,7 @@ index_beginscan(Relation heapRelation,
IndexScanDesc
index_beginscan_bitmap(Relation indexRelation,
Snapshot snapshot,
IndexScanInstrumentation *instrument,
int nkeys)
{
IndexScanDesc scan;
@ -299,6 +302,7 @@ index_beginscan_bitmap(Relation indexRelation,
* up by RelationGetIndexScan.
*/
scan->xs_snapshot = snapshot;
scan->instrument = instrument;
return scan;
}
@ -448,14 +452,19 @@ index_restrpos(IndexScanDesc scan)
/*
* index_parallelscan_estimate - estimate shared memory for parallel scan
*
* When instrument=true, estimate includes SharedIndexScanInstrumentation
* space. When parallel_aware=true, estimate includes whatever space the
* index AM's amestimateparallelscan routine requested when called.
*/
Size
index_parallelscan_estimate(Relation indexRelation, int nkeys, int norderbys,
Snapshot snapshot)
Snapshot snapshot, bool instrument,
bool parallel_aware, int nworkers)
{
Size nbytes;
Assert(snapshot != InvalidSnapshot);
Assert(instrument || parallel_aware);
RELATION_CHECKS;
@ -463,12 +472,22 @@ index_parallelscan_estimate(Relation indexRelation, int nkeys, int norderbys,
nbytes = add_size(nbytes, EstimateSnapshotSpace(snapshot));
nbytes = MAXALIGN(nbytes);
if (instrument)
{
Size sharedinfosz;
sharedinfosz = offsetof(SharedIndexScanInstrumentation, winstrument) +
nworkers * sizeof(IndexScanInstrumentation);
nbytes = add_size(nbytes, sharedinfosz);
nbytes = MAXALIGN(nbytes);
}
/*
* If amestimateparallelscan is not provided, assume there is no
* AM-specific data needed. (It's hard to believe that could work, but
* it's easy enough to cater to it here.)
* If parallel scan index AM interface can't be used (or index AM provides
* no such interface), assume there is no AM-specific data needed
*/
if (indexRelation->rd_indam->amestimateparallelscan != NULL)
if (parallel_aware &&
indexRelation->rd_indam->amestimateparallelscan != NULL)
nbytes = add_size(nbytes,
indexRelation->rd_indam->amestimateparallelscan(nkeys,
norderbys));
@ -488,11 +507,14 @@ index_parallelscan_estimate(Relation indexRelation, int nkeys, int norderbys,
*/
void
index_parallelscan_initialize(Relation heapRelation, Relation indexRelation,
Snapshot snapshot, ParallelIndexScanDesc target)
Snapshot snapshot, bool instrument,
bool parallel_aware, int nworkers,
SharedIndexScanInstrumentation **sharedinfo,
ParallelIndexScanDesc target)
{
Size offset;
Assert(snapshot != InvalidSnapshot);
Assert(instrument || parallel_aware);
RELATION_CHECKS;
@ -502,15 +524,34 @@ index_parallelscan_initialize(Relation heapRelation, Relation indexRelation,
target->ps_locator = heapRelation->rd_locator;
target->ps_indexlocator = indexRelation->rd_locator;
target->ps_offset = offset;
target->ps_offset_ins = 0;
target->ps_offset_am = 0;
SerializeSnapshot(snapshot, target->ps_snapshot_data);
if (instrument)
{
Size sharedinfosz;
target->ps_offset_ins = offset;
sharedinfosz = offsetof(SharedIndexScanInstrumentation, winstrument) +
nworkers * sizeof(IndexScanInstrumentation);
offset = add_size(offset, sharedinfosz);
offset = MAXALIGN(offset);
/* Set leader's *sharedinfo pointer, and initialize stats */
*sharedinfo = (SharedIndexScanInstrumentation *)
OffsetToPointer(target, target->ps_offset_ins);
memset(*sharedinfo, 0, sharedinfosz);
(*sharedinfo)->num_workers = nworkers;
}
/* aminitparallelscan is optional; assume no-op if not provided by AM */
if (indexRelation->rd_indam->aminitparallelscan != NULL)
if (parallel_aware && indexRelation->rd_indam->aminitparallelscan != NULL)
{
void *amtarget;
amtarget = OffsetToPointer(target, offset);
target->ps_offset_am = offset;
amtarget = OffsetToPointer(target, target->ps_offset_am);
indexRelation->rd_indam->aminitparallelscan(amtarget);
}
}
@ -538,8 +579,10 @@ index_parallelrescan(IndexScanDesc scan)
* Caller must be holding suitable locks on the heap and the index.
*/
IndexScanDesc
index_beginscan_parallel(Relation heaprel, Relation indexrel, int nkeys,
int norderbys, ParallelIndexScanDesc pscan)
index_beginscan_parallel(Relation heaprel, Relation indexrel,
IndexScanInstrumentation *instrument,
int nkeys, int norderbys,
ParallelIndexScanDesc pscan)
{
Snapshot snapshot;
IndexScanDesc scan;
@ -558,6 +601,7 @@ index_beginscan_parallel(Relation heaprel, Relation indexrel, int nkeys,
*/
scan->heapRelation = heaprel;
scan->xs_snapshot = snapshot;
scan->instrument = instrument;
/* prepare to fetch index matches from table */
scan->xs_heapfetch = table_index_fetch_begin(heaprel);

10
src/backend/access/nbtree/nbtree.c
Unescape View File

@ -574,7 +574,7 @@ btparallelrescan(IndexScanDesc scan)
Assert(parallel_scan);
btscan = (BTParallelScanDesc) OffsetToPointer(parallel_scan,
parallel_scan->ps_offset);
parallel_scan->ps_offset_am);
/*
* In theory, we don't need to acquire the LWLock here, because there
@ -652,7 +652,7 @@ _bt_parallel_seize(IndexScanDesc scan, BlockNumber *next_scan_page,
}
btscan = (BTParallelScanDesc) OffsetToPointer(parallel_scan,
parallel_scan->ps_offset);
parallel_scan->ps_offset_am);
while (1)
{
@ -760,7 +760,7 @@ _bt_parallel_release(IndexScanDesc scan, BlockNumber next_scan_page,
Assert(BlockNumberIsValid(next_scan_page));
btscan = (BTParallelScanDesc) OffsetToPointer(parallel_scan,
parallel_scan->ps_offset);
parallel_scan->ps_offset_am);
LWLockAcquire(&btscan->btps_lock, LW_EXCLUSIVE);
btscan->btps_nextScanPage = next_scan_page;
@ -799,7 +799,7 @@ _bt_parallel_done(IndexScanDesc scan)
return;
btscan = (BTParallelScanDesc) OffsetToPointer(parallel_scan,
parallel_scan->ps_offset);
parallel_scan->ps_offset_am);
/*
* Mark the parallel scan as done, unless some other process did so
@ -837,7 +837,7 @@ _bt_parallel_primscan_schedule(IndexScanDesc scan, BlockNumber curr_page)
Assert(so->numArrayKeys);
btscan = (BTParallelScanDesc) OffsetToPointer(parallel_scan,
parallel_scan->ps_offset);
parallel_scan->ps_offset_am);
LWLockAcquire(&btscan->btps_lock, LW_EXCLUSIVE);
if (btscan->btps_lastCurrPage == curr_page &&

2
src/backend/access/nbtree/nbtsearch.c
Unescape View File

@ -950,6 +950,8 @@ _bt_first(IndexScanDesc scan, ScanDirection dir)
* _bt_search/_bt_endpoint below
*/
pgstat_count_index_scan(rel);
if (scan->instrument)
scan->instrument->nsearches++;
/*----------
* Examine the scan keys to discover where we need to start the scan.

2
src/backend/access/spgist/spgscan.c
Unescape View File

@ -421,6 +421,8 @@ spgrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys,
/* count an indexscan for stats */
pgstat_count_index_scan(scan->indexRelation);
if (scan->instrument)
scan->instrument->nsearches++;
}
void

63
src/backend/commands/explain.c
Unescape View File

@ -125,6 +125,7 @@ static void show_recursive_union_info(RecursiveUnionState *rstate,
static void show_memoize_info(MemoizeState *mstate, List *ancestors,
ExplainState *es);
static void show_hashagg_info(AggState *aggstate, ExplainState *es);
static void show_indexsearches_info(PlanState *planstate, ExplainState *es);
static void show_tidbitmap_info(BitmapHeapScanState *planstate,
ExplainState *es);
static void show_instrumentation_count(const char *qlabel, int which,
@ -2096,6 +2097,7 @@ ExplainNode(PlanState *planstate, List *ancestors,
if (plan->qual)
show_instrumentation_count("Rows Removed by Filter", 1,
planstate, es);
show_indexsearches_info(planstate, es);
break;
case T_IndexOnlyScan:
show_scan_qual(((IndexOnlyScan *) plan)->indexqual,
@ -2112,10 +2114,12 @@ ExplainNode(PlanState *planstate, List *ancestors,
if (es->analyze)
ExplainPropertyFloat("Heap Fetches", NULL,
planstate->instrument->ntuples2, 0, es);
show_indexsearches_info(planstate, es);
break;
case T_BitmapIndexScan:
show_scan_qual(((BitmapIndexScan *) plan)->indexqualorig,
"Index Cond", planstate, ancestors, es);
show_indexsearches_info(planstate, es);
break;
case T_BitmapHeapScan:
show_scan_qual(((BitmapHeapScan *) plan)->bitmapqualorig,
@ -3855,6 +3859,65 @@ show_hashagg_info(AggState *aggstate, ExplainState *es)
}
}
/*
* Show the total number of index searches for a
* IndexScan/IndexOnlyScan/BitmapIndexScan node
*/
static void
show_indexsearches_info(PlanState *planstate, ExplainState *es)
{
Plan *plan = planstate->plan;
SharedIndexScanInstrumentation *SharedInfo = NULL;
uint64 nsearches = 0;
if (!es->analyze)
return;
/* Initialize counters with stats from the local process first */
switch (nodeTag(plan))
{
case T_IndexScan:
{
IndexScanState *indexstate = ((IndexScanState *) planstate);
nsearches = indexstate->iss_Instrument.nsearches;
SharedInfo = indexstate->iss_SharedInfo;
break;
}
case T_IndexOnlyScan:
{
IndexOnlyScanState *indexstate = ((IndexOnlyScanState *) planstate);
nsearches = indexstate->ioss_Instrument.nsearches;
SharedInfo = indexstate->ioss_SharedInfo;
break;
}
case T_BitmapIndexScan:
{
BitmapIndexScanState *indexstate = ((BitmapIndexScanState *) planstate);
nsearches = indexstate->biss_Instrument.nsearches;
SharedInfo = indexstate->biss_SharedInfo;
break;
}
default:
break;
}
/* Next get the sum of the counters set within each and every process */
if (SharedInfo)
{
for (int i = 0; i < SharedInfo->num_workers; ++i)
{
IndexScanInstrumentation *winstrument = &SharedInfo->winstrument[i];
nsearches += winstrument->nsearches;
}
}
ExplainPropertyUInteger("Index Searches", NULL, nsearches, es);
}
/*
* Show exact/lossy pages for a BitmapHeapScan node
*/

2
src/backend/executor/execIndexing.c
Unescape View File

@ -816,7 +816,7 @@ check_exclusion_or_unique_constraint(Relation heap, Relation index,
retry:
conflict = false;
found_self = false;
index_scan = index_beginscan(heap, index, &DirtySnapshot, indnkeyatts, 0);
index_scan = index_beginscan(heap, index, &DirtySnapshot, NULL, indnkeyatts, 0);
index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))

59
src/backend/executor/execParallel.c
Unescape View File

@ -28,6 +28,7 @@
#include "executor/nodeAgg.h"
#include "executor/nodeAppend.h"
#include "executor/nodeBitmapHeapscan.h"
#include "executor/nodeBitmapIndexscan.h"
#include "executor/nodeCustom.h"
#include "executor/nodeForeignscan.h"
#include "executor/nodeHash.h"
@ -244,14 +245,19 @@ ExecParallelEstimate(PlanState *planstate, ExecParallelEstimateContext *e)
e->pcxt);
break;
case T_IndexScanState:
if (planstate->plan->parallel_aware)
ExecIndexScanEstimate((IndexScanState *) planstate,
e->pcxt);
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecIndexScanEstimate((IndexScanState *) planstate,
e->pcxt);
break;
case T_IndexOnlyScanState:
if (planstate->plan->parallel_aware)
ExecIndexOnlyScanEstimate((IndexOnlyScanState *) planstate,
e->pcxt);
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecIndexOnlyScanEstimate((IndexOnlyScanState *) planstate,
e->pcxt);
break;
case T_BitmapIndexScanState:
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecBitmapIndexScanEstimate((BitmapIndexScanState *) planstate,
e->pcxt);
break;
case T_ForeignScanState:
if (planstate->plan->parallel_aware)
@ -468,14 +474,17 @@ ExecParallelInitializeDSM(PlanState *planstate,
d->pcxt);
break;
case T_IndexScanState:
if (planstate->plan->parallel_aware)
ExecIndexScanInitializeDSM((IndexScanState *) planstate,
d->pcxt);
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecIndexScanInitializeDSM((IndexScanState *) planstate, d->pcxt);
break;
case T_IndexOnlyScanState:
if (planstate->plan->parallel_aware)
ExecIndexOnlyScanInitializeDSM((IndexOnlyScanState *) planstate,
d->pcxt);
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecIndexOnlyScanInitializeDSM((IndexOnlyScanState *) planstate,
d->pcxt);
break;
case T_BitmapIndexScanState:
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecBitmapIndexScanInitializeDSM((BitmapIndexScanState *) planstate, d->pcxt);
break;
case T_ForeignScanState:
if (planstate->plan->parallel_aware)
@ -1002,6 +1011,7 @@ ExecParallelReInitializeDSM(PlanState *planstate,
ExecHashJoinReInitializeDSM((HashJoinState *) planstate,
pcxt);
break;
case T_BitmapIndexScanState:
case T_HashState:
case T_SortState:
case T_IncrementalSortState:
@ -1063,6 +1073,15 @@ ExecParallelRetrieveInstrumentation(PlanState *planstate,
/* Perform any node-type-specific work that needs to be done. */
switch (nodeTag(planstate))
{
case T_IndexScanState:
ExecIndexScanRetrieveInstrumentation((IndexScanState *) planstate);
break;
case T_IndexOnlyScanState:
ExecIndexOnlyScanRetrieveInstrumentation((IndexOnlyScanState *) planstate);
break;
case T_BitmapIndexScanState:
ExecBitmapIndexScanRetrieveInstrumentation((BitmapIndexScanState *) planstate);
break;
case T_SortState:
ExecSortRetrieveInstrumentation((SortState *) planstate);
break;
@ -1330,14 +1349,18 @@ ExecParallelInitializeWorker(PlanState *planstate, ParallelWorkerContext *pwcxt)
ExecSeqScanInitializeWorker((SeqScanState *) planstate, pwcxt);
break;
case T_IndexScanState:
if (planstate->plan->parallel_aware)
ExecIndexScanInitializeWorker((IndexScanState *) planstate,
pwcxt);
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecIndexScanInitializeWorker((IndexScanState *) planstate, pwcxt);
break;
case T_IndexOnlyScanState:
if (planstate->plan->parallel_aware)
ExecIndexOnlyScanInitializeWorker((IndexOnlyScanState *) planstate,
pwcxt);
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecIndexOnlyScanInitializeWorker((IndexOnlyScanState *) planstate,
pwcxt);
break;
case T_BitmapIndexScanState:
/* even when not parallel-aware, for EXPLAIN ANALYZE */
ExecBitmapIndexScanInitializeWorker((BitmapIndexScanState *) planstate,
pwcxt);
break;
case T_ForeignScanState:
if (planstate->plan->parallel_aware)

2
src/backend/executor/execReplication.c
Unescape View File

@ -202,7 +202,7 @@ RelationFindReplTupleByIndex(Relation rel, Oid idxoid,
skey_attoff = build_replindex_scan_key(skey, rel, idxrel, searchslot);
/* Start an index scan. */
scan = index_beginscan(rel, idxrel, &snap, skey_attoff, 0);
scan = index_beginscan(rel, idxrel, &snap, NULL, skey_attoff, 0);
retry:
found = false;

116
src/backend/executor/nodeBitmapIndexscan.c
Unescape View File

@ -183,6 +183,27 @@ ExecEndBitmapIndexScan(BitmapIndexScanState *node)
indexRelationDesc = node->biss_RelationDesc;
indexScanDesc = node->biss_ScanDesc;
/*
* When ending a parallel worker, copy the statistics gathered by the
* worker back into shared memory so that it can be picked up by the main
* process to report in EXPLAIN ANALYZE
*/
if (node->biss_SharedInfo != NULL && IsParallelWorker())
{
IndexScanInstrumentation *winstrument;
Assert(ParallelWorkerNumber <= node->biss_SharedInfo->num_workers);
winstrument = &node->biss_SharedInfo->winstrument[ParallelWorkerNumber];
/*
* We have to accumulate the stats rather than performing a memcpy.
* When a Gather/GatherMerge node finishes it will perform planner
* shutdown on the workers. On rescan it will spin up new workers
* which will have a new BitmapIndexScanState and zeroed stats.
*/
winstrument->nsearches += node->biss_Instrument.nsearches;
}
/*
* close the index relation (no-op if we didn't open it)
*/
@ -302,6 +323,7 @@ ExecInitBitmapIndexScan(BitmapIndexScan *node, EState *estate, int eflags)
indexstate->biss_ScanDesc =
index_beginscan_bitmap(indexstate->biss_RelationDesc,
estate->es_snapshot,
&indexstate->biss_Instrument,
indexstate->biss_NumScanKeys);
/*
@ -319,3 +341,97 @@ ExecInitBitmapIndexScan(BitmapIndexScan *node, EState *estate, int eflags)
*/
return indexstate;
}
/* ----------------------------------------------------------------
* ExecBitmapIndexScanEstimate
*
* Compute the amount of space we'll need in the parallel
* query DSM, and inform pcxt->estimator about our needs.
* ----------------------------------------------------------------
*/
void
ExecBitmapIndexScanEstimate(BitmapIndexScanState *node, ParallelContext *pcxt)
{
Size size;
/*
* Parallel bitmap index scans are not supported, but we still need to
* store the scan's instrumentation in DSM during parallel query
*/
if (!node->ss.ps.instrument || pcxt->nworkers == 0)
return;
size = offsetof(SharedIndexScanInstrumentation, winstrument) +
pcxt->nworkers * sizeof(IndexScanInstrumentation);
shm_toc_estimate_chunk(&pcxt->estimator, size);
shm_toc_estimate_keys(&pcxt->estimator, 1);
}
/* ----------------------------------------------------------------
* ExecBitmapIndexScanInitializeDSM
*
* Set up bitmap index scan shared instrumentation.
* ----------------------------------------------------------------
*/
void
ExecBitmapIndexScanInitializeDSM(BitmapIndexScanState *node,
ParallelContext *pcxt)
{
Size size;
/* don't need this if not instrumenting or no workers */
if (!node->ss.ps.instrument || pcxt->nworkers == 0)
return;
size = offsetof(SharedIndexScanInstrumentation, winstrument) +
pcxt->nworkers * sizeof(IndexScanInstrumentation);
node->biss_SharedInfo =
(SharedIndexScanInstrumentation *) shm_toc_allocate(pcxt->toc,
size);
shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id,
node->biss_SharedInfo);
/* Each per-worker area must start out as zeroes */
memset(node->biss_SharedInfo, 0, size);
node->biss_SharedInfo->num_workers = pcxt->nworkers;
}
/* ----------------------------------------------------------------
* ExecBitmapIndexScanInitializeWorker
*
* Copy relevant information from TOC into planstate.
* ----------------------------------------------------------------
*/
void
ExecBitmapIndexScanInitializeWorker(BitmapIndexScanState *node,
ParallelWorkerContext *pwcxt)
{
/* don't need this if not instrumenting */
if (!node->ss.ps.instrument)
return;
node->biss_SharedInfo = (SharedIndexScanInstrumentation *)
shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
}
/* ----------------------------------------------------------------
* ExecBitmapIndexScanRetrieveInstrumentation
*
* Transfer bitmap index scan statistics from DSM to private memory.
* ----------------------------------------------------------------
*/
void
ExecBitmapIndexScanRetrieveInstrumentation(BitmapIndexScanState *node)
{
SharedIndexScanInstrumentation *SharedInfo = node->biss_SharedInfo;
size_t size;
if (SharedInfo == NULL)
return;
/* Create a copy of SharedInfo in backend-local memory */
size = offsetof(SharedIndexScanInstrumentation, winstrument) +
SharedInfo->num_workers * sizeof(IndexScanInstrumentation);
node->biss_SharedInfo = palloc(size);
memcpy(node->biss_SharedInfo, SharedInfo, size);
}

96
src/backend/executor/nodeIndexonlyscan.c
Unescape View File

@ -92,6 +92,7 @@ IndexOnlyNext(IndexOnlyScanState *node)
scandesc = index_beginscan(node->ss.ss_currentRelation,
node->ioss_RelationDesc,
estate->es_snapshot,
&node->ioss_Instrument,
node->ioss_NumScanKeys,
node->ioss_NumOrderByKeys);
@ -413,6 +414,27 @@ ExecEndIndexOnlyScan(IndexOnlyScanState *node)
node->ioss_VMBuffer = InvalidBuffer;
}
/*
* When ending a parallel worker, copy the statistics gathered by the
* worker back into shared memory so that it can be picked up by the main
* process to report in EXPLAIN ANALYZE
*/
if (node->ioss_SharedInfo != NULL && IsParallelWorker())
{
IndexScanInstrumentation *winstrument;
Assert(ParallelWorkerNumber <= node->ioss_SharedInfo->num_workers);
winstrument = &node->ioss_SharedInfo->winstrument[ParallelWorkerNumber];
/*
* We have to accumulate the stats rather than performing a memcpy.
* When a Gather/GatherMerge node finishes it will perform planner
* shutdown on the workers. On rescan it will spin up new workers
* which will have a new IndexOnlyScanState and zeroed stats.
*/
winstrument->nsearches += node->ioss_Instrument.nsearches;
}
/*
* close the index relation (no-op if we didn't open it)
*/
@ -707,11 +729,21 @@ ExecIndexOnlyScanEstimate(IndexOnlyScanState *node,
ParallelContext *pcxt)
{
EState *estate = node->ss.ps.state;
bool instrument = (node->ss.ps.instrument != NULL);
bool parallel_aware = node->ss.ps.plan->parallel_aware;
if (!instrument && !parallel_aware)
{
/* No DSM required by the scan */
return;
}
node->ioss_PscanLen = index_parallelscan_estimate(node->ioss_RelationDesc,
node->ioss_NumScanKeys,
node->ioss_NumOrderByKeys,
estate->es_snapshot);
estate->es_snapshot,
instrument, parallel_aware,
pcxt->nworkers);
shm_toc_estimate_chunk(&pcxt->estimator, node->ioss_PscanLen);
shm_toc_estimate_keys(&pcxt->estimator, 1);
}
@ -728,16 +760,33 @@ ExecIndexOnlyScanInitializeDSM(IndexOnlyScanState *node,
{
EState *estate = node->ss.ps.state;
ParallelIndexScanDesc piscan;
bool instrument = node->ss.ps.instrument != NULL;
bool parallel_aware = node->ss.ps.plan->parallel_aware;
if (!instrument && !parallel_aware)
{
/* No DSM required by the scan */
return;
}
piscan = shm_toc_allocate(pcxt->toc, node->ioss_PscanLen);
index_parallelscan_initialize(node->ss.ss_currentRelation,
node->ioss_RelationDesc,
estate->es_snapshot,
piscan);
instrument, parallel_aware, pcxt->nworkers,
&node->ioss_SharedInfo, piscan);
shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, piscan);
if (!parallel_aware)
{
/* Only here to initialize SharedInfo in DSM */
return;
}
node->ioss_ScanDesc =
index_beginscan_parallel(node->ss.ss_currentRelation,
node->ioss_RelationDesc,
&node->ioss_Instrument,
node->ioss_NumScanKeys,
node->ioss_NumOrderByKeys,
piscan);
@ -764,6 +813,7 @@ void
ExecIndexOnlyScanReInitializeDSM(IndexOnlyScanState *node,
ParallelContext *pcxt)
{
Assert(node->ss.ps.plan->parallel_aware);
index_parallelrescan(node->ioss_ScanDesc);
}
@ -778,11 +828,31 @@ ExecIndexOnlyScanInitializeWorker(IndexOnlyScanState *node,
ParallelWorkerContext *pwcxt)
{
ParallelIndexScanDesc piscan;
bool instrument = node->ss.ps.instrument != NULL;
bool parallel_aware = node->ss.ps.plan->parallel_aware;
if (!instrument && !parallel_aware)
{
/* No DSM required by the scan */
return;
}
piscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
if (instrument)
node->ioss_SharedInfo = (SharedIndexScanInstrumentation *)
OffsetToPointer(piscan, piscan->ps_offset_ins);
if (!parallel_aware)
{
/* Only here to set up worker node's SharedInfo */
return;
}
node->ioss_ScanDesc =
index_beginscan_parallel(node->ss.ss_currentRelation,
node->ioss_RelationDesc,
&node->ioss_Instrument,
node->ioss_NumScanKeys,
node->ioss_NumOrderByKeys,
piscan);
@ -797,3 +867,25 @@ ExecIndexOnlyScanInitializeWorker(IndexOnlyScanState *node,
node->ioss_ScanKeys, node->ioss_NumScanKeys,
node->ioss_OrderByKeys, node->ioss_NumOrderByKeys);
}
/* ----------------------------------------------------------------
* ExecIndexOnlyScanRetrieveInstrumentation
*
* Transfer index-only scan statistics from DSM to private memory.
* ----------------------------------------------------------------
*/
void
ExecIndexOnlyScanRetrieveInstrumentation(IndexOnlyScanState *node)
{
SharedIndexScanInstrumentation *SharedInfo = node->ioss_SharedInfo;
size_t size;
if (SharedInfo == NULL)
return;
/* Create a copy of SharedInfo in backend-local memory */
size = offsetof(SharedIndexScanInstrumentation, winstrument) +
SharedInfo->num_workers * sizeof(IndexScanInstrumentation);
node->ioss_SharedInfo = palloc(size);
memcpy(node->ioss_SharedInfo, SharedInfo, size);
}

97
src/backend/executor/nodeIndexscan.c
Unescape View File

@ -109,6 +109,7 @@ IndexNext(IndexScanState *node)
scandesc = index_beginscan(node->ss.ss_currentRelation,
node->iss_RelationDesc,
estate->es_snapshot,
&node->iss_Instrument,
node->iss_NumScanKeys,
node->iss_NumOrderByKeys);
@ -204,6 +205,7 @@ IndexNextWithReorder(IndexScanState *node)
scandesc = index_beginscan(node->ss.ss_currentRelation,
node->iss_RelationDesc,
estate->es_snapshot,
&node->iss_Instrument,
node->iss_NumScanKeys,
node->iss_NumOrderByKeys);
@ -793,6 +795,27 @@ ExecEndIndexScan(IndexScanState *node)
indexRelationDesc = node->iss_RelationDesc;
indexScanDesc = node->iss_ScanDesc;
/*
* When ending a parallel worker, copy the statistics gathered by the
* worker back into shared memory so that it can be picked up by the main
* process to report in EXPLAIN ANALYZE
*/
if (node->iss_SharedInfo != NULL && IsParallelWorker())
{
IndexScanInstrumentation *winstrument;
Assert(ParallelWorkerNumber <= node->iss_SharedInfo->num_workers);
winstrument = &node->iss_SharedInfo->winstrument[ParallelWorkerNumber];
/*
* We have to accumulate the stats rather than performing a memcpy.
* When a Gather/GatherMerge node finishes it will perform planner
* shutdown on the workers. On rescan it will spin up new workers
* which will have a new IndexOnlyScanState and zeroed stats.
*/
winstrument->nsearches += node->iss_Instrument.nsearches;
}
/*
* close the index relation (no-op if we didn't open it)
*/
@ -1642,11 +1665,21 @@ ExecIndexScanEstimate(IndexScanState *node,
ParallelContext *pcxt)
{
EState *estate = node->ss.ps.state;
bool instrument = node->ss.ps.instrument != NULL;
bool parallel_aware = node->ss.ps.plan->parallel_aware;
if (!instrument && !parallel_aware)
{
/* No DSM required by the scan */
return;
}
node->iss_PscanLen = index_parallelscan_estimate(node->iss_RelationDesc,
node->iss_NumScanKeys,
node->iss_NumOrderByKeys,
estate->es_snapshot);
estate->es_snapshot,
instrument, parallel_aware,
pcxt->nworkers);
shm_toc_estimate_chunk(&pcxt->estimator, node->iss_PscanLen);
shm_toc_estimate_keys(&pcxt->estimator, 1);
}
@ -1663,16 +1696,33 @@ ExecIndexScanInitializeDSM(IndexScanState *node,
{
EState *estate = node->ss.ps.state;
ParallelIndexScanDesc piscan;
bool instrument = node->ss.ps.instrument != NULL;
bool parallel_aware = node->ss.ps.plan->parallel_aware;
if (!instrument && !parallel_aware)
{
/* No DSM required by the scan */
return;
}
piscan = shm_toc_allocate(pcxt->toc, node->iss_PscanLen);
index_parallelscan_initialize(node->ss.ss_currentRelation,
node->iss_RelationDesc,
estate->es_snapshot,
piscan);
instrument, parallel_aware, pcxt->nworkers,
&node->iss_SharedInfo, piscan);
shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, piscan);
if (!parallel_aware)
{
/* Only here to initialize SharedInfo in DSM */
return;
}
node->iss_ScanDesc =
index_beginscan_parallel(node->ss.ss_currentRelation,
node->iss_RelationDesc,
&node->iss_Instrument,
node->iss_NumScanKeys,
node->iss_NumOrderByKeys,
piscan);
@ -1697,6 +1747,7 @@ void
ExecIndexScanReInitializeDSM(IndexScanState *node,
ParallelContext *pcxt)
{
Assert(node->ss.ps.plan->parallel_aware);
index_parallelrescan(node->iss_ScanDesc);
}
@ -1711,11 +1762,31 @@ ExecIndexScanInitializeWorker(IndexScanState *node,
ParallelWorkerContext *pwcxt)
{
ParallelIndexScanDesc piscan;
bool instrument = node->ss.ps.instrument != NULL;
bool parallel_aware = node->ss.ps.plan->parallel_aware;
if (!instrument && !parallel_aware)
{
/* No DSM required by the scan */
return;
}
piscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
if (instrument)
node->iss_SharedInfo = (SharedIndexScanInstrumentation *)
OffsetToPointer(piscan, piscan->ps_offset_ins);
if (!parallel_aware)
{
/* Only here to set up worker node's SharedInfo */
return;
}
node->iss_ScanDesc =
index_beginscan_parallel(node->ss.ss_currentRelation,
node->iss_RelationDesc,
&node->iss_Instrument,
node->iss_NumScanKeys,
node->iss_NumOrderByKeys,
piscan);
@ -1729,3 +1800,25 @@ ExecIndexScanInitializeWorker(IndexScanState *node,
node->iss_ScanKeys, node->iss_NumScanKeys,
node->iss_OrderByKeys, node->iss_NumOrderByKeys);
}
/* ----------------------------------------------------------------
* ExecIndexScanRetrieveInstrumentation
*
* Transfer index scan statistics from DSM to private memory.
* ----------------------------------------------------------------
*/
void
ExecIndexScanRetrieveInstrumentation(IndexScanState *node)
{
SharedIndexScanInstrumentation *SharedInfo = node->iss_SharedInfo;
size_t size;
if (SharedInfo == NULL)
return;
/* Create a copy of SharedInfo in backend-local memory */
size = offsetof(SharedIndexScanInstrumentation, winstrument) +
SharedInfo->num_workers * sizeof(IndexScanInstrumentation);
node->iss_SharedInfo = palloc(size);
memcpy(node->iss_SharedInfo, SharedInfo, size);
}

2
src/backend/utils/adt/selfuncs.c
Unescape View File

@ -6551,7 +6551,7 @@ get_actual_variable_endpoint(Relation heapRel,
GlobalVisTestFor(heapRel));
index_scan = index_beginscan(heapRel, indexRel,
&SnapshotNonVacuumable,
&SnapshotNonVacuumable, NULL,
1, 0);
/* Set it up for index-only scan */
index_scan->xs_want_itup = true;

34
src/include/access/genam.h
Unescape View File

@ -26,6 +26,27 @@
/* We don't want this file to depend on execnodes.h. */
struct IndexInfo;
/*
* Struct for statistics maintained by amgettuple and amgetbitmap
*
* Note: IndexScanInstrumentation can't contain any pointers, since it is
* copied into a SharedIndexScanInstrumentation during parallel scans
*/
typedef struct IndexScanInstrumentation
{
/* Index search count (incremented with pgstat_count_index_scan call) */
uint64 nsearches;
} IndexScanInstrumentation;
/*
* Struct for every worker's IndexScanInstrumentation, stored in shared memory
*/
typedef struct SharedIndexScanInstrumentation
{
int num_workers;
IndexScanInstrumentation winstrument[FLEXIBLE_ARRAY_MEMBER];
} SharedIndexScanInstrumentation;
/*
* Struct for statistics returned by ambuild
*/
@ -157,9 +178,11 @@ extern void index_insert_cleanup(Relation indexRelation,
extern IndexScanDesc index_beginscan(Relation heapRelation,
Relation indexRelation,
Snapshot snapshot,
IndexScanInstrumentation *instrument,
int nkeys, int norderbys);
extern IndexScanDesc index_beginscan_bitmap(Relation indexRelation,
Snapshot snapshot,
IndexScanInstrumentation *instrument,
int nkeys);
extern void index_rescan(IndexScanDesc scan,
ScanKey keys, int nkeys,
@ -168,13 +191,20 @@ extern void index_endscan(IndexScanDesc scan);
extern void index_markpos(IndexScanDesc scan);
extern void index_restrpos(IndexScanDesc scan);
extern Size index_parallelscan_estimate(Relation indexRelation,
int nkeys, int norderbys, Snapshot snapshot);
int nkeys, int norderbys, Snapshot snapshot,
bool instrument, bool parallel_aware,
int nworkers);
extern void index_parallelscan_initialize(Relation heapRelation,
Relation indexRelation, Snapshot snapshot,
bool instrument, bool parallel_aware,
int nworkers,
SharedIndexScanInstrumentation **sharedinfo,
ParallelIndexScanDesc target);
extern void index_parallelrescan(IndexScanDesc scan);
extern IndexScanDesc index_beginscan_parallel(Relation heaprel,
Relation indexrel, int nkeys, int norderbys,
Relation indexrel,
IndexScanInstrumentation *instrument,
int nkeys, int norderbys,
ParallelIndexScanDesc pscan);
extern ItemPointer index_getnext_tid(IndexScanDesc scan,
ScanDirection direction);

11
src/include/access/relscan.h
Unescape View File

@ -123,6 +123,8 @@ typedef struct IndexFetchTableData
Relation rel;
} IndexFetchTableData;
struct IndexScanInstrumentation;
/*
* We use the same IndexScanDescData structure for both amgettuple-based
* and amgetbitmap-based index scans. Some fields are only relevant in
@ -150,6 +152,12 @@ typedef struct IndexScanDescData
/* index access method's private state */
void *opaque; /* access-method-specific info */
/*
* Instrumentation counters maintained by all index AMs during both
* amgettuple calls and amgetbitmap calls (unless field remains NULL)
*/
struct IndexScanInstrumentation *instrument;
/*
* In an index-only scan, a successful amgettuple call must fill either
* xs_itup (and xs_itupdesc) or xs_hitup (and xs_hitupdesc) to provide the
@ -188,7 +196,8 @@ typedef struct ParallelIndexScanDescData
{
RelFileLocator ps_locator; /* physical table relation to scan */
RelFileLocator ps_indexlocator; /* physical index relation to scan */
Size ps_offset; /* Offset in bytes of am specific structure */
Size ps_offset_ins; /* Offset to SharedIndexScanInstrumentation */
Size ps_offset_am; /* Offset to am-specific structure */
char ps_snapshot_data[FLEXIBLE_ARRAY_MEMBER];
} ParallelIndexScanDescData;

6
src/include/executor/nodeBitmapIndexscan.h
Unescape View File

@ -14,11 +14,17 @@
#ifndef NODEBITMAPINDEXSCAN_H
#define NODEBITMAPINDEXSCAN_H
#include "access/parallel.h"
#include "nodes/execnodes.h"
extern BitmapIndexScanState *ExecInitBitmapIndexScan(BitmapIndexScan *node, EState *estate, int eflags);
extern Node *MultiExecBitmapIndexScan(BitmapIndexScanState *node);
extern void ExecEndBitmapIndexScan(BitmapIndexScanState *node);
extern void ExecReScanBitmapIndexScan(BitmapIndexScanState *node);
extern void ExecBitmapIndexScanEstimate(BitmapIndexScanState *node, ParallelContext *pcxt);
extern void ExecBitmapIndexScanInitializeDSM(BitmapIndexScanState *node, ParallelContext *pcxt);
extern void ExecBitmapIndexScanInitializeWorker(BitmapIndexScanState *node,
ParallelWorkerContext *pwcxt);
extern void ExecBitmapIndexScanRetrieveInstrumentation(BitmapIndexScanState *node);
#endif /* NODEBITMAPINDEXSCAN_H */

1
src/include/executor/nodeIndexonlyscan.h
Unescape View File

@ -32,5 +32,6 @@ extern void ExecIndexOnlyScanReInitializeDSM(IndexOnlyScanState *node,
ParallelContext *pcxt);
extern void ExecIndexOnlyScanInitializeWorker(IndexOnlyScanState *node,
ParallelWorkerContext *pwcxt);
extern void ExecIndexOnlyScanRetrieveInstrumentation(IndexOnlyScanState *node);
#endif /* NODEINDEXONLYSCAN_H */

1
src/include/executor/nodeIndexscan.h
Unescape View File

@ -28,6 +28,7 @@ extern void ExecIndexScanInitializeDSM(IndexScanState *node, ParallelContext *pc
extern void ExecIndexScanReInitializeDSM(IndexScanState *node, ParallelContext *pcxt);
extern void ExecIndexScanInitializeWorker(IndexScanState *node,
ParallelWorkerContext *pwcxt);
extern void ExecIndexScanRetrieveInstrumentation(IndexScanState *node);
/*
* These routines are exported to share code with nodeIndexonlyscan.c and

12
src/include/nodes/execnodes.h
Unescape View File

@ -1680,6 +1680,8 @@ typedef struct
* RuntimeContext expr context for evaling runtime Skeys
* RelationDesc index relation descriptor
* ScanDesc index scan descriptor
* Instrument local index scan instrumentation
* SharedInfo parallel worker instrumentation (no leader entry)
*
* ReorderQueue tuples that need reordering due to re-check
* ReachedEnd have we fetched all tuples from index already?
@ -1706,6 +1708,8 @@ typedef struct IndexScanState
ExprContext *iss_RuntimeContext;
Relation iss_RelationDesc;
struct IndexScanDescData *iss_ScanDesc;
IndexScanInstrumentation iss_Instrument;
SharedIndexScanInstrumentation *iss_SharedInfo;
/* These are needed for re-checking ORDER BY expr ordering */
pairingheap *iss_ReorderQueue;
@ -1732,6 +1736,8 @@ typedef struct IndexScanState
* RuntimeContext expr context for evaling runtime Skeys
* RelationDesc index relation descriptor
* ScanDesc index scan descriptor
* Instrument local index scan instrumentation
* SharedInfo parallel worker instrumentation (no leader entry)
* TableSlot slot for holding tuples fetched from the table
* VMBuffer buffer in use for visibility map testing, if any
* PscanLen size of parallel index-only scan descriptor
@ -1753,6 +1759,8 @@ typedef struct IndexOnlyScanState
ExprContext *ioss_RuntimeContext;
Relation ioss_RelationDesc;
struct IndexScanDescData *ioss_ScanDesc;
IndexScanInstrumentation ioss_Instrument;
SharedIndexScanInstrumentation *ioss_SharedInfo;
TupleTableSlot *ioss_TableSlot;
Buffer ioss_VMBuffer;
Size ioss_PscanLen;
@ -1774,6 +1782,8 @@ typedef struct IndexOnlyScanState
* RuntimeContext expr context for evaling runtime Skeys
* RelationDesc index relation descriptor
* ScanDesc index scan descriptor
* Instrument local index scan instrumentation
* SharedInfo parallel worker instrumentation (no leader entry)
* ----------------
*/
typedef struct BitmapIndexScanState
@ -1790,6 +1800,8 @@ typedef struct BitmapIndexScanState
ExprContext *biss_RuntimeContext;
Relation biss_RelationDesc;
struct IndexScanDescData *biss_ScanDesc;
IndexScanInstrumentation biss_Instrument;
SharedIndexScanInstrumentation *biss_SharedInfo;
} BitmapIndexScanState;
/* ----------------

27
src/test/regress/expected/brin_multi.out
Unescape View File

@ -853,7 +853,8 @@ SELECT * FROM brin_date_test WHERE a = '2023-01-01'::date;
Recheck Cond: (a = '2023-01-01'::date)
-> Bitmap Index Scan on brin_date_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '2023-01-01'::date)
(4 rows)
Index Searches: 1
(5 rows)
DROP TABLE brin_date_test;
RESET enable_seqscan;
@ -872,7 +873,8 @@ SELECT * FROM brin_timestamp_test WHERE a = '2023-01-01'::timestamp;
Recheck Cond: (a = '2023-01-01 00:00:00'::timestamp without time zone)
-> Bitmap Index Scan on brin_timestamp_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '2023-01-01 00:00:00'::timestamp without time zone)
(4 rows)
Index Searches: 1
(5 rows)
EXPLAIN (ANALYZE, TIMING OFF, COSTS OFF, SUMMARY OFF, BUFFERS OFF)
SELECT * FROM brin_timestamp_test WHERE a = '1900-01-01'::timestamp;
@ -882,7 +884,8 @@ SELECT * FROM brin_timestamp_test WHERE a = '1900-01-01'::timestamp;
Recheck Cond: (a = '1900-01-01 00:00:00'::timestamp without time zone)
-> Bitmap Index Scan on brin_timestamp_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '1900-01-01 00:00:00'::timestamp without time zone)
(4 rows)
Index Searches: 1
(5 rows)
DROP TABLE brin_timestamp_test;
RESET enable_seqscan;
@ -900,7 +903,8 @@ SELECT * FROM brin_date_test WHERE a = '2023-01-01'::date;
Recheck Cond: (a = '2023-01-01'::date)
-> Bitmap Index Scan on brin_date_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '2023-01-01'::date)
(4 rows)
Index Searches: 1
(5 rows)
EXPLAIN (ANALYZE, TIMING OFF, COSTS OFF, SUMMARY OFF, BUFFERS OFF)
SELECT * FROM brin_date_test WHERE a = '1900-01-01'::date;
@ -910,7 +914,8 @@ SELECT * FROM brin_date_test WHERE a = '1900-01-01'::date;
Recheck Cond: (a = '1900-01-01'::date)
-> Bitmap Index Scan on brin_date_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '1900-01-01'::date)
(4 rows)
Index Searches: 1
(5 rows)
DROP TABLE brin_date_test;
RESET enable_seqscan;
@ -929,7 +934,8 @@ SELECT * FROM brin_interval_test WHERE a = '-30 years'::interval;
Recheck Cond: (a = '@ 30 years ago'::interval)
-> Bitmap Index Scan on brin_interval_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '@ 30 years ago'::interval)
(4 rows)
Index Searches: 1
(5 rows)
EXPLAIN (ANALYZE, TIMING OFF, COSTS OFF, SUMMARY OFF, BUFFERS OFF)
SELECT * FROM brin_interval_test WHERE a = '30 years'::interval;
@ -939,7 +945,8 @@ SELECT * FROM brin_interval_test WHERE a = '30 years'::interval;
Recheck Cond: (a = '@ 30 years'::interval)
-> Bitmap Index Scan on brin_interval_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '@ 30 years'::interval)
(4 rows)
Index Searches: 1
(5 rows)
DROP TABLE brin_interval_test;
RESET enable_seqscan;
@ -957,7 +964,8 @@ SELECT * FROM brin_interval_test WHERE a = '-30 years'::interval;
Recheck Cond: (a = '@ 30 years ago'::interval)
-> Bitmap Index Scan on brin_interval_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '@ 30 years ago'::interval)
(4 rows)
Index Searches: 1
(5 rows)
EXPLAIN (ANALYZE, TIMING OFF, COSTS OFF, SUMMARY OFF, BUFFERS OFF)
SELECT * FROM brin_interval_test WHERE a = '30 years'::interval;
@ -967,7 +975,8 @@ SELECT * FROM brin_interval_test WHERE a = '30 years'::interval;
Recheck Cond: (a = '@ 30 years'::interval)
-> Bitmap Index Scan on brin_interval_test_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = '@ 30 years'::interval)
(4 rows)
Index Searches: 1
(5 rows)
DROP TABLE brin_interval_test;
RESET enable_seqscan;

49
src/test/regress/expected/memoize.out
Unescape View File

@ -22,8 +22,9 @@ begin
ln := regexp_replace(ln, 'Evictions: 0', 'Evictions: Zero');
ln := regexp_replace(ln, 'Evictions: \d+', 'Evictions: N');
ln := regexp_replace(ln, 'Memory Usage: \d+', 'Memory Usage: N');
ln := regexp_replace(ln, 'Heap Fetches: \d+', 'Heap Fetches: N');
ln := regexp_replace(ln, 'loops=\d+', 'loops=N');
ln := regexp_replace(ln, 'Heap Fetches: \d+', 'Heap Fetches: N');
ln := regexp_replace(ln, 'loops=\d+', 'loops=N');
ln := regexp_replace(ln, 'Index Searches: \d+', 'Index Searches: N');
return next ln;
end loop;
end;
@ -49,7 +50,8 @@ WHERE t2.unique1 < 1000;', false);
-> Index Only Scan using tenk1_unique1 on tenk1 t1 (actual rows=1.00 loops=N)
Index Cond: (unique1 = t2.twenty)
Heap Fetches: N
(12 rows)
Index Searches: N
(13 rows)
-- And check we get the expected results.
SELECT COUNT(*),AVG(t1.unique1) FROM tenk1 t1
@ -80,7 +82,8 @@ WHERE t1.unique1 < 1000;', false);
-> Index Only Scan using tenk1_unique1 on tenk1 t2 (actual rows=1.00 loops=N)
Index Cond: (unique1 = t1.twenty)
Heap Fetches: N
(12 rows)
Index Searches: N
(13 rows)
-- And check we get the expected results.
SELECT COUNT(*),AVG(t2.unique1) FROM tenk1 t1,
@ -106,6 +109,7 @@ WHERE t1.unique1 < 10;', false);
-> Nested Loop Left Join (actual rows=20.00 loops=N)
-> Index Scan using tenk1_unique1 on tenk1 t1 (actual rows=10.00 loops=N)
Index Cond: (unique1 < 10)
Index Searches: N
-> Memoize (actual rows=2.00 loops=N)
Cache Key: t1.two
Cache Mode: binary
@ -115,7 +119,8 @@ WHERE t1.unique1 < 10;', false);
Rows Removed by Filter: 2
-> Index Scan using tenk1_unique1 on tenk1 t2_1 (actual rows=4.00 loops=N)
Index Cond: (unique1 < 4)
(13 rows)
Index Searches: N
(15 rows)
-- And check we get the expected results.
SELECT COUNT(*),AVG(t2.t1two) FROM tenk1 t1 LEFT JOIN
@ -149,7 +154,8 @@ WHERE s.c1 = s.c2 AND t1.unique1 < 1000;', false);
Filter: ((t1.two + 1) = unique1)
Rows Removed by Filter: 9999
Heap Fetches: N
(13 rows)
Index Searches: N
(14 rows)
-- And check we get the expected results.
SELECT COUNT(*), AVG(t1.twenty) FROM tenk1 t1 LEFT JOIN
@ -219,7 +225,8 @@ ON t1.x = t2.t::numeric AND t1.t::numeric = t2.x;', false);
Index Cond: (x = (t1.t)::numeric)
Filter: (t1.x = (t)::numeric)
Heap Fetches: N
(10 rows)
Index Searches: N
(11 rows)
DROP TABLE expr_key;
-- Reduce work_mem and hash_mem_multiplier so that we see some cache evictions
@ -246,7 +253,8 @@ WHERE t2.unique1 < 1200;', true);
-> Index Only Scan using tenk1_unique1 on tenk1 t1 (actual rows=1.00 loops=N)
Index Cond: (unique1 = t2.thousand)
Heap Fetches: N
(12 rows)
Index Searches: N
(13 rows)
CREATE TABLE flt (f float);
CREATE INDEX flt_f_idx ON flt (f);
@ -261,6 +269,7 @@ SELECT * FROM flt f1 INNER JOIN flt f2 ON f1.f = f2.f;', false);
Nested Loop (actual rows=4.00 loops=N)
-> Index Only Scan using flt_f_idx on flt f1 (actual rows=2.00 loops=N)
Heap Fetches: N
Index Searches: N
-> Memoize (actual rows=2.00 loops=N)
Cache Key: f1.f
Cache Mode: logical
@ -268,7 +277,8 @@ SELECT * FROM flt f1 INNER JOIN flt f2 ON f1.f = f2.f;', false);
-> Index Only Scan using flt_f_idx on flt f2 (actual rows=2.00 loops=N)
Index Cond: (f = f1.f)
Heap Fetches: N
(10 rows)
Index Searches: N
(12 rows)
-- Ensure memoize operates in binary mode
SELECT explain_memoize('
@ -278,6 +288,7 @@ SELECT * FROM flt f1 INNER JOIN flt f2 ON f1.f >= f2.f;', false);
Nested Loop (actual rows=4.00 loops=N)
-> Index Only Scan using flt_f_idx on flt f1 (actual rows=2.00 loops=N)
Heap Fetches: N
Index Searches: N
-> Memoize (actual rows=2.00 loops=N)
Cache Key: f1.f
Cache Mode: binary
@ -285,7 +296,8 @@ SELECT * FROM flt f1 INNER JOIN flt f2 ON f1.f >= f2.f;', false);
-> Index Only Scan using flt_f_idx on flt f2 (actual rows=2.00 loops=N)
Index Cond: (f <= f1.f)
Heap Fetches: N
(10 rows)
Index Searches: N
(12 rows)
DROP TABLE flt;
-- Exercise Memoize in binary mode with a large fixed width type and a
@ -311,7 +323,8 @@ SELECT * FROM strtest s1 INNER JOIN strtest s2 ON s1.n >= s2.n;', false);
Hits: 3 Misses: 3 Evictions: Zero Overflows: 0 Memory Usage: NkB
-> Index Scan using strtest_n_idx on strtest s2 (actual rows=4.00 loops=N)
Index Cond: (n <= s1.n)
(9 rows)
Index Searches: N
(10 rows)
-- Ensure we get 3 hits and 3 misses
SELECT explain_memoize('
@ -327,7 +340,8 @@ SELECT * FROM strtest s1 INNER JOIN strtest s2 ON s1.t >= s2.t;', false);
Hits: 3 Misses: 3 Evictions: Zero Overflows: 0 Memory Usage: NkB
-> Index Scan using strtest_t_idx on strtest s2 (actual rows=4.00 loops=N)
Index Cond: (t <= s1.t)
(9 rows)
Index Searches: N
(10 rows)
DROP TABLE strtest;
-- Ensure memoize works with partitionwise join
@ -348,6 +362,7 @@ SELECT * FROM prt t1 INNER JOIN prt t2 ON t1.a = t2.a;', false);
-> Nested Loop (actual rows=16.00 loops=N)
-> Index Only Scan using iprt_p1_a on prt_p1 t1_1 (actual rows=4.00 loops=N)
Heap Fetches: N
Index Searches: N
-> Memoize (actual rows=4.00 loops=N)
Cache Key: t1_1.a
Cache Mode: logical
@ -355,9 +370,11 @@ SELECT * FROM prt t1 INNER JOIN prt t2 ON t1.a = t2.a;', false);
-> Index Only Scan using iprt_p1_a on prt_p1 t2_1 (actual rows=4.00 loops=N)
Index Cond: (a = t1_1.a)
Heap Fetches: N
Index Searches: N
-> Nested Loop (actual rows=16.00 loops=N)
-> Index Only Scan using iprt_p2_a on prt_p2 t1_2 (actual rows=4.00 loops=N)
Heap Fetches: N
Index Searches: N
-> Memoize (actual rows=4.00 loops=N)
Cache Key: t1_2.a
Cache Mode: logical
@ -365,7 +382,8 @@ SELECT * FROM prt t1 INNER JOIN prt t2 ON t1.a = t2.a;', false);
-> Index Only Scan using iprt_p2_a on prt_p2 t2_2 (actual rows=4.00 loops=N)
Index Cond: (a = t1_2.a)
Heap Fetches: N
(21 rows)
Index Searches: N
(25 rows)
-- Ensure memoize works with parameterized union-all Append path
SET enable_partitionwise_join TO off;
@ -378,6 +396,7 @@ ON t1.a = t2.a;', false);
Nested Loop (actual rows=16.00 loops=N)
-> Index Only Scan using iprt_p1_a on prt_p1 t1 (actual rows=4.00 loops=N)
Heap Fetches: N
Index Searches: N
-> Memoize (actual rows=4.00 loops=N)
Cache Key: t1.a
Cache Mode: logical
@ -386,10 +405,12 @@ ON t1.a = t2.a;', false);
-> Index Only Scan using iprt_p1_a on prt_p1 (actual rows=4.00 loops=N)
Index Cond: (a = t1.a)
Heap Fetches: N
Index Searches: N
-> Index Only Scan using iprt_p2_a on prt_p2 (actual rows=0.00 loops=N)
Index Cond: (a = t1.a)
Heap Fetches: N
(14 rows)
Index Searches: N
(17 rows)
DROP TABLE prt;
RESET enable_partitionwise_join;

100
src/test/regress/expected/partition_prune.out
Unescape View File

@ -2369,6 +2369,10 @@ begin
ln := regexp_replace(ln, 'Workers Launched: \d+', 'Workers Launched: N');
ln := regexp_replace(ln, 'actual rows=\d+(?:\.\d+)? loops=\d+', 'actual rows=N loops=N');
ln := regexp_replace(ln, 'Rows Removed by Filter: \d+', 'Rows Removed by Filter: N');
perform regexp_matches(ln, 'Index Searches: \d+');
if found then
continue;
end if;
return next ln;
end loop;
end;
@ -2686,47 +2690,56 @@ select * from ab where a = (select max(a) from lprt_a) and b = (select max(a)-1
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a1_b1_a_idx (never executed)
Index Cond: (a = (InitPlan 1).col1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a1_b2 ab_2 (never executed)
Recheck Cond: (a = (InitPlan 1).col1)
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a1_b2_a_idx (never executed)
Index Cond: (a = (InitPlan 1).col1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a1_b3 ab_3 (never executed)
Recheck Cond: (a = (InitPlan 1).col1)
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a1_b3_a_idx (never executed)
Index Cond: (a = (InitPlan 1).col1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a2_b1 ab_4 (never executed)
Recheck Cond: (a = (InitPlan 1).col1)
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a2_b1_a_idx (never executed)
Index Cond: (a = (InitPlan 1).col1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a2_b2 ab_5 (never executed)
Recheck Cond: (a = (InitPlan 1).col1)
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a2_b2_a_idx (never executed)
Index Cond: (a = (InitPlan 1).col1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a2_b3 ab_6 (never executed)
Recheck Cond: (a = (InitPlan 1).col1)
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a2_b3_a_idx (never executed)
Index Cond: (a = (InitPlan 1).col1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a3_b1 ab_7 (never executed)
Recheck Cond: (a = (InitPlan 1).col1)
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a3_b1_a_idx (never executed)
Index Cond: (a = (InitPlan 1).col1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a3_b2 ab_8 (actual rows=0.00 loops=1)
Recheck Cond: (a = (InitPlan 1).col1)
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a3_b2_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = (InitPlan 1).col1)
Index Searches: 1
-> Bitmap Heap Scan on ab_a3_b3 ab_9 (never executed)
Recheck Cond: (a = (InitPlan 1).col1)
Filter: (b = (InitPlan 2).col1)
-> Bitmap Index Scan on ab_a3_b3_a_idx (never executed)
Index Cond: (a = (InitPlan 1).col1)
(52 rows)
Index Searches: 0
(61 rows)
-- Test run-time partition pruning with UNION ALL parents
explain (analyze, costs off, summary off, timing off, buffers off)
@ -2742,16 +2755,19 @@ select * from (select * from ab where a = 1 union all select * from ab) ab where
Filter: (b = (InitPlan 1).col1)
-> Bitmap Index Scan on ab_a1_b1_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = 1)
Index Searches: 1
-> Bitmap Heap Scan on ab_a1_b2 ab_12 (never executed)
Recheck Cond: (a = 1)
Filter: (b = (InitPlan 1).col1)
-> Bitmap Index Scan on ab_a1_b2_a_idx (never executed)
Index Cond: (a = 1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a1_b3 ab_13 (never executed)
Recheck Cond: (a = 1)
Filter: (b = (InitPlan 1).col1)
-> Bitmap Index Scan on ab_a1_b3_a_idx (never executed)
Index Cond: (a = 1)
Index Searches: 0
-> Seq Scan on ab_a1_b1 ab_1 (actual rows=0.00 loops=1)
Filter: (b = (InitPlan 1).col1)
-> Seq Scan on ab_a1_b2 ab_2 (never executed)
@ -2770,7 +2786,7 @@ select * from (select * from ab where a = 1 union all select * from ab) ab where
Filter: (b = (InitPlan 1).col1)
-> Seq Scan on ab_a3_b3 ab_9 (never executed)
Filter: (b = (InitPlan 1).col1)
(37 rows)
(40 rows)
-- A case containing a UNION ALL with a non-partitioned child.
explain (analyze, costs off, summary off, timing off, buffers off)
@ -2786,16 +2802,19 @@ select * from (select * from ab where a = 1 union all (values(10,5)) union all s
Filter: (b = (InitPlan 1).col1)
-> Bitmap Index Scan on ab_a1_b1_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = 1)
Index Searches: 1
-> Bitmap Heap Scan on ab_a1_b2 ab_12 (never executed)
Recheck Cond: (a = 1)
Filter: (b = (InitPlan 1).col1)
-> Bitmap Index Scan on ab_a1_b2_a_idx (never executed)
Index Cond: (a = 1)
Index Searches: 0
-> Bitmap Heap Scan on ab_a1_b3 ab_13 (never executed)
Recheck Cond: (a = 1)
Filter: (b = (InitPlan 1).col1)
-> Bitmap Index Scan on ab_a1_b3_a_idx (never executed)
Index Cond: (a = 1)
Index Searches: 0
-> Result (actual rows=0.00 loops=1)
One-Time Filter: (5 = (InitPlan 1).col1)
-> Seq Scan on ab_a1_b1 ab_1 (actual rows=0.00 loops=1)
@ -2816,7 +2835,7 @@ select * from (select * from ab where a = 1 union all (values(10,5)) union all s
Filter: (b = (InitPlan 1).col1)
-> Seq Scan on ab_a3_b3 ab_9 (never executed)
Filter: (b = (InitPlan 1).col1)
(39 rows)
(42 rows)
-- Another UNION ALL test, but containing a mix of exec init and exec run-time pruning.
create table xy_1 (x int, y int);
@ -2887,16 +2906,19 @@ update ab_a1 set b = 3 from ab where ab.a = 1 and ab.a = ab_a1.a;');
Recheck Cond: (a = 1)
-> Bitmap Index Scan on ab_a1_b1_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = 1)
Index Searches: 1
-> Bitmap Heap Scan on ab_a1_b2 ab_a1_2 (actual rows=1.00 loops=1)
Recheck Cond: (a = 1)
Heap Blocks: exact=1
-> Bitmap Index Scan on ab_a1_b2_a_idx (actual rows=1.00 loops=1)
Index Cond: (a = 1)
Index Searches: 1
-> Bitmap Heap Scan on ab_a1_b3 ab_a1_3 (actual rows=0.00 loops=1)
Recheck Cond: (a = 1)
Heap Blocks: exact=1
-> Bitmap Index Scan on ab_a1_b3_a_idx (actual rows=1.00 loops=1)
Index Cond: (a = 1)
Index Searches: 1
-> Materialize (actual rows=1.00 loops=1)
Storage: Memory Maximum Storage: NkB
-> Append (actual rows=1.00 loops=1)
@ -2904,17 +2926,20 @@ update ab_a1 set b = 3 from ab where ab.a = 1 and ab.a = ab_a1.a;');
Recheck Cond: (a = 1)
-> Bitmap Index Scan on ab_a1_b1_a_idx (actual rows=0.00 loops=1)
Index Cond: (a = 1)
Index Searches: 1
-> Bitmap Heap Scan on ab_a1_b2 ab_2 (actual rows=1.00 loops=1)
Recheck Cond: (a = 1)
Heap Blocks: exact=1
-> Bitmap Index Scan on ab_a1_b2_a_idx (actual rows=1.00 loops=1)
Index Cond: (a = 1)
Index Searches: 1
-> Bitmap Heap Scan on ab_a1_b3 ab_3 (actual rows=0.00 loops=1)
Recheck Cond: (a = 1)
Heap Blocks: exact=1
-> Bitmap Index Scan on ab_a1_b3_a_idx (actual rows=1.00 loops=1)
Index Cond: (a = 1)
(37 rows)
Index Searches: 1
(43 rows)
table ab;
a | b
@ -2990,17 +3015,23 @@ select * from tbl1 join tprt on tbl1.col1 > tprt.col1;
-> Append (actual rows=3.00 loops=2)
-> Index Scan using tprt1_idx on tprt_1 (actual rows=2.00 loops=2)
Index Cond: (col1 < tbl1.col1)
Index Searches: 2
-> Index Scan using tprt2_idx on tprt_2 (actual rows=2.00 loops=1)
Index Cond: (col1 < tbl1.col1)
Index Searches: 1
-> Index Scan using tprt3_idx on tprt_3 (never executed)
Index Cond: (col1 < tbl1.col1)
Index Searches: 0
-> Index Scan using tprt4_idx on tprt_4 (never executed)
Index Cond: (col1 < tbl1.col1)
Index Searches: 0
-> Index Scan using tprt5_idx on tprt_5 (never executed)
Index Cond: (col1 < tbl1.col1)
Index Searches: 0
-> Index Scan using tprt6_idx on tprt_6 (never executed)
Index Cond: (col1 < tbl1.col1)
(15 rows)
Index Searches: 0
(21 rows)
explain (analyze, costs off, summary off, timing off, buffers off)
select * from tbl1 join tprt on tbl1.col1 = tprt.col1;
@ -3011,17 +3042,23 @@ select * from tbl1 join tprt on tbl1.col1 = tprt.col1;
-> Append (actual rows=1.00 loops=2)
-> Index Scan using tprt1_idx on tprt_1 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt2_idx on tprt_2 (actual rows=1.00 loops=2)
Index Cond: (col1 = tbl1.col1)
Index Searches: 2
-> Index Scan using tprt3_idx on tprt_3 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt4_idx on tprt_4 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt5_idx on tprt_5 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt6_idx on tprt_6 (never executed)
Index Cond: (col1 = tbl1.col1)
(15 rows)
Index Searches: 0
(21 rows)
select tbl1.col1, tprt.col1 from tbl1
inner join tprt on tbl1.col1 > tprt.col1
@ -3056,17 +3093,23 @@ select * from tbl1 inner join tprt on tbl1.col1 > tprt.col1;
-> Append (actual rows=4.60 loops=5)
-> Index Scan using tprt1_idx on tprt_1 (actual rows=2.00 loops=5)
Index Cond: (col1 < tbl1.col1)
Index Searches: 5
-> Index Scan using tprt2_idx on tprt_2 (actual rows=2.75 loops=4)
Index Cond: (col1 < tbl1.col1)
Index Searches: 4
-> Index Scan using tprt3_idx on tprt_3 (actual rows=1.00 loops=2)
Index Cond: (col1 < tbl1.col1)
Index Searches: 2
-> Index Scan using tprt4_idx on tprt_4 (never executed)
Index Cond: (col1 < tbl1.col1)
Index Searches: 0
-> Index Scan using tprt5_idx on tprt_5 (never executed)
Index Cond: (col1 < tbl1.col1)
Index Searches: 0
-> Index Scan using tprt6_idx on tprt_6 (never executed)
Index Cond: (col1 < tbl1.col1)
(15 rows)
Index Searches: 0
(21 rows)
explain (analyze, costs off, summary off, timing off, buffers off)
select * from tbl1 inner join tprt on tbl1.col1 = tprt.col1;
@ -3077,17 +3120,23 @@ select * from tbl1 inner join tprt on tbl1.col1 = tprt.col1;
-> Append (actual rows=0.60 loops=5)
-> Index Scan using tprt1_idx on tprt_1 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt2_idx on tprt_2 (actual rows=1.00 loops=2)
Index Cond: (col1 = tbl1.col1)
Index Searches: 2
-> Index Scan using tprt3_idx on tprt_3 (actual rows=0.33 loops=3)
Index Cond: (col1 = tbl1.col1)
Index Searches: 3
-> Index Scan using tprt4_idx on tprt_4 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt5_idx on tprt_5 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt6_idx on tprt_6 (never executed)
Index Cond: (col1 = tbl1.col1)
(15 rows)
Index Searches: 0
(21 rows)
select tbl1.col1, tprt.col1 from tbl1
inner join tprt on tbl1.col1 > tprt.col1
@ -3141,17 +3190,23 @@ select * from tbl1 join tprt on tbl1.col1 < tprt.col1;
-> Append (actual rows=1.00 loops=1)
-> Index Scan using tprt1_idx on tprt_1 (never executed)
Index Cond: (col1 > tbl1.col1)
Index Searches: 0
-> Index Scan using tprt2_idx on tprt_2 (never executed)
Index Cond: (col1 > tbl1.col1)
Index Searches: 0
-> Index Scan using tprt3_idx on tprt_3 (never executed)
Index Cond: (col1 > tbl1.col1)
Index Searches: 0
-> Index Scan using tprt4_idx on tprt_4 (never executed)
Index Cond: (col1 > tbl1.col1)
Index Searches: 0
-> Index Scan using tprt5_idx on tprt_5 (never executed)
Index Cond: (col1 > tbl1.col1)
Index Searches: 0
-> Index Scan using tprt6_idx on tprt_6 (actual rows=1.00 loops=1)
Index Cond: (col1 > tbl1.col1)
(15 rows)
Index Searches: 1
(21 rows)
select tbl1.col1, tprt.col1 from tbl1
inner join tprt on tbl1.col1 < tprt.col1
@ -3173,17 +3228,23 @@ select * from tbl1 join tprt on tbl1.col1 = tprt.col1;
-> Append (actual rows=0.00 loops=1)
-> Index Scan using tprt1_idx on tprt_1 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt2_idx on tprt_2 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt3_idx on tprt_3 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt4_idx on tprt_4 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt5_idx on tprt_5 (never executed)
Index Cond: (col1 = tbl1.col1)
Index Searches: 0
-> Index Scan using tprt6_idx on tprt_6 (never executed)
Index Cond: (col1 = tbl1.col1)
(15 rows)
Index Searches: 0
(21 rows)
select tbl1.col1, tprt.col1 from tbl1
inner join tprt on tbl1.col1 = tprt.col1
@ -3513,10 +3574,12 @@ explain (analyze, costs off, summary off, timing off, buffers off) execute mt_q1
-> Index Scan using ma_test_p2_b_idx on ma_test_p2 ma_test_1 (actual rows=1.00 loops=1)
Filter: ((a >= $1) AND ((a % 10) = 5))
Rows Removed by Filter: 9
Index Searches: 1
-> Index Scan using ma_test_p3_b_idx on ma_test_p3 ma_test_2 (actual rows=1.00 loops=1)
Filter: ((a >= $1) AND ((a % 10) = 5))
Rows Removed by Filter: 9
(9 rows)
Index Searches: 1
(11 rows)
execute mt_q1(15);
a
@ -3534,7 +3597,8 @@ explain (analyze, costs off, summary off, timing off, buffers off) execute mt_q1
-> Index Scan using ma_test_p3_b_idx on ma_test_p3 ma_test_1 (actual rows=1.00 loops=1)
Filter: ((a >= $1) AND ((a % 10) = 5))
Rows Removed by Filter: 9
(6 rows)
Index Searches: 1
(7 rows)
execute mt_q1(25);
a
@ -3582,13 +3646,17 @@ explain (analyze, costs off, summary off, timing off, buffers off) select * from
-> Limit (actual rows=1.00 loops=1)
-> Index Scan using ma_test_p2_b_idx on ma_test_p2 (actual rows=1.00 loops=1)
Index Cond: (b IS NOT NULL)
Index Searches: 1
-> Index Scan using ma_test_p1_b_idx on ma_test_p1 ma_test_1 (never executed)
Filter: (a >= (InitPlan 2).col1)
Index Searches: 0
-> Index Scan using ma_test_p2_b_idx on ma_test_p2 ma_test_2 (actual rows=10.00 loops=1)
Filter: (a >= (InitPlan 2).col1)
Index Searches: 1
-> Index Scan using ma_test_p3_b_idx on ma_test_p3 ma_test_3 (actual rows=10.00 loops=1)
Filter: (a >= (InitPlan 2).col1)
(14 rows)
Index Searches: 1
(18 rows)
reset enable_seqscan;
reset enable_sort;
@ -4159,13 +4227,17 @@ select * from rangep where b IN((select 1),(select 2)) order by a;
Sort Key: rangep_2.a
-> Index Scan using rangep_0_to_100_1_a_idx on rangep_0_to_100_1 rangep_2 (actual rows=0.00 loops=1)
Filter: (b = ANY (ARRAY[(InitPlan 1).col1, (InitPlan 2).col1]))
Index Searches: 1
-> Index Scan using rangep_0_to_100_2_a_idx on rangep_0_to_100_2 rangep_3 (actual rows=0.00 loops=1)
Filter: (b = ANY (ARRAY[(InitPlan 1).col1, (InitPlan 2).col1]))
Index Searches: 1
-> Index Scan using rangep_0_to_100_3_a_idx on rangep_0_to_100_3 rangep_4 (never executed)
Filter: (b = ANY (ARRAY[(InitPlan 1).col1, (InitPlan 2).col1]))
Index Searches: 0
-> Index Scan using rangep_100_to_200_a_idx on rangep_100_to_200 rangep_5 (actual rows=0.00 loops=1)
Filter: (b = ANY (ARRAY[(InitPlan 1).col1, (InitPlan 2).col1]))
(15 rows)
Index Searches: 1
(19 rows)
reset enable_sort;
drop table rangep;

3
src/test/regress/expected/select.out
Unescape View File

@ -764,7 +764,8 @@ select * from onek2 where unique2 = 11 and stringu1 = 'ATAAAA';
Index Scan using onek2_u2_prtl on onek2 (actual rows=1.00 loops=1)
Index Cond: (unique2 = 11)
Filter: (stringu1 = 'ATAAAA'::name)
(3 rows)
Index Searches: 1
(4 rows)
explain (costs off)
select unique2 from onek2 where unique2 = 11 and stringu1 = 'ATAAAA';

5
src/test/regress/sql/memoize.sql
Unescape View File

@ -23,8 +23,9 @@ begin
ln := regexp_replace(ln, 'Evictions: 0', 'Evictions: Zero');
ln := regexp_replace(ln, 'Evictions: \d+', 'Evictions: N');
ln := regexp_replace(ln, 'Memory Usage: \d+', 'Memory Usage: N');
ln := regexp_replace(ln, 'Heap Fetches: \d+', 'Heap Fetches: N');
ln := regexp_replace(ln, 'loops=\d+', 'loops=N');
ln := regexp_replace(ln, 'Heap Fetches: \d+', 'Heap Fetches: N');
ln := regexp_replace(ln, 'loops=\d+', 'loops=N');
ln := regexp_replace(ln, 'Index Searches: \d+', 'Index Searches: N');
return next ln;
end loop;
end;

4
src/test/regress/sql/partition_prune.sql
Unescape View File

@ -588,6 +588,10 @@ begin
ln := regexp_replace(ln, 'Workers Launched: \d+', 'Workers Launched: N');
ln := regexp_replace(ln, 'actual rows=\d+(?:\.\d+)? loops=\d+', 'actual rows=N loops=N');
ln := regexp_replace(ln, 'Rows Removed by Filter: \d+', 'Rows Removed by Filter: N');
perform regexp_matches(ln, 'Index Searches: \d+');
if found then
continue;
end if;
return next ln;
end loop;
end;

2
src/tools/pgindent/typedefs.list
Unescape View File

@ -1238,6 +1238,7 @@ IndexPath
IndexRuntimeKeyInfo
IndexScan
IndexScanDesc
IndexScanInstrumentation
IndexScanState
IndexStateFlagsAction
IndexStmt
@ -2666,6 +2667,7 @@ SharedExecutorInstrumentation
SharedFileSet
SharedHashInfo
SharedIncrementalSortInfo
SharedIndexScanInstrumentation
SharedInvalCatalogMsg
SharedInvalCatcacheMsg
SharedInvalRelcacheMsg

Write Preview
Loading…
Cancel
Save