public inbox for [email protected]
help / color / mirror / Atom feed[PATCH v4 2/3] Allow CREATE INDEX CONCURRENTLY on partitioned table
3+ messages / 3 participants
[nested] [flat]
* [PATCH v4 2/3] Allow CREATE INDEX CONCURRENTLY on partitioned table
@ 2020-06-06 22:42 Justin Pryzby <[email protected]>
0 siblings, 0 replies; 3+ messages in thread
From: Justin Pryzby @ 2020-06-06 22:42 UTC (permalink / raw)
Note, this effectively reverts 050098b14, so take care to not reintroduce the
bug it fixed.
---
doc/src/sgml/ref/create_index.sgml | 9 --
src/backend/commands/indexcmds.c | 109 +++++++++++++++++++------
src/test/regress/expected/indexing.out | 57 ++++++++++++-
src/test/regress/sql/indexing.sql | 16 +++-
4 files changed, 150 insertions(+), 41 deletions(-)
diff --git a/doc/src/sgml/ref/create_index.sgml b/doc/src/sgml/ref/create_index.sgml
index 33aa64e81d..c780dc9547 100644
--- a/doc/src/sgml/ref/create_index.sgml
+++ b/doc/src/sgml/ref/create_index.sgml
@@ -657,15 +657,6 @@ Indexes:
cannot.
</para>
- <para>
- Concurrent builds for indexes on partitioned tables are currently not
- supported. However, you may concurrently build the index on each
- partition individually and then finally create the partitioned index
- non-concurrently in order to reduce the time where writes to the
- partitioned table will be locked out. In this case, building the
- partitioned index is a metadata only operation.
- </para>
-
</refsect2>
</refsect1>
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index df3e567acb..291046cb16 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -653,17 +653,6 @@ DefineIndex(Oid relationId,
partitioned = rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE;
if (partitioned)
{
- /*
- * Note: we check 'stmt->concurrent' rather than 'concurrent', so that
- * the error is thrown also for temporary tables. Seems better to be
- * consistent, even though we could do it on temporary table because
- * we're not actually doing it concurrently.
- */
- if (stmt->concurrent)
- ereport(ERROR,
- (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
- errmsg("cannot create index on partitioned table \"%s\" concurrently",
- RelationGetRelationName(rel))));
if (stmt->excludeOpNames)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
@@ -1098,6 +1087,9 @@ DefineIndex(Oid relationId,
if (pd->nparts != 0)
flags |= INDEX_CREATE_INVALID;
}
+ else if (concurrent && OidIsValid(parentIndexId))
+ /* Initial concurrent build index partition as invalid */
+ flags |= INDEX_CREATE_INVALID;
if (stmt->deferrable)
constr_flags |= INDEX_CONSTR_CREATE_DEFERRABLE;
@@ -1140,6 +1132,10 @@ DefineIndex(Oid relationId,
CreateComments(indexRelationId, RelationRelationId, 0,
stmt->idxcomment);
+ /* save lockrelid and locktag for below */
+ heaprelid = rel->rd_lockInfo.lockRelId;
+ SET_LOCKTAG_RELATION(heaplocktag, heaprelid.dbId, heaprelid.relId);
+
if (partitioned)
{
/*
@@ -1150,8 +1146,17 @@ DefineIndex(Oid relationId,
*/
if (!stmt->relation || stmt->relation->inh)
{
+ /*
+ * Need to close the relation before recursing into children, so
+ * copy needed data into a longlived context.
+ */
+
+ MemoryContext ind_context = AllocSetContextCreate(PortalContext, "CREATE INDEX",
+ ALLOCSET_DEFAULT_SIZES);
+ MemoryContext oldcontext = MemoryContextSwitchTo(ind_context);
PartitionDesc partdesc = RelationGetPartitionDesc(rel);
int nparts = partdesc->nparts;
+ char *relname = pstrdup(RelationGetRelationName(rel));
Oid *part_oids = palloc(sizeof(Oid) * nparts);
bool invalidate_parent = false;
TupleDesc parentDesc;
@@ -1161,8 +1166,10 @@ DefineIndex(Oid relationId,
nparts);
memcpy(part_oids, partdesc->oids, sizeof(Oid) * nparts);
+ parentDesc = CreateTupleDescCopy(RelationGetDescr(rel));
+ table_close(rel, NoLock);
+ MemoryContextSwitchTo(oldcontext);
- parentDesc = RelationGetDescr(rel);
opfamOids = palloc(sizeof(Oid) * numberOfKeyAttributes);
for (i = 0; i < numberOfKeyAttributes; i++)
opfamOids[i] = get_opclass_family(classObjectId[i]);
@@ -1197,18 +1204,20 @@ DefineIndex(Oid relationId,
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("cannot create unique index on partitioned table \"%s\"",
- RelationGetRelationName(rel)),
+ relname),
errdetail("Table \"%s\" contains partitions that are foreign tables.",
- RelationGetRelationName(rel))));
+ relname)));
table_close(childrel, lockmode);
continue;
}
+ oldcontext = MemoryContextSwitchTo(ind_context);
childidxs = RelationGetIndexList(childrel);
attmap =
build_attrmap_by_name(RelationGetDescr(childrel),
parentDesc);
+ MemoryContextSwitchTo(oldcontext);
foreach(cell, childidxs)
{
@@ -1334,10 +1343,16 @@ DefineIndex(Oid relationId,
createdConstraintId,
is_alter_table, check_rights, check_not_in_use,
skip_build, quiet);
+ if (concurrent)
+ {
+ PushActiveSnapshot(GetTransactionSnapshot());
+ invalidate_parent = true;
+ }
}
- pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
- i + 1);
+ if (!concurrent)
+ pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
+ i + 1);
free_attrmap(attmap);
}
@@ -1364,23 +1379,72 @@ DefineIndex(Oid relationId,
table_close(pg_index, RowExclusiveLock);
heap_freetuple(newtup);
}
+ } else
+ table_close(rel, NoLock);
+
+ if (concurrent)
+ {
+ List *childs;
+ ListCell *lc;
+ int npart = 0;
+
+ /* Reindex invalid child indexes created earlier */
+ MemoryContext ind_context = AllocSetContextCreate(PortalContext, "CREATE INDEX",
+ ALLOCSET_DEFAULT_SIZES);
+ MemoryContext oldcontext = MemoryContextSwitchTo(ind_context);
+ childs = find_inheritance_children(indexRelationId, NoLock);
+ MemoryContextSwitchTo(oldcontext);
+
+ /* Make the catalog changes visible to get_partition_parent */
+ CommandCounterIncrement();
+
+ foreach (lc, childs)
+ {
+ Oid indexrelid = lfirst_oid(lc);
+ Relation cldidx;
+ bool isvalid;
+
+ if (!OidIsValid(parentIndexId))
+ pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
+ npart++);
+
+ cldidx = index_open(indexrelid, ShareUpdateExclusiveLock);
+ isvalid = cldidx->rd_index->indisvalid;
+ index_close(cldidx, NoLock);
+ if (isvalid)
+ continue;
+
+ /* This may be a partitioned index, which is fine too */
+ ReindexRelationConcurrently(indexrelid, 0);
+ PushActiveSnapshot(GetTransactionSnapshot());
+ }
+
+ PopActiveSnapshot();
+ CommitTransactionCommand();
+ StartTransactionCommand();
+
+ /*
+ * CIC needs to mark a partitioned index as VALID, which itself
+ * requires setting READY, which is unset for CIC (even though
+ * it's meaningless for an index without storage).
+ */
+ index_set_state_flags(indexRelationId, INDEX_CREATE_SET_READY);
+ CommandCounterIncrement();
+ index_set_state_flags(indexRelationId, INDEX_CREATE_SET_VALID);
}
/*
* Indexes on partitioned tables are not themselves built, so we're
* done here.
*/
- table_close(rel, NoLock);
if (!OidIsValid(parentIndexId))
pgstat_progress_end_command();
return address;
}
+ table_close(rel, NoLock);
if (!concurrent)
{
- /* Close the heap and we're done, in the non-concurrent case */
- table_close(rel, NoLock);
-
/* If this is the top-level index, we're done. */
if (!OidIsValid(parentIndexId))
pgstat_progress_end_command();
@@ -1388,11 +1452,6 @@ DefineIndex(Oid relationId,
return address;
}
- /* save lockrelid and locktag for below, then close rel */
- heaprelid = rel->rd_lockInfo.lockRelId;
- SET_LOCKTAG_RELATION(heaplocktag, heaprelid.dbId, heaprelid.relId);
- table_close(rel, NoLock);
-
/*
* For a concurrent build, it's important to make the catalog entries
* visible to other transactions before we start to build the index. That
diff --git a/src/test/regress/expected/indexing.out b/src/test/regress/expected/indexing.out
index f78865ef81..1ae58e110f 100644
--- a/src/test/regress/expected/indexing.out
+++ b/src/test/regress/expected/indexing.out
@@ -50,11 +50,60 @@ select relname, relkind, relhassubclass, inhparent::regclass
(8 rows)
drop table idxpart;
--- Some unsupported features
+-- CIC on partitioned table
create table idxpart (a int, b int, c text) partition by range (a);
-create table idxpart1 partition of idxpart for values from (0) to (10);
-create index concurrently on idxpart (a);
-ERROR: cannot create index on partitioned table "idxpart" concurrently
+create table idxpart1 partition of idxpart for values from (0) to (10) partition by range(a);
+create table idxpart11 partition of idxpart1 for values from (0) to (10) partition by range(a);
+create table idxpart2 partition of idxpart for values from (10) to (20);
+insert into idxpart2 values(10),(10); -- not unique
+create index concurrently on idxpart (a); -- partitioned
+create index concurrently on idxpart1 (a); -- partitioned and partition
+create index concurrently on idxpart11 (a); -- partitioned and partition, with no leaves
+create index concurrently on idxpart2 (a); -- leaf
+create unique index concurrently on idxpart (a); -- partitioned, unique failure
+ERROR: could not create unique index "idxpart2_a_idx2"
+DETAIL: Key (a)=(10) is duplicated.
+\d idxpart
+ Partitioned table "public.idxpart"
+ Column | Type | Collation | Nullable | Default
+--------+---------+-----------+----------+---------
+ a | integer | | |
+ b | integer | | |
+ c | text | | |
+Partition key: RANGE (a)
+Indexes:
+ "idxpart_a_idx" btree (a)
+ "idxpart_a_idx1" UNIQUE, btree (a) INVALID
+Number of partitions: 2 (Use \d+ to list them.)
+
+\d idxpart1
+ Partitioned table "public.idxpart1"
+ Column | Type | Collation | Nullable | Default
+--------+---------+-----------+----------+---------
+ a | integer | | |
+ b | integer | | |
+ c | text | | |
+Partition of: idxpart FOR VALUES FROM (0) TO (10)
+Partition key: RANGE (a)
+Indexes:
+ "idxpart1_a_idx" btree (a)
+ "idxpart1_a_idx1" btree (a)
+ "idxpart1_a_idx2" UNIQUE, btree (a)
+Number of partitions: 1 (Use \d+ to list them.)
+
+\d idxpart2
+ Table "public.idxpart2"
+ Column | Type | Collation | Nullable | Default
+--------+---------+-----------+----------+---------
+ a | integer | | |
+ b | integer | | |
+ c | text | | |
+Partition of: idxpart FOR VALUES FROM (10) TO (20)
+Indexes:
+ "idxpart2_a_idx" btree (a)
+ "idxpart2_a_idx1" btree (a)
+ "idxpart2_a_idx2" UNIQUE, btree (a) INVALID
+
drop table idxpart;
-- Verify bugfix with query on indexed partitioned table with no partitions
-- https://postgr.es/m/[email protected]
diff --git a/src/test/regress/sql/indexing.sql b/src/test/regress/sql/indexing.sql
index 35d159f41b..d908ee6d17 100644
--- a/src/test/regress/sql/indexing.sql
+++ b/src/test/regress/sql/indexing.sql
@@ -29,10 +29,20 @@ select relname, relkind, relhassubclass, inhparent::regclass
where relname like 'idxpart%' order by relname;
drop table idxpart;
--- Some unsupported features
+-- CIC on partitioned table
create table idxpart (a int, b int, c text) partition by range (a);
-create table idxpart1 partition of idxpart for values from (0) to (10);
-create index concurrently on idxpart (a);
+create table idxpart1 partition of idxpart for values from (0) to (10) partition by range(a);
+create table idxpart11 partition of idxpart1 for values from (0) to (10) partition by range(a);
+create table idxpart2 partition of idxpart for values from (10) to (20);
+insert into idxpart2 values(10),(10); -- not unique
+create index concurrently on idxpart (a); -- partitioned
+create index concurrently on idxpart1 (a); -- partitioned and partition
+create index concurrently on idxpart11 (a); -- partitioned and partition, with no leaves
+create index concurrently on idxpart2 (a); -- leaf
+create unique index concurrently on idxpart (a); -- partitioned, unique failure
+\d idxpart
+\d idxpart1
+\d idxpart2
drop table idxpart;
-- Verify bugfix with query on indexed partitioned table with no partitions
--
2.17.0
--JYK4vJDZwFMowpUq
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v4-0003-Implement-CLUSTER-of-partitioned-table.patch"
^ permalink raw reply [nested|flat] 3+ messages in thread
* Re: Add TLI number to name of files generated by pg_waldump --save-fullpage
@ 2023-06-27 23:47 Michael Paquier <[email protected]>
2023-06-27 23:58 ` Re: Add TLI number to name of files generated by pg_waldump --save-fullpage David Christensen <[email protected]>
0 siblings, 1 reply; 3+ messages in thread
From: Michael Paquier @ 2023-06-27 23:47 UTC (permalink / raw)
To: Kyotaro Horiguchi <[email protected]>; +Cc: [email protected]; [email protected]; [email protected]
On Tue, Jun 27, 2023 at 04:39:52PM +0900, Kyotaro Horiguchi wrote:
> I meant that the name is structured as
> TLIh-TLIl.<tablespace>.<database>.<relnumber>.<blk>._<fork>, which
> appears to be inconsistent with the comment. (And I'm not sure what
> "TLOID" is..)
Well, to be clear, it should not be TLIh-TLIl but LSNh-LSNl :)
I'm OK with these terms for the comments. This is very internal
anyway so anybody using this feature should know what that means.
And yes, the order of the items is wrong, and I agree that TLOID is a
bit confusing once the TLI is added in the set. I have just used
TBLSPCOID as term in the comment, and adjusted the XXX to be about the
LSN numbers.
Adjusted as per the v2 attached.
--
Michael
Attachments:
[text/x-diff] v2-0001-Add-timeline-to-file-names-generated-with-pg_wald.patch (3.5K, ../../[email protected]/2-v2-0001-Add-timeline-to-file-names-generated-with-pg_wald.patch)
download | inline diff:
From f0936a95651f767e0f56ff507db5d5a02c7629b2 Mon Sep 17 00:00:00 2001
From: Michael Paquier <[email protected]>
Date: Wed, 28 Jun 2023 08:46:26 +0900
Subject: [PATCH v2] Add timeline to file names generated with pg_waldump
--save-fullpage
Reported-by: Fujii Masao
---
src/bin/pg_waldump/pg_waldump.c | 3 ++-
src/bin/pg_waldump/t/002_save_fullpage.pl | 9 +++++----
doc/src/sgml/ref/pg_waldump.sgml | 9 ++++++++-
3 files changed, 15 insertions(+), 6 deletions(-)
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index c6d3ae6344..96845e1a1a 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -518,7 +518,8 @@ XLogRecordSaveFPWs(XLogReaderState *record, const char *savepath)
else
pg_fatal("invalid fork number: %u", fork);
- snprintf(filename, MAXPGPATH, "%s/%08X-%08X.%u.%u.%u.%u%s", savepath,
+ snprintf(filename, MAXPGPATH, "%s/%08X-%08X-%08X.%u.%u.%u.%u%s", savepath,
+ record->seg.ws_tli,
LSN_FORMAT_ARGS(record->ReadRecPtr),
rnode.spcOid, rnode.dbOid, rnode.relNumber, blk, forkname);
diff --git a/src/bin/pg_waldump/t/002_save_fullpage.pl b/src/bin/pg_waldump/t/002_save_fullpage.pl
index 831ffdefef..f0725805f2 100644
--- a/src/bin/pg_waldump/t/002_save_fullpage.pl
+++ b/src/bin/pg_waldump/t/002_save_fullpage.pl
@@ -79,15 +79,16 @@ $node->command_ok(
'pg_waldump with --save-fullpage runs');
# This regexp will match filenames formatted as:
-# XXXXXXXX-XXXXXXXX.DBOID.TLOID.NODEOID.dd_fork with the components being:
-# - WAL LSN in hex format,
-# - Tablespace OID (0 for global)
+# TLI-LSNh-LSNl.TBLSPCOID.DBOID.NODEOID.dd_fork with the components being:
+# - Timeline ID in hex format.
+# - WAL LSN in hex format, as two 8-character numbers.
+# - Tablespace OID (0 for global).
# - Database OID.
# - Relfilenode.
# - Block number.
# - Fork this block came from (vm, init, fsm, or main).
my $file_re =
- qr/^([0-9A-F]{8})-([0-9A-F]{8})[.][0-9]+[.][0-9]+[.][0-9]+[.][0-9]+(?:_vm|_init|_fsm|_main)?$/;
+ qr/^[0-9A-F]{8}-([0-9A-F]{8})-([0-9A-F]{8})[.][0-9]+[.][0-9]+[.][0-9]+[.][0-9]+(?:_vm|_init|_fsm|_main)?$/;
my $file_count = 0;
diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index e5f9637847..4592d6016a 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -283,7 +283,7 @@ PostgreSQL documentation
</para>
<para>
The full page images are saved with the following file name format:
- <literal><replaceable>LSN</replaceable>.<replaceable>RELTABLESPACE</replaceable>.<replaceable>DATOID</replaceable>.<replaceable>RELNODE</replaceable>.<replaceable>BLKNO</replaceable><replaceable>FORK</replaceable></literal>
+ <literal><replaceable>TIMELINE</replaceable>-<replaceable>LSN</replaceable>.<replaceable>RELTABLESPACE</replaceable>.<replaceable>DATOID</replaceable>.<replaceable>RELNODE</replaceable>.<replaceable>BLKNO</replaceable><replaceable>FORK</replaceable></literal>
The file names are composed of the following parts:
<informaltable>
@@ -296,6 +296,13 @@ PostgreSQL documentation
</thead>
<tbody>
+ <row>
+ <entry>TIMELINE</entry>
+ <entry>The timeline of the WAL segment file where the record
+ is located formatted as one 8-character hexadecimal number
+ <literal>%08X</literal></entry>
+ </row>
+
<row>
<entry>LSN</entry>
<entry>The <acronym>LSN</acronym> of the record with this image,
--
2.40.1
[application/pgp-signature] signature.asc (833B, ../../[email protected]/3-signature.asc)
download
^ permalink raw reply [nested|flat] 3+ messages in thread
* Re: Add TLI number to name of files generated by pg_waldump --save-fullpage
2023-06-27 23:47 Re: Add TLI number to name of files generated by pg_waldump --save-fullpage Michael Paquier <[email protected]>
@ 2023-06-27 23:58 ` David Christensen <[email protected]>
0 siblings, 0 replies; 3+ messages in thread
From: David Christensen @ 2023-06-27 23:58 UTC (permalink / raw)
To: Michael Paquier <[email protected]>; +Cc: Kyotaro Horiguchi <[email protected]>; [email protected]; [email protected]
> Adjusted as per the v2 attached.
+1
^ permalink raw reply [nested|flat] 3+ messages in thread
end of thread, other threads:[~2023-06-27 23:58 UTC | newest]
Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-06-06 22:42 [PATCH v4 2/3] Allow CREATE INDEX CONCURRENTLY on partitioned table Justin Pryzby <[email protected]>
2023-06-27 23:47 Re: Add TLI number to name of files generated by pg_waldump --save-fullpage Michael Paquier <[email protected]>
2023-06-27 23:58 ` Re: Add TLI number to name of files generated by pg_waldump --save-fullpage David Christensen <[email protected]>
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox