public inbox for [email protected]
help / color / mirror / Atom feed[PATCH v13 01/18] Allow CREATE INDEX CONCURRENTLY on partitioned table
2+ messages / 2 participants
[nested] [flat]
* [PATCH v13 01/18] Allow CREATE INDEX CONCURRENTLY on partitioned table
@ 2020-06-06 22:42 Justin Pryzby <[email protected]>
0 siblings, 0 replies; 2+ 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 | 143 ++++++++++++++++++-------
src/test/regress/expected/indexing.out | 60 ++++++++++-
src/test/regress/sql/indexing.sql | 18 +++-
4 files changed, 176 insertions(+), 54 deletions(-)
diff --git a/doc/src/sgml/ref/create_index.sgml b/doc/src/sgml/ref/create_index.sgml
index a5271a9f8f..6869a18968 100644
--- a/doc/src/sgml/ref/create_index.sgml
+++ b/doc/src/sgml/ref/create_index.sgml
@@ -686,15 +686,6 @@ 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 127ba7835d..4ac1dacd7d 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -68,6 +68,7 @@
/* non-export function prototypes */
+static void reindex_invalid_child_indexes(Oid indexRelationId);
static bool CompareOpclassOptions(Datum *opts1, Datum *opts2, int natts);
static void CheckPredicate(Expr *predicate);
static void ComputeIndexAttrs(IndexInfo *indexInfo,
@@ -680,17 +681,6 @@ 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),
@@ -1128,6 +1118,11 @@ DefineIndex(Oid relationId,
if (pd->nparts != 0)
flags |= INDEX_CREATE_INVALID;
}
+ else if (concurrent && OidIsValid(parentIndexId))
+ {
+ /* If concurrent, initially build index partitions as "invalid" */
+ flags |= INDEX_CREATE_INVALID;
+ }
if (stmt->deferrable)
constr_flags |= INDEX_CONSTR_CREATE_DEFERRABLE;
@@ -1183,6 +1178,14 @@ DefineIndex(Oid relationId,
partdesc = RelationGetPartitionDesc(rel);
if ((!stmt->relation || stmt->relation->inh) && partdesc->nparts > 0)
{
+ /*
+ * 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);
int nparts = partdesc->nparts;
Oid *part_oids = palloc(sizeof(Oid) * nparts);
bool invalidate_parent = false;
@@ -1193,8 +1196,10 @@ 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]);
@@ -1237,10 +1242,12 @@ DefineIndex(Oid relationId,
continue;
}
+ oldcontext = MemoryContextSwitchTo(ind_context);
childidxs = RelationGetIndexList(childrel);
attmap =
build_attrmap_by_name(RelationGetDescr(childrel),
parentDesc);
+ MemoryContextSwitchTo(oldcontext);
foreach(cell, childidxs)
{
@@ -1311,10 +1318,14 @@ DefineIndex(Oid relationId,
*/
if (!found)
{
- IndexStmt *childStmt = copyObject(stmt);
+ IndexStmt *childStmt;
bool found_whole_row;
ListCell *lc;
+ oldcontext = MemoryContextSwitchTo(ind_context);
+ childStmt = copyObject(stmt);
+ MemoryContextSwitchTo(oldcontext);
+
/*
* We can't use the same index name for the child index,
* so clear idxname to let the recursive invocation choose
@@ -1366,10 +1377,18 @@ DefineIndex(Oid relationId,
createdConstraintId,
is_alter_table, check_rights, check_not_in_use,
skip_build, quiet);
+ if (concurrent)
+ {
+ PopActiveSnapshot();
+ PushActiveSnapshot(GetTransactionSnapshot());
+ invalidate_parent = true;
+ }
}
- pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
- i + 1);
+ /* For concurrent build, this is a catalog-only stage */
+ if (!concurrent)
+ pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
+ i + 1);
free_attrmap(attmap);
}
@@ -1379,41 +1398,33 @@ DefineIndex(Oid relationId,
* invalid, this is incorrect, so update our row to invalid too.
*/
if (invalidate_parent)
- {
- Relation pg_index = table_open(IndexRelationId, RowExclusiveLock);
- HeapTuple tup,
- newtup;
-
- tup = SearchSysCache1(INDEXRELID,
- ObjectIdGetDatum(indexRelationId));
- if (!HeapTupleIsValid(tup))
- elog(ERROR, "cache lookup failed for index %u",
- indexRelationId);
- newtup = heap_copytuple(tup);
- ((Form_pg_index) GETSTRUCT(newtup))->indisvalid = false;
- CatalogTupleUpdate(pg_index, &tup->t_self, newtup);
- ReleaseSysCache(tup);
- table_close(pg_index, RowExclusiveLock);
- heap_freetuple(newtup);
- }
- }
+ index_set_state_flags(indexRelationId, INDEX_DROP_CLEAR_VALID);
+ } else
+ table_close(rel, NoLock);
/*
* Indexes on partitioned tables are not themselves built, so we're
* done here.
*/
- table_close(rel, NoLock);
if (!OidIsValid(parentIndexId))
+ {
+ if (concurrent)
+ reindex_invalid_child_indexes(indexRelationId);
+
pgstat_progress_end_command();
+ }
+
return address;
}
- if (!concurrent)
+ if (!concurrent || OidIsValid(parentIndexId))
{
- /* Close the heap and we're done, in the non-concurrent case */
- table_close(rel, NoLock);
+ /*
+ * We're done if this is the top-level index,
+ * or the catalog-only phase of a partition built concurrently
+ */
- /* If this is the top-level index, we're done. */
+ table_close(rel, NoLock);
if (!OidIsValid(parentIndexId))
pgstat_progress_end_command();
@@ -1617,6 +1628,62 @@ DefineIndex(Oid relationId,
return address;
}
+/* Reindex invalid child indexes created earlier */
+static void
+reindex_invalid_child_indexes(Oid indexRelationId)
+{
+ ListCell *lc;
+ int npart = 0;
+ ReindexParams params = {
+ .options = REINDEXOPT_CONCURRENTLY
+ };
+
+ MemoryContext ind_context = AllocSetContextCreate(PortalContext, "CREATE INDEX",
+ ALLOCSET_DEFAULT_SIZES);
+ MemoryContext oldcontext;
+ List *childs = find_inheritance_children(indexRelationId, ShareLock);
+ List *partitions = NIL;
+
+ PreventInTransactionBlock(true, "REINDEX INDEX");
+
+ foreach (lc, childs)
+ {
+ Oid partoid = lfirst_oid(lc);
+
+ /* XXX: need to retrofit progress reporting into it */
+ // pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
+ // npart++);
+
+ if (get_index_isvalid(partoid) ||
+ !RELKIND_HAS_STORAGE(get_rel_relkind(partoid)))
+ continue;
+
+ /* Save partition OID */
+ oldcontext = MemoryContextSwitchTo(ind_context);
+ partitions = lappend_oid(partitions, partoid);
+ MemoryContextSwitchTo(oldcontext);
+ }
+
+ /*
+ * Process each partition listed in a separate transaction. Note that
+ * this commits and then starts a new transaction immediately.
+ * XXX: since this is done in 2*N transactions, it could just as well
+ * call ReindexRelationConcurrently directly
+ */
+ ReindexMultipleInternal(partitions, ¶ms);
+
+ /*
+ * 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).
+ * This must be done only while holding a lock which precludes adding
+ * partitions.
+ * See also: validatePartitionedIndex().
+ */
+ index_set_state_flags(indexRelationId, INDEX_CREATE_SET_READY);
+ CommandCounterIncrement();
+ index_set_state_flags(indexRelationId, INDEX_CREATE_SET_VALID);
+}
/*
* CheckMutability
diff --git a/src/test/regress/expected/indexing.out b/src/test/regress/expected/indexing.out
index c93f4470c9..f04abc6897 100644
--- a/src/test/regress/expected/indexing.out
+++ b/src/test/regress/expected/indexing.out
@@ -50,11 +50,63 @@ 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 idxpart111 partition of idxpart11 default partition by range(a);
+create table idxpart1111 partition of idxpart111 default 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_ccnew"
+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) INVALID
+ "idxpart1_a_idx1" btree (a)
+ "idxpart1_a_idx2" UNIQUE, btree (a) INVALID
+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
+ "idxpart2_a_idx2_ccnew" 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 42f398b67c..3d4b6e9bc9 100644
--- a/src/test/regress/sql/indexing.sql
+++ b/src/test/regress/sql/indexing.sql
@@ -29,10 +29,22 @@ 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 idxpart111 partition of idxpart11 default partition by range(a);
+create table idxpart1111 partition of idxpart111 default 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
--QTprm0S8XgL7H0Dt
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v13-0002-f-progress-reporting.patch"
^ permalink raw reply [nested|flat] 2+ messages in thread
* Re:[PATCH]A minor improvement to the error-report in SimpleLruWriteAll()
@ 2024-05-28 12:15 Long Song <[email protected]>
0 siblings, 0 replies; 2+ messages in thread
From: Long Song @ 2024-05-28 12:15 UTC (permalink / raw)
To: pgsql-hackers
Hi,
Actually, I still wonder why only the error message
of the last failure to close the file was recorded.
For this unusual situation, it is acceptable to
record all failure information without causing
too much logging.
Was it designed that way on purpose?
At 2024-05-25 17:29:00, "Long Song" <[email protected]> wrote:
Hi hackers,
When I read the code, I noticed that in SimpleLruWriteAll(), only the last error is
recorded when the file fails to close. Like the following,
```void
SimpleLruWriteAll(SlruCtl ctl, bool allow_redirtied)
{
SlruShared shared = ctl->shared;
SlruWriteAllData fdata;
int64 pageno = 0;
int prevbank = SlotGetBankNumber(0);
bool ok;
...
/*
* Now close any files that were open
*/
ok = true;
for (int i = 0; i < fdata.num_files; i++)
{
if (CloseTransientFile(fdata.fd[i]) != 0)
{
slru_errcause = SLRU_CLOSE_FAILED;
slru_errno = errno;
pageno = fdata.segno[i] * SLRU_PAGES_PER_SEGMENT;
ok = false;
}
}
if (!ok)
SlruReportIOError(ctl, pageno, InvalidTransactionId);
```
// Here, SlruReportIOError() is called only once, meaning that the last error message is
recorded. In my opinion, since failure to close a file is not common, logging an error
message every time a failure occurs will not result in much log growth, but detailed error
logging will help in most cases.
So, I changed the code to move the call to SlruReportIOError() inside the while loop.
Attached is the patch, I hope it can help.
^ permalink raw reply [nested|flat] 2+ messages in thread
end of thread, other threads:[~2024-05-28 12:15 UTC | newest]
Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-06-06 22:42 [PATCH v13 01/18] Allow CREATE INDEX CONCURRENTLY on partitioned table Justin Pryzby <[email protected]>
2024-05-28 12:15 Re:[PATCH]A minor improvement to the error-report in SimpleLruWriteAll() Long Song <[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