public inbox for [email protected]help / color / mirror / Atom feed
[PATCH v4 3/3] Implement CLUSTER of partitioned table.. 2+ messages / 2 participants [nested] [flat]
* [PATCH v4 3/3] Implement CLUSTER of partitioned table.. @ 2020-06-07 21:58 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw) This requires either specification of a partitioned index on which to cluster, or that an partitioned index was previously set clustered. --- src/backend/commands/cluster.c | 139 +++++++++++++++++++------- src/bin/psql/tab-complete.c | 1 + src/test/regress/expected/cluster.out | 23 ++++- src/test/regress/sql/cluster.sql | 12 ++- 4 files changed, 133 insertions(+), 42 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 04d12a7ece..7409c17b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "catalog/namespace.h" #include "catalog/objectaccess.h" #include "catalog/pg_am.h" +#include "catalog/pg_inherits.h" #include "catalog/toasting.h" #include "commands/cluster.h" #include "commands/progress.h" @@ -72,6 +73,9 @@ static void copy_table_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex, bool verbose, bool *pSwapToastByContent, TransactionId *pFreezeXid, MultiXactId *pCutoffMulti); static List *get_tables_to_cluster(MemoryContext cluster_context); +static List *get_tables_to_cluster_partitioned(MemoryContext cluster_context, + Oid indexOid); +static void cluster_multiple_rels(List *rvs, int options); /*--------------------------------------------------------------------------- @@ -124,14 +128,6 @@ cluster(ClusterStmt *stmt, bool isTopLevel) (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), errmsg("cannot cluster temporary tables of other sessions"))); - /* - * Reject clustering a partitioned table. - */ - if (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot cluster a partitioned table"))); - if (stmt->indexname == NULL) { ListCell *index; @@ -169,8 +165,37 @@ cluster(ClusterStmt *stmt, bool isTopLevel) /* close relation, keep lock till commit */ table_close(rel, NoLock); - /* Do the job. */ - cluster_rel(tableOid, indexOid, stmt->options); + if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE) + { + /* Do the job. */ + cluster_rel(tableOid, indexOid, stmt->options); + } else { + List *rvs; + MemoryContext cluster_context; + + /* Check index directly since cluster_rel isn't called for partitioned table */ + check_index_is_clusterable(rel, indexOid, true, AccessExclusiveLock); + + /* Refuse to hold strong locks in a user transaction */ + PreventInTransactionBlock(isTopLevel, "CLUSTER"); + + cluster_context = AllocSetContextCreate(PortalContext, + "Cluster", + ALLOCSET_DEFAULT_SIZES); + + rvs = get_tables_to_cluster_partitioned(cluster_context, indexOid); + cluster_multiple_rels(rvs, stmt->options); + + /* Start a new transaction for the cleanup work. */ + StartTransactionCommand(); + + rel = table_open(tableOid, ShareUpdateExclusiveLock); + mark_index_clustered(rel, indexOid, true); + table_close(rel, NoLock); + + /* Clean up working storage */ + MemoryContextDelete(cluster_context); + } } else { @@ -180,7 +205,6 @@ cluster(ClusterStmt *stmt, bool isTopLevel) */ MemoryContext cluster_context; List *rvs; - ListCell *rv; /* * We cannot run this form of CLUSTER inside a user transaction block; @@ -204,25 +228,7 @@ cluster(ClusterStmt *stmt, bool isTopLevel) */ rvs = get_tables_to_cluster(cluster_context); - /* Commit to get out of starting transaction */ - PopActiveSnapshot(); - CommitTransactionCommand(); - - /* Ok, now that we've got them all, cluster them one by one */ - foreach(rv, rvs) - { - RelToCluster *rvtc = (RelToCluster *) lfirst(rv); - - /* Start a new transaction for each relation. */ - StartTransactionCommand(); - /* functions in indexes may want a snapshot set */ - PushActiveSnapshot(GetTransactionSnapshot()); - /* Do the job. */ - cluster_rel(rvtc->tableOid, rvtc->indexOid, - stmt->options | CLUOPT_RECHECK); - PopActiveSnapshot(); - CommitTransactionCommand(); - } + cluster_multiple_rels(rvs, stmt->options); /* Start a new transaction for the cleanup work. */ StartTransactionCommand(); @@ -483,12 +489,6 @@ mark_index_clustered(Relation rel, Oid indexOid, bool is_internal) Relation pg_index; ListCell *index; - /* Disallow applying to a partitioned table */ - if (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot mark index clustered in partitioned table"))); - /* * If the index is already marked clustered, no need to do anything. */ @@ -1557,3 +1557,70 @@ get_tables_to_cluster(MemoryContext cluster_context) return rvs; } + +/* + * Return a List of tables and associated index, where each index is a + * partition of the given index + */ +static List * +get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid) +{ + List *inhoids; + ListCell *lc; + List *rvs = NIL; + + MemoryContext old_context = MemoryContextSwitchTo(cluster_context); + + inhoids = find_all_inheritors(indexOid, NoLock, NULL); + foreach(lc, inhoids) + { + Oid indexrelid = lfirst_oid(lc); + Oid relid = IndexGetRelation(indexrelid, false); + RelToCluster *rvtc; + + /* + * We have a full list of direct and indirect children, so skip + * partitioned tables and just handle their children. + */ + if (get_rel_relkind(relid) == RELKIND_PARTITIONED_TABLE) + continue; + + rvtc = (RelToCluster *) palloc(sizeof(RelToCluster)); + rvtc->tableOid = relid; + rvtc->indexOid = indexrelid; + rvs = lappend(rvs, rvtc); + } + + MemoryContextSwitchTo(old_context); + return rvs; +} + +/* Cluster each relation in a separate transaction */ +static void +cluster_multiple_rels(List *rvs, int options) +{ + ListCell *lc; + + /* Commit to get out of starting transaction */ + PopActiveSnapshot(); + CommitTransactionCommand(); + + /* Ok, now that we've got them all, cluster them one by one */ + foreach(lc, rvs) + { + RelToCluster *rvtc = (RelToCluster *) lfirst(lc); + + /* Start a new transaction for each relation. */ + StartTransactionCommand(); + + /* functions in indexes may want a snapshot set */ + PushActiveSnapshot(GetTransactionSnapshot()); + + /* Do the job. */ + cluster_rel(rvtc->tableOid, rvtc->indexOid, + options | CLUOPT_RECHECK); + + PopActiveSnapshot(); + CommitTransactionCommand(); + } +} diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c index c4af40bfa9..e68808218a 100644 --- a/src/bin/psql/tab-complete.c +++ b/src/bin/psql/tab-complete.c @@ -587,6 +587,7 @@ static const SchemaQuery Query_for_list_of_clusterables = { .catname = "pg_catalog.pg_class c", .selcondition = "c.relkind IN (" CppAsString2(RELKIND_RELATION) ", " + CppAsString2(RELKIND_PARTITIONED_TABLE) ", " CppAsString2(RELKIND_MATVIEW) ")", .viscondition = "pg_catalog.pg_table_is_visible(c.oid)", .namespace = "c.relnamespace", diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out index bdae8fe00c..21b28fde6e 100644 --- a/src/test/regress/expected/cluster.out +++ b/src/test/regress/expected/cluster.out @@ -439,13 +439,28 @@ select * from clstr_temp; drop table clstr_temp; RESET SESSION AUTHORIZATION; --- Check that partitioned tables cannot be clustered +-- Check that partitioned tables can be clustered CREATE TABLE clstrpart (a int) PARTITION BY RANGE (a); +CREATE TABLE clstrpart1 PARTITION OF clstrpart FOR VALUES FROM (1)TO(10) PARTITION BY RANGE (a); +CREATE TABLE clstrpart11 PARTITION OF clstrpart1 FOR VALUES FROM (1)TO(10); +CREATE TABLE clstrpart12 PARTITION OF clstrpart1 FOR VALUES FROM (10)TO(20) PARTITION BY RANGE(a); +CREATE TABLE clstrpart2 PARTITION OF clstrpart FOR VALUES FROM (20)TO(30); CREATE INDEX clstrpart_idx ON clstrpart (a); -ALTER TABLE clstrpart CLUSTER ON clstrpart_idx; -ERROR: cannot mark index clustered in partitioned table +ALTER TABLE clstrpart SET WITHOUT CLUSTER; CLUSTER clstrpart USING clstrpart_idx; -ERROR: cannot cluster a partitioned table +CLUSTER clstrpart1 USING clstrpart1_a_idx; -- partition which is itself partitioned +CLUSTER clstrpart12 USING clstrpart12_a_idx; -- partition which is itself partitioned, no childs +CLUSTER clstrpart2 USING clstrpart2_a_idx; -- leaf +\d clstrpart + Partitioned table "public.clstrpart" + Column | Type | Collation | Nullable | Default +--------+---------+-----------+----------+--------- + a | integer | | | +Partition key: RANGE (a) +Indexes: + "clstrpart_idx" btree (a) CLUSTER +Number of partitions: 2 (Use \d+ to list them.) + DROP TABLE clstrpart; -- Test CLUSTER with external tuplesorting create table clstr_4 as select * from tenk1; diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql index 188183647c..4a76848213 100644 --- a/src/test/regress/sql/cluster.sql +++ b/src/test/regress/sql/cluster.sql @@ -196,11 +196,19 @@ drop table clstr_temp; RESET SESSION AUTHORIZATION; --- Check that partitioned tables cannot be clustered +-- Check that partitioned tables can be clustered CREATE TABLE clstrpart (a int) PARTITION BY RANGE (a); +CREATE TABLE clstrpart1 PARTITION OF clstrpart FOR VALUES FROM (1)TO(10) PARTITION BY RANGE (a); +CREATE TABLE clstrpart11 PARTITION OF clstrpart1 FOR VALUES FROM (1)TO(10); +CREATE TABLE clstrpart12 PARTITION OF clstrpart1 FOR VALUES FROM (10)TO(20) PARTITION BY RANGE(a); +CREATE TABLE clstrpart2 PARTITION OF clstrpart FOR VALUES FROM (20)TO(30); CREATE INDEX clstrpart_idx ON clstrpart (a); -ALTER TABLE clstrpart CLUSTER ON clstrpart_idx; +ALTER TABLE clstrpart SET WITHOUT CLUSTER; CLUSTER clstrpart USING clstrpart_idx; +CLUSTER clstrpart1 USING clstrpart1_a_idx; -- partition which is itself partitioned +CLUSTER clstrpart12 USING clstrpart12_a_idx; -- partition which is itself partitioned, no childs +CLUSTER clstrpart2 USING clstrpart2_a_idx; -- leaf +\d clstrpart DROP TABLE clstrpart; -- Test CLUSTER with external tuplesorting -- 2.17.0 --JYK4vJDZwFMowpUq-- ^ permalink raw reply [nested|flat] 2+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 2+ messages in thread
end of thread, other threads:[~2026-03-17 19:22 UTC | newest] Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[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