From ab0dfc961b6a821f23d9c40c723d11380ce195a6 Mon Sep 17 00:00:00 2001 From: Alvaro Herrera Date: Tue, 2 Apr 2019 15:18:08 -0300 Subject: [PATCH] Report progress of CREATE INDEX operations This uses the progress reporting infrastructure added by c16dc1aca5e0, adding support for CREATE INDEX and CREATE INDEX CONCURRENTLY. There are two pieces to this: one is index-AM-agnostic, and the other is AM-specific. The latter is fairly elaborate for btrees, including reportage for parallel index builds and the separate phases that btree index creation uses; other index AMs, which are much simpler in their building procedures, have simplistic reporting only, but that seems sufficient, at least for non-concurrent builds. The index-AM-agnostic part is fairly complete, providing insight into the CONCURRENTLY wait phases as well as block-based progress during the index validation table scan. (The index validation index scan requires patching each AM, which has not been included here.) Reviewers: Rahila Syed, Pavan Deolasee, Tatsuro Yamada Discussion: https://postgr.es/m/20181220220022.mg63bhk26zdpvmcj@alvherre.pgsql --- contrib/amcheck/verify_nbtree.c | 2 +- contrib/bloom/blinsert.c | 2 +- contrib/bloom/blutils.c | 1 + doc/src/sgml/indexam.sgml | 13 ++ doc/src/sgml/monitoring.sgml | 224 ++++++++++++++++++++++- src/backend/access/brin/brin.c | 5 +- src/backend/access/gin/gininsert.c | 2 +- src/backend/access/gin/ginutil.c | 1 + src/backend/access/gist/gist.c | 1 + src/backend/access/gist/gistbuild.c | 2 +- src/backend/access/hash/hash.c | 7 +- src/backend/access/hash/hashsort.c | 6 + src/backend/access/heap/heapam_handler.c | 107 +++++++++++ src/backend/access/nbtree/nbtree.c | 9 + src/backend/access/nbtree/nbtsort.c | 56 +++++- src/backend/access/nbtree/nbtutils.c | 24 +++ src/backend/access/spgist/spginsert.c | 2 +- src/backend/access/spgist/spgutils.c | 1 + src/backend/catalog/index.c | 57 +++++- src/backend/catalog/system_views.sql | 27 +++ src/backend/commands/indexcmds.c | 72 +++++++- src/backend/storage/ipc/standby.c | 2 +- src/backend/storage/lmgr/lmgr.c | 46 ++++- src/backend/storage/lmgr/lock.c | 7 +- src/backend/utils/adt/amutils.c | 23 +++ src/backend/utils/adt/pgstatfuncs.c | 2 + src/include/access/amapi.h | 4 + src/include/access/genam.h | 1 + src/include/access/nbtree.h | 11 ++ src/include/access/tableam.h | 7 + src/include/catalog/catversion.h | 2 +- src/include/catalog/pg_proc.dat | 10 +- src/include/commands/progress.h | 37 +++- src/include/pgstat.h | 5 +- src/include/storage/lmgr.h | 4 +- src/include/storage/lock.h | 2 +- src/test/regress/expected/rules.out | 30 ++- 37 files changed, 768 insertions(+), 46 deletions(-) diff --git a/contrib/amcheck/verify_nbtree.c b/contrib/amcheck/verify_nbtree.c index 9d5b2e5be6..591e0a3e46 100644 --- a/contrib/amcheck/verify_nbtree.c +++ b/contrib/amcheck/verify_nbtree.c @@ -566,7 +566,7 @@ bt_check_every_level(Relation rel, Relation heaprel, bool heapkeyspace, RelationGetRelationName(state->rel), RelationGetRelationName(state->heaprel)); - table_index_build_scan(state->heaprel, state->rel, indexinfo, true, + table_index_build_scan(state->heaprel, state->rel, indexinfo, true, false, bt_tuple_present_callback, (void *) state, scan); ereport(DEBUG1, diff --git a/contrib/bloom/blinsert.c b/contrib/bloom/blinsert.c index 1b8df7e1e8..4b2186b8dd 100644 --- a/contrib/bloom/blinsert.c +++ b/contrib/bloom/blinsert.c @@ -142,7 +142,7 @@ blbuild(Relation heap, Relation index, IndexInfo *indexInfo) initCachedPage(&buildstate); /* Do the heap scan */ - reltuples = table_index_build_scan(heap, index, indexInfo, true, + reltuples = table_index_build_scan(heap, index, indexInfo, true, true, bloomBuildCallback, (void *) &buildstate, NULL); diff --git a/contrib/bloom/blutils.c b/contrib/bloom/blutils.c index d078dfbd46..ee3bd56274 100644 --- a/contrib/bloom/blutils.c +++ b/contrib/bloom/blutils.c @@ -132,6 +132,7 @@ blhandler(PG_FUNCTION_ARGS) amroutine->amcostestimate = blcostestimate; amroutine->amoptions = bloptions; amroutine->amproperty = NULL; + amroutine->ambuildphasename = NULL; amroutine->amvalidate = blvalidate; amroutine->ambeginscan = blbeginscan; amroutine->amrescan = blrescan; diff --git a/doc/src/sgml/indexam.sgml b/doc/src/sgml/indexam.sgml index b56d3b3daa..ff8290da9f 100644 --- a/doc/src/sgml/indexam.sgml +++ b/doc/src/sgml/indexam.sgml @@ -127,6 +127,7 @@ typedef struct IndexAmRoutine amcostestimate_function amcostestimate; amoptions_function amoptions; amproperty_function amproperty; /* can be NULL */ + ambuildphasename_function ambuildphasename; /* can be NULL */ amvalidate_function amvalidate; ambeginscan_function ambeginscan; amrescan_function amrescan; @@ -468,6 +469,18 @@ amproperty (Oid index_oid, int attno, +char * +ambuildphasename (int64 phasenum); + + Return the textual name of the given build phase number. + The phase numbers are those reported during an index build via the + pgstat_progress_update_param interface. + The phase names are then exposed in the + pg_stat_progress_create_index view. + + + + bool amvalidate (Oid opclassoid); diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index f1df14bdea..6679260508 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -336,6 +336,14 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser + + pg_stat_progress_create_indexpg_stat_progress_create_index + One row for each backend running CREATE INDEX, showing + current progress. + See . + + + pg_stat_progress_vacuumpg_stat_progress_vacuum One row for each backend (including autovacuum worker processes) running @@ -3403,10 +3411,224 @@ SELECT pg_stat_get_backend_pid(s.backendid) AS pid, PostgreSQL has the ability to report the progress of certain commands during command execution. Currently, the only commands - which support progress reporting are VACUUM and + which support progress reporting are CREATE INDEX, + VACUUM and CLUSTER. This may be expanded in the future. + + CREATE INDEX Progress Reporting + + + Whenever CREATE INDEX is running, the + pg_stat_progress_create_index view will contain + one row for each backend that is currently creating indexes. The tables + below describe the information that will be reported and provide information + about how to interpret it. + + + + <structname>pg_stat_progress_create_index</structname> View + + + + Column + Type + Description + + + + + + pid + integer + Process ID of backend. + + + datid + oid + OID of the database to which this backend is connected. + + + datname + name + Name of the database to which this backend is connected. + + + relid + oid + OID of the table on which the index is being created. + + + phase + text + + Current processing phase of index creation. See . + + + + lockers_total + bigint + + Total number of lockers to wait for, when applicable. + + + + lockers_done + bigint + + Number of lockers already waited for. + + + + current_locked_pid + bigint + + Process ID of the locker currently being waited for. + + + + blocks_total + bigint + + Total number of blocks to be processed in the current phase. + + + + blocks_done + bigint + + Number of blocks already processed in the current phase. + + + + tuples_total + bigint + + Total number of tuples to be processed in the current phase. + + + + tuples_done + bigint + + Number of tuples already processed in the current phase. + + + + partitions_total + bigint + + When creating an index on a partitioned table, this column is set to + the total number of partitions on which the index is to be created. + + + + partitions_done + bigint + + When creating an index on a partitioned table, this column is set to + the number of partitions on which the index has been completed. + + + + +
+ + + CREATE INDEX phases + + + + Phase + Description + + + + + initializing + + CREATE INDEX is preparing to create the index. This + phase is expected to be very brief. + + + + waiting for old snapshots + + CREATE INDEX CONCURRENTLY is waiting for transactions + that can potentially see the table to release their snapshots. + This phase is skipped when not in concurrent mode. + Columns lockers_total, lockers_done + and current_locker_pid contain the progress + information for this phase. + + + + building index + + The index is being built by the access method-specific code. In this phase, + access methods that support progress reporting fill in their own progress data, + and the subphase is indicated in this column. Typically, + blocks_total and blocks_done + will contain progress data, as well as potentially + tuples_total and tuples_done. + + + + waiting for writer snapshots + + CREATE INDEX CONCURRENTLY is waiting for transactions + that can potentially write into the table to release their snapshots. + This phase is skipped when not in concurrent mode. + Columns lockers_total, lockers_done + and current_locker_pid contain the progress + information for this phase. + + + + index validation: scanning index + + CREATE INDEX CONCURRENTLY is scanning the index searching + for tuples that need to be validated. + This phase is skipped when not in concurrent mode. + Columns blocks_total (set to the total size of the index) + and blocks_done contain the progress information for this phase. + + + + index validation: sorting tuples + + CREATE INDEX CONCURRENTLY is sorting the output of the + index scanning phase. + + + + index validation: scanning table + + CREATE INDEX CONCURRENTLY is scanning the table + to validate the index tuples collected in the previous two phases. + This phase is skipped when not in concurrent mode. + Columns blocks_total (set to the total size of the table) + and blocks_done contain the progress information for this phase. + + + + waiting for reader snapshots + + CREATE INDEX CONCURRENTLY is waiting for transactions + that can potentially see the table to release their snapshots. This + phase is skipped when not in concurrent mode. + Columns lockers_total, lockers_done + and current_locker_pid contain the progress + information for this phase. + + + + +
+ + + VACUUM Progress Reporting diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 6e96d24ca2..5c2b0c7635 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -112,6 +112,7 @@ brinhandler(PG_FUNCTION_ARGS) amroutine->amcostestimate = brincostestimate; amroutine->amoptions = brinoptions; amroutine->amproperty = NULL; + amroutine->ambuildphasename = NULL; amroutine->amvalidate = brinvalidate; amroutine->ambeginscan = brinbeginscan; amroutine->amrescan = brinrescan; @@ -719,7 +720,7 @@ brinbuild(Relation heap, Relation index, IndexInfo *indexInfo) * Now scan the relation. No syncscan allowed here because we want the * heap blocks in physical order. */ - reltuples = table_index_build_scan(heap, index, indexInfo, false, + reltuples = table_index_build_scan(heap, index, indexInfo, false, true, brinbuildCallback, (void *) state, NULL); /* process the final batch */ @@ -1236,7 +1237,7 @@ summarize_range(IndexInfo *indexInfo, BrinBuildState *state, Relation heapRel, * cases. */ state->bs_currRangeStart = heapBlk; - table_index_build_range_scan(heapRel, state->bs_irel, indexInfo, false, true, + table_index_build_range_scan(heapRel, state->bs_irel, indexInfo, false, true, false, heapBlk, scanNumBlks, brinbuildCallback, (void *) state, NULL); diff --git a/src/backend/access/gin/gininsert.c b/src/backend/access/gin/gininsert.c index b02f69b0dc..edc353a7fe 100644 --- a/src/backend/access/gin/gininsert.c +++ b/src/backend/access/gin/gininsert.c @@ -395,7 +395,7 @@ ginbuild(Relation heap, Relation index, IndexInfo *indexInfo) * Do the heap scan. We disallow sync scan here because dataPlaceToPage * prefers to receive tuples in TID order. */ - reltuples = table_index_build_scan(heap, index, indexInfo, false, + reltuples = table_index_build_scan(heap, index, indexInfo, false, true, ginBuildCallback, (void *) &buildstate, NULL); diff --git a/src/backend/access/gin/ginutil.c b/src/backend/access/gin/ginutil.c index afc20232ac..d2360eeafb 100644 --- a/src/backend/access/gin/ginutil.c +++ b/src/backend/access/gin/ginutil.c @@ -64,6 +64,7 @@ ginhandler(PG_FUNCTION_ARGS) amroutine->amcostestimate = gincostestimate; amroutine->amoptions = ginoptions; amroutine->amproperty = NULL; + amroutine->ambuildphasename = NULL; amroutine->amvalidate = ginvalidate; amroutine->ambeginscan = ginbeginscan; amroutine->amrescan = ginrescan; diff --git a/src/backend/access/gist/gist.c b/src/backend/access/gist/gist.c index 2fddb23496..f44c922b5d 100644 --- a/src/backend/access/gist/gist.c +++ b/src/backend/access/gist/gist.c @@ -86,6 +86,7 @@ gisthandler(PG_FUNCTION_ARGS) amroutine->amcostestimate = gistcostestimate; amroutine->amoptions = gistoptions; amroutine->amproperty = gistproperty; + amroutine->ambuildphasename = NULL; amroutine->amvalidate = gistvalidate; amroutine->ambeginscan = gistbeginscan; amroutine->amrescan = gistrescan; diff --git a/src/backend/access/gist/gistbuild.c b/src/backend/access/gist/gistbuild.c index 3652fde5bb..6024671989 100644 --- a/src/backend/access/gist/gistbuild.c +++ b/src/backend/access/gist/gistbuild.c @@ -205,7 +205,7 @@ gistbuild(Relation heap, Relation index, IndexInfo *indexInfo) /* * Do the heap scan. */ - reltuples = table_index_build_scan(heap, index, indexInfo, true, + reltuples = table_index_build_scan(heap, index, indexInfo, true, true, gistBuildCallback, (void *) &buildstate, NULL); diff --git a/src/backend/access/hash/hash.c b/src/backend/access/hash/hash.c index 5cc12a1713..048e40e46f 100644 --- a/src/backend/access/hash/hash.c +++ b/src/backend/access/hash/hash.c @@ -23,9 +23,11 @@ #include "access/relscan.h" #include "access/tableam.h" #include "catalog/index.h" +#include "commands/progress.h" #include "commands/vacuum.h" #include "miscadmin.h" #include "optimizer/plancat.h" +#include "pgstat.h" #include "utils/builtins.h" #include "utils/index_selfuncs.h" #include "utils/rel.h" @@ -83,6 +85,7 @@ hashhandler(PG_FUNCTION_ARGS) amroutine->amcostestimate = hashcostestimate; amroutine->amoptions = hashoptions; amroutine->amproperty = NULL; + amroutine->ambuildphasename = NULL; amroutine->amvalidate = hashvalidate; amroutine->ambeginscan = hashbeginscan; amroutine->amrescan = hashrescan; @@ -160,9 +163,11 @@ hashbuild(Relation heap, Relation index, IndexInfo *indexInfo) buildstate.heapRel = heap; /* do the heap scan */ - reltuples = table_index_build_scan(heap, index, indexInfo, true, + reltuples = table_index_build_scan(heap, index, indexInfo, true, true, hashbuildCallback, (void *) &buildstate, NULL); + pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_TOTAL, + buildstate.indtuples); if (buildstate.spool) { diff --git a/src/backend/access/hash/hashsort.c b/src/backend/access/hash/hashsort.c index 8c55436b19..00a57470a7 100644 --- a/src/backend/access/hash/hashsort.c +++ b/src/backend/access/hash/hashsort.c @@ -26,7 +26,9 @@ #include "postgres.h" #include "access/hash.h" +#include "commands/progress.h" #include "miscadmin.h" +#include "pgstat.h" #include "utils/tuplesort.h" @@ -116,6 +118,7 @@ void _h_indexbuild(HSpool *hspool, Relation heapRel) { IndexTuple itup; + long tups_done = 0; #ifdef USE_ASSERT_CHECKING uint32 hashkey = 0; #endif @@ -141,5 +144,8 @@ _h_indexbuild(HSpool *hspool, Relation heapRel) #endif _hash_doinsert(hspool->index, itup, heapRel); + + pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, + ++tups_done); } } diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 5c96fc91b7..6693d7eb2d 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -57,6 +57,8 @@ static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, OffsetNumber tupoffset); +static BlockNumber heapam_scan_get_blocks_done(HeapScanDesc hscan); + static const TableAmRoutine heapam_methods; @@ -1120,6 +1122,7 @@ heapam_index_build_range_scan(Relation heapRelation, IndexInfo *indexInfo, bool allow_sync, bool anyvisible, + bool progress, BlockNumber start_blockno, BlockNumber numblocks, IndexBuildCallback callback, @@ -1140,6 +1143,7 @@ heapam_index_build_range_scan(Relation heapRelation, Snapshot snapshot; bool need_unregister_snapshot = false; TransactionId OldestXmin; + BlockNumber previous_blkno = InvalidBlockNumber; BlockNumber root_blkno = InvalidBlockNumber; OffsetNumber root_offsets[MaxHeapTuplesPerPage]; @@ -1227,6 +1231,25 @@ heapam_index_build_range_scan(Relation heapRelation, hscan = (HeapScanDesc) scan; + /* Publish number of blocks to scan */ + if (progress) + { + BlockNumber nblocks; + + if (hscan->rs_base.rs_parallel != NULL) + { + ParallelBlockTableScanDesc pbscan; + + pbscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel; + nblocks = pbscan->phs_nblocks; + } + else + nblocks = hscan->rs_nblocks; + + pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_TOTAL, + nblocks); + } + /* * Must call GetOldestXmin() with SnapshotAny. Should never call * GetOldestXmin() with MVCC snapshot. (It's especially worth checking @@ -1259,6 +1282,19 @@ heapam_index_build_range_scan(Relation heapRelation, CHECK_FOR_INTERRUPTS(); + /* Report scan progress, if asked to. */ + if (progress) + { + BlockNumber blocks_done = heapam_scan_get_blocks_done(hscan); + + if (blocks_done != previous_blkno) + { + pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_DONE, + blocks_done); + previous_blkno = blocks_done; + } + } + /* * When dealing with a HOT-chain of updated tuples, we want to index * the values of the live tuple (if any), but index it under the TID @@ -1600,6 +1636,25 @@ heapam_index_build_range_scan(Relation heapRelation, } } + /* Report scan progress one last time. */ + if (progress) + { + BlockNumber blks_done; + + if (hscan->rs_base.rs_parallel != NULL) + { + ParallelBlockTableScanDesc pbscan; + + pbscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel; + blks_done = pbscan->phs_nblocks; + } + else + blks_done = hscan->rs_nblocks; + + pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_DONE, + blks_done); + } + table_endscan(scan); /* we can now forget our snapshot, if set and registered by us */ @@ -1636,6 +1691,7 @@ heapam_index_validate_scan(Relation heapRelation, BlockNumber root_blkno = InvalidBlockNumber; OffsetNumber root_offsets[MaxHeapTuplesPerPage]; bool in_index[MaxHeapTuplesPerPage]; + BlockNumber previous_blkno = InvalidBlockNumber; /* state variables for the merge */ ItemPointer indexcursor = NULL; @@ -1676,6 +1732,9 @@ heapam_index_validate_scan(Relation heapRelation, false); /* syncscan not OK */ hscan = (HeapScanDesc) scan; + pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_TOTAL, + hscan->rs_nblocks); + /* * Scan all tuples matching the snapshot. */ @@ -1689,6 +1748,14 @@ heapam_index_validate_scan(Relation heapRelation, state->htups += 1; + if ((previous_blkno == InvalidBlockNumber) || + (hscan->rs_cblock != previous_blkno)) + { + pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_DONE, + hscan->rs_cblock); + previous_blkno = hscan->rs_cblock; + } + /* * As commented in table_index_build_scan, we should index heap-only * tuples under the TIDs of their root tuples; so when we advance onto @@ -1849,6 +1916,46 @@ heapam_index_validate_scan(Relation heapRelation, indexInfo->ii_PredicateState = NULL; } +/* + * Return the number of blocks that have been read by this scan since + * starting. This is meant for progress reporting rather than be fully + * accurate: in a parallel scan, workers can be concurrently reading blocks + * further ahead than what we report. + */ +static BlockNumber +heapam_scan_get_blocks_done(HeapScanDesc hscan) +{ + ParallelBlockTableScanDesc bpscan = NULL; + BlockNumber startblock; + BlockNumber blocks_done; + + if (hscan->rs_base.rs_parallel != NULL) + { + bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel; + startblock = bpscan->phs_startblock; + } + else + startblock = hscan->rs_startblock; + + /* + * Might have wrapped around the end of the relation, if startblock was + * not zero. + */ + if (hscan->rs_cblock > startblock) + blocks_done = hscan->rs_cblock - startblock; + else + { + BlockNumber nblocks; + + nblocks = bpscan != NULL ? bpscan->phs_nblocks : hscan->rs_nblocks; + blocks_done = nblocks - startblock + + hscan->rs_cblock; + } + + return blocks_done; +} + + /* ------------------------------------------------------------------------ * Planner related callbacks for the heap AM diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c index ac6f1eb342..7370379c6a 100644 --- a/src/backend/access/nbtree/nbtree.c +++ b/src/backend/access/nbtree/nbtree.c @@ -22,6 +22,7 @@ #include "access/nbtxlog.h" #include "access/relscan.h" #include "access/xlog.h" +#include "commands/progress.h" #include "commands/vacuum.h" #include "miscadmin.h" #include "nodes/execnodes.h" @@ -133,6 +134,7 @@ bthandler(PG_FUNCTION_ARGS) amroutine->amcostestimate = btcostestimate; amroutine->amoptions = btoptions; amroutine->amproperty = btproperty; + amroutine->ambuildphasename = btbuildphasename; amroutine->amvalidate = btvalidate; amroutine->ambeginscan = btbeginscan; amroutine->amrescan = btrescan; @@ -1021,6 +1023,10 @@ btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats, if (needLock) UnlockRelationForExtension(rel, ExclusiveLock); + if (info->report_progress) + pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_TOTAL, + num_pages); + /* Quit if we've scanned the whole relation */ if (blkno >= num_pages) break; @@ -1028,6 +1034,9 @@ btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats, for (; blkno < num_pages; blkno++) { btvacuumpage(&vstate, blkno, blkno); + if (info->report_progress) + pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_DONE, + blkno); } } diff --git a/src/backend/access/nbtree/nbtsort.c b/src/backend/access/nbtree/nbtsort.c index 14d9545768..9ac4c1e1c0 100644 --- a/src/backend/access/nbtree/nbtsort.c +++ b/src/backend/access/nbtree/nbtsort.c @@ -66,6 +66,7 @@ #include "access/xlog.h" #include "access/xloginsert.h" #include "catalog/index.h" +#include "commands/progress.h" #include "miscadmin.h" #include "pgstat.h" #include "storage/smgr.h" @@ -298,7 +299,8 @@ static double _bt_parallel_heapscan(BTBuildState *buildstate, static void _bt_leader_participate_as_worker(BTBuildState *buildstate); static void _bt_parallel_scan_and_sort(BTSpool *btspool, BTSpool *btspool2, BTShared *btshared, Sharedsort *sharedsort, - Sharedsort *sharedsort2, int sortmem); + Sharedsort *sharedsort2, int sortmem, + bool progress); /* @@ -394,6 +396,10 @@ _bt_spools_heapscan(Relation heap, Relation index, BTBuildState *buildstate, /* Save as primary spool */ buildstate->spool = btspool; + /* Report table scan phase started */ + pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, + PROGRESS_BTREE_PHASE_INDEXBUILD_TABLESCAN); + /* Attempt to launch parallel worker scan when required */ if (indexInfo->ii_ParallelWorkers > 0) _bt_begin_parallel(buildstate, indexInfo->ii_Concurrent, @@ -480,13 +486,31 @@ _bt_spools_heapscan(Relation heap, Relation index, BTBuildState *buildstate, /* Fill spool using either serial or parallel heap scan */ if (!buildstate->btleader) - reltuples = table_index_build_scan(heap, index, indexInfo, true, + reltuples = table_index_build_scan(heap, index, indexInfo, true, true, _bt_build_callback, (void *) buildstate, NULL); else reltuples = _bt_parallel_heapscan(buildstate, &indexInfo->ii_BrokenHotChain); + /* + * Set the progress target for the next phase. Reset the block number + * values set by table_index_build_scan + */ + { + const int index[] = { + PROGRESS_CREATEIDX_TUPLES_TOTAL, + PROGRESS_SCAN_BLOCKS_TOTAL, + PROGRESS_SCAN_BLOCKS_DONE + }; + const int64 val[] = { + buildstate->indtuples, + 0, 0 + }; + + pgstat_progress_update_multi_param(3, index, val); + } + /* okay, all heap tuples are spooled */ if (buildstate->spool2 && !buildstate->havedead) { @@ -535,9 +559,15 @@ _bt_leafbuild(BTSpool *btspool, BTSpool *btspool2) } #endif /* BTREE_BUILD_STATS */ + pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, + PROGRESS_BTREE_PHASE_PERFORMSORT_1); tuplesort_performsort(btspool->sortstate); if (btspool2) + { + pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, + PROGRESS_BTREE_PHASE_PERFORMSORT_2); tuplesort_performsort(btspool2->sortstate); + } wstate.heap = btspool->heap; wstate.index = btspool->index; @@ -554,6 +584,8 @@ _bt_leafbuild(BTSpool *btspool, BTSpool *btspool2) wstate.btws_pages_written = 0; wstate.btws_zeropage = NULL; /* until needed */ + pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, + PROGRESS_BTREE_PHASE_LEAF_LOAD); _bt_load(&wstate, btspool, btspool2); } @@ -1098,6 +1130,7 @@ _bt_load(BTWriteState *wstate, BTSpool *btspool, BTSpool *btspool2) int i, keysz = IndexRelationGetNumberOfKeyAttributes(wstate->index); SortSupport sortKeys; + long tuples_done = 0; if (merge) { @@ -1202,6 +1235,10 @@ _bt_load(BTWriteState *wstate, BTSpool *btspool, BTSpool *btspool2) _bt_buildadd(wstate, state, itup2); itup2 = tuplesort_getindextuple(btspool2->sortstate, true); } + + /* Report progress */ + pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, + ++tuples_done); } pfree(sortKeys); } @@ -1216,6 +1253,10 @@ _bt_load(BTWriteState *wstate, BTSpool *btspool, BTSpool *btspool2) state = _bt_pagestate(wstate, 0); _bt_buildadd(wstate, state, itup); + + /* Report progress */ + pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, + ++tuples_done); } } @@ -1528,7 +1569,7 @@ _bt_leader_participate_as_worker(BTBuildState *buildstate) /* Perform work common to all participants */ _bt_parallel_scan_and_sort(leaderworker, leaderworker2, btleader->btshared, btleader->sharedsort, btleader->sharedsort2, - sortmem); + sortmem, true); #ifdef BTREE_BUILD_STATS if (log_btree_build_stats) @@ -1619,7 +1660,7 @@ _bt_parallel_build_main(dsm_segment *seg, shm_toc *toc) /* Perform sorting of spool, and possibly a spool2 */ sortmem = maintenance_work_mem / btshared->scantuplesortstates; _bt_parallel_scan_and_sort(btspool, btspool2, btshared, sharedsort, - sharedsort2, sortmem); + sharedsort2, sortmem, false); #ifdef BTREE_BUILD_STATS if (log_btree_build_stats) @@ -1648,7 +1689,7 @@ _bt_parallel_build_main(dsm_segment *seg, shm_toc *toc) static void _bt_parallel_scan_and_sort(BTSpool *btspool, BTSpool *btspool2, BTShared *btshared, Sharedsort *sharedsort, - Sharedsort *sharedsort2, int sortmem) + Sharedsort *sharedsort2, int sortmem, bool progress) { SortCoordinate coordinate; BTBuildState buildstate; @@ -1705,9 +1746,10 @@ _bt_parallel_scan_and_sort(BTSpool *btspool, BTSpool *btspool2, /* Join parallel scan */ indexInfo = BuildIndexInfo(btspool->index); indexInfo->ii_Concurrent = btshared->isconcurrent; - scan = table_beginscan_parallel(btspool->heap, ParallelTableScanFromBTShared(btshared)); + scan = table_beginscan_parallel(btspool->heap, + ParallelTableScanFromBTShared(btshared)); reltuples = table_index_build_scan(btspool->heap, btspool->index, indexInfo, - true, _bt_build_callback, + true, progress, _bt_build_callback, (void *) &buildstate, scan); /* diff --git a/src/backend/access/nbtree/nbtutils.c b/src/backend/access/nbtree/nbtutils.c index 140ac92026..7e409d616f 100644 --- a/src/backend/access/nbtree/nbtutils.c +++ b/src/backend/access/nbtree/nbtutils.c @@ -20,6 +20,7 @@ #include "access/nbtree.h" #include "access/reloptions.h" #include "access/relscan.h" +#include "commands/progress.h" #include "miscadmin.h" #include "utils/array.h" #include "utils/datum.h" @@ -2051,6 +2052,29 @@ btproperty(Oid index_oid, int attno, } } +/* + * btbuildphasename() -- Return name of index build phase. + */ +char * +btbuildphasename(int64 phasenum) +{ + switch (phasenum) + { + case PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE: + return "initializing"; + case PROGRESS_BTREE_PHASE_INDEXBUILD_TABLESCAN: + return "scanning table"; + case PROGRESS_BTREE_PHASE_PERFORMSORT_1: + return "sorting live tuples"; + case PROGRESS_BTREE_PHASE_PERFORMSORT_2: + return "sorting dead tuples"; + case PROGRESS_BTREE_PHASE_LEAF_LOAD: + return "loading tuples in tree"; + default: + return NULL; + } +} + /* * _bt_truncate() -- create tuple without unneeded suffix attributes. * diff --git a/src/backend/access/spgist/spginsert.c b/src/backend/access/spgist/spginsert.c index 390ad9ac51..b06feafdc2 100644 --- a/src/backend/access/spgist/spginsert.c +++ b/src/backend/access/spgist/spginsert.c @@ -143,7 +143,7 @@ spgbuild(Relation heap, Relation index, IndexInfo *indexInfo) "SP-GiST build temporary context", ALLOCSET_DEFAULT_SIZES); - reltuples = table_index_build_scan(heap, index, indexInfo, true, + reltuples = table_index_build_scan(heap, index, indexInfo, true, true, spgistBuildCallback, (void *) &buildstate, NULL); diff --git a/src/backend/access/spgist/spgutils.c b/src/backend/access/spgist/spgutils.c index 8e63c1fad2..45472db147 100644 --- a/src/backend/access/spgist/spgutils.c +++ b/src/backend/access/spgist/spgutils.c @@ -67,6 +67,7 @@ spghandler(PG_FUNCTION_ARGS) amroutine->amcostestimate = spgcostestimate; amroutine->amoptions = spgoptions; amroutine->amproperty = spgproperty; + amroutine->ambuildphasename = NULL; amroutine->amvalidate = spgvalidate; amroutine->ambeginscan = spgbeginscan; amroutine->amrescan = spgrescan; diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index 0d9d405c54..2ed7fdb021 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -51,9 +51,9 @@ #include "catalog/pg_trigger.h" #include "catalog/pg_type.h" #include "catalog/storage.h" -#include "commands/tablecmds.h" #include "commands/event_trigger.h" #include "commands/progress.h" +#include "commands/tablecmds.h" #include "commands/trigger.h" #include "executor/executor.h" #include "miscadmin.h" @@ -2047,7 +2047,7 @@ index_drop(Oid indexId, bool concurrent, bool concurrent_lock_mode) * to acquire an exclusive lock on our table. The lock code will * detect deadlock and error out properly. */ - WaitForLockers(heaplocktag, AccessExclusiveLock); + WaitForLockers(heaplocktag, AccessExclusiveLock, true); /* Finish invalidation of index and mark it as dead */ index_concurrently_set_dead(heapId, indexId); @@ -2063,7 +2063,7 @@ index_drop(Oid indexId, bool concurrent, bool concurrent_lock_mode) * Wait till every transaction that saw the old index state has * finished. */ - WaitForLockers(heaplocktag, AccessExclusiveLock); + WaitForLockers(heaplocktag, AccessExclusiveLock, true); /* * Re-open relations to allow us to complete our actions. @@ -2712,6 +2712,25 @@ index_build(Relation heapRelation, save_sec_context | SECURITY_RESTRICTED_OPERATION); save_nestlevel = NewGUCNestLevel(); + /* Set up initial progress report status */ + { + const int index[] = { + PROGRESS_CREATEIDX_PHASE, + PROGRESS_CREATEIDX_SUBPHASE, + PROGRESS_CREATEIDX_TUPLES_DONE, + PROGRESS_CREATEIDX_TUPLES_TOTAL, + PROGRESS_SCAN_BLOCKS_DONE, + PROGRESS_SCAN_BLOCKS_TOTAL + }; + const int64 val[] = { + PROGRESS_CREATEIDX_PHASE_BUILD, + PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE, + 0, 0, 0, 0 + }; + + pgstat_progress_update_multi_param(6, index, val); + } + /* * Call the access method's build procedure */ @@ -3000,6 +3019,21 @@ validate_index(Oid heapId, Oid indexId, Snapshot snapshot) int save_sec_context; int save_nestlevel; + { + const int index[] = { + PROGRESS_CREATEIDX_PHASE, + PROGRESS_CREATEIDX_TUPLES_DONE, + PROGRESS_CREATEIDX_TUPLES_TOTAL, + PROGRESS_SCAN_BLOCKS_DONE, + PROGRESS_SCAN_BLOCKS_TOTAL + }; + const int64 val[] = { + PROGRESS_CREATEIDX_PHASE_VALIDATE_IDXSCAN, + 0, 0, 0, 0 + }; + pgstat_progress_update_multi_param(5, index, val); + } + /* Open and lock the parent heap relation */ heapRelation = table_open(heapId, ShareUpdateExclusiveLock); /* And the target index relation */ @@ -3030,6 +3064,7 @@ validate_index(Oid heapId, Oid indexId, Snapshot snapshot) */ ivinfo.index = indexRelation; ivinfo.analyze_only = false; + ivinfo.report_progress = true; ivinfo.estimated_count = true; ivinfo.message_level = DEBUG2; ivinfo.num_heap_tuples = heapRelation->rd_rel->reltuples; @@ -3047,15 +3082,31 @@ validate_index(Oid heapId, Oid indexId, Snapshot snapshot) NULL, false); state.htups = state.itups = state.tups_inserted = 0; + /* ambulkdelete updates progress metrics */ (void) index_bulk_delete(&ivinfo, NULL, validate_index_callback, (void *) &state); /* Execute the sort */ + { + const int index[] = { + PROGRESS_CREATEIDX_PHASE, + PROGRESS_SCAN_BLOCKS_DONE, + PROGRESS_SCAN_BLOCKS_TOTAL + }; + const int64 val[] = { + PROGRESS_CREATEIDX_PHASE_VALIDATE_SORT, + 0, 0 + }; + + pgstat_progress_update_multi_param(3, index, val); + } tuplesort_performsort(state.tuplesort); /* * Now scan the heap and "merge" it with the index */ + pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE, + PROGRESS_CREATEIDX_PHASE_VALIDATE_TABLESCAN); table_index_validate_scan(heapRelation, indexRelation, indexInfo, diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index b89df70653..3f2a7ef015 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -934,6 +934,33 @@ CREATE VIEW pg_stat_progress_cluster AS FROM pg_stat_get_progress_info('CLUSTER') AS S LEFT JOIN pg_database D ON S.datid = D.oid; +CREATE VIEW pg_stat_progress_create_index AS + SELECT + S.pid AS pid, S.datid AS datid, D.datname AS datname, + S.relid AS relid, + CASE S.param10 WHEN 0 THEN 'initializing' + WHEN 1 THEN 'waiting for old snapshots' + WHEN 2 THEN 'building index' || + COALESCE((': ' || pg_indexam_progress_phasename(S.param9::oid, S.param11)), + '') + WHEN 3 THEN 'waiting for writer snapshots' + WHEN 4 THEN 'index validation: scanning index' + WHEN 5 THEN 'index validation: sorting tuples' + WHEN 6 THEN 'index validation: scanning table' + WHEN 7 THEN 'waiting for reader snapshots' + END as phase, + S.param4 AS lockers_total, + S.param5 AS lockers_done, + S.param6 AS current_locker_pid, + S.param16 AS blocks_total, + S.param17 AS blocks_done, + S.param12 AS tuples_total, + S.param13 AS tuples_done, + S.param14 AS partitions_total, + S.param15 AS partitions_done + FROM pg_stat_get_progress_info('CREATE INDEX') AS S + LEFT JOIN pg_database D ON S.datid = D.oid; + CREATE VIEW pg_user_mappings AS SELECT U.oid AS umid, diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c index 53971fc725..348d543297 100644 --- a/src/backend/commands/indexcmds.c +++ b/src/backend/commands/indexcmds.c @@ -36,6 +36,7 @@ #include "commands/dbcommands.h" #include "commands/defrem.h" #include "commands/event_trigger.h" +#include "commands/progress.h" #include "commands/tablecmds.h" #include "commands/tablespace.h" #include "mb/pg_wchar.h" @@ -47,10 +48,12 @@ #include "parser/parse_func.h" #include "parser/parse_oper.h" #include "partitioning/partdesc.h" +#include "pgstat.h" #include "rewrite/rewriteManip.h" #include "storage/lmgr.h" #include "storage/proc.h" #include "storage/procarray.h" +#include "storage/sinvaladt.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/fmgroids.h" @@ -334,7 +337,7 @@ CheckIndexCompatible(Oid oldId, * doesn't show up in the output, we know we can forget about it. */ static void -WaitForOlderSnapshots(TransactionId limitXmin) +WaitForOlderSnapshots(TransactionId limitXmin, bool progress) { int n_old_snapshots; int i; @@ -343,6 +346,8 @@ WaitForOlderSnapshots(TransactionId limitXmin) old_snapshots = GetCurrentVirtualXIDs(limitXmin, true, false, PROC_IS_AUTOVACUUM | PROC_IN_VACUUM, &n_old_snapshots); + if (progress) + pgstat_progress_update_param(PROGRESS_WAITFOR_TOTAL, n_old_snapshots); for (i = 0; i < n_old_snapshots; i++) { @@ -378,7 +383,19 @@ WaitForOlderSnapshots(TransactionId limitXmin) } if (VirtualTransactionIdIsValid(old_snapshots[i])) + { + if (progress) + { + PGPROC *holder = BackendIdGetProc(old_snapshots[i].backendId); + + pgstat_progress_update_param(PROGRESS_WAITFOR_CURRENT_PID, + holder->pid); + } VirtualXactLock(old_snapshots[i], true); + } + + if (progress) + pgstat_progress_update_param(PROGRESS_WAITFOR_DONE, i + 1); } } @@ -452,6 +469,15 @@ DefineIndex(Oid relationId, Snapshot snapshot; int i; + + /* + * Start progress report. If we're building a partition, this was already + * done. + */ + if (!OidIsValid(parentIndexId)) + pgstat_progress_start_command(PROGRESS_COMMAND_CREATE_INDEX, + relationId); + /* * count key attributes in index */ @@ -668,6 +694,9 @@ DefineIndex(Oid relationId, accessMethodId = accessMethodForm->oid; amRoutine = GetIndexAmRoutine(accessMethodForm->amhandler); + pgstat_progress_update_param(PROGRESS_CREATEIDX_ACCESS_METHOD_OID, + accessMethodId); + if (stmt->unique && !amRoutine->amcanunique) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), @@ -948,6 +977,11 @@ DefineIndex(Oid relationId, if (!OidIsValid(indexRelationId)) { table_close(rel, NoLock); + + /* If this is the top-level index, we're done */ + if (!OidIsValid(parentIndexId)) + pgstat_progress_end_command(); + return address; } @@ -973,6 +1007,9 @@ DefineIndex(Oid relationId, TupleDesc parentDesc; Oid *opfamOids; + pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_TOTAL, + nparts); + memcpy(part_oids, partdesc->oids, sizeof(Oid) * nparts); parentDesc = CreateTupleDescCopy(RelationGetDescr(rel)); @@ -1122,6 +1159,8 @@ DefineIndex(Oid relationId, skip_build, quiet); } + pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE, + i + 1); pfree(attmap); } @@ -1156,6 +1195,8 @@ DefineIndex(Oid relationId, * Indexes on partitioned tables are not themselves built, so we're * done here. */ + if (!OidIsValid(parentIndexId)) + pgstat_progress_end_command(); return address; } @@ -1163,6 +1204,11 @@ DefineIndex(Oid relationId, { /* 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(); + return address; } @@ -1214,7 +1260,9 @@ DefineIndex(Oid relationId, * exclusive lock on our table. The lock code will detect deadlock and * error out properly. */ - WaitForLockers(heaplocktag, ShareLock); + pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE, + PROGRESS_CREATEIDX_PHASE_WAIT_1); + WaitForLockers(heaplocktag, ShareLock, true); /* * At this moment we are sure that there are no transactions with the @@ -1255,7 +1303,9 @@ DefineIndex(Oid relationId, * We once again wait until no transaction can have the table open with * the index marked as read-only for updates. */ - WaitForLockers(heaplocktag, ShareLock); + pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE, + PROGRESS_CREATEIDX_PHASE_WAIT_2); + WaitForLockers(heaplocktag, ShareLock, true); /* * Now take the "reference snapshot" that will be used by validate_index() @@ -1312,7 +1362,9 @@ DefineIndex(Oid relationId, * before the reference snap was taken, we have to wait out any * transactions that might have older snapshots. */ - WaitForOlderSnapshots(limitXmin); + pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE, + PROGRESS_CREATEIDX_PHASE_WAIT_3); + WaitForOlderSnapshots(limitXmin, true); /* * Index can now be marked valid -- update its pg_index entry @@ -1334,6 +1386,8 @@ DefineIndex(Oid relationId, */ UnlockRelationIdForSession(&heaprelid, ShareUpdateExclusiveLock); + pgstat_progress_end_command(); + return address; } @@ -2913,7 +2967,7 @@ ReindexRelationConcurrently(Oid relationOid, int options) * DefineIndex() for more details. */ - WaitForLockersMultiple(lockTags, ShareLock); + WaitForLockersMultiple(lockTags, ShareLock, false); CommitTransactionCommand(); forboth(lc, indexIds, lc2, newIndexIds) @@ -2955,7 +3009,7 @@ ReindexRelationConcurrently(Oid relationOid, int options) * for more details. */ - WaitForLockersMultiple(lockTags, ShareLock); + WaitForLockersMultiple(lockTags, ShareLock, false); CommitTransactionCommand(); foreach(lc, newIndexIds) @@ -3003,7 +3057,7 @@ ReindexRelationConcurrently(Oid relationOid, int options) * before the reference snap was taken, we have to wait out any * transactions that might have older snapshots. */ - WaitForOlderSnapshots(limitXmin); + WaitForOlderSnapshots(limitXmin, false); CommitTransactionCommand(); } @@ -3074,7 +3128,7 @@ ReindexRelationConcurrently(Oid relationOid, int options) * index_drop() for more details. */ - WaitForLockersMultiple(lockTags, AccessExclusiveLock); + WaitForLockersMultiple(lockTags, AccessExclusiveLock, false); foreach(lc, indexIds) { @@ -3096,7 +3150,7 @@ ReindexRelationConcurrently(Oid relationOid, int options) * Drop the old indexes. */ - WaitForLockersMultiple(lockTags, AccessExclusiveLock); + WaitForLockersMultiple(lockTags, AccessExclusiveLock, false); PushActiveSnapshot(GetTransactionSnapshot()); diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index cd56dca3ae..215f1463bb 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -401,7 +401,7 @@ ResolveRecoveryConflictWithLock(LOCKTAG locktag) */ VirtualTransactionId *backends; - backends = GetLockConflicts(&locktag, AccessExclusiveLock); + backends = GetLockConflicts(&locktag, AccessExclusiveLock, NULL); ResolveRecoveryConflictWithVirtualXIDs(backends, PROCSIG_RECOVERY_CONFLICT_LOCK); } diff --git a/src/backend/storage/lmgr/lmgr.c b/src/backend/storage/lmgr/lmgr.c index e688ba8117..0b04b09378 100644 --- a/src/backend/storage/lmgr/lmgr.c +++ b/src/backend/storage/lmgr/lmgr.c @@ -19,9 +19,12 @@ #include "access/transam.h" #include "access/xact.h" #include "catalog/catalog.h" +#include "commands/progress.h" #include "miscadmin.h" +#include "pgstat.h" #include "storage/lmgr.h" #include "storage/procarray.h" +#include "storage/sinvaladt.h" #include "utils/inval.h" @@ -857,10 +860,12 @@ XactLockTableWaitErrorCb(void *arg) * after we obtained our initial list of lockers, we will not wait for them. */ void -WaitForLockersMultiple(List *locktags, LOCKMODE lockmode) +WaitForLockersMultiple(List *locktags, LOCKMODE lockmode, bool progress) { List *holders = NIL; ListCell *lc; + int total = 0; + int done = 0; /* Done if no locks to wait for */ if (list_length(locktags) == 0) @@ -870,10 +875,17 @@ WaitForLockersMultiple(List *locktags, LOCKMODE lockmode) foreach(lc, locktags) { LOCKTAG *locktag = lfirst(lc); + int count; - holders = lappend(holders, GetLockConflicts(locktag, lockmode)); + holders = lappend(holders, + GetLockConflicts(locktag, lockmode, + progress ? &count : NULL)); + total += count; } + if (progress) + pgstat_progress_update_param(PROGRESS_WAITFOR_TOTAL, total); + /* * Note: GetLockConflicts() never reports our own xid, hence we need not * check for that. Also, prepared xacts are not reported, which is fine @@ -887,10 +899,36 @@ WaitForLockersMultiple(List *locktags, LOCKMODE lockmode) while (VirtualTransactionIdIsValid(*lockholders)) { + /* + * If requested, publish who we're going to wait for. This is not + * 100% accurate if they're already gone, but we don't care. + */ + if (progress) + { + PGPROC *holder = BackendIdGetProc(lockholders->backendId); + + pgstat_progress_update_param(PROGRESS_WAITFOR_CURRENT_PID, + holder->pid); + } VirtualXactLock(*lockholders, true); lockholders++; + + if (progress) + pgstat_progress_update_param(PROGRESS_WAITFOR_DONE, ++done); } } + if (progress) + { + const int index[] = { + PROGRESS_WAITFOR_TOTAL, + PROGRESS_WAITFOR_DONE, + PROGRESS_WAITFOR_CURRENT_PID + }; + const int64 values[] = { + 0, 0, 0 + }; + pgstat_progress_update_multi_param(3, index, values); + } list_free_deep(holders); } @@ -901,12 +939,12 @@ WaitForLockersMultiple(List *locktags, LOCKMODE lockmode) * Same as WaitForLockersMultiple, for a single lock tag. */ void -WaitForLockers(LOCKTAG heaplocktag, LOCKMODE lockmode) +WaitForLockers(LOCKTAG heaplocktag, LOCKMODE lockmode, bool progress) { List *l; l = list_make1(&heaplocktag); - WaitForLockersMultiple(l, lockmode); + WaitForLockersMultiple(l, lockmode, progress); list_free(l); } diff --git a/src/backend/storage/lmgr/lock.c b/src/backend/storage/lmgr/lock.c index 78fdbd6ff8..c8958766f1 100644 --- a/src/backend/storage/lmgr/lock.c +++ b/src/backend/storage/lmgr/lock.c @@ -2807,6 +2807,7 @@ FastPathGetRelationLockEntry(LOCALLOCK *locallock) * xacts merely awaiting such a lock are NOT reported. * * The result array is palloc'd and is terminated with an invalid VXID. + * *countp, if not null, is updated to the number of items set. * * Of course, the result could be out of date by the time it's returned, * so use of this function has to be thought about carefully. @@ -2817,7 +2818,7 @@ FastPathGetRelationLockEntry(LOCALLOCK *locallock) * uses of the result. */ VirtualTransactionId * -GetLockConflicts(const LOCKTAG *locktag, LOCKMODE lockmode) +GetLockConflicts(const LOCKTAG *locktag, LOCKMODE lockmode, int *countp) { static VirtualTransactionId *vxids; LOCKMETHODID lockmethodid = locktag->locktag_lockmethodid; @@ -2964,6 +2965,8 @@ GetLockConflicts(const LOCKTAG *locktag, LOCKMODE lockmode) LWLockRelease(partitionLock); vxids[count].backendId = InvalidBackendId; vxids[count].localTransactionId = InvalidLocalTransactionId; + if (countp) + *countp = count; return vxids; } @@ -3019,6 +3022,8 @@ GetLockConflicts(const LOCKTAG *locktag, LOCKMODE lockmode) vxids[count].backendId = InvalidBackendId; vxids[count].localTransactionId = InvalidLocalTransactionId; + if (countp) + *countp = count; return vxids; } diff --git a/src/backend/utils/adt/amutils.c b/src/backend/utils/adt/amutils.c index 060ffe501e..e81d6cc056 100644 --- a/src/backend/utils/adt/amutils.c +++ b/src/backend/utils/adt/amutils.c @@ -445,3 +445,26 @@ pg_index_column_has_property(PG_FUNCTION_ARGS) return indexam_property(fcinfo, propname, InvalidOid, relid, attno); } + +/* + * Return the name of the given phase, as used for progress reporting by the + * given AM. + */ +Datum +pg_indexam_progress_phasename(PG_FUNCTION_ARGS) +{ + Oid amoid = PG_GETARG_OID(0); + int32 phasenum = PG_GETARG_INT32(1); + IndexAmRoutine *routine; + char *name; + + routine = GetIndexAmRoutineByAmId(amoid, true); + if (routine == NULL || !routine->ambuildphasename) + PG_RETURN_NULL(); + + name = routine->ambuildphasename(phasenum); + if (!name) + PG_RETURN_NULL(); + + PG_RETURN_TEXT_P(CStringGetTextDatum(name)); +} diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 90a817a25c..7c2afe6427 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -470,6 +470,8 @@ pg_stat_get_progress_info(PG_FUNCTION_ARGS) cmdtype = PROGRESS_COMMAND_VACUUM; else if (pg_strcasecmp(cmd, "CLUSTER") == 0) cmdtype = PROGRESS_COMMAND_CLUSTER; + else if (pg_strcasecmp(cmd, "CREATE INDEX") == 0) + cmdtype = PROGRESS_COMMAND_CREATE_INDEX; else ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), diff --git a/src/include/access/amapi.h b/src/include/access/amapi.h index 653ddc976b..09a7404267 100644 --- a/src/include/access/amapi.h +++ b/src/include/access/amapi.h @@ -108,6 +108,9 @@ typedef bool (*amproperty_function) (Oid index_oid, int attno, IndexAMProperty prop, const char *propname, bool *res, bool *isnull); +/* name of phase as used in progress reporting */ +typedef char *(*ambuildphasename_function) (int64 phasenum); + /* validate definition of an opclass for this AM */ typedef bool (*amvalidate_function) (Oid opclassoid); @@ -213,6 +216,7 @@ typedef struct IndexAmRoutine amcostestimate_function amcostestimate; amoptions_function amoptions; amproperty_function amproperty; /* can be NULL */ + ambuildphasename_function ambuildphasename; /* can be NULL */ amvalidate_function amvalidate; ambeginscan_function ambeginscan; amrescan_function amrescan; diff --git a/src/include/access/genam.h b/src/include/access/genam.h index 70c7351a08..9717183ef2 100644 --- a/src/include/access/genam.h +++ b/src/include/access/genam.h @@ -45,6 +45,7 @@ typedef struct IndexVacuumInfo { Relation index; /* the index being vacuumed */ bool analyze_only; /* ANALYZE (without any actual vacuum) */ + bool report_progress; /* emit progress.h status reports */ bool estimated_count; /* num_heap_tuples is an estimate */ int message_level; /* ereport level for progress messages */ double num_heap_tuples; /* tuples remaining in heap */ diff --git a/src/include/access/nbtree.h b/src/include/access/nbtree.h index a1ffa98336..fbc8134cfd 100644 --- a/src/include/access/nbtree.h +++ b/src/include/access/nbtree.h @@ -671,6 +671,16 @@ typedef BTScanOpaqueData *BTScanOpaque; #define SK_BT_DESC (INDOPTION_DESC << SK_BT_INDOPTION_SHIFT) #define SK_BT_NULLS_FIRST (INDOPTION_NULLS_FIRST << SK_BT_INDOPTION_SHIFT) +/* + * Constant definition for progress reporting. Phase numbers must match + * btbuildphasename. + */ +/* PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE is 1 (see progress.h) */ +#define PROGRESS_BTREE_PHASE_INDEXBUILD_TABLESCAN 2 +#define PROGRESS_BTREE_PHASE_PERFORMSORT_1 3 +#define PROGRESS_BTREE_PHASE_PERFORMSORT_2 4 +#define PROGRESS_BTREE_PHASE_LEAF_LOAD 5 + /* * external entry points for btree, in nbtree.c */ @@ -784,6 +794,7 @@ extern bytea *btoptions(Datum reloptions, bool validate); extern bool btproperty(Oid index_oid, int attno, IndexAMProperty prop, const char *propname, bool *res, bool *isnull); +extern char *btbuildphasename(int64 phasenum); extern IndexTuple _bt_truncate(Relation rel, IndexTuple lastleft, IndexTuple firstright, BTScanInsert itup_key); extern int _bt_keep_natts_fast(Relation rel, IndexTuple lastleft, diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h index 4efe178ed1..4b760c2cd7 100644 --- a/src/include/access/tableam.h +++ b/src/include/access/tableam.h @@ -507,6 +507,7 @@ typedef struct TableAmRoutine struct IndexInfo *index_nfo, bool allow_sync, bool anyvisible, + bool progress, BlockNumber start_blockno, BlockNumber end_blockno, IndexBuildCallback callback, @@ -1369,6 +1370,8 @@ table_scan_analyze_next_tuple(TableScanDesc scan, TransactionId OldestXmin, * so here because the AM might reject some of the tuples for its own reasons, * such as being unable to store NULLs. * + * If 'progress', the PROGRESS_SCAN_BLOCKS_TOTAL counter is updated when + * starting the scan, and PROGRESS_SCAN_BLOCKS_DONE is updated as we go along. * * A side effect is to set indexInfo->ii_BrokenHotChain to true if we detect * any potentially broken HOT chains. Currently, we set this if there are any @@ -1382,6 +1385,7 @@ table_index_build_scan(Relation heap_rel, Relation index_rel, struct IndexInfo *index_nfo, bool allow_sync, + bool progress, IndexBuildCallback callback, void *callback_state, TableScanDesc scan) @@ -1391,6 +1395,7 @@ table_index_build_scan(Relation heap_rel, index_nfo, allow_sync, false, + progress, 0, InvalidBlockNumber, callback, @@ -1414,6 +1419,7 @@ table_index_build_range_scan(Relation heap_rel, struct IndexInfo *index_nfo, bool allow_sync, bool anyvisible, + bool progress, BlockNumber start_blockno, BlockNumber numblocks, IndexBuildCallback callback, @@ -1425,6 +1431,7 @@ table_index_build_range_scan(Relation heap_rel, index_nfo, allow_sync, anyvisible, + progress, start_blockno, numblocks, callback, diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h index dfb94bfadf..43142b67c5 100644 --- a/src/include/catalog/catversion.h +++ b/src/include/catalog/catversion.h @@ -53,6 +53,6 @@ */ /* yyyymmddN */ -#define CATALOG_VERSION_NO 201904011 +#define CATALOG_VERSION_NO 201904021 #endif diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index eac909109c..a7050edca0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -924,6 +924,10 @@ proname => 'pg_index_column_has_property', provolatile => 's', prorettype => 'bool', proargtypes => 'regclass int4 text', prosrc => 'pg_index_column_has_property' }, +{ oid => '676', descr => 'return name of given index build phase', + proname => 'pg_indexam_progress_phasename', provolatile => 'i', + prorettype => 'text', proargtypes => 'oid int8', + prosrc => 'pg_indexam_progress_phasename' }, { oid => '339', proname => 'poly_same', prorettype => 'bool', @@ -5122,9 +5126,9 @@ proname => 'pg_stat_get_progress_info', prorows => '100', proretset => 't', provolatile => 's', proparallel => 'r', prorettype => 'record', proargtypes => 'text', - proallargtypes => '{text,int4,oid,oid,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8}', - proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o}', - proargnames => '{cmdtype,pid,datid,relid,param1,param2,param3,param4,param5,param6,param7,param8,param9,param10}', + proallargtypes => '{text,int4,oid,oid,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8}', + proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}', + proargnames => '{cmdtype,pid,datid,relid,param1,param2,param3,param4,param5,param6,param7,param8,param9,param10,param11,param12,param13,param14,param15,param16,param17,param18,param19,param20}', prosrc => 'pg_stat_get_progress_info' }, { oid => '3099', descr => 'statistics: information about currently active replication', diff --git a/src/include/commands/progress.h b/src/include/commands/progress.h index 04542d9e92..f046fa13b1 100644 --- a/src/include/commands/progress.h +++ b/src/include/commands/progress.h @@ -44,7 +44,7 @@ #define PROGRESS_CLUSTER_HEAP_BLKS_SCANNED 6 #define PROGRESS_CLUSTER_INDEX_REBUILD_COUNT 7 -/* Phases of cluster (as dvertised via PROGRESS_CLUSTER_PHASE) */ +/* Phases of cluster (as advertised via PROGRESS_CLUSTER_PHASE) */ #define PROGRESS_CLUSTER_PHASE_SEQ_SCAN_HEAP 1 #define PROGRESS_CLUSTER_PHASE_INDEX_SCAN_HEAP 2 #define PROGRESS_CLUSTER_PHASE_SORT_TUPLES 3 @@ -57,4 +57,39 @@ #define PROGRESS_CLUSTER_COMMAND_CLUSTER 1 #define PROGRESS_CLUSTER_COMMAND_VACUUM_FULL 2 +/* Progress parameters for CREATE INDEX */ +/* 3, 4 and 5 reserved for "waitfor" metrics */ +#define PROGRESS_CREATEIDX_ACCESS_METHOD_OID 8 +#define PROGRESS_CREATEIDX_PHASE 9 /* AM-agnostic phase # */ +#define PROGRESS_CREATEIDX_SUBPHASE 10 /* phase # filled by AM */ +#define PROGRESS_CREATEIDX_TUPLES_TOTAL 11 +#define PROGRESS_CREATEIDX_TUPLES_DONE 12 +#define PROGRESS_CREATEIDX_PARTITIONS_TOTAL 13 +#define PROGRESS_CREATEIDX_PARTITIONS_DONE 14 +/* 15 and 16 reserved for "block number" metrics */ + +/* Phases of CREATE INDEX (as advertised via PROGRESS_CREATEIDX_PHASE) */ +#define PROGRESS_CREATEIDX_PHASE_WAIT_1 1 +#define PROGRESS_CREATEIDX_PHASE_BUILD 2 +#define PROGRESS_CREATEIDX_PHASE_WAIT_2 3 +#define PROGRESS_CREATEIDX_PHASE_VALIDATE_IDXSCAN 4 +#define PROGRESS_CREATEIDX_PHASE_VALIDATE_SORT 5 +#define PROGRESS_CREATEIDX_PHASE_VALIDATE_TABLESCAN 6 +#define PROGRESS_CREATEIDX_PHASE_WAIT_3 7 + +/* + * Subphases of CREATE INDEX, for index_build. + */ +#define PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE 1 +/* Additional phases are defined by each AM */ + +/* Lock holder wait counts */ +#define PROGRESS_WAITFOR_TOTAL 3 +#define PROGRESS_WAITFOR_DONE 4 +#define PROGRESS_WAITFOR_CURRENT_PID 5 + +/* Block numbers in a generic relation scan */ +#define PROGRESS_SCAN_BLOCKS_TOTAL 15 +#define PROGRESS_SCAN_BLOCKS_DONE 16 + #endif diff --git a/src/include/pgstat.h b/src/include/pgstat.h index c080fa6388..53d4a9c431 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -951,10 +951,11 @@ typedef enum ProgressCommandType { PROGRESS_COMMAND_INVALID, PROGRESS_COMMAND_VACUUM, - PROGRESS_COMMAND_CLUSTER + PROGRESS_COMMAND_CLUSTER, + PROGRESS_COMMAND_CREATE_INDEX } ProgressCommandType; -#define PGSTAT_NUM_PROGRESS_PARAM 10 +#define PGSTAT_NUM_PROGRESS_PARAM 20 /* ---------- * Shared-memory data structures diff --git a/src/include/storage/lmgr.h b/src/include/storage/lmgr.h index 3d705faba5..4f2872de35 100644 --- a/src/include/storage/lmgr.h +++ b/src/include/storage/lmgr.h @@ -78,8 +78,8 @@ extern void XactLockTableWait(TransactionId xid, Relation rel, extern bool ConditionalXactLockTableWait(TransactionId xid); /* Lock VXIDs, specified by conflicting locktags */ -extern void WaitForLockers(LOCKTAG heaplocktag, LOCKMODE lockmode); -extern void WaitForLockersMultiple(List *locktags, LOCKMODE lockmode); +extern void WaitForLockers(LOCKTAG heaplocktag, LOCKMODE lockmode, bool progress); +extern void WaitForLockersMultiple(List *locktags, LOCKMODE lockmode, bool progress); /* Lock an XID for tuple insertion (used to wait for an insertion to finish) */ extern uint32 SpeculativeInsertionLockAcquire(TransactionId xid); diff --git a/src/include/storage/lock.h b/src/include/storage/lock.h index badf7fd682..048947c50d 100644 --- a/src/include/storage/lock.h +++ b/src/include/storage/lock.h @@ -544,7 +544,7 @@ extern bool LockHeldByMe(const LOCKTAG *locktag, LOCKMODE lockmode); extern bool LockHasWaiters(const LOCKTAG *locktag, LOCKMODE lockmode, bool sessionLock); extern VirtualTransactionId *GetLockConflicts(const LOCKTAG *locktag, - LOCKMODE lockmode); + LOCKMODE lockmode, int *countp); extern void AtPrepare_Locks(void); extern void PostPrepare_Locks(TransactionId xid); extern int LockCheckConflicts(LockMethod lockMethodTable, diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index d5f309fbfb..51d7a150cf 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1856,7 +1856,33 @@ pg_stat_progress_cluster| SELECT s.pid, s.param6 AS heap_blks_total, s.param7 AS heap_blks_scanned, s.param8 AS index_rebuild_count - FROM (pg_stat_get_progress_info('CLUSTER'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10) + FROM (pg_stat_get_progress_info('CLUSTER'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20) + LEFT JOIN pg_database d ON ((s.datid = d.oid))); +pg_stat_progress_create_index| SELECT s.pid, + s.datid, + d.datname, + s.relid, + CASE s.param10 + WHEN 0 THEN 'initializing'::text + WHEN 1 THEN 'waiting for old snapshots'::text + WHEN 2 THEN ('building index'::text || COALESCE((': '::text || pg_indexam_progress_phasename((s.param9)::oid, s.param11)), ''::text)) + WHEN 3 THEN 'waiting for writer snapshots'::text + WHEN 4 THEN 'index validation: scan index'::text + WHEN 5 THEN 'index validation: sort index scan results'::text + WHEN 6 THEN 'index validation: scan heap'::text + WHEN 7 THEN 'waiting for reader snapshots'::text + ELSE NULL::text + END AS phase, + s.param4 AS lockers_total, + s.param5 AS lockers_done, + s.param6 AS current_locker_pid, + s.param16 AS blocks_total, + s.param17 AS blocks_done, + s.param12 AS tuples_total, + s.param13 AS tuples_done, + s.param14 AS partitions_total, + s.param15 AS partitions_done + FROM (pg_stat_get_progress_info('CREATE INDEX'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20) LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_progress_vacuum| SELECT s.pid, s.datid, @@ -1878,7 +1904,7 @@ pg_stat_progress_vacuum| SELECT s.pid, s.param5 AS index_vacuum_count, s.param6 AS max_dead_tuples, s.param7 AS num_dead_tuples - FROM (pg_stat_get_progress_info('VACUUM'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10) + FROM (pg_stat_get_progress_info('VACUUM'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20) LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_replication| SELECT s.pid, s.usesysid,