From 2e33b43599ad3868ee180f149050444bf0a7ca15 Mon Sep 17 00:00:00 2001 From: Noah Misch Date: Sat, 23 Oct 2021 18:36:38 -0700 Subject: [PATCH] Avoid race in RelationBuildDesc() affecting CREATE INDEX CONCURRENTLY. CIC and REINDEX CONCURRENTLY assume backends see their catalog changes no later than each backend's next transaction start. That failed to hold when a backend absorbed a relevant invalidation in the middle of running RelationBuildDesc() on the CIC index. Queries that use the resulting index can silently fail to find rows. Fix this for future index builds by making RelationBuildDesc() loop until it finishes without accepting a relevant invalidation. It may be necessary to reindex to recover from past occurrences; REINDEX CONCURRENTLY suffices. Back-patch to 9.6 (all supported versions). Noah Misch and Andrey Borodin, reviewed (in earlier versions) by Andres Freund. Discussion: https://postgr.es/m/20210730022548.GA1940096@gust.leadboat.com --- contrib/amcheck/Makefile | 2 + contrib/amcheck/t/002_cic.pl | 78 +++++++++++++++++ src/backend/utils/cache/inval.c | 12 ++- src/backend/utils/cache/relcache.c | 115 ++++++++++++++++++++++-- src/include/utils/inval.h | 1 + src/include/utils/relcache.h | 2 +- src/test/perl/PostgresNode.pm | 135 +++++++++++++++++++++++++++++ src/tools/pgindent/typedefs.list | 1 + 8 files changed, 336 insertions(+), 10 deletions(-) create mode 100644 contrib/amcheck/t/002_cic.pl diff --git a/contrib/amcheck/Makefile b/contrib/amcheck/Makefile index a2b1b1036b3..9a62e84defc 100644 --- a/contrib/amcheck/Makefile +++ b/contrib/amcheck/Makefile @@ -11,6 +11,8 @@ PGFILEDESC = "amcheck - function for verifying relation integrity" REGRESS = check check_btree +TAP_TESTS = 1 + ifdef USE_PGXS PG_CONFIG = pg_config PGXS := $(shell $(PG_CONFIG) --pgxs) diff --git a/contrib/amcheck/t/002_cic.pl b/contrib/amcheck/t/002_cic.pl new file mode 100644 index 00000000000..26b56054b13 --- /dev/null +++ b/contrib/amcheck/t/002_cic.pl @@ -0,0 +1,78 @@ + +# Copyright (c) 2021, PostgreSQL Global Development Group + +# Test CREATE INDEX CONCURRENTLY with concurrent modifications +use strict; +use warnings; + +use Config; +use PostgresNode; +use TestLib; + +use Test::More tests => 4; + +my ($node, $result); + +# +# Test set-up +# +$node = get_new_node('CIC_test'); +$node->init; +$node->append_conf('postgresql.conf', 'lock_timeout = 180000'); +$node->start; +$node->safe_psql('postgres', q(CREATE EXTENSION amcheck)); +$node->safe_psql('postgres', q(CREATE TABLE tbl(i int))); +$node->safe_psql('postgres', q(CREATE INDEX idx ON tbl(i))); + +# +# Stress CIC with pgbench +# + +# Run background pgbench with CIC. We cannot mix-in this script into single +# pgbench: CIC will deadlock with itself occasionally. +my $pgbench_out = ''; +my $pgbench_timer = IPC::Run::timeout(180); +my $pgbench_h = $node->background_pgbench( + '--no-vacuum --client=1 --transactions=200', + { + '002_pgbench_concurrent_cic' => q( + DROP INDEX CONCURRENTLY idx; + CREATE INDEX CONCURRENTLY idx ON tbl(i); + SELECT bt_index_check('idx',true); + ) + }, + \$pgbench_out, + $pgbench_timer); + +# Run pgbench. +$node->pgbench( + '--no-vacuum --client=5 --transactions=200', + 0, + [qr{actually processed}], + [qr{^$}], + 'concurrent INSERTs', + { + '002_pgbench_concurrent_transaction' => q( + BEGIN; + INSERT INTO tbl VALUES(0); + COMMIT; + ), + '002_pgbench_concurrent_transaction_savepoints' => q( + BEGIN; + SAVEPOINT s1; + INSERT INTO tbl VALUES(0); + COMMIT; + ) + }); + +$pgbench_h->pump_nb; +$pgbench_h->finish(); +$result = + ($Config{osname} eq "MSWin32") + ? ($pgbench_h->full_results)[0] + : $pgbench_h->result(0); +is($result, 0, "pgbench with CIC works"); + +# done +$node->stop; +done_testing(); diff --git a/src/backend/utils/cache/inval.c b/src/backend/utils/cache/inval.c index 4fbc6d0720d..809c3a0972c 100644 --- a/src/backend/utils/cache/inval.c +++ b/src/backend/utils/cache/inval.c @@ -584,7 +584,7 @@ LocalExecuteInvalidationMessage(SharedInvalidationMessage *msg) int i; if (msg->rc.relId == InvalidOid) - RelationCacheInvalidate(); + RelationCacheInvalidate(false); else RelationCacheInvalidateEntry(msg->rc.relId); @@ -641,12 +641,18 @@ LocalExecuteInvalidationMessage(SharedInvalidationMessage *msg) */ void InvalidateSystemCaches(void) +{ + InvalidateSystemCachesExtended(false); +} + +void +InvalidateSystemCachesExtended(bool debug_discard) { int i; InvalidateCatalogSnapshot(); ResetCatalogCaches(); - RelationCacheInvalidate(); /* gets smgr and relmap too */ + RelationCacheInvalidate(debug_discard); /* gets smgr and relmap too */ for (i = 0; i < syscache_callback_count; i++) { @@ -717,7 +723,7 @@ AcceptInvalidationMessages(void) if (recursion_depth < 3) { recursion_depth++; - InvalidateSystemCaches(); + InvalidateSystemCachesExtended(true); recursion_depth--; } } diff --git a/src/backend/utils/cache/relcache.c b/src/backend/utils/cache/relcache.c index 32e75560ead..7976a0d66d4 100644 --- a/src/backend/utils/cache/relcache.c +++ b/src/backend/utils/cache/relcache.c @@ -150,6 +150,24 @@ bool criticalSharedRelcachesBuilt = false; */ static long relcacheInvalsReceived = 0L; +/* + * in_progress_list is a stack of ongoing RelationBuildDesc() calls. CREATE + * INDEX CONCURRENTLY makes catalog changes under ShareUpdateExclusiveLock. + * It critically relies on each backend absorbing those changes no later than + * next transaction start. Hence, RelationBuildDesc() loops until it finishes + * without accepting a relevant invalidation. (Most invalidation consumers + * don't do this.) + */ +typedef struct inprogressent +{ + Oid reloid; /* OID of relation being built */ + bool invalidated; /* whether an invalidation arrived for it */ +} InProgressEnt; + +static InProgressEnt *in_progress_list; +static int in_progress_list_len; +static int in_progress_list_maxlen; + /* * eoxact_list[] stores the OIDs of relations that (might) need AtEOXact * cleanup work. This list intentionally has limited size; if it overflows, @@ -1043,6 +1061,7 @@ equalRSDesc(RowSecurityDesc *rsdesc1, RowSecurityDesc *rsdesc2) static Relation RelationBuildDesc(Oid targetRelId, bool insertIt) { + int in_progress_offset; Relation relation; Oid relid; HeapTuple pg_class_tuple; @@ -1070,6 +1089,21 @@ RelationBuildDesc(Oid targetRelId, bool insertIt) oldcxt = MemoryContextSwitchTo(tmpcxt); #endif + /* Register to catch invalidation messages */ + if (in_progress_list_len >= in_progress_list_maxlen) + { + int allocsize; + + allocsize = in_progress_list_maxlen * 2; + in_progress_list = repalloc(in_progress_list, + allocsize * sizeof(*in_progress_list)); + in_progress_list_maxlen = allocsize; + } + in_progress_offset = in_progress_list_len++; + in_progress_list[in_progress_offset].reloid = targetRelId; +retry: + in_progress_list[in_progress_offset].invalidated = false; + /* * find the tuple in pg_class corresponding to the given relation id */ @@ -1085,6 +1119,8 @@ RelationBuildDesc(Oid targetRelId, bool insertIt) MemoryContextSwitchTo(oldcxt); MemoryContextDelete(tmpcxt); #endif + Assert(in_progress_offset + 1 == in_progress_list_len); + in_progress_list_len--; return NULL; } @@ -1244,6 +1280,21 @@ RelationBuildDesc(Oid targetRelId, bool insertIt) */ heap_freetuple(pg_class_tuple); + /* + * If an invalidation arrived mid-build, start over. Between here and the + * end of this function, don't add code that does or reasonably could read + * system catalogs. That range must be free from invalidation processing + * for the !insertIt case. For the insertIt case, RelationCacheInsert() + * will enroll this relation in ordinary relcache invalidation processing, + */ + if (in_progress_list[in_progress_offset].invalidated) + { + RelationDestroyRelation(relation, false); + goto retry; + } + Assert(in_progress_offset + 1 == in_progress_list_len); + in_progress_list_len--; + /* * Insert newly created relation into relcache hash table, if requested. * @@ -2586,6 +2637,14 @@ RelationClearRelation(Relation relation, bool rebuild) /* Build temporary entry, but don't link it into hashtable */ newrel = RelationBuildDesc(save_relid, false); + + /* + * Between here and the end of the swap, don't add code that does or + * reasonably could read system catalogs. That range must be free + * from invalidation processing. See RelationBuildDesc() manipulation + * of in_progress_list. + */ + if (newrel == NULL) { /* @@ -2816,6 +2875,14 @@ RelationCacheInvalidateEntry(Oid relationId) relcacheInvalsReceived++; RelationFlushRelation(relation); } + else + { + int i; + + for (i = 0; i < in_progress_list_len; i++) + if (in_progress_list[i].reloid == relationId) + in_progress_list[i].invalidated = true; + } } /* @@ -2824,11 +2891,11 @@ RelationCacheInvalidateEntry(Oid relationId) * and rebuild those with positive reference counts. Also reset the smgr * relation cache and re-read relation mapping data. * - * This is currently used only to recover from SI message buffer overflow, - * so we do not touch relations having new-in-transaction relfilenodes; they - * cannot be targets of cross-backend SI updates (and our own updates now go - * through a separate linked list that isn't limited by the SI message - * buffer size). + * Apart from debug_discard_caches, this is currently used only to recover + * from SI message buffer overflow, so we do not touch relations having + * new-in-transaction relfilenodes; they cannot be targets of cross-backend + * SI updates (and our own updates now go through a separate linked list + * that isn't limited by the SI message buffer size). * * We do this in two phases: the first pass deletes deletable items, and * the second one rebuilds the rebuildable items. This is essential for @@ -2846,9 +2913,14 @@ RelationCacheInvalidateEntry(Oid relationId) * second pass processes nailed-in-cache items before other nondeletable * items. This should ensure that system catalogs are up to date before * we attempt to use them to reload information about other open relations. + * + * After those two phases of work having immediate effects, we normally + * signal any RelationBuildDesc() on the stack to start over. However, we + * don't do this if called as part of debug_discard_caches. Otherwise, + * RelationBuildDesc() would become an infinite loop. */ void -RelationCacheInvalidate(void) +RelationCacheInvalidate(bool debug_discard) { HASH_SEQ_STATUS status; RelIdCacheEnt *idhentry; @@ -2856,6 +2928,7 @@ RelationCacheInvalidate(void) List *rebuildFirstList = NIL; List *rebuildList = NIL; ListCell *l; + int i; /* * Reload relation mapping data before starting to reconstruct cache. @@ -2942,6 +3015,11 @@ RelationCacheInvalidate(void) RelationClearRelation(relation, true); } list_free(rebuildList); + + if (!debug_discard) + /* Any RelationBuildDesc() on the stack must start over. */ + for (i = 0; i < in_progress_list_len; i++) + in_progress_list[i].invalidated = true; } /* @@ -3092,6 +3170,13 @@ AtEOXact_RelationCache(bool isCommit) RelIdCacheEnt *idhentry; int i; + /* + * Forget in_progress_list. This is relevant when we're aborting due to + * an error during RelationBuildDesc(). + */ + Assert(in_progress_list_len == 0 || !isCommit); + in_progress_list_len = 0; + /* * Unless the eoxact_list[] overflowed, we only need to examine the rels * listed in it. Otherwise fall back on a hash_seq_search scan. @@ -3238,6 +3323,14 @@ AtEOSubXact_RelationCache(bool isCommit, SubTransactionId mySubid, RelIdCacheEnt *idhentry; int i; + /* + * Forget in_progress_list. This is relevant when we're aborting due to + * an error during RelationBuildDesc(). We don't commit subtransactions + * during RelationBuildDesc(). + */ + Assert(in_progress_list_len == 0 || !isCommit); + in_progress_list_len = 0; + /* * Unless the eoxact_list[] overflowed, we only need to examine the rels * listed in it. Otherwise fall back on a hash_seq_search scan. Same @@ -3786,6 +3879,7 @@ void RelationCacheInitialize(void) { HASHCTL ctl; + int allocsize; /* * make sure cache memory context exists @@ -3802,6 +3896,15 @@ RelationCacheInitialize(void) RelationIdCache = hash_create("Relcache by OID", INITRELCACHESIZE, &ctl, HASH_ELEM | HASH_BLOBS); + /* + * reserve enough in_progress_list slots for many cases + */ + allocsize = 4; + in_progress_list = + MemoryContextAlloc(CacheMemoryContext, + allocsize * sizeof(*in_progress_list)); + in_progress_list_maxlen = allocsize; + /* * relation mapper needs to be initialized too */ diff --git a/src/include/utils/inval.h b/src/include/utils/inval.h index bc5081cf721..4c6b86c9610 100644 --- a/src/include/utils/inval.h +++ b/src/include/utils/inval.h @@ -61,4 +61,5 @@ extern void CacheRegisterRelcacheCallback(RelcacheCallbackFunction func, extern void CallSyscacheCallbacks(int cacheid, uint32 hashvalue); extern void InvalidateSystemCaches(void); +extern void InvalidateSystemCachesExtended(bool debug_discard); #endif /* INVAL_H */ diff --git a/src/include/utils/relcache.h b/src/include/utils/relcache.h index a432a407b08..ff478c3ba7f 100644 --- a/src/include/utils/relcache.h +++ b/src/include/utils/relcache.h @@ -120,7 +120,7 @@ extern void RelationForgetRelation(Oid rid); extern void RelationCacheInvalidateEntry(Oid relationId); -extern void RelationCacheInvalidate(void); +extern void RelationCacheInvalidate(bool debug_discard); extern void RelationCloseSmgrByOid(Oid relationId); diff --git a/src/test/perl/PostgresNode.pm b/src/test/perl/PostgresNode.pm index 52f552be85b..cbcb74866b9 100644 --- a/src/test/perl/PostgresNode.pm +++ b/src/test/perl/PostgresNode.pm @@ -1638,6 +1638,141 @@ sub interactive_psql return $harness; } +# Common sub of pgbench-invoking interfaces. Makes any requested script files +# and returns pgbench command-line options causing use of those files. +sub _pgbench_make_files +{ + my ($self, $files) = @_; + my @file_opts; + + if (defined $files) + { + + # note: files are ordered for determinism + for my $fn (sort keys %$files) + { + my $filename = $self->basedir . '/' . $fn; + push @file_opts, '-f', $filename; + + # cleanup file weight + $filename =~ s/\@\d+$//; + + #push @filenames, $filename; + # filenames are expected to be unique on a test + if (-e $filename) + { + ok(0, "$filename must not already exist"); + unlink $filename or die "cannot unlink $filename: $!"; + } + TestLib::append_to_file($filename, $$files{$fn}); + } + } + + return @file_opts; +} + +=pod + +=item $node->pgbench($opts, $stat, $out, $err, $name, $files, @args) + +Invoke B, with parameters and files. + +=over + +=item $opts + +Options as a string to be split on spaces. + +=item $stat + +Expected exit status. + +=item $out + +Reference to a regexp list that must match stdout. + +=item $err + +Reference to a regexp list that must match stderr. + +=item $name + +Name of test for error messages. + +=item $files + +Reference to filename/contents dictionary. + +=item @args + +Further raw options or arguments. + +=back + +=cut + +sub pgbench +{ + local $Test::Builder::Level = $Test::Builder::Level + 1; + + my ($self, $opts, $stat, $out, $err, $name, $files, @args) = @_; + my @cmd = ( + 'pgbench', + split(/\s+/, $opts), + $self->_pgbench_make_files($files), @args); + + $self->command_checks_all(\@cmd, $stat, $out, $err, $name); +} + +=pod + +=item $node->background_pgbench($opts, $files, \$stdout, $timer) => harness + +Invoke B and return an IPC::Run harness object. The process's stdin +is empty, and its stdout and stderr go to the $stdout scalar reference. This +allows the caller to act on other parts of the system while B is +running. Errors from B are the caller's problem. + +The specified timer object is attached to the harness, as well. It's caller's +responsibility to select the timeout length, and to restart the timer after +each command if the timeout is per-command. + +Be sure to "finish" the harness when done with it. + +=over + +=item $opts + +Options as a string to be split on spaces. + +=item $files + +Reference to filename/contents dictionary. + +=back + +=cut + +sub background_pgbench +{ + my ($self, $opts, $files, $stdout, $timer) = @_; + + my @cmd = + ('pgbench', split(/\s+/, $opts), $self->_pgbench_make_files($files)); + + local $ENV{PGHOST} = $self->host; + local $ENV{PGPORT} = $self->port; + + my $stdin = ""; + # IPC::Run would otherwise append to existing contents: + $$stdout = "" if ref($stdout); + + my $harness = IPC::Run::start \@cmd, '<', \$stdin, '>', $stdout, '2>&1', + $timer; + + return $harness; +} + =pod =item $node->poll_query_until($dbname, $query [, $expected ]) diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 918d14bcae2..50fdb17fa3f 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1044,6 +1044,7 @@ ImportForeignSchemaStmt ImportForeignSchemaType ImportForeignSchema_function ImportQual +InProgressEnt IncludeWal InclusionOpaque IncrementVarSublevelsUp_context