diff options
Diffstat (limited to 'src/backend/access')
28 files changed, 1320 insertions, 926 deletions
diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 01e1db7f856..4204088fa0d 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -68,7 +68,7 @@ typedef struct BrinShared int scantuplesortstates; /* Query ID, for report in worker processes */ - uint64 queryid; + int64 queryid; /* * workersdonecv is used to monitor the progress of workers. All parallel diff --git a/src/backend/access/common/reloptions.c b/src/backend/access/common/reloptions.c index 46c1dce222d..50747c16396 100644 --- a/src/backend/access/common/reloptions.c +++ b/src/backend/access/common/reloptions.c @@ -1243,8 +1243,9 @@ transformRelOptions(Datum oldOptions, List *defList, const char *namspace, } else { - text *t; + const char *name; const char *value; + text *t; Size len; /* @@ -1291,11 +1292,19 @@ transformRelOptions(Datum oldOptions, List *defList, const char *namspace, * have just "name", assume "name=true" is meant. Note: the * namespace is not output. */ + name = def->defname; if (def->arg != NULL) value = defGetString(def); else value = "true"; + /* Insist that name not contain "=", else "a=b=c" is ambiguous */ + if (strchr(name, '=') != NULL) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid option name \"%s\": must not contain \"=\"", + name))); + /* * This is not a great place for this test, but there's no other * convenient place to filter the option out. As WITH (oids = @@ -1303,7 +1312,7 @@ transformRelOptions(Datum oldOptions, List *defList, const char *namspace, * amount of ugly. */ if (acceptOidsOff && def->defnamespace == NULL && - strcmp(def->defname, "oids") == 0) + strcmp(name, "oids") == 0) { if (defGetBoolean(def)) ereport(ERROR, @@ -1313,11 +1322,11 @@ transformRelOptions(Datum oldOptions, List *defList, const char *namspace, continue; } - len = VARHDRSZ + strlen(def->defname) + 1 + strlen(value); + len = VARHDRSZ + strlen(name) + 1 + strlen(value); /* +1 leaves room for sprintf's trailing null */ t = (text *) palloc(len + 1); SET_VARSIZE(t, len); - sprintf(VARDATA(t), "%s=%s", def->defname, value); + sprintf(VARDATA(t), "%s=%s", name, value); astate = accumArrayResult(astate, PointerGetDatum(t), false, TEXTOID, diff --git a/src/backend/access/common/tupdesc.c b/src/backend/access/common/tupdesc.c index ffd0c78f905..020d00cd01c 100644 --- a/src/backend/access/common/tupdesc.c +++ b/src/backend/access/common/tupdesc.c @@ -142,11 +142,18 @@ void verify_compact_attribute(TupleDesc tupdesc, int attnum) { #ifdef USE_ASSERT_CHECKING - CompactAttribute *cattr = &tupdesc->compact_attrs[attnum]; + CompactAttribute cattr; Form_pg_attribute attr = TupleDescAttr(tupdesc, attnum); CompactAttribute tmp; /* + * Make a temp copy of the TupleDesc's CompactAttribute. This may be a + * shared TupleDesc and the attcacheoff might get changed by another + * backend. + */ + memcpy(&cattr, &tupdesc->compact_attrs[attnum], sizeof(CompactAttribute)); + + /* * Populate the temporary CompactAttribute from the corresponding * Form_pg_attribute */ @@ -156,11 +163,11 @@ verify_compact_attribute(TupleDesc tupdesc, int attnum) * Make the attcacheoff match since it's been reset to -1 by * populate_compact_attribute_internal. Same with attnullability. */ - tmp.attcacheoff = cattr->attcacheoff; - tmp.attnullability = cattr->attnullability; + tmp.attcacheoff = cattr.attcacheoff; + tmp.attnullability = cattr.attnullability; /* Check the freshly populated CompactAttribute matches the TupleDesc's */ - Assert(memcmp(&tmp, cattr, sizeof(CompactAttribute)) == 0); + Assert(memcmp(&tmp, &cattr, sizeof(CompactAttribute)) == 0); #endif } diff --git a/src/backend/access/gist/gistutil.c b/src/backend/access/gist/gistutil.c index a6b701943d3..c0aa7d0222f 100644 --- a/src/backend/access/gist/gistutil.c +++ b/src/backend/access/gist/gistutil.c @@ -1058,11 +1058,11 @@ gistGetFakeLSN(Relation rel) } /* - * This is a stratnum support function for GiST opclasses that use the - * RT*StrategyNumber constants. + * This is a stratnum translation support function for GiST opclasses that use + * the RT*StrategyNumber constants. */ Datum -gist_stratnum_common(PG_FUNCTION_ARGS) +gist_translate_cmptype_common(PG_FUNCTION_ARGS) { CompareType cmptype = PG_GETARG_INT32(0); @@ -1090,9 +1090,9 @@ gist_stratnum_common(PG_FUNCTION_ARGS) /* * Returns the opclass's private stratnum used for the given compare type. * - * Calls the opclass's GIST_STRATNUM_PROC support function, if any, - * and returns the result. - * Returns InvalidStrategy if the function is not defined. + * Calls the opclass's GIST_TRANSLATE_CMPTYPE_PROC support function, if any, + * and returns the result. Returns InvalidStrategy if the function is not + * defined. */ StrategyNumber gisttranslatecmptype(CompareType cmptype, Oid opfamily) @@ -1101,7 +1101,7 @@ gisttranslatecmptype(CompareType cmptype, Oid opfamily) Datum result; /* Check whether the function is provided. */ - funcid = get_opfamily_proc(opfamily, ANYOID, ANYOID, GIST_STRATNUM_PROC); + funcid = get_opfamily_proc(opfamily, ANYOID, ANYOID, GIST_TRANSLATE_CMPTYPE_PROC); if (!OidIsValid(funcid)) return InvalidStrategy; diff --git a/src/backend/access/gist/gistvalidate.c b/src/backend/access/gist/gistvalidate.c index 2a49e6d20f0..2ed6f74fce9 100644 --- a/src/backend/access/gist/gistvalidate.c +++ b/src/backend/access/gist/gistvalidate.c @@ -138,7 +138,7 @@ gistvalidate(Oid opclassoid) ok = check_amproc_signature(procform->amproc, VOIDOID, true, 1, 1, INTERNALOID); break; - case GIST_STRATNUM_PROC: + case GIST_TRANSLATE_CMPTYPE_PROC: ok = check_amproc_signature(procform->amproc, INT2OID, true, 1, 1, INT4OID) && procform->amproclefttype == ANYOID && @@ -265,7 +265,7 @@ gistvalidate(Oid opclassoid) if (i == GIST_DISTANCE_PROC || i == GIST_FETCH_PROC || i == GIST_COMPRESS_PROC || i == GIST_DECOMPRESS_PROC || i == GIST_OPTIONS_PROC || i == GIST_SORTSUPPORT_PROC || - i == GIST_STRATNUM_PROC) + i == GIST_TRANSLATE_CMPTYPE_PROC) continue; /* optional methods */ ereport(INFO, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), @@ -336,7 +336,7 @@ gistadjustmembers(Oid opfamilyoid, case GIST_FETCH_PROC: case GIST_OPTIONS_PROC: case GIST_SORTSUPPORT_PROC: - case GIST_STRATNUM_PROC: + case GIST_TRANSLATE_CMPTYPE_PROC: /* Optional, so force it to be a soft family dependency */ op->ref_is_hard = false; op->ref_is_family = true; diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c index 9ec8cda1c68..0dcd6ee817e 100644 --- a/src/backend/access/heap/heapam.c +++ b/src/backend/access/heap/heapam.c @@ -213,6 +213,27 @@ static const int MultiXactStatusLock[MaxMultiXactStatus + 1] = #define TUPLOCK_from_mxstatus(status) \ (MultiXactStatusLock[(status)]) +/* + * Check that we have a valid snapshot if we might need TOAST access. + */ +static inline void +AssertHasSnapshotForToast(Relation rel) +{ +#ifdef USE_ASSERT_CHECKING + + /* bootstrap mode in particular breaks this rule */ + if (!IsNormalProcessingMode()) + return; + + /* if the relation doesn't have a TOAST table, we are good */ + if (!OidIsValid(rel->rd_rel->reltoastrelid)) + return; + + Assert(HaveRegisteredOrActiveSnapshot()); + +#endif /* USE_ASSERT_CHECKING */ +} + /* ---------------------------------------------------------------- * heap support routines * ---------------------------------------------------------------- @@ -2066,6 +2087,8 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid, Assert(HeapTupleHeaderGetNatts(tup->t_data) <= RelationGetNumberOfAttributes(relation)); + AssertHasSnapshotForToast(relation); + /* * Fill in tuple header fields and toast the tuple if necessary. * @@ -2343,6 +2366,8 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples, /* currently not needed (thus unsupported) for heap_multi_insert() */ Assert(!(options & HEAP_INSERT_NO_LOGICAL)); + AssertHasSnapshotForToast(relation); + needwal = RelationNeedsWAL(relation); saveFreeSpace = RelationGetTargetPageFreeSpace(relation, HEAP_DEFAULT_FILLFACTOR); @@ -2765,6 +2790,8 @@ heap_delete(Relation relation, ItemPointer tid, Assert(ItemPointerIsValid(tid)); + AssertHasSnapshotForToast(relation); + /* * Forbid this during a parallel operation, lest it allocate a combo CID. * Other workers might need that combo CID for visibility checks, and we @@ -3260,6 +3287,8 @@ heap_update(Relation relation, ItemPointer otid, HeapTuple newtup, Assert(HeapTupleHeaderGetNatts(newtup->t_data) <= RelationGetNumberOfAttributes(relation)); + AssertHasSnapshotForToast(relation); + /* * Forbid this during a parallel operation, lest it allocate a combo CID. * Other workers might need that combo CID for visibility checks, and we @@ -4953,7 +4982,7 @@ l3: case LockWaitError: if (!ConditionalMultiXactIdWait((MultiXactId) xwait, status, infomask, relation, - NULL, log_lock_failure)) + NULL, log_lock_failures)) ereport(ERROR, (errcode(ERRCODE_LOCK_NOT_AVAILABLE), errmsg("could not obtain lock on row in relation \"%s\"", @@ -4991,7 +5020,7 @@ l3: } break; case LockWaitError: - if (!ConditionalXactLockTableWait(xwait, log_lock_failure)) + if (!ConditionalXactLockTableWait(xwait, log_lock_failures)) ereport(ERROR, (errcode(ERRCODE_LOCK_NOT_AVAILABLE), errmsg("could not obtain lock on row in relation \"%s\"", @@ -5256,7 +5285,7 @@ heap_acquire_tuplock(Relation relation, ItemPointer tid, LockTupleMode mode, break; case LockWaitError: - if (!ConditionalLockTupleTuplock(relation, tid, mode, log_lock_failure)) + if (!ConditionalLockTupleTuplock(relation, tid, mode, log_lock_failures)) ereport(ERROR, (errcode(ERRCODE_LOCK_NOT_AVAILABLE), errmsg("could not obtain lock on row in relation \"%s\"", diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index ac082fefa77..cb4bc35c93e 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -464,7 +464,7 @@ tuple_lock_retry: return TM_WouldBlock; break; case LockWaitError: - if (!ConditionalXactLockTableWait(SnapshotDirty.xmax, log_lock_failure)) + if (!ConditionalXactLockTableWait(SnapshotDirty.xmax, log_lock_failures)) ereport(ERROR, (errcode(ERRCODE_LOCK_NOT_AVAILABLE), errmsg("could not obtain lock on row in relation \"%s\"", diff --git a/src/backend/access/heap/heapam_xlog.c b/src/backend/access/heap/heapam_xlog.c index 30f4c2d3c67..eb4bd3d6ae3 100644 --- a/src/backend/access/heap/heapam_xlog.c +++ b/src/backend/access/heap/heapam_xlog.c @@ -438,6 +438,9 @@ heap_xlog_insert(XLogReaderState *record) ItemPointerSetBlockNumber(&target_tid, blkno); ItemPointerSetOffsetNumber(&target_tid, xlrec->offnum); + /* No freezing in the heap_insert() code path */ + Assert(!(xlrec->flags & XLH_INSERT_ALL_FROZEN_SET)); + /* * The visibility map may need to be fixed even if the heap page is * already up-to-date. @@ -508,10 +511,6 @@ heap_xlog_insert(XLogReaderState *record) if (xlrec->flags & XLH_INSERT_ALL_VISIBLE_CLEARED) PageClearAllVisible(page); - /* XLH_INSERT_ALL_FROZEN_SET implies that all tuples are visible */ - if (xlrec->flags & XLH_INSERT_ALL_FROZEN_SET) - PageSetAllVisible(page); - MarkBufferDirty(buffer); } if (BufferIsValid(buffer)) diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c index f28326bad09..14036c27e87 100644 --- a/src/backend/access/heap/vacuumlazy.c +++ b/src/backend/access/heap/vacuumlazy.c @@ -423,7 +423,7 @@ typedef struct LVSavedErrInfo /* non-export function prototypes */ static void lazy_scan_heap(LVRelState *vacrel); static void heap_vacuum_eager_scan_setup(LVRelState *vacrel, - VacuumParams *params); + const VacuumParams params); static BlockNumber heap_vac_scan_next_block(ReadStream *stream, void *callback_private_data, void *per_buffer_data); @@ -431,7 +431,7 @@ static void find_next_unskippable_block(LVRelState *vacrel, bool *skipsallvis); static bool lazy_scan_new_or_empty(LVRelState *vacrel, Buffer buf, BlockNumber blkno, Page page, bool sharelock, Buffer vmbuffer); -static void lazy_scan_prune(LVRelState *vacrel, Buffer buf, +static int lazy_scan_prune(LVRelState *vacrel, Buffer buf, BlockNumber blkno, Page page, Buffer vmbuffer, bool all_visible_according_to_vm, bool *has_lpdead_items, bool *vm_page_frozen); @@ -485,7 +485,7 @@ static void restore_vacuum_error_info(LVRelState *vacrel, * vacuum options or for relfrozenxid/relminmxid advancement. */ static void -heap_vacuum_eager_scan_setup(LVRelState *vacrel, VacuumParams *params) +heap_vacuum_eager_scan_setup(LVRelState *vacrel, const VacuumParams params) { uint32 randseed; BlockNumber allvisible; @@ -504,7 +504,7 @@ heap_vacuum_eager_scan_setup(LVRelState *vacrel, VacuumParams *params) vacrel->eager_scan_remaining_successes = 0; /* If eager scanning is explicitly disabled, just return. */ - if (params->max_eager_freeze_failure_rate == 0) + if (params.max_eager_freeze_failure_rate == 0) return; /* @@ -581,11 +581,11 @@ heap_vacuum_eager_scan_setup(LVRelState *vacrel, VacuumParams *params) vacrel->next_eager_scan_region_start = randseed % EAGER_SCAN_REGION_SIZE; - Assert(params->max_eager_freeze_failure_rate > 0 && - params->max_eager_freeze_failure_rate <= 1); + Assert(params.max_eager_freeze_failure_rate > 0 && + params.max_eager_freeze_failure_rate <= 1); vacrel->eager_scan_max_fails_per_region = - params->max_eager_freeze_failure_rate * + params.max_eager_freeze_failure_rate * EAGER_SCAN_REGION_SIZE; /* @@ -612,7 +612,7 @@ heap_vacuum_eager_scan_setup(LVRelState *vacrel, VacuumParams *params) * and locked the relation. */ void -heap_vacuum_rel(Relation rel, VacuumParams *params, +heap_vacuum_rel(Relation rel, const VacuumParams params, BufferAccessStrategy bstrategy) { LVRelState *vacrel; @@ -634,9 +634,9 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, ErrorContextCallback errcallback; char **indnames = NULL; - verbose = (params->options & VACOPT_VERBOSE) != 0; + verbose = (params.options & VACOPT_VERBOSE) != 0; instrument = (verbose || (AmAutoVacuumWorkerProcess() && - params->log_min_duration >= 0)); + params.log_min_duration >= 0)); if (instrument) { pg_rusage_init(&ru0); @@ -699,9 +699,9 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, * The truncate param allows user to avoid attempting relation truncation, * though it can't force truncation to happen. */ - Assert(params->index_cleanup != VACOPTVALUE_UNSPECIFIED); - Assert(params->truncate != VACOPTVALUE_UNSPECIFIED && - params->truncate != VACOPTVALUE_AUTO); + Assert(params.index_cleanup != VACOPTVALUE_UNSPECIFIED); + Assert(params.truncate != VACOPTVALUE_UNSPECIFIED && + params.truncate != VACOPTVALUE_AUTO); /* * While VacuumFailSafeActive is reset to false before calling this, we @@ -711,14 +711,14 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, vacrel->consider_bypass_optimization = true; vacrel->do_index_vacuuming = true; vacrel->do_index_cleanup = true; - vacrel->do_rel_truncate = (params->truncate != VACOPTVALUE_DISABLED); - if (params->index_cleanup == VACOPTVALUE_DISABLED) + vacrel->do_rel_truncate = (params.truncate != VACOPTVALUE_DISABLED); + if (params.index_cleanup == VACOPTVALUE_DISABLED) { /* Force disable index vacuuming up-front */ vacrel->do_index_vacuuming = false; vacrel->do_index_cleanup = false; } - else if (params->index_cleanup == VACOPTVALUE_ENABLED) + else if (params.index_cleanup == VACOPTVALUE_ENABLED) { /* Force index vacuuming. Note that failsafe can still bypass. */ vacrel->consider_bypass_optimization = false; @@ -726,7 +726,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, else { /* Default/auto, make all decisions dynamically */ - Assert(params->index_cleanup == VACOPTVALUE_AUTO); + Assert(params.index_cleanup == VACOPTVALUE_AUTO); } /* Initialize page counters explicitly (be tidy) */ @@ -757,7 +757,6 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, vacrel->vm_new_visible_pages = 0; vacrel->vm_new_visible_frozen_pages = 0; vacrel->vm_new_frozen_pages = 0; - vacrel->rel_pages = orig_rel_pages = RelationGetNumberOfBlocks(rel); /* * Get cutoffs that determine which deleted tuples are considered DEAD, @@ -776,7 +775,9 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, * to increase the number of dead tuples it can prune away.) */ vacrel->aggressive = vacuum_get_cutoffs(rel, params, &vacrel->cutoffs); + vacrel->rel_pages = orig_rel_pages = RelationGetNumberOfBlocks(rel); vacrel->vistest = GlobalVisTestFor(rel); + /* Initialize state used to track oldest extant XID/MXID */ vacrel->NewRelfrozenXid = vacrel->cutoffs.OldestXmin; vacrel->NewRelminMxid = vacrel->cutoffs.OldestMxact; @@ -788,7 +789,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, */ vacrel->skippedallvis = false; skipwithvm = true; - if (params->options & VACOPT_DISABLE_PAGE_SKIPPING) + if (params.options & VACOPT_DISABLE_PAGE_SKIPPING) { /* * Force aggressive mode, and disable skipping blocks using the @@ -829,7 +830,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, * is already dangerously old.) */ lazy_check_wraparound_failsafe(vacrel); - dead_items_alloc(vacrel, params->nworkers); + dead_items_alloc(vacrel, params.nworkers); /* * Call lazy_scan_heap to perform all required heap pruning, index @@ -946,9 +947,9 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, { TimestampTz endtime = GetCurrentTimestamp(); - if (verbose || params->log_min_duration == 0 || + if (verbose || params.log_min_duration == 0 || TimestampDifferenceExceeds(starttime, endtime, - params->log_min_duration)) + params.log_min_duration)) { long secs_dur; int usecs_dur; @@ -983,10 +984,10 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, * Aggressiveness already reported earlier, in dedicated * VACUUM VERBOSE ereport */ - Assert(!params->is_wraparound); + Assert(!params.is_wraparound); msgfmt = _("finished vacuuming \"%s.%s.%s\": index scans: %d\n"); } - else if (params->is_wraparound) + else if (params.is_wraparound) { /* * While it's possible for a VACUUM to be both is_wraparound @@ -1244,6 +1245,7 @@ lazy_scan_heap(LVRelState *vacrel) Buffer buf; Page page; uint8 blk_info = 0; + int ndeleted = 0; bool has_lpdead_items; void *per_buffer_data = NULL; bool vm_page_frozen = false; @@ -1386,10 +1388,10 @@ lazy_scan_heap(LVRelState *vacrel) * line pointers previously marked LP_DEAD. */ if (got_cleanup_lock) - lazy_scan_prune(vacrel, buf, blkno, page, - vmbuffer, - blk_info & VAC_BLK_ALL_VISIBLE_ACCORDING_TO_VM, - &has_lpdead_items, &vm_page_frozen); + ndeleted = lazy_scan_prune(vacrel, buf, blkno, page, + vmbuffer, + blk_info & VAC_BLK_ALL_VISIBLE_ACCORDING_TO_VM, + &has_lpdead_items, &vm_page_frozen); /* * Count an eagerly scanned page as a failure or a success. @@ -1413,12 +1415,26 @@ lazy_scan_heap(LVRelState *vacrel) if (vm_page_frozen) { - Assert(vacrel->eager_scan_remaining_successes > 0); - vacrel->eager_scan_remaining_successes--; + if (vacrel->eager_scan_remaining_successes > 0) + vacrel->eager_scan_remaining_successes--; if (vacrel->eager_scan_remaining_successes == 0) { /* + * Report only once that we disabled eager scanning. We + * may eagerly read ahead blocks in excess of the success + * or failure caps before attempting to freeze them, so we + * could reach here even after disabling additional eager + * scanning. + */ + if (vacrel->eager_scan_max_fails_per_region > 0) + ereport(vacrel->verbose ? INFO : DEBUG2, + (errmsg("disabling eager scanning after freezing %u eagerly scanned blocks of relation \"%s.%s.%s\"", + orig_eager_scan_success_limit, + vacrel->dbname, vacrel->relnamespace, + vacrel->relname))); + + /* * If we hit our success cap, permanently disable eager * scanning by setting the other eager scan management * fields to their disabled values. @@ -1426,19 +1442,10 @@ lazy_scan_heap(LVRelState *vacrel) vacrel->eager_scan_remaining_fails = 0; vacrel->next_eager_scan_region_start = InvalidBlockNumber; vacrel->eager_scan_max_fails_per_region = 0; - - ereport(vacrel->verbose ? INFO : DEBUG2, - (errmsg("disabling eager scanning after freezing %u eagerly scanned blocks of \"%s.%s.%s\"", - orig_eager_scan_success_limit, - vacrel->dbname, vacrel->relnamespace, - vacrel->relname))); } } - else - { - Assert(vacrel->eager_scan_remaining_fails > 0); + else if (vacrel->eager_scan_remaining_fails > 0) vacrel->eager_scan_remaining_fails--; - } } /* @@ -1475,7 +1482,7 @@ lazy_scan_heap(LVRelState *vacrel) * table has indexes. There will only be newly-freed space if we * held the cleanup lock and lazy_scan_prune() was called. */ - if (got_cleanup_lock && vacrel->nindexes == 0 && has_lpdead_items && + if (got_cleanup_lock && vacrel->nindexes == 0 && ndeleted > 0 && blkno - next_fsm_block_to_vacuum >= VACUUM_FSM_EVERY_PAGES) { FreeSpaceMapVacuumRange(vacrel->rel, next_fsm_block_to_vacuum, @@ -1866,8 +1873,6 @@ lazy_scan_new_or_empty(LVRelState *vacrel, Buffer buf, BlockNumber blkno, */ if (!PageIsAllVisible(page)) { - uint8 old_vmbits; - START_CRIT_SECTION(); /* mark buffer dirty before writing a WAL record */ @@ -1887,24 +1892,16 @@ lazy_scan_new_or_empty(LVRelState *vacrel, Buffer buf, BlockNumber blkno, log_newpage_buffer(buf, true); PageSetAllVisible(page); - old_vmbits = visibilitymap_set(vacrel->rel, blkno, buf, - InvalidXLogRecPtr, - vmbuffer, InvalidTransactionId, - VISIBILITYMAP_ALL_VISIBLE | - VISIBILITYMAP_ALL_FROZEN); + visibilitymap_set(vacrel->rel, blkno, buf, + InvalidXLogRecPtr, + vmbuffer, InvalidTransactionId, + VISIBILITYMAP_ALL_VISIBLE | + VISIBILITYMAP_ALL_FROZEN); END_CRIT_SECTION(); - /* - * If the page wasn't already set all-visible and/or all-frozen in - * the VM, count it as newly set for logging. - */ - if ((old_vmbits & VISIBILITYMAP_ALL_VISIBLE) == 0) - { - vacrel->vm_new_visible_pages++; - vacrel->vm_new_visible_frozen_pages++; - } - else if ((old_vmbits & VISIBILITYMAP_ALL_FROZEN) == 0) - vacrel->vm_new_frozen_pages++; + /* Count the newly all-frozen pages for logging */ + vacrel->vm_new_visible_pages++; + vacrel->vm_new_visible_frozen_pages++; } freespace = PageGetHeapFreeSpace(page); @@ -1940,8 +1937,10 @@ cmpOffsetNumbers(const void *a, const void *b) * *vm_page_frozen is set to true if the page is newly set all-frozen in the * VM. The caller currently only uses this for determining whether an eagerly * scanned page was successfully set all-frozen. + * + * Returns the number of tuples deleted from the page during HOT pruning. */ -static void +static int lazy_scan_prune(LVRelState *vacrel, Buffer buf, BlockNumber blkno, @@ -2212,6 +2211,8 @@ lazy_scan_prune(LVRelState *vacrel, *vm_page_frozen = true; } } + + return presult.ndeleted; } /* @@ -2909,7 +2910,6 @@ lazy_vacuum_heap_page(LVRelState *vacrel, BlockNumber blkno, Buffer buffer, if (heap_page_is_all_visible(vacrel, buffer, &visibility_cutoff_xid, &all_frozen)) { - uint8 old_vmbits; uint8 flags = VISIBILITYMAP_ALL_VISIBLE; if (all_frozen) @@ -2919,25 +2919,15 @@ lazy_vacuum_heap_page(LVRelState *vacrel, BlockNumber blkno, Buffer buffer, } PageSetAllVisible(page); - old_vmbits = visibilitymap_set(vacrel->rel, blkno, buffer, - InvalidXLogRecPtr, - vmbuffer, visibility_cutoff_xid, - flags); - - /* - * If the page wasn't already set all-visible and/or all-frozen in the - * VM, count it as newly set for logging. - */ - if ((old_vmbits & VISIBILITYMAP_ALL_VISIBLE) == 0) - { - vacrel->vm_new_visible_pages++; - if (all_frozen) - vacrel->vm_new_visible_frozen_pages++; - } + visibilitymap_set(vacrel->rel, blkno, buffer, + InvalidXLogRecPtr, + vmbuffer, visibility_cutoff_xid, + flags); - else if ((old_vmbits & VISIBILITYMAP_ALL_FROZEN) == 0 && - all_frozen) - vacrel->vm_new_frozen_pages++; + /* Count the newly set VM page for logging */ + vacrel->vm_new_visible_pages++; + if (all_frozen) + vacrel->vm_new_visible_frozen_pages++; } /* Revert to the previous phase information for error traceback */ diff --git a/src/backend/access/nbtree/nbtpreprocesskeys.c b/src/backend/access/nbtree/nbtpreprocesskeys.c index a136e4bbfdf..21c519cd108 100644 --- a/src/backend/access/nbtree/nbtpreprocesskeys.c +++ b/src/backend/access/nbtree/nbtpreprocesskeys.c @@ -16,6 +16,7 @@ #include "postgres.h" #include "access/nbtree.h" +#include "common/int.h" #include "lib/qunique.h" #include "utils/array.h" #include "utils/lsyscache.h" @@ -56,6 +57,8 @@ static void _bt_skiparray_strat_decrement(IndexScanDesc scan, ScanKey arraysk, BTArrayKeyInfo *array); static void _bt_skiparray_strat_increment(IndexScanDesc scan, ScanKey arraysk, BTArrayKeyInfo *array); +static void _bt_unmark_keys(IndexScanDesc scan, int *keyDataMap); +static int _bt_reorder_array_cmp(const void *a, const void *b); static ScanKey _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys); static void _bt_preprocess_array_keys_final(IndexScanDesc scan, int *keyDataMap); static int _bt_num_array_keys(IndexScanDesc scan, Oid *skip_eq_ops_out, @@ -96,7 +99,7 @@ static int _bt_compare_array_elements(const void *a, const void *b, void *arg); * incomplete sets of cross-type operators, we may fail to detect redundant * or contradictory keys, but we can survive that.) * - * The output keys must be sorted by index attribute. Presently we expect + * Required output keys are sorted by index attribute. Presently we expect * (but verify) that the input keys are already so sorted --- this is done * by match_clauses_to_index() in indxpath.c. Some reordering of the keys * within each attribute may be done as a byproduct of the processing here. @@ -127,29 +130,36 @@ static int _bt_compare_array_elements(const void *a, const void *b, void *arg); * This has the potential to be much more efficient than a full index scan * (though it behaves like a full scan when there's many distinct "x" values). * - * If possible, redundant keys are eliminated: we keep only the tightest + * Typically, redundant keys are eliminated: we keep only the tightest * >/>= bound and the tightest </<= bound, and if there's an = key then * that's the only one returned. (So, we return either a single = key, * or one or two boundary-condition keys for each attr.) However, if we * cannot compare two keys for lack of a suitable cross-type operator, - * we cannot eliminate either. If there are two such keys of the same - * operator strategy, the second one is just pushed into the output array - * without further processing here. We may also emit both >/>= or both - * </<= keys if we can't compare them. The logic about required keys still - * works if we don't eliminate redundant keys. - * - * Note that one reason we need direction-sensitive required-key flags is - * precisely that we may not be able to eliminate redundant keys. Suppose - * we have "x > 4::int AND x > 10::bigint", and we are unable to determine - * which key is more restrictive for lack of a suitable cross-type operator. - * _bt_first will arbitrarily pick one of the keys to do the initial - * positioning with. If it picks x > 4, then the x > 10 condition will fail - * until we reach index entries > 10; but we can't stop the scan just because - * x > 10 is failing. On the other hand, if we are scanning backwards, then - * failure of either key is indeed enough to stop the scan. (In general, when - * inequality keys are present, the initial-positioning code only promises to - * position before the first possible match, not exactly at the first match, - * for a forward scan; or after the last match for a backward scan.) + * we cannot eliminate either key. + * + * When all redundant keys could not be eliminated, we'll output a key array + * that can more or less be treated as if it had no redundant keys. Suppose + * we have "x > 4::int AND x > 10::bigint AND x < 70", and we are unable to + * determine which > key is more restrictive for lack of a suitable cross-type + * operator. We'll arbitrarily pick one of the > keys; the other > key won't + * be marked required. Obviously, the scan will be less efficient if we + * choose x > 4 over x > 10 -- but it can still largely proceed as if there + * was only a single > condition. "x > 10" will be placed at the end of the + * so->keyData[] output array. It'll always be evaluated last, after the keys + * that could be marked required in the usual way (after "x > 4 AND x < 70"). + * This can sometimes result in so->keyData[] keys that aren't even in index + * attribute order (if the qual involves multiple attributes). The scan's + * required keys will still be in attribute order, though, so it can't matter. + * + * This scheme ensures that _bt_first always uses the same set of keys at the + * start of a forwards scan as those _bt_checkkeys uses to determine when to + * end a similar backwards scan (and vice-versa). _bt_advance_array_keys + * depends on this: it expects to be able to reliably predict what the next + * _bt_first call will do by testing whether _bt_checkkeys' routines report + * that the final tuple on the page is past the end of matches for the scan's + * keys with the scan direction flipped. If it is (if continuescan=false), + * then it follows that calling _bt_first will, at a minimum, relocate the + * scan to the very next leaf page (in the current scan direction). * * As a byproduct of this work, we can detect contradictory quals such * as "x = 1 AND x > 2". If we see that, we return so->qual_ok = false, @@ -188,7 +198,8 @@ _bt_preprocess_keys(IndexScanDesc scan) int numberOfEqualCols; ScanKey inkeys; BTScanKeyPreproc xform[BTMaxStrategyNumber]; - bool test_result; + bool test_result, + redundant_key_kept = false; AttrNumber attno; ScanKey arrayKeyData; int *keyDataMap = NULL; @@ -388,7 +399,8 @@ _bt_preprocess_keys(IndexScanDesc scan) xform[j].inkey = NULL; xform[j].inkeyi = -1; } - /* else, cannot determine redundancy, keep both keys */ + else + redundant_key_kept = true; } /* track number of attrs for which we have "=" keys */ numberOfEqualCols++; @@ -409,6 +421,8 @@ _bt_preprocess_keys(IndexScanDesc scan) else xform[BTLessStrategyNumber - 1].inkey = NULL; } + else + redundant_key_kept = true; } /* try to keep only one of >, >= */ @@ -426,6 +440,8 @@ _bt_preprocess_keys(IndexScanDesc scan) else xform[BTGreaterStrategyNumber - 1].inkey = NULL; } + else + redundant_key_kept = true; } /* @@ -466,25 +482,6 @@ _bt_preprocess_keys(IndexScanDesc scan) /* check strategy this key's operator corresponds to */ j = inkey->sk_strategy - 1; - /* if row comparison, push it directly to the output array */ - if (inkey->sk_flags & SK_ROW_HEADER) - { - ScanKey outkey = &so->keyData[new_numberOfKeys++]; - - memcpy(outkey, inkey, sizeof(ScanKeyData)); - if (arrayKeyData) - keyDataMap[new_numberOfKeys - 1] = i; - if (numberOfEqualCols == attno - 1) - _bt_mark_scankey_required(outkey); - - /* - * We don't support RowCompare using equality; such a qual would - * mess up the numberOfEqualCols tracking. - */ - Assert(j != (BTEqualStrategyNumber - 1)); - continue; - } - if (inkey->sk_strategy == BTEqualStrategyNumber && (inkey->sk_flags & SK_SEARCHARRAY)) { @@ -593,9 +590,8 @@ _bt_preprocess_keys(IndexScanDesc scan) * the new scan key. * * Note: We do things this way around so that our arrays are - * always in the same order as their corresponding scan keys, - * even with incomplete opfamilies. _bt_advance_array_keys - * depends on this. + * always in the same order as their corresponding scan keys. + * _bt_preprocess_array_keys_final expects this. */ ScanKey outkey = &so->keyData[new_numberOfKeys++]; @@ -607,6 +603,7 @@ _bt_preprocess_keys(IndexScanDesc scan) xform[j].inkey = inkey; xform[j].inkeyi = i; xform[j].arrayidx = arrayidx; + redundant_key_kept = true; } } } @@ -622,6 +619,15 @@ _bt_preprocess_keys(IndexScanDesc scan) if (arrayKeyData) _bt_preprocess_array_keys_final(scan, keyDataMap); + /* + * If there are remaining redundant inequality keys, we must make sure + * that each index attribute has no more than one required >/>= key, and + * no more than one required </<= key. Attributes that have one or more + * required = keys now must keep only one required key (the first = key). + */ + if (unlikely(redundant_key_kept) && so->qual_ok) + _bt_unmark_keys(scan, keyDataMap); + /* Could pfree arrayKeyData/keyDataMap now, but not worth the cycles */ } @@ -746,9 +752,12 @@ _bt_fix_scankey_strategy(ScanKey skey, int16 *indoption) * * Depending on the operator type, the key may be required for both scan * directions or just one. Also, if the key is a row comparison header, - * we have to mark its first subsidiary ScanKey as required. (Subsequent - * subsidiary ScanKeys are normally for lower-order columns, and thus - * cannot be required, since they're after the first non-equality scankey.) + * we have to mark the appropriate subsidiary ScanKeys as required. In such + * cases, the first subsidiary key is required, but subsequent ones are + * required only as long as they correspond to successive index columns and + * match the leading column as to sort direction. Otherwise the row + * comparison ordering is different from the index ordering and so we can't + * stop the scan on the basis of those lower-order columns. * * Note: when we set required-key flag bits in a subsidiary scankey, we are * scribbling on a data structure belonging to the index AM's caller, not on @@ -786,12 +795,25 @@ _bt_mark_scankey_required(ScanKey skey) if (skey->sk_flags & SK_ROW_HEADER) { ScanKey subkey = (ScanKey) DatumGetPointer(skey->sk_argument); + AttrNumber attno = skey->sk_attno; /* First subkey should be same column/operator as the header */ - Assert(subkey->sk_flags & SK_ROW_MEMBER); - Assert(subkey->sk_attno == skey->sk_attno); + Assert(subkey->sk_attno == attno); Assert(subkey->sk_strategy == skey->sk_strategy); - subkey->sk_flags |= addflags; + + for (;;) + { + Assert(subkey->sk_flags & SK_ROW_MEMBER); + if (subkey->sk_attno != attno) + break; /* non-adjacent key, so not required */ + if (subkey->sk_strategy != skey->sk_strategy) + break; /* wrong direction, so not required */ + subkey->sk_flags |= addflags; + if (subkey->sk_flags & SK_ROW_END) + break; + subkey++; + attno++; + } } } @@ -847,8 +869,7 @@ _bt_compare_scankey_args(IndexScanDesc scan, ScanKey op, cmp_op; StrategyNumber strat; - Assert(!((leftarg->sk_flags | rightarg->sk_flags) & - (SK_ROW_HEADER | SK_ROW_MEMBER))); + Assert(!((leftarg->sk_flags | rightarg->sk_flags) & SK_ROW_MEMBER)); /* * First, deal with cases where one or both args are NULL. This should @@ -925,6 +946,16 @@ _bt_compare_scankey_args(IndexScanDesc scan, ScanKey op, } /* + * We don't yet know how to determine redundancy when it involves a row + * compare key (barring simple cases involving IS NULL/IS NOT NULL) + */ + if ((leftarg->sk_flags | rightarg->sk_flags) & SK_ROW_HEADER) + { + Assert(!((leftarg->sk_flags | rightarg->sk_flags) & SK_BT_SKIP)); + return false; + } + + /* * If either leftarg or rightarg are equality-type array scankeys, we need * specialized handling (since by now we know that IS NULL wasn't used) */ @@ -1468,6 +1499,283 @@ _bt_skiparray_strat_increment(IndexScanDesc scan, ScanKey arraysk, } /* + * _bt_unmark_keys() -- make superfluous required keys nonrequired after all + * + * When _bt_preprocess_keys fails to eliminate one or more redundant keys, it + * calls here to make sure that no index attribute has more than one > or >= + * key marked required, and no more than one required < or <= key. Attributes + * with = keys will always get one = key as their required key. All other + * keys that were initially marked required get "unmarked" here. That way, + * _bt_first and _bt_checkkeys will reliably agree on which keys to use to + * start and/or to end the scan. + * + * We also relocate keys that become/started out nonrequired to the end of + * so->keyData[]. That way, _bt_first and _bt_checkkeys cannot fail to reach + * a required key due to some earlier nonrequired key getting in the way. + * + * Only call here when _bt_compare_scankey_args returned false at least once + * (otherwise, calling here will just waste cycles). + */ +static void +_bt_unmark_keys(IndexScanDesc scan, int *keyDataMap) +{ + BTScanOpaque so = (BTScanOpaque) scan->opaque; + AttrNumber attno; + bool *unmarkikey; + int nunmark, + nunmarked, + nkept, + firsti; + ScanKey keepKeys, + unmarkKeys; + FmgrInfo *keepOrderProcs = NULL, + *unmarkOrderProcs = NULL; + bool haveReqEquals, + haveReqForward, + haveReqBackward; + + /* + * Do an initial pass over so->keyData[] that determines which keys to + * keep as required. We expect so->keyData[] to still be in attribute + * order when we're called (though we don't expect any particular order + * among each attribute's keys). + * + * When both equality and inequality keys remain on a single attribute, we + * *must* make sure that exactly one of the equalities remains required. + * Any requiredness markings that we might leave on later keys/attributes + * are predicated on there being required = keys on all prior columns. + */ + unmarkikey = palloc0(so->numberOfKeys * sizeof(bool)); + nunmark = 0; + + /* Set things up for first key's attribute */ + attno = so->keyData[0].sk_attno; + firsti = 0; + haveReqEquals = false; + haveReqForward = false; + haveReqBackward = false; + for (int i = 0; i < so->numberOfKeys; i++) + { + ScanKey origkey = &so->keyData[i]; + + if (origkey->sk_attno != attno) + { + /* Reset for next attribute */ + attno = origkey->sk_attno; + firsti = i; + + haveReqEquals = false; + haveReqForward = false; + haveReqBackward = false; + } + + /* Equalities get priority over inequalities */ + if (haveReqEquals) + { + /* + * We already found the first "=" key for this attribute. We've + * already decided that all its other keys will be unmarked. + */ + Assert(!(origkey->sk_flags & SK_SEARCHNULL)); + unmarkikey[i] = true; + nunmark++; + continue; + } + else if ((origkey->sk_flags & SK_BT_REQFWD) && + (origkey->sk_flags & SK_BT_REQBKWD)) + { + /* + * Found the first "=" key for attno. All other attno keys will + * be unmarked. + */ + Assert(origkey->sk_strategy == BTEqualStrategyNumber); + + haveReqEquals = true; + for (int j = firsti; j < i; j++) + { + /* Unmark any prior inequality keys on attno after all */ + if (!unmarkikey[j]) + { + unmarkikey[j] = true; + nunmark++; + } + } + continue; + } + + /* Deal with inequalities next */ + if ((origkey->sk_flags & SK_BT_REQFWD) && !haveReqForward) + { + haveReqForward = true; + continue; + } + else if ((origkey->sk_flags & SK_BT_REQBKWD) && !haveReqBackward) + { + haveReqBackward = true; + continue; + } + + /* + * We have either a redundant inequality key that will be unmarked, or + * we have a key that wasn't marked required in the first place + */ + unmarkikey[i] = true; + nunmark++; + } + + /* Should only be called when _bt_compare_scankey_args reported failure */ + Assert(nunmark > 0); + + /* + * Next, allocate temp arrays: one for required keys that'll remain + * required, the other for all remaining keys + */ + unmarkKeys = palloc(nunmark * sizeof(ScanKeyData)); + keepKeys = palloc((so->numberOfKeys - nunmark) * sizeof(ScanKeyData)); + nunmarked = 0; + nkept = 0; + if (so->numArrayKeys) + { + unmarkOrderProcs = palloc(nunmark * sizeof(FmgrInfo)); + keepOrderProcs = palloc((so->numberOfKeys - nunmark) * sizeof(FmgrInfo)); + } + + /* + * Next, copy the contents of so->keyData[] into the appropriate temp + * array. + * + * Scans with = array keys need us to maintain invariants around the order + * of so->orderProcs[] and so->arrayKeys[] relative to so->keyData[]. See + * _bt_preprocess_array_keys_final for a full explanation. + */ + for (int i = 0; i < so->numberOfKeys; i++) + { + ScanKey origkey = &so->keyData[i]; + ScanKey unmark; + + if (!unmarkikey[i]) + { + /* + * Key gets to keep its original requiredness markings. + * + * Key will stay in its original position, unless we're going to + * unmark an earlier key (in which case this key gets moved back). + */ + memcpy(keepKeys + nkept, origkey, sizeof(ScanKeyData)); + + if (so->numArrayKeys) + { + keyDataMap[i] = nkept; + memcpy(keepOrderProcs + nkept, &so->orderProcs[i], + sizeof(FmgrInfo)); + } + + nkept++; + continue; + } + + /* + * Key will be unmarked as needed, and moved to the end of the array, + * next to other keys that will become (or always were) nonrequired + */ + unmark = unmarkKeys + nunmarked; + memcpy(unmark, origkey, sizeof(ScanKeyData)); + + if (so->numArrayKeys) + { + keyDataMap[i] = (so->numberOfKeys - nunmark) + nunmarked; + memcpy(&unmarkOrderProcs[nunmarked], &so->orderProcs[i], + sizeof(FmgrInfo)); + } + + /* + * Preprocessing only generates skip arrays when it knows that they'll + * be the only required = key on the attr. We'll never unmark them. + */ + Assert(!(unmark->sk_flags & SK_BT_SKIP)); + + /* + * Also shouldn't have to unmark an IS NULL or an IS NOT NULL key. + * They aren't cross-type, so an incomplete opfamily can't matter. + */ + Assert(!(unmark->sk_flags & SK_ISNULL) || + !(unmark->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD))); + + /* Clear requiredness flags on redundant key (and on any subkeys) */ + unmark->sk_flags &= ~(SK_BT_REQFWD | SK_BT_REQBKWD); + if (unmark->sk_flags & SK_ROW_HEADER) + { + ScanKey subkey = (ScanKey) DatumGetPointer(unmark->sk_argument); + + Assert(subkey->sk_strategy == unmark->sk_strategy); + for (;;) + { + Assert(subkey->sk_flags & SK_ROW_MEMBER); + subkey->sk_flags &= ~(SK_BT_REQFWD | SK_BT_REQBKWD); + if (subkey->sk_flags & SK_ROW_END) + break; + subkey++; + } + } + + nunmarked++; + } + + /* Copy both temp arrays back into so->keyData[] to reorder */ + Assert(nkept == so->numberOfKeys - nunmark); + Assert(nunmarked == nunmark); + memcpy(so->keyData, keepKeys, sizeof(ScanKeyData) * nkept); + memcpy(so->keyData + nkept, unmarkKeys, sizeof(ScanKeyData) * nunmarked); + + /* Done with temp arrays */ + pfree(unmarkikey); + pfree(keepKeys); + pfree(unmarkKeys); + + /* + * Now copy so->orderProcs[] temp entries needed by scans with = array + * keys back (just like with the so->keyData[] temp arrays) + */ + if (so->numArrayKeys) + { + memcpy(so->orderProcs, keepOrderProcs, sizeof(FmgrInfo) * nkept); + memcpy(so->orderProcs + nkept, unmarkOrderProcs, + sizeof(FmgrInfo) * nunmarked); + + /* Also fix-up array->scan_key references */ + for (int arridx = 0; arridx < so->numArrayKeys; arridx++) + { + BTArrayKeyInfo *array = &so->arrayKeys[arridx]; + + array->scan_key = keyDataMap[array->scan_key]; + } + + /* + * Sort so->arrayKeys[] based on its new BTArrayKeyInfo.scan_key + * offsets, so that its order matches so->keyData[] order as expected + */ + qsort(so->arrayKeys, so->numArrayKeys, sizeof(BTArrayKeyInfo), + _bt_reorder_array_cmp); + + /* Done with temp arrays */ + pfree(unmarkOrderProcs); + pfree(keepOrderProcs); + } +} + +/* + * qsort comparator for reordering so->arrayKeys[] BTArrayKeyInfo entries + */ +static int +_bt_reorder_array_cmp(const void *a, const void *b) +{ + BTArrayKeyInfo *arraya = (BTArrayKeyInfo *) a; + BTArrayKeyInfo *arrayb = (BTArrayKeyInfo *) b; + + return pg_cmp_s32(arraya->scan_key, arrayb->scan_key); +} + +/* * _bt_preprocess_array_keys() -- Preprocess SK_SEARCHARRAY scan keys * * If there are any SK_SEARCHARRAY scan keys, deconstruct the array(s) and diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c index 765659887af..fdff960c130 100644 --- a/src/backend/access/nbtree/nbtree.c +++ b/src/backend/access/nbtree/nbtree.c @@ -228,6 +228,8 @@ btgettuple(IndexScanDesc scan, ScanDirection dir) BTScanOpaque so = (BTScanOpaque) scan->opaque; bool res; + Assert(scan->heapRelation != NULL); + /* btree indexes are never lossy */ scan->xs_recheck = false; @@ -289,6 +291,8 @@ btgetbitmap(IndexScanDesc scan, TIDBitmap *tbm) int64 ntids = 0; ItemPointer heapTid; + Assert(scan->heapRelation == NULL); + /* Each loop iteration performs another primitive index scan */ do { @@ -393,6 +397,34 @@ btrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys, BTScanPosInvalidate(so->currPos); } + /* + * We prefer to eagerly drop leaf page pins before btgettuple returns. + * This avoids making VACUUM wait to acquire a cleanup lock on the page. + * + * We cannot safely drop leaf page pins during index-only scans due to a + * race condition involving VACUUM setting pages all-visible in the VM. + * It's also unsafe for plain index scans that use a non-MVCC snapshot. + * + * When we drop pins eagerly, the mechanism that marks so->killedItems[] + * index tuples LP_DEAD has to deal with concurrent TID recycling races. + * The scheme used to detect unsafe TID recycling won't work when scanning + * unlogged relations (since it involves saving an affected page's LSN). + * Opt out of eager pin dropping during unlogged relation scans for now + * (this is preferable to opting out of kill_prior_tuple LP_DEAD setting). + * + * Also opt out of dropping leaf page pins eagerly during bitmap scans. + * Pins cannot be held for more than an instant during bitmap scans either + * way, so we might as well avoid wasting cycles on acquiring page LSNs. + * + * See nbtree/README section on making concurrent TID recycling safe. + * + * Note: so->dropPin should never change across rescans. + */ + so->dropPin = (!scan->xs_want_itup && + IsMVCCSnapshot(scan->xs_snapshot) && + RelationNeedsWAL(scan->indexRelation) && + scan->heapRelation != NULL); + so->markItemIndex = -1; so->needPrimScan = false; so->scanBehind = false; diff --git a/src/backend/access/nbtree/nbtsearch.c b/src/backend/access/nbtree/nbtsearch.c index fe9a3886913..4af1ff1e9e5 100644 --- a/src/backend/access/nbtree/nbtsearch.c +++ b/src/backend/access/nbtree/nbtsearch.c @@ -25,7 +25,7 @@ #include "utils/rel.h" -static void _bt_drop_lock_and_maybe_pin(IndexScanDesc scan, BTScanPos sp); +static inline void _bt_drop_lock_and_maybe_pin(Relation rel, BTScanOpaque so); static Buffer _bt_moveright(Relation rel, Relation heaprel, BTScanInsert key, Buffer buf, bool forupdate, BTStack stack, int access); @@ -57,24 +57,29 @@ static bool _bt_endpoint(IndexScanDesc scan, ScanDirection dir); /* * _bt_drop_lock_and_maybe_pin() * - * Unlock the buffer; and if it is safe to release the pin, do that, too. - * This will prevent vacuum from stalling in a blocked state trying to read a - * page when a cursor is sitting on it. - * - * See nbtree/README section on making concurrent TID recycling safe. + * Unlock so->currPos.buf. If scan is so->dropPin, drop the pin, too. + * Dropping the pin prevents VACUUM from blocking on acquiring a cleanup lock. */ -static void -_bt_drop_lock_and_maybe_pin(IndexScanDesc scan, BTScanPos sp) +static inline void +_bt_drop_lock_and_maybe_pin(Relation rel, BTScanOpaque so) { - _bt_unlockbuf(scan->indexRelation, sp->buf); - - if (IsMVCCSnapshot(scan->xs_snapshot) && - RelationNeedsWAL(scan->indexRelation) && - !scan->xs_want_itup) + if (!so->dropPin) { - ReleaseBuffer(sp->buf); - sp->buf = InvalidBuffer; + /* Just drop the lock (not the pin) */ + _bt_unlockbuf(rel, so->currPos.buf); + return; } + + /* + * Drop both the lock and the pin. + * + * Have to set so->currPos.lsn so that _bt_killitems has a way to detect + * when concurrent heap TID recycling by VACUUM might have taken place. + */ + Assert(RelationNeedsWAL(rel)); + so->currPos.lsn = BufferGetLSNAtomic(so->currPos.buf); + _bt_relbuf(rel, so->currPos.buf); + so->currPos.buf = InvalidBuffer; } /* @@ -866,8 +871,8 @@ _bt_compare(Relation rel, * if backwards scan, the last item) in the tree that satisfies the * qualifications in the scan key. On success exit, data about the * matching tuple(s) on the page has been loaded into so->currPos. We'll - * drop all locks and hold onto a pin on page's buffer, except when - * _bt_drop_lock_and_maybe_pin dropped the pin to avoid blocking VACUUM. + * drop all locks and hold onto a pin on page's buffer, except during + * so->dropPin scans, when we drop both the lock and the pin. * _bt_returnitem sets the next item to return to scan on success exit. * * If there are no matching items in the index, we return false, with no @@ -955,46 +960,51 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) /*---------- * Examine the scan keys to discover where we need to start the scan. + * The selected scan keys (at most one per index column) are remembered by + * storing their addresses into the local startKeys[] array. The final + * startKeys[] entry's strategy is set in strat_total. (Actually, there + * are a couple of cases where we force a less/more restrictive strategy.) * - * We want to identify the keys that can be used as starting boundaries; - * these are =, >, or >= keys for a forward scan or =, <, <= keys for - * a backwards scan. We can use keys for multiple attributes so long as - * the prior attributes had only =, >= (resp. =, <=) keys. Once we accept - * a > or < boundary or find an attribute with no boundary (which can be - * thought of as the same as "> -infinity"), we can't use keys for any - * attributes to its right, because it would break our simplistic notion - * of what initial positioning strategy to use. + * We must use the key that was marked required (in the direction opposite + * our own scan's) during preprocessing. Each index attribute can only + * have one such required key. In general, the keys that we use to find + * an initial position when scanning forwards are the same keys that end + * the scan on the leaf level when scanning backwards (and vice-versa). * * When the scan keys include cross-type operators, _bt_preprocess_keys - * may not be able to eliminate redundant keys; in such cases we will - * arbitrarily pick a usable one for each attribute. This is correct - * but possibly not optimal behavior. (For example, with keys like - * "x >= 4 AND x >= 5" we would elect to scan starting at x=4 when - * x=5 would be more efficient.) Since the situation only arises given - * a poorly-worded query plus an incomplete opfamily, live with it. + * may not be able to eliminate redundant keys; in such cases it will + * arbitrarily pick a usable key for each attribute (and scan direction), + * ensuring that there is no more than one key required in each direction. + * We stop considering further keys once we reach the first nonrequired + * key (which must come after all required keys), so this can't affect us. + * + * The required keys that we use as starting boundaries have to be =, >, + * or >= keys for a forward scan or =, <, <= keys for a backwards scan. + * We can use keys for multiple attributes so long as the prior attributes + * had only =, >= (resp. =, <=) keys. These rules are very similar to the + * rules that preprocessing used to determine which keys to mark required. + * We cannot always use every required key as a positioning key, though. + * Skip arrays necessitate independently applying our own rules here. + * Skip arrays are always generally considered = array keys, but we'll + * nevertheless treat them as inequalities at certain points of the scan. + * When that happens, it _might_ have implications for the number of + * required keys that we can safely use for initial positioning purposes. * - * When both equality and inequality keys appear for a single attribute - * (again, only possible when cross-type operators appear), we *must* - * select one of the equality keys for the starting point, because - * _bt_checkkeys() will stop the scan as soon as an equality qual fails. - * For example, if we have keys like "x >= 4 AND x = 10" and we elect to - * start at x=4, we will fail and stop before reaching x=10. If multiple - * equality quals survive preprocessing, however, it doesn't matter which - * one we use --- by definition, they are either redundant or - * contradictory. + * For example, a forward scan with a skip array on its leading attribute + * (with no low_compare/high_compare) will have at least two required scan + * keys, but we won't use any of them as boundary keys during the scan's + * initial call here. Our positioning key during the first call here can + * be thought of as representing "> -infinity". Similarly, if such a skip + * array's low_compare is "a > 'foo'", then we position using "a > 'foo'" + * during the scan's initial call here; a lower-order key such as "b = 42" + * can't be used until the "a" array advances beyond MINVAL/low_compare. * - * In practice we rarely see any "attribute boundary key gaps" here. - * Preprocessing can usually backfill skip array keys for any attributes - * that were omitted from the original scan->keyData[] input keys. All - * array keys are always considered = keys, but we'll sometimes need to - * treat the current key value as if we were using an inequality strategy. - * This happens with range skip arrays, which store inequality keys in the - * array's low_compare/high_compare fields (used to find the first/last - * set of matches, when = key will lack a usable sk_argument value). - * These are always preferred over any redundant "standard" inequality - * keys on the same column (per the usual rule about preferring = keys). - * Note also that any column with an = skip array key can never have an - * additional, contradictory = key. + * On the other hand, if such a skip array's low_compare was "a >= 'foo'", + * then we _can_ use "a >= 'foo' AND b = 42" during the initial call here. + * A subsequent call here might have us use "a = 'fop' AND b = 42". Note + * that we treat = and >= as equivalent when scanning forwards (just as we + * treat = and <= as equivalent when scanning backwards). We effectively + * do the same thing (though with a distinct "a" element/value) each time. * * All keys (with the exception of SK_SEARCHNULL keys and SK_BT_SKIP * array keys whose array is "null_elem=true") imply a NOT NULL qualifier. @@ -1006,21 +1016,20 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) * traversing a lot of null entries at the start of the scan. * * In this loop, row-comparison keys are treated the same as keys on their - * first (leftmost) columns. We'll add on lower-order columns of the row - * comparison below, if possible. + * first (leftmost) columns. We'll add all lower-order columns of the row + * comparison that were marked required during preprocessing below. * - * The selected scan keys (at most one per index column) are remembered by - * storing their addresses into the local startKeys[] array. - * - * _bt_checkkeys/_bt_advance_array_keys decide whether and when to start - * the next primitive index scan (for scans with array keys) based in part - * on an understanding of how it'll enable us to reposition the scan. - * They're directly aware of how we'll sometimes cons up an explicit - * SK_SEARCHNOTNULL key. They'll even end primitive scans by applying a - * symmetric "deduce NOT NULL" rule of their own. This allows top-level - * scans to skip large groups of NULLs through repeated deductions about - * key strictness (for a required inequality key) and whether NULLs in the - * key's index column are stored last or first (relative to non-NULLs). + * _bt_advance_array_keys needs to know exactly how we'll reposition the + * scan (should it opt to schedule another primitive index scan). It is + * critical that primscans only be scheduled when they'll definitely make + * some useful progress. _bt_advance_array_keys does this by calling + * _bt_checkkeys routines that report whether a tuple is past the end of + * matches for the scan's keys (given the scan's current array elements). + * If the page's final tuple is "after the end of matches" for a scan that + * uses the *opposite* scan direction, then it must follow that it's also + * "before the start of matches" for the actual current scan direction. + * It is therefore essential that all of our initial positioning rules are + * symmetric with _bt_checkkeys's corresponding continuescan=false rule. * If you update anything here, _bt_checkkeys/_bt_advance_array_keys might * need to be kept in sync. *---------- @@ -1029,18 +1038,17 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) if (so->numberOfKeys > 0) { AttrNumber curattr; - ScanKey chosen; + ScanKey bkey; ScanKey impliesNN; ScanKey cur; /* - * chosen is the so-far-chosen key for the current attribute, if any. - * We don't cast the decision in stone until we reach keys for the - * next attribute. + * bkey will be set to the key that preprocessing left behind as the + * boundary key for this attribute, in this scan direction (if any) */ cur = so->keyData; curattr = 1; - chosen = NULL; + bkey = NULL; /* Also remember any scankey that implies a NOT NULL constraint */ impliesNN = NULL; @@ -1053,23 +1061,29 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) { if (i >= so->numberOfKeys || cur->sk_attno != curattr) { + /* Done looking for the curattr boundary key */ + Assert(bkey == NULL || + (bkey->sk_attno == curattr && + (bkey->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)))); + Assert(impliesNN == NULL || + (impliesNN->sk_attno == curattr && + (impliesNN->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)))); + /* - * Done looking at keys for curattr. - * * If this is a scan key for a skip array whose current * element is MINVAL, choose low_compare (when scanning * backwards it'll be MAXVAL, and we'll choose high_compare). * - * Note: if the array's low_compare key makes 'chosen' NULL, + * Note: if the array's low_compare key makes 'bkey' NULL, * then we behave as if the array's first element is -inf, * except when !array->null_elem implies a usable NOT NULL * constraint. */ - if (chosen != NULL && - (chosen->sk_flags & (SK_BT_MINVAL | SK_BT_MAXVAL))) + if (bkey != NULL && + (bkey->sk_flags & (SK_BT_MINVAL | SK_BT_MAXVAL))) { - int ikey = chosen - so->keyData; - ScanKey skipequalitykey = chosen; + int ikey = bkey - so->keyData; + ScanKey skipequalitykey = bkey; BTArrayKeyInfo *array = NULL; for (int arridx = 0; arridx < so->numArrayKeys; arridx++) @@ -1082,35 +1096,35 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) if (ScanDirectionIsForward(dir)) { Assert(!(skipequalitykey->sk_flags & SK_BT_MAXVAL)); - chosen = array->low_compare; + bkey = array->low_compare; } else { Assert(!(skipequalitykey->sk_flags & SK_BT_MINVAL)); - chosen = array->high_compare; + bkey = array->high_compare; } - Assert(chosen == NULL || - chosen->sk_attno == skipequalitykey->sk_attno); + Assert(bkey == NULL || + bkey->sk_attno == skipequalitykey->sk_attno); if (!array->null_elem) impliesNN = skipequalitykey; else - Assert(chosen == NULL && impliesNN == NULL); + Assert(bkey == NULL && impliesNN == NULL); } /* * If we didn't find a usable boundary key, see if we can * deduce a NOT NULL key */ - if (chosen == NULL && impliesNN != NULL && + if (bkey == NULL && impliesNN != NULL && ((impliesNN->sk_flags & SK_BT_NULLS_FIRST) ? ScanDirectionIsForward(dir) : ScanDirectionIsBackward(dir))) { /* Yes, so build the key in notnullkeys[keysz] */ - chosen = ¬nullkeys[keysz]; - ScanKeyEntryInitialize(chosen, + bkey = ¬nullkeys[keysz]; + ScanKeyEntryInitialize(bkey, (SK_SEARCHNOTNULL | SK_ISNULL | (impliesNN->sk_flags & (SK_BT_DESC | SK_BT_NULLS_FIRST))), @@ -1125,12 +1139,12 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) } /* - * If we still didn't find a usable boundary key, quit; else - * save the boundary key pointer in startKeys. + * If preprocessing didn't leave a usable boundary key, quit; + * else save the boundary key pointer in startKeys[] */ - if (chosen == NULL) + if (bkey == NULL) break; - startKeys[keysz++] = chosen; + startKeys[keysz++] = bkey; /* * We can only consider adding more boundary keys when the one @@ -1138,7 +1152,7 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) * (during backwards scans we can only do so when the key that * we just added to startKeys[] uses the = or <= strategy) */ - strat_total = chosen->sk_strategy; + strat_total = bkey->sk_strategy; if (strat_total == BTGreaterStrategyNumber || strat_total == BTLessStrategyNumber) break; @@ -1149,19 +1163,19 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) * make strat_total > or < (and stop adding boundary keys). * This can only happen with opclasses that lack skip support. */ - if (chosen->sk_flags & (SK_BT_NEXT | SK_BT_PRIOR)) + if (bkey->sk_flags & (SK_BT_NEXT | SK_BT_PRIOR)) { - Assert(chosen->sk_flags & SK_BT_SKIP); + Assert(bkey->sk_flags & SK_BT_SKIP); Assert(strat_total == BTEqualStrategyNumber); if (ScanDirectionIsForward(dir)) { - Assert(!(chosen->sk_flags & SK_BT_PRIOR)); + Assert(!(bkey->sk_flags & SK_BT_PRIOR)); strat_total = BTGreaterStrategyNumber; } else { - Assert(!(chosen->sk_flags & SK_BT_NEXT)); + Assert(!(bkey->sk_flags & SK_BT_NEXT)); strat_total = BTLessStrategyNumber; } @@ -1175,24 +1189,30 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) /* * Done if that was the last scan key output by preprocessing. - * Also done if there is a gap index attribute that lacks a - * usable key (only possible when preprocessing was unable to - * generate a skip array key to "fill in the gap"). + * Also done if we've now examined all keys marked required. */ if (i >= so->numberOfKeys || - cur->sk_attno != curattr + 1) + !(cur->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD))) break; /* * Reset for next attr. */ + Assert(cur->sk_attno == curattr + 1); curattr = cur->sk_attno; - chosen = NULL; + bkey = NULL; impliesNN = NULL; } /* - * Can we use this key as a starting boundary for this attr? + * If we've located the starting boundary key for curattr, we have + * no interest in curattr's other required key + */ + if (bkey != NULL) + continue; + + /* + * Is this key the starting boundary key for curattr? * * If not, does it imply a NOT NULL constraint? (Because * SK_SEARCHNULL keys are always assigned BTEqualStrategyNumber, @@ -1202,27 +1222,20 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) { case BTLessStrategyNumber: case BTLessEqualStrategyNumber: - if (chosen == NULL) - { - if (ScanDirectionIsBackward(dir)) - chosen = cur; - else - impliesNN = cur; - } + if (ScanDirectionIsBackward(dir)) + bkey = cur; + else if (impliesNN == NULL) + impliesNN = cur; break; case BTEqualStrategyNumber: - /* override any non-equality choice */ - chosen = cur; + bkey = cur; break; case BTGreaterEqualStrategyNumber: case BTGreaterStrategyNumber: - if (chosen == NULL) - { - if (ScanDirectionIsForward(dir)) - chosen = cur; - else - impliesNN = cur; - } + if (ScanDirectionIsForward(dir)) + bkey = cur; + else if (impliesNN == NULL) + impliesNN = cur; break; } } @@ -1248,16 +1261,18 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) Assert(keysz <= INDEX_MAX_KEYS); for (int i = 0; i < keysz; i++) { - ScanKey cur = startKeys[i]; + ScanKey bkey = startKeys[i]; - Assert(cur->sk_attno == i + 1); + Assert(bkey->sk_attno == i + 1); - if (cur->sk_flags & SK_ROW_HEADER) + if (bkey->sk_flags & SK_ROW_HEADER) { /* * Row comparison header: look to the first row member instead */ - ScanKey subkey = (ScanKey) DatumGetPointer(cur->sk_argument); + ScanKey subkey = (ScanKey) DatumGetPointer(bkey->sk_argument); + bool loosen_strat = false, + tighten_strat = false; /* * Cannot be a NULL in the first row member: _bt_preprocess_keys @@ -1265,122 +1280,160 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) * ever getting this far */ Assert(subkey->sk_flags & SK_ROW_MEMBER); - Assert(subkey->sk_attno == cur->sk_attno); + Assert(subkey->sk_attno == bkey->sk_attno); Assert(!(subkey->sk_flags & SK_ISNULL)); /* + * This is either a > or >= key (during backwards scans it is + * either < or <=) that was marked required during preprocessing. + * Later so->keyData[] keys can't have been marked required, so + * our row compare header key must be the final startKeys[] entry. + */ + Assert(subkey->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)); + Assert(i == keysz - 1); + + /* * The member scankeys are already in insertion format (ie, they * have sk_func = 3-way-comparison function) */ memcpy(inskey.scankeys + i, subkey, sizeof(ScanKeyData)); /* - * If the row comparison is the last positioning key we accepted, - * try to add additional keys from the lower-order row members. - * (If we accepted independent conditions on additional index - * columns, we use those instead --- doesn't seem worth trying to - * determine which is more restrictive.) Note that this is OK - * even if the row comparison is of ">" or "<" type, because the - * condition applied to all but the last row member is effectively - * ">=" or "<=", and so the extra keys don't break the positioning - * scheme. But, by the same token, if we aren't able to use all - * the row members, then the part of the row comparison that we - * did use has to be treated as just a ">=" or "<=" condition, and - * so we'd better adjust strat_total accordingly. + * Now look to later row compare members. + * + * If there's an "index attribute gap" between two row compare + * members, the second member won't have been marked required, and + * so can't be used as a starting boundary key here. The part of + * the row comparison that we do still use has to be treated as a + * ">=" or "<=" condition. For example, a qual "(a, c) > (1, 42)" + * with an omitted intervening index attribute "b" will use an + * insertion scan key "a >= 1". Even the first "a = 1" tuple on + * the leaf level might satisfy the row compare qual. + * + * We're able to use a _more_ restrictive strategy when we reach a + * NULL row compare member, since they're always unsatisfiable. + * For example, a qual "(a, b, c) >= (1, NULL, 77)" will use an + * insertion scan key "a > 1". All tuples where "a = 1" cannot + * possibly satisfy the row compare qual, so this is safe. */ - if (i == keysz - 1) + Assert(!(subkey->sk_flags & SK_ROW_END)); + for (;;) { - bool used_all_subkeys = false; + subkey++; + Assert(subkey->sk_flags & SK_ROW_MEMBER); - Assert(!(subkey->sk_flags & SK_ROW_END)); - for (;;) + if (subkey->sk_flags & SK_ISNULL) { - subkey++; - Assert(subkey->sk_flags & SK_ROW_MEMBER); - if (subkey->sk_attno != keysz + 1) - break; /* out-of-sequence, can't use it */ - if (subkey->sk_strategy != cur->sk_strategy) - break; /* wrong direction, can't use it */ - if (subkey->sk_flags & SK_ISNULL) - break; /* can't use null keys */ - Assert(keysz < INDEX_MAX_KEYS); - memcpy(inskey.scankeys + keysz, subkey, - sizeof(ScanKeyData)); - keysz++; - if (subkey->sk_flags & SK_ROW_END) - { - used_all_subkeys = true; - break; - } + /* + * NULL member key, can only use earlier keys. + * + * We deliberately avoid checking if this key is marked + * required. All earlier keys are required, and this key + * is unsatisfiable either way, so we can't miss anything. + */ + tighten_strat = true; + break; } - if (!used_all_subkeys) + + if (!(subkey->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD))) { - switch (strat_total) - { - case BTLessStrategyNumber: - strat_total = BTLessEqualStrategyNumber; - break; - case BTGreaterStrategyNumber: - strat_total = BTGreaterEqualStrategyNumber; - break; - } + /* nonrequired member key, can only use earlier keys */ + loosen_strat = true; + break; } - break; /* done with outer loop */ + + Assert(subkey->sk_attno == keysz + 1); + Assert(subkey->sk_strategy == bkey->sk_strategy); + Assert(keysz < INDEX_MAX_KEYS); + + memcpy(inskey.scankeys + keysz, subkey, + sizeof(ScanKeyData)); + keysz++; + if (subkey->sk_flags & SK_ROW_END) + break; } - } - else - { - /* - * Ordinary comparison key. Transform the search-style scan key - * to an insertion scan key by replacing the sk_func with the - * appropriate btree comparison function. - * - * If scankey operator is not a cross-type comparison, we can use - * the cached comparison function; otherwise gotta look it up in - * the catalogs. (That can't lead to infinite recursion, since no - * indexscan initiated by syscache lookup will use cross-data-type - * operators.) - * - * We support the convention that sk_subtype == InvalidOid means - * the opclass input type; this is a hack to simplify life for - * ScanKeyInit(). - */ - if (cur->sk_subtype == rel->rd_opcintype[i] || - cur->sk_subtype == InvalidOid) + Assert(!(loosen_strat && tighten_strat)); + if (loosen_strat) { - FmgrInfo *procinfo; - - procinfo = index_getprocinfo(rel, cur->sk_attno, BTORDER_PROC); - ScanKeyEntryInitializeWithInfo(inskey.scankeys + i, - cur->sk_flags, - cur->sk_attno, - InvalidStrategy, - cur->sk_subtype, - cur->sk_collation, - procinfo, - cur->sk_argument); + /* Use less restrictive strategy (and fewer member keys) */ + switch (strat_total) + { + case BTLessStrategyNumber: + strat_total = BTLessEqualStrategyNumber; + break; + case BTGreaterStrategyNumber: + strat_total = BTGreaterEqualStrategyNumber; + break; + } } - else + if (tighten_strat) { - RegProcedure cmp_proc; - - cmp_proc = get_opfamily_proc(rel->rd_opfamily[i], - rel->rd_opcintype[i], - cur->sk_subtype, - BTORDER_PROC); - if (!RegProcedureIsValid(cmp_proc)) - elog(ERROR, "missing support function %d(%u,%u) for attribute %d of index \"%s\"", - BTORDER_PROC, rel->rd_opcintype[i], cur->sk_subtype, - cur->sk_attno, RelationGetRelationName(rel)); - ScanKeyEntryInitialize(inskey.scankeys + i, - cur->sk_flags, - cur->sk_attno, - InvalidStrategy, - cur->sk_subtype, - cur->sk_collation, - cmp_proc, - cur->sk_argument); + /* Use more restrictive strategy (and fewer member keys) */ + switch (strat_total) + { + case BTLessEqualStrategyNumber: + strat_total = BTLessStrategyNumber; + break; + case BTGreaterEqualStrategyNumber: + strat_total = BTGreaterStrategyNumber; + break; + } } + + /* done adding to inskey (row comparison keys always come last) */ + break; + } + + /* + * Ordinary comparison key/search-style key. + * + * Transform the search-style scan key to an insertion scan key by + * replacing the sk_func with the appropriate btree 3-way-comparison + * function. + * + * If scankey operator is not a cross-type comparison, we can use the + * cached comparison function; otherwise gotta look it up in the + * catalogs. (That can't lead to infinite recursion, since no + * indexscan initiated by syscache lookup will use cross-data-type + * operators.) + * + * We support the convention that sk_subtype == InvalidOid means the + * opclass input type; this hack simplifies life for ScanKeyInit(). + */ + if (bkey->sk_subtype == rel->rd_opcintype[i] || + bkey->sk_subtype == InvalidOid) + { + FmgrInfo *procinfo; + + procinfo = index_getprocinfo(rel, bkey->sk_attno, BTORDER_PROC); + ScanKeyEntryInitializeWithInfo(inskey.scankeys + i, + bkey->sk_flags, + bkey->sk_attno, + InvalidStrategy, + bkey->sk_subtype, + bkey->sk_collation, + procinfo, + bkey->sk_argument); + } + else + { + RegProcedure cmp_proc; + + cmp_proc = get_opfamily_proc(rel->rd_opfamily[i], + rel->rd_opcintype[i], + bkey->sk_subtype, BTORDER_PROC); + if (!RegProcedureIsValid(cmp_proc)) + elog(ERROR, "missing support function %d(%u,%u) for attribute %d of index \"%s\"", + BTORDER_PROC, rel->rd_opcintype[i], bkey->sk_subtype, + bkey->sk_attno, RelationGetRelationName(rel)); + ScanKeyEntryInitialize(inskey.scankeys + i, + bkey->sk_flags, + bkey->sk_attno, + InvalidStrategy, + bkey->sk_subtype, + bkey->sk_collation, + cmp_proc, + bkey->sk_argument); } } @@ -1469,6 +1522,8 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) if (!BufferIsValid(so->currPos.buf)) { + Assert(!so->needPrimScan); + /* * We only get here if the index is completely empty. Lock relation * because nothing finer to lock exists. Without a buffer lock, it's @@ -1487,7 +1542,6 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) if (!BufferIsValid(so->currPos.buf)) { - Assert(!so->needPrimScan); _bt_parallel_done(scan); return false; } @@ -1610,7 +1664,13 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum, so->currPos.currPage = BufferGetBlockNumber(so->currPos.buf); so->currPos.prevPage = opaque->btpo_prev; so->currPos.nextPage = opaque->btpo_next; + /* delay setting so->currPos.lsn until _bt_drop_lock_and_maybe_pin */ + so->currPos.dir = dir; + so->currPos.nextTupleOffset = 0; + /* either moreRight or moreLeft should be set now (may be unset later) */ + Assert(ScanDirectionIsForward(dir) ? so->currPos.moreRight : + so->currPos.moreLeft); Assert(!P_IGNORE(opaque)); Assert(BTScanPosIsPinned(so->currPos)); Assert(!so->needPrimScan); @@ -1626,14 +1686,6 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum, so->currPos.currPage); } - /* initialize remaining currPos fields related to current page */ - so->currPos.lsn = BufferGetLSNAtomic(so->currPos.buf); - so->currPos.dir = dir; - so->currPos.nextTupleOffset = 0; - /* either moreLeft or moreRight should be set now (may be unset later) */ - Assert(ScanDirectionIsForward(dir) ? so->currPos.moreRight : - so->currPos.moreLeft); - PredicateLockPage(rel, so->currPos.currPage, scan->xs_snapshot); /* initialize local variables */ @@ -2107,10 +2159,9 @@ _bt_returnitem(IndexScanDesc scan, BTScanOpaque so) * * Wrapper on _bt_readnextpage that performs final steps for the current page. * - * On entry, if so->currPos.buf is valid the buffer is pinned but not locked. - * If there's no pin held, it's because _bt_drop_lock_and_maybe_pin dropped - * the pin eagerly earlier on. The scan must have so->currPos.currPage set to - * a valid block, in any case. + * On entry, so->currPos must be valid. Its buffer will be pinned, though + * never locked. (Actually, when so->dropPin there won't even be a pin held, + * though so->currPos.currPage must still be set to a valid block number.) */ static bool _bt_steppage(IndexScanDesc scan, ScanDirection dir) @@ -2251,12 +2302,14 @@ _bt_readfirstpage(IndexScanDesc scan, OffsetNumber offnum, ScanDirection dir) */ if (_bt_readpage(scan, dir, offnum, true)) { + Relation rel = scan->indexRelation; + /* * _bt_readpage succeeded. Drop the lock (and maybe the pin) on * so->currPos.buf in preparation for btgettuple returning tuples. */ Assert(BTScanPosIsPinned(so->currPos)); - _bt_drop_lock_and_maybe_pin(scan, &so->currPos); + _bt_drop_lock_and_maybe_pin(rel, so); return true; } @@ -2278,9 +2331,12 @@ _bt_readfirstpage(IndexScanDesc scan, OffsetNumber offnum, ScanDirection dir) * previously-saved right link or left link. lastcurrblkno is the page that * was current at the point where the blkno link was saved, which we use to * reason about concurrent page splits/page deletions during backwards scans. + * In the common case where seized=false, blkno is either so->currPos.nextPage + * or so->currPos.prevPage, and lastcurrblkno is so->currPos.currPage. * - * On entry, caller shouldn't hold any locks or pins on any page (we work - * directly off of blkno and lastcurrblkno instead). Parallel scan callers + * On entry, so->currPos shouldn't be locked by caller. so->currPos.buf must + * be InvalidBuffer/unpinned as needed by caller (note that lastcurrblkno + * won't need to be read again in almost all cases). Parallel scan callers * that seized the scan before calling here should pass seized=true; such a * caller's blkno and lastcurrblkno arguments come from the seized scan. * seized=false callers just pass us the blkno/lastcurrblkno taken from their @@ -2294,11 +2350,11 @@ _bt_readfirstpage(IndexScanDesc scan, OffsetNumber offnum, ScanDirection dir) * * On success exit, so->currPos is updated to contain data from the next * interesting page, and we return true. We hold a pin on the buffer on - * success exit, except when _bt_drop_lock_and_maybe_pin decided it was safe - * to eagerly drop the pin (to avoid blocking VACUUM). + * success exit (except during so->dropPin index scans, when we drop the pin + * eagerly to avoid blocking VACUUM). * - * If there are no more matching records in the given direction, we drop all - * locks and pins, invalidate so->currPos, and return false. + * If there are no more matching records in the given direction, we invalidate + * so->currPos (while ensuring it retains no locks or pins), and return false. * * We always release the scan for a parallel scan caller, regardless of * success or failure; we'll call _bt_parallel_release as soon as possible. @@ -2413,7 +2469,7 @@ _bt_readnextpage(IndexScanDesc scan, BlockNumber blkno, */ Assert(so->currPos.currPage == blkno); Assert(BTScanPosIsPinned(so->currPos)); - _bt_drop_lock_and_maybe_pin(scan, &so->currPos); + _bt_drop_lock_and_maybe_pin(rel, so); return true; } diff --git a/src/backend/access/nbtree/nbtsort.c b/src/backend/access/nbtree/nbtsort.c index 3794cc924ad..9d70e89c1f3 100644 --- a/src/backend/access/nbtree/nbtsort.c +++ b/src/backend/access/nbtree/nbtsort.c @@ -105,7 +105,7 @@ typedef struct BTShared int scantuplesortstates; /* Query ID, for report in worker processes */ - uint64 queryid; + int64 queryid; /* * workersdonecv is used to monitor the progress of workers. All parallel diff --git a/src/backend/access/nbtree/nbtutils.c b/src/backend/access/nbtree/nbtutils.c index 1a15dfcb7d3..9aed207995f 100644 --- a/src/backend/access/nbtree/nbtutils.c +++ b/src/backend/access/nbtree/nbtutils.c @@ -44,7 +44,6 @@ static bool _bt_array_decrement(Relation rel, ScanKey skey, BTArrayKeyInfo *arra static bool _bt_array_increment(Relation rel, ScanKey skey, BTArrayKeyInfo *array); static bool _bt_advance_array_keys_increment(IndexScanDesc scan, ScanDirection dir, bool *skip_array_set); -static void _bt_rewind_nonrequired_arrays(IndexScanDesc scan, ScanDirection dir); static bool _bt_tuple_before_array_skeys(IndexScanDesc scan, ScanDirection dir, IndexTuple tuple, TupleDesc tupdesc, int tupnatts, bool readpagetup, int sktrig, bool *scanBehind); @@ -52,7 +51,6 @@ static bool _bt_advance_array_keys(IndexScanDesc scan, BTReadPageState *pstate, IndexTuple tuple, int tupnatts, TupleDesc tupdesc, int sktrig, bool sktrig_required); #ifdef USE_ASSERT_CHECKING -static bool _bt_verify_arrays_bt_first(IndexScanDesc scan, ScanDirection dir); static bool _bt_verify_keys_with_arraykeys(IndexScanDesc scan); #endif static bool _bt_oppodir_checkkeys(IndexScanDesc scan, ScanDirection dir, @@ -1035,73 +1033,6 @@ _bt_advance_array_keys_increment(IndexScanDesc scan, ScanDirection dir, } /* - * _bt_rewind_nonrequired_arrays() -- Rewind SAOP arrays not marked required - * - * Called when _bt_advance_array_keys decides to start a new primitive index - * scan on the basis of the current scan position being before the position - * that _bt_first is capable of repositioning the scan to by applying an - * inequality operator required in the opposite-to-scan direction only. - * - * Although equality strategy scan keys (for both arrays and non-arrays alike) - * are either marked required in both directions or in neither direction, - * there is a sense in which non-required arrays behave like required arrays. - * With a qual such as "WHERE a IN (100, 200) AND b >= 3 AND c IN (5, 6, 7)", - * the scan key on "c" is non-required, but nevertheless enables positioning - * the scan at the first tuple >= "(100, 3, 5)" on the leaf level during the - * first descent of the tree by _bt_first. Later on, there could also be a - * second descent, that places the scan right before tuples >= "(200, 3, 5)". - * _bt_first must never be allowed to build an insertion scan key whose "c" - * entry is set to a value other than 5, the "c" array's first element/value. - * (Actually, it's the first in the current scan direction. This example uses - * a forward scan.) - * - * Calling here resets the array scan key elements for the scan's non-required - * arrays. This is strictly necessary for correctness in a subset of cases - * involving "required in opposite direction"-triggered primitive index scans. - * Not all callers are at risk of _bt_first using a non-required array like - * this, but advancement always resets the arrays when another primitive scan - * is scheduled, just to keep things simple. Array advancement even makes - * sure to reset non-required arrays during scans that have no inequalities. - * (Advancement still won't call here when there are no inequalities, though - * that's just because it's all handled indirectly instead.) - * - * Note: _bt_verify_arrays_bt_first is called by an assertion to enforce that - * everybody got this right. - * - * Note: In practice almost all SAOP arrays are marked required during - * preprocessing (if necessary by generating skip arrays). It is hardly ever - * truly necessary to call here, but consistently doing so is simpler. - */ -static void -_bt_rewind_nonrequired_arrays(IndexScanDesc scan, ScanDirection dir) -{ - Relation rel = scan->indexRelation; - BTScanOpaque so = (BTScanOpaque) scan->opaque; - int arrayidx = 0; - - for (int ikey = 0; ikey < so->numberOfKeys; ikey++) - { - ScanKey cur = so->keyData + ikey; - BTArrayKeyInfo *array = NULL; - - if (!(cur->sk_flags & SK_SEARCHARRAY) || - cur->sk_strategy != BTEqualStrategyNumber) - continue; - - array = &so->arrayKeys[arrayidx++]; - Assert(array->scan_key == ikey); - - if ((cur->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD))) - continue; - - Assert(array->num_elems != -1); /* No non-required skip arrays */ - - _bt_array_set_low_or_high(rel, cur, array, - ScanDirectionIsForward(dir)); - } -} - -/* * _bt_tuple_before_array_skeys() -- too early to advance required arrays? * * We always compare the tuple using the current array keys (which we assume @@ -1380,8 +1311,6 @@ _bt_start_prim_scan(IndexScanDesc scan, ScanDirection dir) */ if (so->needPrimScan) { - Assert(_bt_verify_arrays_bt_first(scan, dir)); - /* * Flag was set -- must call _bt_first again, which will reset the * scan's needPrimScan flag @@ -2007,14 +1936,7 @@ _bt_advance_array_keys(IndexScanDesc scan, BTReadPageState *pstate, */ else if (has_required_opposite_direction_only && pstate->finaltup && unlikely(!_bt_oppodir_checkkeys(scan, dir, pstate->finaltup))) - { - /* - * Make sure that any SAOP arrays that were not marked required by - * preprocessing are reset to their first element for this direction - */ - _bt_rewind_nonrequired_arrays(scan, dir); goto new_prim_scan; - } continue_scan: @@ -2045,8 +1967,6 @@ continue_scan: */ so->oppositeDirCheck = has_required_opposite_direction_only; - _bt_rewind_nonrequired_arrays(scan, dir); - /* * skip by setting "look ahead" mechanism's offnum for forwards scans * (backwards scans check scanBehind flag directly instead) @@ -2143,48 +2063,6 @@ end_toplevel_scan: #ifdef USE_ASSERT_CHECKING /* - * Verify that the scan's qual state matches what we expect at the point that - * _bt_start_prim_scan is about to start a just-scheduled new primitive scan. - * - * We enforce a rule against non-required array scan keys: they must start out - * with whatever element is the first for the scan's current scan direction. - * See _bt_rewind_nonrequired_arrays comments for an explanation. - */ -static bool -_bt_verify_arrays_bt_first(IndexScanDesc scan, ScanDirection dir) -{ - BTScanOpaque so = (BTScanOpaque) scan->opaque; - int arrayidx = 0; - - for (int ikey = 0; ikey < so->numberOfKeys; ikey++) - { - ScanKey cur = so->keyData + ikey; - BTArrayKeyInfo *array = NULL; - int first_elem_dir; - - if (!(cur->sk_flags & SK_SEARCHARRAY) || - cur->sk_strategy != BTEqualStrategyNumber) - continue; - - array = &so->arrayKeys[arrayidx++]; - - if (((cur->sk_flags & SK_BT_REQFWD) && ScanDirectionIsForward(dir)) || - ((cur->sk_flags & SK_BT_REQBKWD) && ScanDirectionIsBackward(dir))) - continue; - - if (ScanDirectionIsForward(dir)) - first_elem_dir = 0; - else - first_elem_dir = array->num_elems - 1; - - if (array->cur_elem != first_elem_dir) - return false; - } - - return _bt_verify_keys_with_arraykeys(scan); -} - -/* * Verify that the scan's "so->keyData[]" scan keys are in agreement with * its array key state */ @@ -2194,6 +2072,7 @@ _bt_verify_keys_with_arraykeys(IndexScanDesc scan) BTScanOpaque so = (BTScanOpaque) scan->opaque; int last_sk_attno = InvalidAttrNumber, arrayidx = 0; + bool nonrequiredseen = false; if (!so->qual_ok) return false; @@ -2217,8 +2096,16 @@ _bt_verify_keys_with_arraykeys(IndexScanDesc scan) if (array->num_elems != -1 && cur->sk_argument != array->elem_values[array->cur_elem]) return false; - if (last_sk_attno > cur->sk_attno) - return false; + if (cur->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)) + { + if (last_sk_attno > cur->sk_attno) + return false; + if (nonrequiredseen) + return false; + } + else + nonrequiredseen = true; + last_sk_attno = cur->sk_attno; } @@ -2551,37 +2438,12 @@ _bt_set_startikey(IndexScanDesc scan, BTReadPageState *pstate) if (!(key->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD))) { /* Scan key isn't marked required (corner case) */ - Assert(!(key->sk_flags & SK_ROW_HEADER)); break; /* unsafe */ } if (key->sk_flags & SK_ROW_HEADER) { - /* - * RowCompare inequality. - * - * Only the first subkey from a RowCompare can ever be marked - * required (that happens when the row header is marked required). - * There is no simple, general way for us to transitively deduce - * whether or not every tuple on the page satisfies a RowCompare - * key based only on firsttup and lasttup -- so we just give up. - */ - if (!start_past_saop_eq && !so->skipScan) - break; /* unsafe to go further */ - - /* - * We have to be even more careful with RowCompares that come - * after an array: we assume it's unsafe to even bypass the array. - * Calling _bt_start_array_keys to recover the scan's arrays - * following use of forcenonrequired mode isn't compatible with - * _bt_check_rowcompare's continuescan=false behavior with NULL - * row compare members. _bt_advance_array_keys must not make a - * decision on the basis of a key not being satisfied in the - * opposite-to-scan direction until the scan reaches a leaf page - * where the same key begins to be satisfied in scan direction. - * The _bt_first !used_all_subkeys behavior makes this limitation - * hard to work around some other way. - */ - return; /* completely unsafe to set pstate.startikey */ + /* RowCompare inequalities currently aren't supported */ + break; /* "unsafe" */ } if (key->sk_strategy != BTEqualStrategyNumber) { @@ -3078,6 +2940,31 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, Assert(subkey->sk_flags & SK_ROW_MEMBER); + /* When a NULL row member is compared, the row never matches */ + if (subkey->sk_flags & SK_ISNULL) + { + /* + * Unlike the simple-scankey case, this isn't a disallowed case + * (except when it's the first row element that has the NULL arg). + * But it can never match. If all the earlier row comparison + * columns are required for the scan direction, we can stop the + * scan, because there can't be another tuple that will succeed. + */ + Assert(subkey != (ScanKey) DatumGetPointer(skey->sk_argument)); + subkey--; + if (forcenonrequired) + { + /* treating scan's keys as non-required */ + } + else if ((subkey->sk_flags & SK_BT_REQFWD) && + ScanDirectionIsForward(dir)) + *continuescan = false; + else if ((subkey->sk_flags & SK_BT_REQBKWD) && + ScanDirectionIsBackward(dir)) + *continuescan = false; + return false; + } + if (subkey->sk_attno > tupnatts) { /* @@ -3087,11 +2974,7 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, * attribute passes the qual. */ Assert(BTreeTupleIsPivot(tuple)); - cmpresult = 0; - if (subkey->sk_flags & SK_ROW_END) - break; - subkey++; - continue; + return true; } datum = index_getattr(tuple, @@ -3101,6 +2984,8 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, if (isNull) { + int reqflags; + if (forcenonrequired) { /* treating scan's keys as non-required */ @@ -3111,15 +2996,35 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, * Since NULLs are sorted before non-NULLs, we know we have * reached the lower limit of the range of values for this * index attr. On a backward scan, we can stop if this qual - * is one of the "must match" subset. We can stop regardless - * of whether the qual is > or <, so long as it's required, - * because it's not possible for any future tuples to pass. On - * a forward scan, however, we must keep going, because we may - * have initially positioned to the start of the index. - * (_bt_advance_array_keys also relies on this behavior during - * forward scans.) + * is one of the "must match" subset. However, on a forwards + * scan, we must keep going, because we may have initially + * positioned to the start of the index. + * + * All required NULLS FIRST > row members can use NULL tuple + * values to end backwards scans, just like with other values. + * A qual "WHERE (a, b, c) > (9, 42, 'foo')" can terminate a + * backwards scan upon reaching the index's rightmost "a = 9" + * tuple whose "b" column contains a NULL (if not sooner). + * Since "b" is NULLS FIRST, we can treat its NULLs as "<" 42. */ - if ((subkey->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)) && + reqflags = SK_BT_REQBKWD; + + /* + * When a most significant required NULLS FIRST < row compare + * member sees NULL tuple values during a backwards scan, it + * signals the end of matches for the whole row compare/scan. + * A qual "WHERE (a, b, c) < (9, 42, 'foo')" will terminate a + * backwards scan upon reaching the rightmost tuple whose "a" + * column has a NULL. The "a" NULL value is "<" 9, and yet + * our < row compare will still end the scan. (This isn't + * safe with later/lower-order row members. Notice that it + * can only happen with an "a" NULL some time after the scan + * completely stops needing to use its "b" and "c" members.) + */ + if (subkey == (ScanKey) DatumGetPointer(skey->sk_argument)) + reqflags |= SK_BT_REQFWD; /* safe, first row member */ + + if ((subkey->sk_flags & reqflags) && ScanDirectionIsBackward(dir)) *continuescan = false; } @@ -3129,15 +3034,35 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, * Since NULLs are sorted after non-NULLs, we know we have * reached the upper limit of the range of values for this * index attr. On a forward scan, we can stop if this qual is - * one of the "must match" subset. We can stop regardless of - * whether the qual is > or <, so long as it's required, - * because it's not possible for any future tuples to pass. On - * a backward scan, however, we must keep going, because we - * may have initially positioned to the end of the index. - * (_bt_advance_array_keys also relies on this behavior during - * backward scans.) + * one of the "must match" subset. However, on a backward + * scan, we must keep going, because we may have initially + * positioned to the end of the index. + * + * All required NULLS LAST < row members can use NULL tuple + * values to end forwards scans, just like with other values. + * A qual "WHERE (a, b, c) < (9, 42, 'foo')" can terminate a + * forwards scan upon reaching the index's leftmost "a = 9" + * tuple whose "b" column contains a NULL (if not sooner). + * Since "b" is NULLS LAST, we can treat its NULLs as ">" 42. + */ + reqflags = SK_BT_REQFWD; + + /* + * When a most significant required NULLS LAST > row compare + * member sees NULL tuple values during a forwards scan, it + * signals the end of matches for the whole row compare/scan. + * A qual "WHERE (a, b, c) > (9, 42, 'foo')" will terminate a + * forwards scan upon reaching the leftmost tuple whose "a" + * column has a NULL. The "a" NULL value is ">" 9, and yet + * our > row compare will end the scan. (This isn't safe with + * later/lower-order row members. Notice that it can only + * happen with an "a" NULL some time after the scan completely + * stops needing to use its "b" and "c" members.) */ - if ((subkey->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)) && + if (subkey == (ScanKey) DatumGetPointer(skey->sk_argument)) + reqflags |= SK_BT_REQBKWD; /* safe, first row member */ + + if ((subkey->sk_flags & reqflags) && ScanDirectionIsForward(dir)) *continuescan = false; } @@ -3148,30 +3073,6 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, return false; } - if (subkey->sk_flags & SK_ISNULL) - { - /* - * Unlike the simple-scankey case, this isn't a disallowed case - * (except when it's the first row element that has the NULL arg). - * But it can never match. If all the earlier row comparison - * columns are required for the scan direction, we can stop the - * scan, because there can't be another tuple that will succeed. - */ - Assert(subkey != (ScanKey) DatumGetPointer(skey->sk_argument)); - subkey--; - if (forcenonrequired) - { - /* treating scan's keys as non-required */ - } - else if ((subkey->sk_flags & SK_BT_REQFWD) && - ScanDirectionIsForward(dir)) - *continuescan = false; - else if ((subkey->sk_flags & SK_BT_REQBKWD) && - ScanDirectionIsBackward(dir)) - *continuescan = false; - return false; - } - /* Perform the test --- three-way comparison not bool operator */ cmpresult = DatumGetInt32(FunctionCall2Coll(&subkey->sk_func, subkey->sk_collation, @@ -3330,87 +3231,85 @@ _bt_checkkeys_look_ahead(IndexScanDesc scan, BTReadPageState *pstate, * current page and killed tuples thereon (generally, this should only be * called if so->numKilled > 0). * - * The caller does not have a lock on the page and may or may not have the - * page pinned in a buffer. Note that read-lock is sufficient for setting - * LP_DEAD status (which is only a hint). - * - * We match items by heap TID before assuming they are the right ones to - * delete. We cope with cases where items have moved right due to insertions. - * If an item has moved off the current page due to a split, we'll fail to - * find it and do nothing (this is not an error case --- we assume the item - * will eventually get marked in a future indexscan). + * Caller should not have a lock on the so->currPos page, but must hold a + * buffer pin when !so->dropPin. When we return, it still won't be locked. + * It'll continue to hold whatever pins were held before calling here. * - * Note that if we hold a pin on the target page continuously from initially - * reading the items until applying this function, VACUUM cannot have deleted - * any items from the page, and so there is no need to search left from the - * recorded offset. (This observation also guarantees that the item is still - * the right one to delete, which might otherwise be questionable since heap - * TIDs can get recycled.) This holds true even if the page has been modified - * by inserts and page splits, so there is no need to consult the LSN. + * We match items by heap TID before assuming they are the right ones to set + * LP_DEAD. If the scan is one that holds a buffer pin on the target page + * continuously from initially reading the items until applying this function + * (if it is a !so->dropPin scan), VACUUM cannot have deleted any items on the + * page, so the page's TIDs can't have been recycled by now. There's no risk + * that we'll confuse a new index tuple that happens to use a recycled TID + * with a now-removed tuple with the same TID (that used to be on this same + * page). We can't rely on that during scans that drop buffer pins eagerly + * (so->dropPin scans), though, so we must condition setting LP_DEAD bits on + * the page LSN having not changed since back when _bt_readpage saw the page. + * We totally give up on setting LP_DEAD bits when the page LSN changed. * - * If the pin was released after reading the page, then we re-read it. If it - * has been modified since we read it (as determined by the LSN), we dare not - * flag any entries because it is possible that the old entry was vacuumed - * away and the TID was re-used by a completely different heap tuple. + * We give up much less often during !so->dropPin scans, but it still happens. + * We cope with cases where items have moved right due to insertions. If an + * item has moved off the current page due to a split, we'll fail to find it + * and just give up on it. */ void _bt_killitems(IndexScanDesc scan) { + Relation rel = scan->indexRelation; BTScanOpaque so = (BTScanOpaque) scan->opaque; Page page; BTPageOpaque opaque; OffsetNumber minoff; OffsetNumber maxoff; - int i; int numKilled = so->numKilled; bool killedsomething = false; - bool droppedpin PG_USED_FOR_ASSERTS_ONLY; + Buffer buf; + Assert(numKilled > 0); Assert(BTScanPosIsValid(so->currPos)); + Assert(scan->heapRelation != NULL); /* can't be a bitmap index scan */ - /* - * Always reset the scan state, so we don't look for same items on other - * pages. - */ + /* Always invalidate so->killedItems[] before leaving so->currPos */ so->numKilled = 0; - if (BTScanPosIsPinned(so->currPos)) + if (!so->dropPin) { /* * We have held the pin on this page since we read the index tuples, * so all we need to do is lock it. The pin will have prevented - * re-use of any TID on the page, so there is no need to check the - * LSN. + * concurrent VACUUMs from recycling any of the TIDs on the page. */ - droppedpin = false; - _bt_lockbuf(scan->indexRelation, so->currPos.buf, BT_READ); - - page = BufferGetPage(so->currPos.buf); + Assert(BTScanPosIsPinned(so->currPos)); + buf = so->currPos.buf; + _bt_lockbuf(rel, buf, BT_READ); } else { - Buffer buf; + XLogRecPtr latestlsn; - droppedpin = true; - /* Attempt to re-read the buffer, getting pin and lock. */ - buf = _bt_getbuf(scan->indexRelation, so->currPos.currPage, BT_READ); + Assert(!BTScanPosIsPinned(so->currPos)); + Assert(RelationNeedsWAL(rel)); + buf = _bt_getbuf(rel, so->currPos.currPage, BT_READ); - page = BufferGetPage(buf); - if (BufferGetLSNAtomic(buf) == so->currPos.lsn) - so->currPos.buf = buf; - else + latestlsn = BufferGetLSNAtomic(buf); + Assert(!XLogRecPtrIsInvalid(so->currPos.lsn)); + Assert(so->currPos.lsn <= latestlsn); + if (so->currPos.lsn != latestlsn) { - /* Modified while not pinned means hinting is not safe. */ - _bt_relbuf(scan->indexRelation, buf); + /* Modified, give up on hinting */ + _bt_relbuf(rel, buf); return; } + + /* Unmodified, hinting is safe */ } + page = BufferGetPage(buf); opaque = BTPageGetOpaque(page); minoff = P_FIRSTDATAKEY(opaque); maxoff = PageGetMaxOffsetNumber(page); - for (i = 0; i < numKilled; i++) + for (int i = 0; i < numKilled; i++) { int itemIndex = so->killedItems[i]; BTScanPosItem *kitem = &so->currPos.items[itemIndex]; @@ -3442,7 +3341,7 @@ _bt_killitems(IndexScanDesc scan) * correctness. * * Note that the page may have been modified in almost any way - * since we first read it (in the !droppedpin case), so it's + * since we first read it (in the !so->dropPin case), so it's * possible that this posting list tuple wasn't a posting list * tuple when we first encountered its heap TIDs. */ @@ -3458,7 +3357,7 @@ _bt_killitems(IndexScanDesc scan) * though only in the common case where the page can't * have been concurrently modified */ - Assert(kitem->indexOffset == offnum || !droppedpin); + Assert(kitem->indexOffset == offnum || !so->dropPin); /* * Read-ahead to later kitems here. @@ -3522,10 +3421,13 @@ _bt_killitems(IndexScanDesc scan) if (killedsomething) { opaque->btpo_flags |= BTP_HAS_GARBAGE; - MarkBufferDirtyHint(so->currPos.buf, true); + MarkBufferDirtyHint(buf, true); } - _bt_unlockbuf(scan->indexRelation, so->currPos.buf); + if (!so->dropPin) + _bt_unlockbuf(rel, buf); + else + _bt_relbuf(rel, buf); } diff --git a/src/backend/access/rmgrdesc/replorigindesc.c b/src/backend/access/rmgrdesc/replorigindesc.c index 5dd74233996..35e3af2903e 100644 --- a/src/backend/access/rmgrdesc/replorigindesc.c +++ b/src/backend/access/rmgrdesc/replorigindesc.c @@ -29,7 +29,7 @@ replorigin_desc(StringInfo buf, XLogReaderState *record) xlrec = (xl_replorigin_set *) rec; - appendStringInfo(buf, "set %u; lsn %X/%X; force: %d", + appendStringInfo(buf, "set %u; lsn %X/%08X; force: %d", xlrec->node_id, LSN_FORMAT_ARGS(xlrec->remote_lsn), xlrec->force); diff --git a/src/backend/access/rmgrdesc/xactdesc.c b/src/backend/access/rmgrdesc/xactdesc.c index 305598e2865..f0f696855b9 100644 --- a/src/backend/access/rmgrdesc/xactdesc.c +++ b/src/backend/access/rmgrdesc/xactdesc.c @@ -359,7 +359,7 @@ xact_desc_commit(StringInfo buf, uint8 info, xl_xact_commit *xlrec, RepOriginId if (parsed.xinfo & XACT_XINFO_HAS_ORIGIN) { - appendStringInfo(buf, "; origin: node %u, lsn %X/%X, at %s", + appendStringInfo(buf, "; origin: node %u, lsn %X/%08X, at %s", origin_id, LSN_FORMAT_ARGS(parsed.origin_lsn), timestamptz_to_str(parsed.origin_timestamp)); @@ -384,7 +384,7 @@ xact_desc_abort(StringInfo buf, uint8 info, xl_xact_abort *xlrec, RepOriginId or if (parsed.xinfo & XACT_XINFO_HAS_ORIGIN) { - appendStringInfo(buf, "; origin: node %u, lsn %X/%X, at %s", + appendStringInfo(buf, "; origin: node %u, lsn %X/%08X, at %s", origin_id, LSN_FORMAT_ARGS(parsed.origin_lsn), timestamptz_to_str(parsed.origin_timestamp)); @@ -418,7 +418,7 @@ xact_desc_prepare(StringInfo buf, uint8 info, xl_xact_prepare *xlrec, RepOriginI * way as PrepareRedoAdd(). */ if (origin_id != InvalidRepOriginId) - appendStringInfo(buf, "; origin: node %u, lsn %X/%X, at %s", + appendStringInfo(buf, "; origin: node %u, lsn %X/%08X, at %s", origin_id, LSN_FORMAT_ARGS(parsed.origin_lsn), timestamptz_to_str(parsed.origin_timestamp)); diff --git a/src/backend/access/rmgrdesc/xlogdesc.c b/src/backend/access/rmgrdesc/xlogdesc.c index 58040f28656..cd6c2a2f650 100644 --- a/src/backend/access/rmgrdesc/xlogdesc.c +++ b/src/backend/access/rmgrdesc/xlogdesc.c @@ -65,7 +65,7 @@ xlog_desc(StringInfo buf, XLogReaderState *record) { CheckPoint *checkpoint = (CheckPoint *) rec; - appendStringInfo(buf, "redo %X/%X; " + appendStringInfo(buf, "redo %X/%08X; " "tli %u; prev tli %u; fpw %s; wal_level %s; xid %u:%u; oid %u; multi %u; offset %u; " "oldest xid %u in DB %u; oldest multi %u in DB %u; " "oldest/newest commit timestamp xid: %u/%u; " @@ -111,7 +111,7 @@ xlog_desc(StringInfo buf, XLogReaderState *record) XLogRecPtr startpoint; memcpy(&startpoint, rec, sizeof(XLogRecPtr)); - appendStringInfo(buf, "%X/%X", LSN_FORMAT_ARGS(startpoint)); + appendStringInfo(buf, "%X/%08X", LSN_FORMAT_ARGS(startpoint)); } else if (info == XLOG_PARAMETER_CHANGE) { @@ -156,7 +156,7 @@ xlog_desc(StringInfo buf, XLogReaderState *record) xl_overwrite_contrecord xlrec; memcpy(&xlrec, rec, sizeof(xl_overwrite_contrecord)); - appendStringInfo(buf, "lsn %X/%X; time %s", + appendStringInfo(buf, "lsn %X/%08X; time %s", LSN_FORMAT_ARGS(xlrec.overwritten_lsn), timestamptz_to_str(xlrec.overwrite_time)); } diff --git a/src/backend/access/transam/commit_ts.c b/src/backend/access/transam/commit_ts.c index 113fae1437a..225ff7ca9f2 100644 --- a/src/backend/access/transam/commit_ts.c +++ b/src/backend/access/transam/commit_ts.c @@ -707,6 +707,13 @@ ActivateCommitTs(void) TransactionId xid; int64 pageno; + /* + * During bootstrap, we should not register commit timestamps so skip the + * activation in this case. + */ + if (IsBootstrapProcessingMode()) + return; + /* If we've done this already, there's nothing to do */ LWLockAcquire(CommitTsLock, LW_EXCLUSIVE); if (commitTsShared->commitTsActive) diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c index 3c06ac45532..7a7afe3edc6 100644 --- a/src/backend/access/transam/multixact.c +++ b/src/backend/access/transam/multixact.c @@ -1847,7 +1847,7 @@ AtPrepare_MultiXact(void) * Clean up after successful PREPARE TRANSACTION */ void -PostPrepare_MultiXact(TransactionId xid) +PostPrepare_MultiXact(FullTransactionId fxid) { MultiXactId myOldestMember; @@ -1858,7 +1858,7 @@ PostPrepare_MultiXact(TransactionId xid) myOldestMember = OldestMemberMXactId[MyProcNumber]; if (MultiXactIdIsValid(myOldestMember)) { - ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(xid, false); + ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(fxid, false); /* * Even though storing MultiXactId is atomic, acquire lock to make @@ -1896,10 +1896,10 @@ PostPrepare_MultiXact(TransactionId xid) * Recover the state of a prepared transaction at startup */ void -multixact_twophase_recover(TransactionId xid, uint16 info, +multixact_twophase_recover(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { - ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(xid, false); + ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(fxid, false); MultiXactId oldestMember; /* @@ -1917,10 +1917,10 @@ multixact_twophase_recover(TransactionId xid, uint16 info, * Similar to AtEOXact_MultiXact but for COMMIT PREPARED */ void -multixact_twophase_postcommit(TransactionId xid, uint16 info, +multixact_twophase_postcommit(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { - ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(xid, true); + ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(fxid, true); Assert(len == sizeof(MultiXactId)); @@ -1932,10 +1932,10 @@ multixact_twophase_postcommit(TransactionId xid, uint16 info, * This is actually just the same as the COMMIT case. */ void -multixact_twophase_postabort(TransactionId xid, uint16 info, +multixact_twophase_postabort(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { - multixact_twophase_postcommit(xid, info, recdata, len); + multixact_twophase_postcommit(fxid, info, recdata, len); } /* diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c index a27f27cc037..186eb91f609 100644 --- a/src/backend/access/transam/timeline.c +++ b/src/backend/access/transam/timeline.c @@ -154,7 +154,7 @@ readTimeLineHistory(TimeLineID targetTLI) if (*ptr == '\0' || *ptr == '#') continue; - nfields = sscanf(fline, "%u\t%X/%X", &tli, &switchpoint_hi, &switchpoint_lo); + nfields = sscanf(fline, "%u\t%X/%08X", &tli, &switchpoint_hi, &switchpoint_lo); if (nfields < 1) { @@ -399,7 +399,7 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI, * parent file failed to end with one. */ snprintf(buffer, sizeof(buffer), - "%s%u\t%X/%X\t%s\n", + "%s%u\t%X/%08X\t%s\n", (srcfd < 0) ? "" : "\n", parentTLI, LSN_FORMAT_ARGS(switchpoint), diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c index 73a80559194..85cbe397cb2 100644 --- a/src/backend/access/transam/twophase.c +++ b/src/backend/access/transam/twophase.c @@ -159,7 +159,7 @@ typedef struct GlobalTransactionData */ XLogRecPtr prepare_start_lsn; /* XLOG offset of prepare record start */ XLogRecPtr prepare_end_lsn; /* XLOG offset of prepare record end */ - TransactionId xid; /* The GXACT id */ + FullTransactionId fxid; /* The GXACT full xid */ Oid owner; /* ID of user that executed the xact */ ProcNumber locking_backend; /* backend currently working on the xact */ @@ -197,6 +197,7 @@ static GlobalTransaction MyLockedGxact = NULL; static bool twophaseExitRegistered = false; +static void PrepareRedoRemoveFull(FullTransactionId fxid, bool giveWarning); static void RecordTransactionCommitPrepared(TransactionId xid, int nchildren, TransactionId *children, @@ -216,19 +217,19 @@ static void RecordTransactionAbortPrepared(TransactionId xid, int nstats, xl_xact_stats_item *stats, const char *gid); -static void ProcessRecords(char *bufptr, TransactionId xid, +static void ProcessRecords(char *bufptr, FullTransactionId fxid, const TwoPhaseCallback callbacks[]); static void RemoveGXact(GlobalTransaction gxact); static void XlogReadTwoPhaseData(XLogRecPtr lsn, char **buf, int *len); -static char *ProcessTwoPhaseBuffer(TransactionId xid, +static char *ProcessTwoPhaseBuffer(FullTransactionId fxid, XLogRecPtr prepare_start_lsn, bool fromdisk, bool setParent, bool setNextXid); -static void MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, +static void MarkAsPreparingGuts(GlobalTransaction gxact, FullTransactionId fxid, const char *gid, TimestampTz prepared_at, Oid owner, Oid databaseid); -static void RemoveTwoPhaseFile(TransactionId xid, bool giveWarning); -static void RecreateTwoPhaseFile(TransactionId xid, void *content, int len); +static void RemoveTwoPhaseFile(FullTransactionId fxid, bool giveWarning); +static void RecreateTwoPhaseFile(FullTransactionId fxid, void *content, int len); /* * Initialization of shared memory @@ -356,7 +357,7 @@ PostPrepare_Twophase(void) * Reserve the GID for the given transaction. */ GlobalTransaction -MarkAsPreparing(TransactionId xid, const char *gid, +MarkAsPreparing(FullTransactionId fxid, const char *gid, TimestampTz prepared_at, Oid owner, Oid databaseid) { GlobalTransaction gxact; @@ -407,7 +408,7 @@ MarkAsPreparing(TransactionId xid, const char *gid, gxact = TwoPhaseState->freeGXacts; TwoPhaseState->freeGXacts = gxact->next; - MarkAsPreparingGuts(gxact, xid, gid, prepared_at, owner, databaseid); + MarkAsPreparingGuts(gxact, fxid, gid, prepared_at, owner, databaseid); gxact->ondisk = false; @@ -430,11 +431,13 @@ MarkAsPreparing(TransactionId xid, const char *gid, * Note: This function should be called with appropriate locks held. */ static void -MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, const char *gid, - TimestampTz prepared_at, Oid owner, Oid databaseid) +MarkAsPreparingGuts(GlobalTransaction gxact, FullTransactionId fxid, + const char *gid, TimestampTz prepared_at, Oid owner, + Oid databaseid) { PGPROC *proc; int i; + TransactionId xid = XidFromFullTransactionId(fxid); Assert(LWLockHeldByMeInMode(TwoPhaseStateLock, LW_EXCLUSIVE)); @@ -479,7 +482,7 @@ MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, const char *gid, proc->subxidStatus.count = 0; gxact->prepared_at = prepared_at; - gxact->xid = xid; + gxact->fxid = fxid; gxact->owner = owner; gxact->locking_backend = MyProcNumber; gxact->valid = false; @@ -797,12 +800,12 @@ pg_prepared_xact(PG_FUNCTION_ARGS) * caller had better hold it. */ static GlobalTransaction -TwoPhaseGetGXact(TransactionId xid, bool lock_held) +TwoPhaseGetGXact(FullTransactionId fxid, bool lock_held) { GlobalTransaction result = NULL; int i; - static TransactionId cached_xid = InvalidTransactionId; + static FullTransactionId cached_fxid = {InvalidTransactionId}; static GlobalTransaction cached_gxact = NULL; Assert(!lock_held || LWLockHeldByMe(TwoPhaseStateLock)); @@ -811,7 +814,7 @@ TwoPhaseGetGXact(TransactionId xid, bool lock_held) * During a recovery, COMMIT PREPARED, or ABORT PREPARED, we'll be called * repeatedly for the same XID. We can save work with a simple cache. */ - if (xid == cached_xid) + if (FullTransactionIdEquals(fxid, cached_fxid)) return cached_gxact; if (!lock_held) @@ -821,7 +824,7 @@ TwoPhaseGetGXact(TransactionId xid, bool lock_held) { GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; - if (gxact->xid == xid) + if (FullTransactionIdEquals(gxact->fxid, fxid)) { result = gxact; break; @@ -832,9 +835,10 @@ TwoPhaseGetGXact(TransactionId xid, bool lock_held) LWLockRelease(TwoPhaseStateLock); if (result == NULL) /* should not happen */ - elog(ERROR, "failed to find GlobalTransaction for xid %u", xid); + elog(ERROR, "failed to find GlobalTransaction for xid %u", + XidFromFullTransactionId(fxid)); - cached_xid = xid; + cached_fxid = fxid; cached_gxact = result; return result; @@ -881,7 +885,7 @@ TwoPhaseGetXidByVirtualXID(VirtualTransactionId vxid, *have_more = true; break; } - result = gxact->xid; + result = XidFromFullTransactionId(gxact->fxid); } } @@ -892,7 +896,7 @@ TwoPhaseGetXidByVirtualXID(VirtualTransactionId vxid, /* * TwoPhaseGetDummyProcNumber - * Get the dummy proc number for prepared transaction specified by XID + * Get the dummy proc number for prepared transaction * * Dummy proc numbers are similar to proc numbers of real backends. They * start at MaxBackends, and are unique across all currently active real @@ -900,24 +904,24 @@ TwoPhaseGetXidByVirtualXID(VirtualTransactionId vxid, * TwoPhaseStateLock will not be taken, so the caller had better hold it. */ ProcNumber -TwoPhaseGetDummyProcNumber(TransactionId xid, bool lock_held) +TwoPhaseGetDummyProcNumber(FullTransactionId fxid, bool lock_held) { - GlobalTransaction gxact = TwoPhaseGetGXact(xid, lock_held); + GlobalTransaction gxact = TwoPhaseGetGXact(fxid, lock_held); return gxact->pgprocno; } /* * TwoPhaseGetDummyProc - * Get the PGPROC that represents a prepared transaction specified by XID + * Get the PGPROC that represents a prepared transaction * * If lock_held is set to true, TwoPhaseStateLock will not be taken, so the * caller had better hold it. */ PGPROC * -TwoPhaseGetDummyProc(TransactionId xid, bool lock_held) +TwoPhaseGetDummyProc(FullTransactionId fxid, bool lock_held) { - GlobalTransaction gxact = TwoPhaseGetGXact(xid, lock_held); + GlobalTransaction gxact = TwoPhaseGetGXact(fxid, lock_held); return GetPGProcByNumber(gxact->pgprocno); } @@ -942,10 +946,8 @@ AdjustToFullTransactionId(TransactionId xid) } static inline int -TwoPhaseFilePath(char *path, TransactionId xid) +TwoPhaseFilePath(char *path, FullTransactionId fxid) { - FullTransactionId fxid = AdjustToFullTransactionId(xid); - return snprintf(path, MAXPGPATH, TWOPHASE_DIR "/%08X%08X", EpochFromFullTransactionId(fxid), XidFromFullTransactionId(fxid)); @@ -1049,7 +1051,7 @@ void StartPrepare(GlobalTransaction gxact) { PGPROC *proc = GetPGProcByNumber(gxact->pgprocno); - TransactionId xid = gxact->xid; + TransactionId xid = XidFromFullTransactionId(gxact->fxid); TwoPhaseFileHeader hdr; TransactionId *children; RelFileLocator *commitrels; @@ -1281,10 +1283,11 @@ RegisterTwoPhaseRecord(TwoPhaseRmgrId rmid, uint16 info, * If it looks OK (has a valid magic number and CRC), return the palloc'd * contents of the file, issuing an error when finding corrupted data. If * missing_ok is true, which indicates that missing files can be safely - * ignored, then return NULL. This state can be reached when doing recovery. + * ignored, then return NULL. This state can be reached when doing recovery + * after discarding two-phase files from frozen epochs. */ static char * -ReadTwoPhaseFile(TransactionId xid, bool missing_ok) +ReadTwoPhaseFile(FullTransactionId fxid, bool missing_ok) { char path[MAXPGPATH]; char *buf; @@ -1296,7 +1299,7 @@ ReadTwoPhaseFile(TransactionId xid, bool missing_ok) file_crc; int r; - TwoPhaseFilePath(path, xid); + TwoPhaseFilePath(path, fxid); fd = OpenTransientFile(path, O_RDONLY | PG_BINARY); if (fd < 0) @@ -1426,12 +1429,12 @@ XlogReadTwoPhaseData(XLogRecPtr lsn, char **buf, int *len) if (errormsg) ereport(ERROR, (errcode_for_file_access(), - errmsg("could not read two-phase state from WAL at %X/%X: %s", + errmsg("could not read two-phase state from WAL at %X/%08X: %s", LSN_FORMAT_ARGS(lsn), errormsg))); else ereport(ERROR, (errcode_for_file_access(), - errmsg("could not read two-phase state from WAL at %X/%X", + errmsg("could not read two-phase state from WAL at %X/%08X", LSN_FORMAT_ARGS(lsn)))); } @@ -1439,7 +1442,7 @@ XlogReadTwoPhaseData(XLogRecPtr lsn, char **buf, int *len) (XLogRecGetInfo(xlogreader) & XLOG_XACT_OPMASK) != XLOG_XACT_PREPARE) ereport(ERROR, (errcode_for_file_access(), - errmsg("expected two-phase state data is not present in WAL at %X/%X", + errmsg("expected two-phase state data is not present in WAL at %X/%08X", LSN_FORMAT_ARGS(lsn)))); if (len != NULL) @@ -1461,6 +1464,7 @@ StandbyTransactionIdIsPrepared(TransactionId xid) char *buf; TwoPhaseFileHeader *hdr; bool result; + FullTransactionId fxid; Assert(TransactionIdIsValid(xid)); @@ -1468,7 +1472,8 @@ StandbyTransactionIdIsPrepared(TransactionId xid) return false; /* nothing to do */ /* Read and validate file */ - buf = ReadTwoPhaseFile(xid, true); + fxid = AdjustToFullTransactionId(xid); + buf = ReadTwoPhaseFile(fxid, true); if (buf == NULL) return false; @@ -1488,6 +1493,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) { GlobalTransaction gxact; PGPROC *proc; + FullTransactionId fxid; TransactionId xid; bool ondisk; char *buf; @@ -1509,7 +1515,8 @@ FinishPreparedTransaction(const char *gid, bool isCommit) */ gxact = LockGXact(gid, GetUserId()); proc = GetPGProcByNumber(gxact->pgprocno); - xid = gxact->xid; + fxid = gxact->fxid; + xid = XidFromFullTransactionId(fxid); /* * Read and validate 2PC state data. State data will typically be stored @@ -1517,7 +1524,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) * to disk if for some reason they have lived for a long time. */ if (gxact->ondisk) - buf = ReadTwoPhaseFile(xid, false); + buf = ReadTwoPhaseFile(fxid, false); else XlogReadTwoPhaseData(gxact->prepare_start_lsn, &buf, NULL); @@ -1636,11 +1643,11 @@ FinishPreparedTransaction(const char *gid, bool isCommit) /* And now do the callbacks */ if (isCommit) - ProcessRecords(bufptr, xid, twophase_postcommit_callbacks); + ProcessRecords(bufptr, fxid, twophase_postcommit_callbacks); else - ProcessRecords(bufptr, xid, twophase_postabort_callbacks); + ProcessRecords(bufptr, fxid, twophase_postabort_callbacks); - PredicateLockTwoPhaseFinish(xid, isCommit); + PredicateLockTwoPhaseFinish(fxid, isCommit); /* * Read this value while holding the two-phase lock, as the on-disk 2PC @@ -1664,7 +1671,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) * And now we can clean up any files we may have left. */ if (ondisk) - RemoveTwoPhaseFile(xid, true); + RemoveTwoPhaseFile(fxid, true); MyLockedGxact = NULL; @@ -1677,7 +1684,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) * Scan 2PC state data in memory and call the indicated callbacks for each 2PC record. */ static void -ProcessRecords(char *bufptr, TransactionId xid, +ProcessRecords(char *bufptr, FullTransactionId fxid, const TwoPhaseCallback callbacks[]) { for (;;) @@ -1691,24 +1698,28 @@ ProcessRecords(char *bufptr, TransactionId xid, bufptr += MAXALIGN(sizeof(TwoPhaseRecordOnDisk)); if (callbacks[record->rmid] != NULL) - callbacks[record->rmid] (xid, record->info, bufptr, record->len); + callbacks[record->rmid] (fxid, record->info, bufptr, record->len); bufptr += MAXALIGN(record->len); } } /* - * Remove the 2PC file for the specified XID. + * Remove the 2PC file. * * If giveWarning is false, do not complain about file-not-present; * this is an expected case during WAL replay. + * + * This routine is used at early stages at recovery where future and + * past orphaned files are checked, hence the FullTransactionId to build + * a complete file name fit for the removal. */ static void -RemoveTwoPhaseFile(TransactionId xid, bool giveWarning) +RemoveTwoPhaseFile(FullTransactionId fxid, bool giveWarning) { char path[MAXPGPATH]; - TwoPhaseFilePath(path, xid); + TwoPhaseFilePath(path, fxid); if (unlink(path)) if (errno != ENOENT || giveWarning) ereport(WARNING, @@ -1723,7 +1734,7 @@ RemoveTwoPhaseFile(TransactionId xid, bool giveWarning) * Note: content and len don't include CRC. */ static void -RecreateTwoPhaseFile(TransactionId xid, void *content, int len) +RecreateTwoPhaseFile(FullTransactionId fxid, void *content, int len) { char path[MAXPGPATH]; pg_crc32c statefile_crc; @@ -1734,7 +1745,7 @@ RecreateTwoPhaseFile(TransactionId xid, void *content, int len) COMP_CRC32C(statefile_crc, content, len); FIN_CRC32C(statefile_crc); - TwoPhaseFilePath(path, xid); + TwoPhaseFilePath(path, fxid); fd = OpenTransientFile(path, O_CREAT | O_TRUNC | O_WRONLY | PG_BINARY); @@ -1846,7 +1857,7 @@ CheckPointTwoPhase(XLogRecPtr redo_horizon) int len; XlogReadTwoPhaseData(gxact->prepare_start_lsn, &buf, &len); - RecreateTwoPhaseFile(gxact->xid, buf, len); + RecreateTwoPhaseFile(gxact->fxid, buf, len); gxact->ondisk = true; gxact->prepare_start_lsn = InvalidXLogRecPtr; gxact->prepare_end_lsn = InvalidXLogRecPtr; @@ -1897,19 +1908,17 @@ restoreTwoPhaseData(void) if (strlen(clde->d_name) == 16 && strspn(clde->d_name, "0123456789ABCDEF") == 16) { - TransactionId xid; FullTransactionId fxid; char *buf; fxid = FullTransactionIdFromU64(strtou64(clde->d_name, NULL, 16)); - xid = XidFromFullTransactionId(fxid); - buf = ProcessTwoPhaseBuffer(xid, InvalidXLogRecPtr, + buf = ProcessTwoPhaseBuffer(fxid, InvalidXLogRecPtr, true, false, false); if (buf == NULL) continue; - PrepareRedoAdd(buf, InvalidXLogRecPtr, + PrepareRedoAdd(fxid, buf, InvalidXLogRecPtr, InvalidXLogRecPtr, InvalidRepOriginId); } } @@ -1968,9 +1977,7 @@ PrescanPreparedTransactions(TransactionId **xids_p, int *nxids_p) Assert(gxact->inredo); - xid = gxact->xid; - - buf = ProcessTwoPhaseBuffer(xid, + buf = ProcessTwoPhaseBuffer(gxact->fxid, gxact->prepare_start_lsn, gxact->ondisk, false, true); @@ -1981,6 +1988,7 @@ PrescanPreparedTransactions(TransactionId **xids_p, int *nxids_p) * OK, we think this file is valid. Incorporate xid into the * running-minimum result. */ + xid = XidFromFullTransactionId(gxact->fxid); if (TransactionIdPrecedes(xid, result)) result = xid; @@ -2036,15 +2044,12 @@ StandbyRecoverPreparedTransactions(void) LWLockAcquire(TwoPhaseStateLock, LW_EXCLUSIVE); for (i = 0; i < TwoPhaseState->numPrepXacts; i++) { - TransactionId xid; char *buf; GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; Assert(gxact->inredo); - xid = gxact->xid; - - buf = ProcessTwoPhaseBuffer(xid, + buf = ProcessTwoPhaseBuffer(gxact->fxid, gxact->prepare_start_lsn, gxact->ondisk, true, false); if (buf != NULL) @@ -2077,16 +2082,14 @@ RecoverPreparedTransactions(void) LWLockAcquire(TwoPhaseStateLock, LW_EXCLUSIVE); for (i = 0; i < TwoPhaseState->numPrepXacts; i++) { - TransactionId xid; char *buf; GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; + FullTransactionId fxid = gxact->fxid; char *bufptr; TwoPhaseFileHeader *hdr; TransactionId *subxids; const char *gid; - xid = gxact->xid; - /* * Reconstruct subtrans state for the transaction --- needed because * pg_subtrans is not preserved over a restart. Note that we are @@ -2096,17 +2099,20 @@ RecoverPreparedTransactions(void) * SubTransSetParent has been set before, if the prepared transaction * generated xid assignment records. */ - buf = ProcessTwoPhaseBuffer(xid, + buf = ProcessTwoPhaseBuffer(gxact->fxid, gxact->prepare_start_lsn, gxact->ondisk, true, false); if (buf == NULL) continue; ereport(LOG, - (errmsg("recovering prepared transaction %u from shared memory", xid))); + (errmsg("recovering prepared transaction %u of epoch %u from shared memory", + XidFromFullTransactionId(gxact->fxid), + EpochFromFullTransactionId(gxact->fxid)))); hdr = (TwoPhaseFileHeader *) buf; - Assert(TransactionIdEquals(hdr->xid, xid)); + Assert(TransactionIdEquals(hdr->xid, + XidFromFullTransactionId(gxact->fxid))); bufptr = buf + MAXALIGN(sizeof(TwoPhaseFileHeader)); gid = (const char *) bufptr; bufptr += MAXALIGN(hdr->gidlen); @@ -2122,7 +2128,7 @@ RecoverPreparedTransactions(void) * Recreate its GXACT and dummy PGPROC. But, check whether it was * added in redo and already has a shmem entry for it. */ - MarkAsPreparingGuts(gxact, xid, gid, + MarkAsPreparingGuts(gxact, gxact->fxid, gid, hdr->prepared_at, hdr->owner, hdr->database); @@ -2137,7 +2143,7 @@ RecoverPreparedTransactions(void) /* * Recover other state (notably locks) using resource managers. */ - ProcessRecords(bufptr, xid, twophase_recover_callbacks); + ProcessRecords(bufptr, fxid, twophase_recover_callbacks); /* * Release locks held by the standby process after we process each @@ -2145,7 +2151,7 @@ RecoverPreparedTransactions(void) * additional locks at any one time. */ if (InHotStandby) - StandbyReleaseLockTree(xid, hdr->nsubxacts, subxids); + StandbyReleaseLockTree(hdr->xid, hdr->nsubxacts, subxids); /* * We're done with recovering this transaction. Clear MyLockedGxact, @@ -2164,7 +2170,7 @@ RecoverPreparedTransactions(void) /* * ProcessTwoPhaseBuffer * - * Given a transaction id, read it either from disk or read it directly + * Given a FullTransactionId, read it either from disk or read it directly * via shmem xlog record pointer using the provided "prepare_start_lsn". * * If setParent is true, set up subtransaction parent linkages. @@ -2173,13 +2179,12 @@ RecoverPreparedTransactions(void) * value scanned. */ static char * -ProcessTwoPhaseBuffer(TransactionId xid, +ProcessTwoPhaseBuffer(FullTransactionId fxid, XLogRecPtr prepare_start_lsn, bool fromdisk, bool setParent, bool setNextXid) { FullTransactionId nextXid = TransamVariables->nextXid; - TransactionId origNextXid = XidFromFullTransactionId(nextXid); TransactionId *subxids; char *buf; TwoPhaseFileHeader *hdr; @@ -2191,41 +2196,46 @@ ProcessTwoPhaseBuffer(TransactionId xid, Assert(prepare_start_lsn != InvalidXLogRecPtr); /* Already processed? */ - if (TransactionIdDidCommit(xid) || TransactionIdDidAbort(xid)) + if (TransactionIdDidCommit(XidFromFullTransactionId(fxid)) || + TransactionIdDidAbort(XidFromFullTransactionId(fxid))) { if (fromdisk) { ereport(WARNING, - (errmsg("removing stale two-phase state file for transaction %u", - xid))); - RemoveTwoPhaseFile(xid, true); + (errmsg("removing stale two-phase state file for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); + RemoveTwoPhaseFile(fxid, true); } else { ereport(WARNING, - (errmsg("removing stale two-phase state from memory for transaction %u", - xid))); - PrepareRedoRemove(xid, true); + (errmsg("removing stale two-phase state from memory for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); + PrepareRedoRemoveFull(fxid, true); } return NULL; } /* Reject XID if too new */ - if (TransactionIdFollowsOrEquals(xid, origNextXid)) + if (FullTransactionIdFollowsOrEquals(fxid, nextXid)) { if (fromdisk) { ereport(WARNING, - (errmsg("removing future two-phase state file for transaction %u", - xid))); - RemoveTwoPhaseFile(xid, true); + (errmsg("removing future two-phase state file for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); + RemoveTwoPhaseFile(fxid, true); } else { ereport(WARNING, - (errmsg("removing future two-phase state from memory for transaction %u", - xid))); - PrepareRedoRemove(xid, true); + (errmsg("removing future two-phase state from memory for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); + PrepareRedoRemoveFull(fxid, true); } return NULL; } @@ -2233,7 +2243,7 @@ ProcessTwoPhaseBuffer(TransactionId xid, if (fromdisk) { /* Read and validate file */ - buf = ReadTwoPhaseFile(xid, false); + buf = ReadTwoPhaseFile(fxid, false); } else { @@ -2243,18 +2253,20 @@ ProcessTwoPhaseBuffer(TransactionId xid, /* Deconstruct header */ hdr = (TwoPhaseFileHeader *) buf; - if (!TransactionIdEquals(hdr->xid, xid)) + if (!TransactionIdEquals(hdr->xid, XidFromFullTransactionId(fxid))) { if (fromdisk) ereport(ERROR, (errcode(ERRCODE_DATA_CORRUPTED), - errmsg("corrupted two-phase state file for transaction %u", - xid))); + errmsg("corrupted two-phase state file for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); else ereport(ERROR, (errcode(ERRCODE_DATA_CORRUPTED), - errmsg("corrupted two-phase state in memory for transaction %u", - xid))); + errmsg("corrupted two-phase state in memory for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); } /* @@ -2268,14 +2280,14 @@ ProcessTwoPhaseBuffer(TransactionId xid, { TransactionId subxid = subxids[i]; - Assert(TransactionIdFollows(subxid, xid)); + Assert(TransactionIdFollows(subxid, XidFromFullTransactionId(fxid))); /* update nextXid if needed */ if (setNextXid) AdvanceNextFullTransactionIdPastXid(subxid); if (setParent) - SubTransSetParent(subxid, xid); + SubTransSetParent(subxid, XidFromFullTransactionId(fxid)); } return buf; @@ -2466,8 +2478,9 @@ RecordTransactionAbortPrepared(TransactionId xid, * data, the entry is marked as located on disk. */ void -PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, - XLogRecPtr end_lsn, RepOriginId origin_id) +PrepareRedoAdd(FullTransactionId fxid, char *buf, + XLogRecPtr start_lsn, XLogRecPtr end_lsn, + RepOriginId origin_id) { TwoPhaseFileHeader *hdr = (TwoPhaseFileHeader *) buf; char *bufptr; @@ -2477,6 +2490,13 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, Assert(LWLockHeldByMeInMode(TwoPhaseStateLock, LW_EXCLUSIVE)); Assert(RecoveryInProgress()); + if (!FullTransactionIdIsValid(fxid)) + { + Assert(InRecovery); + fxid = FullTransactionIdFromAllowableAt(TransamVariables->nextXid, + hdr->xid); + } + bufptr = buf + MAXALIGN(sizeof(TwoPhaseFileHeader)); gid = (const char *) bufptr; @@ -2505,14 +2525,15 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, { char path[MAXPGPATH]; - TwoPhaseFilePath(path, hdr->xid); + Assert(InRecovery); + TwoPhaseFilePath(path, fxid); if (access(path, F_OK) == 0) { ereport(reachedConsistency ? ERROR : WARNING, (errmsg("could not recover two-phase state file for transaction %u", hdr->xid), - errdetail("Two-phase state file has been found in WAL record %X/%X, but this transaction has already been restored from disk.", + errdetail("Two-phase state file has been found in WAL record %X/%08X, but this transaction has already been restored from disk.", LSN_FORMAT_ARGS(start_lsn)))); return; } @@ -2536,7 +2557,7 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, gxact->prepared_at = hdr->prepared_at; gxact->prepare_start_lsn = start_lsn; gxact->prepare_end_lsn = end_lsn; - gxact->xid = hdr->xid; + gxact->fxid = fxid; gxact->owner = hdr->owner; gxact->locking_backend = INVALID_PROC_NUMBER; gxact->valid = false; @@ -2555,11 +2576,13 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, false /* backward */ , false /* WAL */ ); } - elog(DEBUG2, "added 2PC data in shared memory for transaction %u", gxact->xid); + elog(DEBUG2, "added 2PC data in shared memory for transaction %u of epoch %u", + XidFromFullTransactionId(gxact->fxid), + EpochFromFullTransactionId(gxact->fxid)); } /* - * PrepareRedoRemove + * PrepareRedoRemoveFull * * Remove the corresponding gxact entry from TwoPhaseState. Also remove * the 2PC file if a prepared transaction was saved via an earlier checkpoint. @@ -2567,8 +2590,8 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, * Caller must hold TwoPhaseStateLock in exclusive mode, because TwoPhaseState * is updated. */ -void -PrepareRedoRemove(TransactionId xid, bool giveWarning) +static void +PrepareRedoRemoveFull(FullTransactionId fxid, bool giveWarning) { GlobalTransaction gxact = NULL; int i; @@ -2581,7 +2604,7 @@ PrepareRedoRemove(TransactionId xid, bool giveWarning) { gxact = TwoPhaseState->prepXacts[i]; - if (gxact->xid == xid) + if (FullTransactionIdEquals(gxact->fxid, fxid)) { Assert(gxact->inredo); found = true; @@ -2598,13 +2621,29 @@ PrepareRedoRemove(TransactionId xid, bool giveWarning) /* * And now we can clean up any files we may have left. */ - elog(DEBUG2, "removing 2PC data for transaction %u", xid); + elog(DEBUG2, "removing 2PC data for transaction %u of epoch %u ", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)); + if (gxact->ondisk) - RemoveTwoPhaseFile(xid, giveWarning); + RemoveTwoPhaseFile(fxid, giveWarning); + RemoveGXact(gxact); } /* + * Wrapper of PrepareRedoRemoveFull(), for TransactionIds. + */ +void +PrepareRedoRemove(TransactionId xid, bool giveWarning) +{ + FullTransactionId fxid = + FullTransactionIdFromAllowableAt(TransamVariables->nextXid, xid); + + PrepareRedoRemoveFull(fxid, giveWarning); +} + +/* * LookupGXact * Check if the prepared transaction with the given GID, lsn and timestamp * exists. @@ -2648,7 +2687,7 @@ LookupGXact(const char *gid, XLogRecPtr prepare_end_lsn, * between publisher and subscriber. */ if (gxact->ondisk) - buf = ReadTwoPhaseFile(gxact->xid, false); + buf = ReadTwoPhaseFile(gxact->fxid, false); else { Assert(gxact->prepare_start_lsn); diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c index b885513f765..41601fcb280 100644 --- a/src/backend/access/transam/xact.c +++ b/src/backend/access/transam/xact.c @@ -2515,7 +2515,7 @@ static void PrepareTransaction(void) { TransactionState s = CurrentTransactionState; - TransactionId xid = GetCurrentTransactionId(); + FullTransactionId fxid = GetCurrentFullTransactionId(); GlobalTransaction gxact; TimestampTz prepared_at; @@ -2644,7 +2644,7 @@ PrepareTransaction(void) * Reserve the GID for this transaction. This could fail if the requested * GID is invalid or already in use. */ - gxact = MarkAsPreparing(xid, prepareGID, prepared_at, + gxact = MarkAsPreparing(fxid, prepareGID, prepared_at, GetUserId(), MyDatabaseId); prepareGID = NULL; @@ -2694,7 +2694,7 @@ PrepareTransaction(void) * ProcArrayClearTransaction(). Otherwise, a GetLockConflicts() would * conclude "xact already committed or aborted" for our locks. */ - PostPrepare_Locks(xid); + PostPrepare_Locks(fxid); /* * Let others know about no transaction in progress by me. This has to be @@ -2738,9 +2738,9 @@ PrepareTransaction(void) PostPrepare_smgr(); - PostPrepare_MultiXact(xid); + PostPrepare_MultiXact(fxid); - PostPrepare_PredicateLocks(xid); + PostPrepare_PredicateLocks(fxid); ResourceOwnerRelease(TopTransactionResourceOwner, RESOURCE_RELEASE_LOCKS, @@ -6420,7 +6420,8 @@ xact_redo(XLogReaderState *record) * gxact entry. */ LWLockAcquire(TwoPhaseStateLock, LW_EXCLUSIVE); - PrepareRedoAdd(XLogRecGetData(record), + PrepareRedoAdd(InvalidFullTransactionId, + XLogRecGetData(record), record->ReadRecPtr, record->EndRecPtr, XLogRecGetOrigin(record)); diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 1914859b2ee..a8cc6402d62 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -1028,7 +1028,7 @@ XLogInsertRecord(XLogRecData *rdata, oldCxt = MemoryContextSwitchTo(walDebugCxt); initStringInfo(&buf); - appendStringInfo(&buf, "INSERT @ %X/%X: ", LSN_FORMAT_ARGS(EndPos)); + appendStringInfo(&buf, "INSERT @ %X/%08X: ", LSN_FORMAT_ARGS(EndPos)); /* * We have to piece together the WAL record data from the XLogRecData @@ -1549,8 +1549,8 @@ WaitXLogInsertionsToFinish(XLogRecPtr upto) if (upto > reservedUpto) { ereport(LOG, - (errmsg("request to flush past end of generated WAL; request %X/%X, current position %X/%X", - LSN_FORMAT_ARGS(upto), LSN_FORMAT_ARGS(reservedUpto)))); + errmsg("request to flush past end of generated WAL; request %X/%08X, current position %X/%08X", + LSN_FORMAT_ARGS(upto), LSN_FORMAT_ARGS(reservedUpto))); upto = reservedUpto; } @@ -1716,7 +1716,7 @@ GetXLogBuffer(XLogRecPtr ptr, TimeLineID tli) endptr = pg_atomic_read_u64(&XLogCtl->xlblocks[idx]); if (expectedEndPtr != endptr) - elog(PANIC, "could not find WAL buffer for %X/%X", + elog(PANIC, "could not find WAL buffer for %X/%08X", LSN_FORMAT_ARGS(ptr)); } else @@ -1776,7 +1776,7 @@ WALReadFromBuffers(char *dstbuf, XLogRecPtr startptr, Size count, inserted = pg_atomic_read_u64(&XLogCtl->logInsertResult); if (startptr + count > inserted) ereport(ERROR, - errmsg("cannot read past end of generated WAL: requested %X/%X, current position %X/%X", + errmsg("cannot read past end of generated WAL: requested %X/%08X, current position %X/%08X", LSN_FORMAT_ARGS(startptr + count), LSN_FORMAT_ARGS(inserted))); @@ -2281,7 +2281,7 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic) #ifdef WAL_DEBUG if (XLOG_DEBUG && npages > 0) { - elog(DEBUG1, "initialized %d pages, up to %X/%X", + elog(DEBUG1, "initialized %d pages, up to %X/%08X", npages, LSN_FORMAT_ARGS(NewPageEndPtr)); } #endif @@ -2492,7 +2492,7 @@ XLogWrite(XLogwrtRqst WriteRqst, TimeLineID tli, bool flexible) XLogRecPtr EndPtr = pg_atomic_read_u64(&XLogCtl->xlblocks[curridx]); if (LogwrtResult.Write >= EndPtr) - elog(PANIC, "xlog write request %X/%X is past end of log %X/%X", + elog(PANIC, "xlog write request %X/%08X is past end of log %X/%08X", LSN_FORMAT_ARGS(LogwrtResult.Write), LSN_FORMAT_ARGS(EndPtr)); @@ -2892,7 +2892,7 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) newMinRecoveryPoint = GetCurrentReplayRecPtr(&newMinRecoveryPointTLI); if (!force && newMinRecoveryPoint < lsn) elog(WARNING, - "xlog min recovery request %X/%X is past current point %X/%X", + "xlog min recovery request %X/%08X is past current point %X/%08X", LSN_FORMAT_ARGS(lsn), LSN_FORMAT_ARGS(newMinRecoveryPoint)); /* update control file */ @@ -2905,9 +2905,9 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) LocalMinRecoveryPointTLI = newMinRecoveryPointTLI; ereport(DEBUG2, - (errmsg_internal("updated min recovery point to %X/%X on timeline %u", - LSN_FORMAT_ARGS(newMinRecoveryPoint), - newMinRecoveryPointTLI))); + errmsg_internal("updated min recovery point to %X/%08X on timeline %u", + LSN_FORMAT_ARGS(newMinRecoveryPoint), + newMinRecoveryPointTLI)); } } LWLockRelease(ControlFileLock); @@ -2945,7 +2945,7 @@ XLogFlush(XLogRecPtr record) #ifdef WAL_DEBUG if (XLOG_DEBUG) - elog(LOG, "xlog flush request %X/%X; write %X/%X; flush %X/%X", + elog(LOG, "xlog flush request %X/%08X; write %X/%08X; flush %X/%08X", LSN_FORMAT_ARGS(record), LSN_FORMAT_ARGS(LogwrtResult.Write), LSN_FORMAT_ARGS(LogwrtResult.Flush)); @@ -3078,7 +3078,7 @@ XLogFlush(XLogRecPtr record) */ if (LogwrtResult.Flush < record) elog(ERROR, - "xlog flush request %X/%X is not satisfied --- flushed only to %X/%X", + "xlog flush request %X/%08X is not satisfied --- flushed only to %X/%08X", LSN_FORMAT_ARGS(record), LSN_FORMAT_ARGS(LogwrtResult.Flush)); } @@ -3205,7 +3205,7 @@ XLogBackgroundFlush(void) #ifdef WAL_DEBUG if (XLOG_DEBUG) - elog(LOG, "xlog bg flush request write %X/%X; flush: %X/%X, current is write %X/%X; flush %X/%X", + elog(LOG, "xlog bg flush request write %X/%08X; flush: %X/%08X, current is write %X/%08X; flush %X/%08X", LSN_FORMAT_ARGS(WriteRqst.Write), LSN_FORMAT_ARGS(WriteRqst.Flush), LSN_FORMAT_ARGS(LogwrtResult.Write), @@ -6921,7 +6921,7 @@ LogCheckpointEnd(bool restartpoint) "%d removed, %d recycled; write=%ld.%03d s, " "sync=%ld.%03d s, total=%ld.%03d s; sync files=%d, " "longest=%ld.%03d s, average=%ld.%03d s; distance=%d kB, " - "estimate=%d kB; lsn=%X/%X, redo lsn=%X/%X", + "estimate=%d kB; lsn=%X/%08X, redo lsn=%X/%08X", CheckpointStats.ckpt_bufs_written, (double) CheckpointStats.ckpt_bufs_written * 100 / NBuffers, CheckpointStats.ckpt_slru_written, @@ -6945,7 +6945,7 @@ LogCheckpointEnd(bool restartpoint) "%d removed, %d recycled; write=%ld.%03d s, " "sync=%ld.%03d s, total=%ld.%03d s; sync files=%d, " "longest=%ld.%03d s, average=%ld.%03d s; distance=%d kB, " - "estimate=%d kB; lsn=%X/%X, redo lsn=%X/%X", + "estimate=%d kB; lsn=%X/%08X, redo lsn=%X/%08X", CheckpointStats.ckpt_bufs_written, (double) CheckpointStats.ckpt_bufs_written * 100 / NBuffers, CheckpointStats.ckpt_slru_written, @@ -7498,6 +7498,10 @@ CreateCheckPoint(int flags) if (PriorRedoPtr != InvalidXLogRecPtr) UpdateCheckPointDistanceEstimate(RedoRecPtr - PriorRedoPtr); +#ifdef USE_INJECTION_POINTS + INJECTION_POINT("checkpoint-before-old-wal-removal", NULL); +#endif + /* * Delete old log files, those no longer needed for last checkpoint to * prevent the disk holding the xlog from growing full. @@ -7637,7 +7641,7 @@ CreateOverwriteContrecordRecord(XLogRecPtr aborted_lsn, XLogRecPtr pagePtr, if (!RecoveryInProgress()) elog(ERROR, "can only be used at end of recovery"); if (pagePtr % XLOG_BLCKSZ != 0) - elog(ERROR, "invalid position for missing continuation record %X/%X", + elog(ERROR, "invalid position for missing continuation record %X/%08X", LSN_FORMAT_ARGS(pagePtr)); /* The current WAL insert position should be right after the page header */ @@ -7648,7 +7652,7 @@ CreateOverwriteContrecordRecord(XLogRecPtr aborted_lsn, XLogRecPtr pagePtr, startPos += SizeOfXLogShortPHD; recptr = GetXLogInsertRecPtr(); if (recptr != startPos) - elog(ERROR, "invalid WAL insert position %X/%X for OVERWRITE_CONTRECORD", + elog(ERROR, "invalid WAL insert position %X/%08X for OVERWRITE_CONTRECORD", LSN_FORMAT_ARGS(recptr)); START_CRIT_SECTION(); @@ -7678,7 +7682,7 @@ CreateOverwriteContrecordRecord(XLogRecPtr aborted_lsn, XLogRecPtr pagePtr, /* check that the record was inserted to the right place */ if (ProcLastRecPtr != startPos) - elog(ERROR, "OVERWRITE_CONTRECORD was inserted to unexpected position %X/%X", + elog(ERROR, "OVERWRITE_CONTRECORD was inserted to unexpected position %X/%08X", LSN_FORMAT_ARGS(ProcLastRecPtr)); XLogFlush(recptr); @@ -7747,8 +7751,7 @@ RecoveryRestartPoint(const CheckPoint *checkPoint, XLogReaderState *record) if (XLogHaveInvalidPages()) { elog(DEBUG2, - "could not record restart point at %X/%X because there " - "are unresolved references to invalid pages", + "could not record restart point at %X/%08X because there are unresolved references to invalid pages", LSN_FORMAT_ARGS(checkPoint->redo)); return; } @@ -7828,8 +7831,8 @@ CreateRestartPoint(int flags) lastCheckPoint.redo <= ControlFile->checkPointCopy.redo) { ereport(DEBUG2, - (errmsg_internal("skipping restartpoint, already performed at %X/%X", - LSN_FORMAT_ARGS(lastCheckPoint.redo)))); + errmsg_internal("skipping restartpoint, already performed at %X/%08X", + LSN_FORMAT_ARGS(lastCheckPoint.redo))); UpdateMinRecoveryPoint(InvalidXLogRecPtr, true); if (flags & CHECKPOINT_IS_SHUTDOWN) @@ -8013,10 +8016,10 @@ CreateRestartPoint(int flags) xtime = GetLatestXTime(); ereport((log_checkpoints ? LOG : DEBUG2), - (errmsg("recovery restart point at %X/%X", - LSN_FORMAT_ARGS(lastCheckPoint.redo)), - xtime ? errdetail("Last completed transaction was at log time %s.", - timestamptz_to_str(xtime)) : 0)); + errmsg("recovery restart point at %X/%08X", + LSN_FORMAT_ARGS(lastCheckPoint.redo)), + xtime ? errdetail("Last completed transaction was at log time %s.", + timestamptz_to_str(xtime)) : 0); /* * Finally, execute archive_cleanup_command, if any. @@ -8277,8 +8280,8 @@ XLogRestorePoint(const char *rpName) RecPtr = XLogInsert(RM_XLOG_ID, XLOG_RESTORE_POINT); ereport(LOG, - (errmsg("restore point \"%s\" created at %X/%X", - rpName, LSN_FORMAT_ARGS(RecPtr)))); + errmsg("restore point \"%s\" created at %X/%08X", + rpName, LSN_FORMAT_ARGS(RecPtr))); return RecPtr; } diff --git a/src/backend/access/transam/xlogbackup.c b/src/backend/access/transam/xlogbackup.c index 342590e0a46..cda4b38b7d6 100644 --- a/src/backend/access/transam/xlogbackup.c +++ b/src/backend/access/transam/xlogbackup.c @@ -42,7 +42,7 @@ build_backup_content(BackupState *state, bool ishistoryfile) XLByteToSeg(state->startpoint, startsegno, wal_segment_size); XLogFileName(startxlogfile, state->starttli, startsegno, wal_segment_size); - appendStringInfo(result, "START WAL LOCATION: %X/%X (file %s)\n", + appendStringInfo(result, "START WAL LOCATION: %X/%08X (file %s)\n", LSN_FORMAT_ARGS(state->startpoint), startxlogfile); if (ishistoryfile) @@ -52,11 +52,11 @@ build_backup_content(BackupState *state, bool ishistoryfile) XLByteToSeg(state->stoppoint, stopsegno, wal_segment_size); XLogFileName(stopxlogfile, state->stoptli, stopsegno, wal_segment_size); - appendStringInfo(result, "STOP WAL LOCATION: %X/%X (file %s)\n", + appendStringInfo(result, "STOP WAL LOCATION: %X/%08X (file %s)\n", LSN_FORMAT_ARGS(state->stoppoint), stopxlogfile); } - appendStringInfo(result, "CHECKPOINT LOCATION: %X/%X\n", + appendStringInfo(result, "CHECKPOINT LOCATION: %X/%08X\n", LSN_FORMAT_ARGS(state->checkpointloc)); appendStringInfoString(result, "BACKUP METHOD: streamed\n"); appendStringInfo(result, "BACKUP FROM: %s\n", @@ -81,7 +81,7 @@ build_backup_content(BackupState *state, bool ishistoryfile) Assert(XLogRecPtrIsInvalid(state->istartpoint) == (state->istarttli == 0)); if (!XLogRecPtrIsInvalid(state->istartpoint)) { - appendStringInfo(result, "INCREMENTAL FROM LSN: %X/%X\n", + appendStringInfo(result, "INCREMENTAL FROM LSN: %X/%08X\n", LSN_FORMAT_ARGS(state->istartpoint)); appendStringInfo(result, "INCREMENTAL FROM TLI: %u\n", state->istarttli); diff --git a/src/backend/access/transam/xlogprefetcher.c b/src/backend/access/transam/xlogprefetcher.c index 7735562db01..ed3aacabc98 100644 --- a/src/backend/access/transam/xlogprefetcher.c +++ b/src/backend/access/transam/xlogprefetcher.c @@ -546,7 +546,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing all readahead until %X/%X is replayed due to possible TLI change", + "suppressing all readahead until %X/%08X is replayed due to possible TLI change", LSN_FORMAT_ARGS(record->lsn)); #endif @@ -579,7 +579,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing prefetch in database %u until %X/%X is replayed due to raw file copy", + "suppressing prefetch in database %u until %X/%08X is replayed due to raw file copy", rlocator.dbOid, LSN_FORMAT_ARGS(record->lsn)); #endif @@ -607,7 +607,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing prefetch in relation %u/%u/%u until %X/%X is replayed, which creates the relation", + "suppressing prefetch in relation %u/%u/%u until %X/%08X is replayed, which creates the relation", xlrec->rlocator.spcOid, xlrec->rlocator.dbOid, xlrec->rlocator.relNumber, @@ -630,7 +630,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing prefetch in relation %u/%u/%u from block %u until %X/%X is replayed, which truncates the relation", + "suppressing prefetch in relation %u/%u/%u from block %u until %X/%08X is replayed, which truncates the relation", xlrec->rlocator.spcOid, xlrec->rlocator.dbOid, xlrec->rlocator.relNumber, @@ -729,7 +729,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) { #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing all prefetch in relation %u/%u/%u until %X/%X is replayed, because the relation does not exist on disk", + "suppressing all prefetch in relation %u/%u/%u until %X/%08X is replayed, because the relation does not exist on disk", reln->smgr_rlocator.locator.spcOid, reln->smgr_rlocator.locator.dbOid, reln->smgr_rlocator.locator.relNumber, @@ -750,7 +750,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) { #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing prefetch in relation %u/%u/%u from block %u until %X/%X is replayed, because the relation is too small", + "suppressing prefetch in relation %u/%u/%u from block %u until %X/%08X is replayed, because the relation is too small", reln->smgr_rlocator.locator.spcOid, reln->smgr_rlocator.locator.dbOid, reln->smgr_rlocator.locator.relNumber, @@ -928,7 +928,7 @@ XLogPrefetcherIsFiltered(XLogPrefetcher *prefetcher, RelFileLocator rlocator, { #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "prefetch of %u/%u/%u block %u suppressed; filtering until LSN %X/%X is replayed (blocks >= %u filtered)", + "prefetch of %u/%u/%u block %u suppressed; filtering until LSN %X/%08X is replayed (blocks >= %u filtered)", rlocator.spcOid, rlocator.dbOid, rlocator.relNumber, blockno, LSN_FORMAT_ARGS(filter->filter_until_replayed), filter->filter_from_block); @@ -944,7 +944,7 @@ XLogPrefetcherIsFiltered(XLogPrefetcher *prefetcher, RelFileLocator rlocator, { #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "prefetch of %u/%u/%u block %u suppressed; filtering until LSN %X/%X is replayed (whole database)", + "prefetch of %u/%u/%u block %u suppressed; filtering until LSN %X/%08X is replayed (whole database)", rlocator.spcOid, rlocator.dbOid, rlocator.relNumber, blockno, LSN_FORMAT_ARGS(filter->filter_until_replayed)); #endif diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c index 2790ade1f91..ac1f801b1eb 100644 --- a/src/backend/access/transam/xlogreader.c +++ b/src/backend/access/transam/xlogreader.c @@ -617,7 +617,7 @@ restart: } else if (targetRecOff < pageHeaderSize) { - report_invalid_record(state, "invalid record offset at %X/%X: expected at least %u, got %u", + report_invalid_record(state, "invalid record offset at %X/%08X: expected at least %u, got %u", LSN_FORMAT_ARGS(RecPtr), pageHeaderSize, targetRecOff); goto err; @@ -626,7 +626,7 @@ restart: if ((((XLogPageHeader) state->readBuf)->xlp_info & XLP_FIRST_IS_CONTRECORD) && targetRecOff == pageHeaderSize) { - report_invalid_record(state, "contrecord is requested by %X/%X", + report_invalid_record(state, "contrecord is requested by %X/%08X", LSN_FORMAT_ARGS(RecPtr)); goto err; } @@ -667,7 +667,7 @@ restart: if (total_len < SizeOfXLogRecord) { report_invalid_record(state, - "invalid record length at %X/%X: expected at least %u, got %u", + "invalid record length at %X/%08X: expected at least %u, got %u", LSN_FORMAT_ARGS(RecPtr), (uint32) SizeOfXLogRecord, total_len); goto err; @@ -756,7 +756,7 @@ restart: if (!(pageHeader->xlp_info & XLP_FIRST_IS_CONTRECORD)) { report_invalid_record(state, - "there is no contrecord flag at %X/%X", + "there is no contrecord flag at %X/%08X", LSN_FORMAT_ARGS(RecPtr)); goto err; } @@ -769,7 +769,7 @@ restart: total_len != (pageHeader->xlp_rem_len + gotlen)) { report_invalid_record(state, - "invalid contrecord length %u (expected %lld) at %X/%X", + "invalid contrecord length %u (expected %lld) at %X/%08X", pageHeader->xlp_rem_len, ((long long) total_len) - gotlen, LSN_FORMAT_ARGS(RecPtr)); @@ -1132,7 +1132,7 @@ ValidXLogRecordHeader(XLogReaderState *state, XLogRecPtr RecPtr, if (record->xl_tot_len < SizeOfXLogRecord) { report_invalid_record(state, - "invalid record length at %X/%X: expected at least %u, got %u", + "invalid record length at %X/%08X: expected at least %u, got %u", LSN_FORMAT_ARGS(RecPtr), (uint32) SizeOfXLogRecord, record->xl_tot_len); return false; @@ -1140,7 +1140,7 @@ ValidXLogRecordHeader(XLogReaderState *state, XLogRecPtr RecPtr, if (!RmgrIdIsValid(record->xl_rmid)) { report_invalid_record(state, - "invalid resource manager ID %u at %X/%X", + "invalid resource manager ID %u at %X/%08X", record->xl_rmid, LSN_FORMAT_ARGS(RecPtr)); return false; } @@ -1153,7 +1153,7 @@ ValidXLogRecordHeader(XLogReaderState *state, XLogRecPtr RecPtr, if (!(record->xl_prev < RecPtr)) { report_invalid_record(state, - "record with incorrect prev-link %X/%X at %X/%X", + "record with incorrect prev-link %X/%08X at %X/%08X", LSN_FORMAT_ARGS(record->xl_prev), LSN_FORMAT_ARGS(RecPtr)); return false; @@ -1169,7 +1169,7 @@ ValidXLogRecordHeader(XLogReaderState *state, XLogRecPtr RecPtr, if (record->xl_prev != PrevRecPtr) { report_invalid_record(state, - "record with incorrect prev-link %X/%X at %X/%X", + "record with incorrect prev-link %X/%08X at %X/%08X", LSN_FORMAT_ARGS(record->xl_prev), LSN_FORMAT_ARGS(RecPtr)); return false; @@ -1207,7 +1207,7 @@ ValidXLogRecord(XLogReaderState *state, XLogRecord *record, XLogRecPtr recptr) if (!EQ_CRC32C(record->xl_crc, crc)) { report_invalid_record(state, - "incorrect resource manager data checksum in record at %X/%X", + "incorrect resource manager data checksum in record at %X/%08X", LSN_FORMAT_ARGS(recptr)); return false; } @@ -1241,7 +1241,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize); report_invalid_record(state, - "invalid magic number %04X in WAL segment %s, LSN %X/%X, offset %u", + "invalid magic number %04X in WAL segment %s, LSN %X/%08X, offset %u", hdr->xlp_magic, fname, LSN_FORMAT_ARGS(recptr), @@ -1256,7 +1256,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize); report_invalid_record(state, - "invalid info bits %04X in WAL segment %s, LSN %X/%X, offset %u", + "invalid info bits %04X in WAL segment %s, LSN %X/%08X, offset %u", hdr->xlp_info, fname, LSN_FORMAT_ARGS(recptr), @@ -1298,7 +1298,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, /* hmm, first page of file doesn't have a long header? */ report_invalid_record(state, - "invalid info bits %04X in WAL segment %s, LSN %X/%X, offset %u", + "invalid info bits %04X in WAL segment %s, LSN %X/%08X, offset %u", hdr->xlp_info, fname, LSN_FORMAT_ARGS(recptr), @@ -1318,7 +1318,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize); report_invalid_record(state, - "unexpected pageaddr %X/%X in WAL segment %s, LSN %X/%X, offset %u", + "unexpected pageaddr %X/%08X in WAL segment %s, LSN %X/%08X, offset %u", LSN_FORMAT_ARGS(hdr->xlp_pageaddr), fname, LSN_FORMAT_ARGS(recptr), @@ -1344,7 +1344,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize); report_invalid_record(state, - "out-of-sequence timeline ID %u (after %u) in WAL segment %s, LSN %X/%X, offset %u", + "out-of-sequence timeline ID %u (after %u) in WAL segment %s, LSN %X/%08X, offset %u", hdr->xlp_tli, state->latestPageTLI, fname, @@ -1756,7 +1756,7 @@ DecodeXLogRecord(XLogReaderState *state, if (block_id <= decoded->max_block_id) { report_invalid_record(state, - "out-of-order block_id %u at %X/%X", + "out-of-order block_id %u at %X/%08X", block_id, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; @@ -1780,14 +1780,14 @@ DecodeXLogRecord(XLogReaderState *state, if (blk->has_data && blk->data_len == 0) { report_invalid_record(state, - "BKPBLOCK_HAS_DATA set, but no data included at %X/%X", + "BKPBLOCK_HAS_DATA set, but no data included at %X/%08X", LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; } if (!blk->has_data && blk->data_len != 0) { report_invalid_record(state, - "BKPBLOCK_HAS_DATA not set, but data length is %u at %X/%X", + "BKPBLOCK_HAS_DATA not set, but data length is %u at %X/%08X", (unsigned int) blk->data_len, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; @@ -1823,7 +1823,7 @@ DecodeXLogRecord(XLogReaderState *state, blk->bimg_len == BLCKSZ)) { report_invalid_record(state, - "BKPIMAGE_HAS_HOLE set, but hole offset %u length %u block image length %u at %X/%X", + "BKPIMAGE_HAS_HOLE set, but hole offset %u length %u block image length %u at %X/%08X", (unsigned int) blk->hole_offset, (unsigned int) blk->hole_length, (unsigned int) blk->bimg_len, @@ -1839,7 +1839,7 @@ DecodeXLogRecord(XLogReaderState *state, (blk->hole_offset != 0 || blk->hole_length != 0)) { report_invalid_record(state, - "BKPIMAGE_HAS_HOLE not set, but hole offset %u length %u at %X/%X", + "BKPIMAGE_HAS_HOLE not set, but hole offset %u length %u at %X/%08X", (unsigned int) blk->hole_offset, (unsigned int) blk->hole_length, LSN_FORMAT_ARGS(state->ReadRecPtr)); @@ -1853,7 +1853,7 @@ DecodeXLogRecord(XLogReaderState *state, blk->bimg_len == BLCKSZ) { report_invalid_record(state, - "BKPIMAGE_COMPRESSED set, but block image length %u at %X/%X", + "BKPIMAGE_COMPRESSED set, but block image length %u at %X/%08X", (unsigned int) blk->bimg_len, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; @@ -1868,7 +1868,7 @@ DecodeXLogRecord(XLogReaderState *state, blk->bimg_len != BLCKSZ) { report_invalid_record(state, - "neither BKPIMAGE_HAS_HOLE nor BKPIMAGE_COMPRESSED set, but block image length is %u at %X/%X", + "neither BKPIMAGE_HAS_HOLE nor BKPIMAGE_COMPRESSED set, but block image length is %u at %X/%08X", (unsigned int) blk->data_len, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; @@ -1884,7 +1884,7 @@ DecodeXLogRecord(XLogReaderState *state, if (rlocator == NULL) { report_invalid_record(state, - "BKPBLOCK_SAME_REL set but no previous rel at %X/%X", + "BKPBLOCK_SAME_REL set but no previous rel at %X/%08X", LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; } @@ -1896,7 +1896,7 @@ DecodeXLogRecord(XLogReaderState *state, else { report_invalid_record(state, - "invalid block_id %u at %X/%X", + "invalid block_id %u at %X/%08X", block_id, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; } @@ -1963,7 +1963,7 @@ DecodeXLogRecord(XLogReaderState *state, shortdata_err: report_invalid_record(state, - "record with invalid length at %X/%X", + "record with invalid length at %X/%08X", LSN_FORMAT_ARGS(state->ReadRecPtr)); err: *errormsg = state->errormsg_buf; @@ -2073,14 +2073,14 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) !record->record->blocks[block_id].in_use) { report_invalid_record(record, - "could not restore image at %X/%X with invalid block %d specified", + "could not restore image at %X/%08X with invalid block %d specified", LSN_FORMAT_ARGS(record->ReadRecPtr), block_id); return false; } if (!record->record->blocks[block_id].has_image) { - report_invalid_record(record, "could not restore image at %X/%X with invalid state, block %d", + report_invalid_record(record, "could not restore image at %X/%08X with invalid state, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), block_id); return false; @@ -2107,7 +2107,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) bkpb->bimg_len, BLCKSZ - bkpb->hole_length) <= 0) decomp_success = false; #else - report_invalid_record(record, "could not restore image at %X/%X compressed with %s not supported by build, block %d", + report_invalid_record(record, "could not restore image at %X/%08X compressed with %s not supported by build, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), "LZ4", block_id); @@ -2124,7 +2124,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) if (ZSTD_isError(decomp_result)) decomp_success = false; #else - report_invalid_record(record, "could not restore image at %X/%X compressed with %s not supported by build, block %d", + report_invalid_record(record, "could not restore image at %X/%08X compressed with %s not supported by build, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), "zstd", block_id); @@ -2133,7 +2133,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) } else { - report_invalid_record(record, "could not restore image at %X/%X compressed with unknown method, block %d", + report_invalid_record(record, "could not restore image at %X/%08X compressed with unknown method, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), block_id); return false; @@ -2141,7 +2141,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) if (!decomp_success) { - report_invalid_record(record, "could not decompress image at %X/%X, block %d", + report_invalid_record(record, "could not decompress image at %X/%08X, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), block_id); return false; diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c index 6ce979f2d8b..23878b2dd91 100644 --- a/src/backend/access/transam/xlogrecovery.c +++ b/src/backend/access/transam/xlogrecovery.c @@ -620,10 +620,10 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, * than ControlFile->checkPoint is used. */ ereport(LOG, - (errmsg("starting backup recovery with redo LSN %X/%X, checkpoint LSN %X/%X, on timeline ID %u", - LSN_FORMAT_ARGS(RedoStartLSN), - LSN_FORMAT_ARGS(CheckPointLoc), - CheckPointTLI))); + errmsg("starting backup recovery with redo LSN %X/%08X, checkpoint LSN %X/%08X, on timeline ID %u", + LSN_FORMAT_ARGS(RedoStartLSN), + LSN_FORMAT_ARGS(CheckPointLoc), + CheckPointTLI)); /* * When a backup_label file is present, we want to roll forward from @@ -636,8 +636,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN); ereport(DEBUG1, - (errmsg_internal("checkpoint record is at %X/%X", - LSN_FORMAT_ARGS(CheckPointLoc)))); + errmsg_internal("checkpoint record is at %X/%08X", + LSN_FORMAT_ARGS(CheckPointLoc))); InRecovery = true; /* force recovery even if SHUTDOWNED */ /* @@ -652,23 +652,23 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, if (!ReadRecord(xlogprefetcher, LOG, false, checkPoint.ThisTimeLineID)) ereport(FATAL, - (errmsg("could not find redo location %X/%X referenced by checkpoint record at %X/%X", - LSN_FORMAT_ARGS(checkPoint.redo), LSN_FORMAT_ARGS(CheckPointLoc)), - errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n" - "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" - "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", - DataDir, DataDir, DataDir, DataDir))); + errmsg("could not find redo location %X/%08X referenced by checkpoint record at %X/%08X", + LSN_FORMAT_ARGS(checkPoint.redo), LSN_FORMAT_ARGS(CheckPointLoc)), + errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n" + "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" + "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", + DataDir, DataDir, DataDir, DataDir)); } } else { ereport(FATAL, - (errmsg("could not locate required checkpoint record at %X/%X", - LSN_FORMAT_ARGS(CheckPointLoc)), - errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n" - "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" - "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", - DataDir, DataDir, DataDir, DataDir))); + errmsg("could not locate required checkpoint record at %X/%08X", + LSN_FORMAT_ARGS(CheckPointLoc)), + errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n" + "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" + "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", + DataDir, DataDir, DataDir, DataDir)); wasShutdown = false; /* keep compiler quiet */ } @@ -773,8 +773,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, */ if (!XLogRecPtrIsInvalid(ControlFile->backupStartPoint)) ereport(LOG, - (errmsg("restarting backup recovery with redo LSN %X/%X", - LSN_FORMAT_ARGS(ControlFile->backupStartPoint)))); + errmsg("restarting backup recovery with redo LSN %X/%08X", + LSN_FORMAT_ARGS(ControlFile->backupStartPoint))); /* Get the last valid checkpoint record. */ CheckPointLoc = ControlFile->checkPoint; @@ -786,8 +786,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, if (record != NULL) { ereport(DEBUG1, - (errmsg_internal("checkpoint record is at %X/%X", - LSN_FORMAT_ARGS(CheckPointLoc)))); + errmsg_internal("checkpoint record is at %X/%08X", + LSN_FORMAT_ARGS(CheckPointLoc))); } else { @@ -798,8 +798,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, * simplify processing around checkpoints. */ ereport(PANIC, - (errmsg("could not locate a valid checkpoint record at %X/%X", - LSN_FORMAT_ARGS(CheckPointLoc)))); + errmsg("could not locate a valid checkpoint record at %X/%08X", + LSN_FORMAT_ARGS(CheckPointLoc))); } memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN); @@ -824,8 +824,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, recoveryTargetName))); else if (recoveryTarget == RECOVERY_TARGET_LSN) ereport(LOG, - (errmsg("starting point-in-time recovery to WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryTargetLSN)))); + errmsg("starting point-in-time recovery to WAL location (LSN) \"%X/%08X\"", + LSN_FORMAT_ARGS(recoveryTargetLSN))); else if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE) ereport(LOG, (errmsg("starting point-in-time recovery to earliest consistent point"))); @@ -855,7 +855,7 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, (errmsg("requested timeline %u is not a child of this server's history", recoveryTargetTLI), /* translator: %s is a backup_label file or a pg_control file */ - errdetail("Latest checkpoint in file \"%s\" is at %X/%X on timeline %u, but in the history of the requested timeline, the server forked off from that timeline at %X/%X.", + errdetail("Latest checkpoint in file \"%s\" is at %X/%08X on timeline %u, but in the history of the requested timeline, the server forked off from that timeline at %X/%08X.", haveBackupLabel ? "backup_label" : "pg_control", LSN_FORMAT_ARGS(CheckPointLoc), CheckPointTLI, @@ -870,15 +870,15 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, tliOfPointInHistory(ControlFile->minRecoveryPoint - 1, expectedTLEs) != ControlFile->minRecoveryPointTLI) ereport(FATAL, - (errmsg("requested timeline %u does not contain minimum recovery point %X/%X on timeline %u", - recoveryTargetTLI, - LSN_FORMAT_ARGS(ControlFile->minRecoveryPoint), - ControlFile->minRecoveryPointTLI))); + errmsg("requested timeline %u does not contain minimum recovery point %X/%08X on timeline %u", + recoveryTargetTLI, + LSN_FORMAT_ARGS(ControlFile->minRecoveryPoint), + ControlFile->minRecoveryPointTLI)); ereport(DEBUG1, - (errmsg_internal("redo record is at %X/%X; shutdown %s", - LSN_FORMAT_ARGS(checkPoint.redo), - wasShutdown ? "true" : "false"))); + errmsg_internal("redo record is at %X/%08X; shutdown %s", + LSN_FORMAT_ARGS(checkPoint.redo), + wasShutdown ? "true" : "false")); ereport(DEBUG1, (errmsg_internal("next transaction ID: " UINT64_FORMAT "; next OID: %u", U64FromFullTransactionId(checkPoint.nextXid), @@ -1253,14 +1253,14 @@ read_backup_label(XLogRecPtr *checkPointLoc, TimeLineID *backupLabelTLI, * is pretty crude, but we are not expecting any variability in the file * format). */ - if (fscanf(lfp, "START WAL LOCATION: %X/%X (file %08X%16s)%c", + if (fscanf(lfp, "START WAL LOCATION: %X/%08X (file %08X%16s)%c", &hi, &lo, &tli_from_walseg, startxlogfilename, &ch) != 5 || ch != '\n') ereport(FATAL, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE))); RedoStartLSN = ((uint64) hi) << 32 | lo; RedoStartTLI = tli_from_walseg; - if (fscanf(lfp, "CHECKPOINT LOCATION: %X/%X%c", + if (fscanf(lfp, "CHECKPOINT LOCATION: %X/%08X%c", &hi, &lo, &ch) != 3 || ch != '\n') ereport(FATAL, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), @@ -1332,7 +1332,7 @@ read_backup_label(XLogRecPtr *checkPointLoc, TimeLineID *backupLabelTLI, tli_from_file, BACKUP_LABEL_FILE))); } - if (fscanf(lfp, "INCREMENTAL FROM LSN: %X/%X\n", &hi, &lo) > 0) + if (fscanf(lfp, "INCREMENTAL FROM LSN: %X/%08X\n", &hi, &lo) > 0) ereport(FATAL, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("this is an incremental backup, not a data directory"), @@ -1722,8 +1722,8 @@ PerformWalRecovery(void) if (record->xl_rmid != RM_XLOG_ID || (record->xl_info & ~XLR_INFO_MASK) != XLOG_CHECKPOINT_REDO) ereport(FATAL, - (errmsg("unexpected record type found at redo point %X/%X", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)))); + errmsg("unexpected record type found at redo point %X/%08X", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr))); } else { @@ -1745,8 +1745,8 @@ PerformWalRecovery(void) RmgrStartup(); ereport(LOG, - (errmsg("redo starts at %X/%X", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)))); + errmsg("redo starts at %X/%08X", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr))); /* Prepare to report progress of the redo phase. */ if (!StandbyMode) @@ -1758,7 +1758,7 @@ PerformWalRecovery(void) do { if (!StandbyMode) - ereport_startup_progress("redo in progress, elapsed time: %ld.%02d s, current LSN: %X/%X", + ereport_startup_progress("redo in progress, elapsed time: %ld.%02d s, current LSN: %X/%08X", LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)); #ifdef WAL_DEBUG @@ -1767,7 +1767,7 @@ PerformWalRecovery(void) StringInfoData buf; initStringInfo(&buf); - appendStringInfo(&buf, "REDO @ %X/%X; LSN %X/%X: ", + appendStringInfo(&buf, "REDO @ %X/%08X; LSN %X/%08X: ", LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), LSN_FORMAT_ARGS(xlogreader->EndRecPtr)); xlog_outrec(&buf, xlogreader); @@ -1880,9 +1880,9 @@ PerformWalRecovery(void) RmgrCleanup(); ereport(LOG, - (errmsg("redo done at %X/%X system usage: %s", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), - pg_rusage_show(&ru0)))); + errmsg("redo done at %X/%08X system usage: %s", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), + pg_rusage_show(&ru0))); xtime = GetLatestXTime(); if (xtime) ereport(LOG, @@ -2092,7 +2092,7 @@ xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI) memcpy(&xlrec, XLogRecGetData(record), sizeof(xl_overwrite_contrecord)); if (xlrec.overwritten_lsn != record->overwrittenRecPtr) - elog(FATAL, "mismatching overwritten LSN %X/%X -> %X/%X", + elog(FATAL, "mismatching overwritten LSN %X/%08X -> %X/%08X", LSN_FORMAT_ARGS(xlrec.overwritten_lsn), LSN_FORMAT_ARGS(record->overwrittenRecPtr)); @@ -2101,9 +2101,9 @@ xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI) missingContrecPtr = InvalidXLogRecPtr; ereport(LOG, - (errmsg("successfully skipped missing contrecord at %X/%X, overwritten at %s", - LSN_FORMAT_ARGS(xlrec.overwritten_lsn), - timestamptz_to_str(xlrec.overwrite_time)))); + errmsg("successfully skipped missing contrecord at %X/%08X, overwritten at %s", + LSN_FORMAT_ARGS(xlrec.overwritten_lsn), + timestamptz_to_str(xlrec.overwrite_time))); /* Verifying the record should only happen once */ record->overwrittenRecPtr = InvalidXLogRecPtr; @@ -2129,7 +2129,7 @@ xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI) backupEndPoint = lsn; } else - elog(DEBUG1, "saw end-of-backup record for backup starting at %X/%X, waiting for %X/%X", + elog(DEBUG1, "saw end-of-backup record for backup starting at %X/%08X, waiting for %X/%08X", LSN_FORMAT_ARGS(startpoint), LSN_FORMAT_ARGS(backupStartPoint)); } } @@ -2224,9 +2224,9 @@ CheckRecoveryConsistency(void) backupEndRequired = false; ereport(LOG, - (errmsg("completed backup recovery with redo LSN %X/%X and end LSN %X/%X", - LSN_FORMAT_ARGS(saveBackupStartPoint), - LSN_FORMAT_ARGS(saveBackupEndPoint)))); + errmsg("completed backup recovery with redo LSN %X/%08X and end LSN %X/%08X", + LSN_FORMAT_ARGS(saveBackupStartPoint), + LSN_FORMAT_ARGS(saveBackupEndPoint))); } /* @@ -2255,8 +2255,8 @@ CheckRecoveryConsistency(void) reachedConsistency = true; SendPostmasterSignal(PMSIGNAL_RECOVERY_CONSISTENT); ereport(LOG, - (errmsg("consistent recovery state reached at %X/%X", - LSN_FORMAT_ARGS(lastReplayedEndRecPtr)))); + errmsg("consistent recovery state reached at %X/%08X", + LSN_FORMAT_ARGS(lastReplayedEndRecPtr))); } /* @@ -2293,7 +2293,7 @@ rm_redo_error_callback(void *arg) xlog_block_info(&buf, record); /* translator: %s is a WAL record description */ - errcontext("WAL redo at %X/%X for %s", + errcontext("WAL redo at %X/%08X for %s", LSN_FORMAT_ARGS(record->ReadRecPtr), buf.data); @@ -2328,7 +2328,7 @@ xlog_outdesc(StringInfo buf, XLogReaderState *record) static void xlog_outrec(StringInfo buf, XLogReaderState *record) { - appendStringInfo(buf, "prev %X/%X; xid %u", + appendStringInfo(buf, "prev %X/%08X; xid %u", LSN_FORMAT_ARGS(XLogRecGetPrev(record)), XLogRecGetXid(record)); @@ -2416,10 +2416,10 @@ checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, TimeLineID prevTLI, lsn < minRecoveryPoint && newTLI > minRecoveryPointTLI) ereport(PANIC, - (errmsg("unexpected timeline ID %u in checkpoint record, before reaching minimum recovery point %X/%X on timeline %u", - newTLI, - LSN_FORMAT_ARGS(minRecoveryPoint), - minRecoveryPointTLI))); + errmsg("unexpected timeline ID %u in checkpoint record, before reaching minimum recovery point %X/%08X on timeline %u", + newTLI, + LSN_FORMAT_ARGS(minRecoveryPoint), + minRecoveryPointTLI)); /* Looks good */ } @@ -2621,8 +2621,8 @@ recoveryStopsBefore(XLogReaderState *record) recoveryStopTime = 0; recoveryStopName[0] = '\0'; ereport(LOG, - (errmsg("recovery stopping before WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryStopLSN)))); + errmsg("recovery stopping before WAL location (LSN) \"%X/%08X\"", + LSN_FORMAT_ARGS(recoveryStopLSN))); return true; } @@ -2789,8 +2789,8 @@ recoveryStopsAfter(XLogReaderState *record) recoveryStopTime = 0; recoveryStopName[0] = '\0'; ereport(LOG, - (errmsg("recovery stopping after WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryStopLSN)))); + errmsg("recovery stopping after WAL location (LSN) \"%X/%08X\"", + LSN_FORMAT_ARGS(recoveryStopLSN))); return true; } @@ -2910,7 +2910,7 @@ getRecoveryStopReason(void) timestamptz_to_str(recoveryStopTime)); else if (recoveryTarget == RECOVERY_TARGET_LSN) snprintf(reason, sizeof(reason), - "%s LSN %X/%X\n", + "%s LSN %X/%08X\n", recoveryStopAfter ? "after" : "before", LSN_FORMAT_ARGS(recoveryStopLSN)); else if (recoveryTarget == RECOVERY_TARGET_NAME) @@ -3213,11 +3213,11 @@ ReadRecord(XLogPrefetcher *xlogprefetcher, int emode, XLogFileName(fname, xlogreader->seg.ws_tli, segno, wal_segment_size); ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr), - (errmsg("unexpected timeline ID %u in WAL segment %s, LSN %X/%X, offset %u", - xlogreader->latestPageTLI, - fname, - LSN_FORMAT_ARGS(xlogreader->latestPagePtr), - offset))); + errmsg("unexpected timeline ID %u in WAL segment %s, LSN %X/%08X, offset %u", + xlogreader->latestPageTLI, + fname, + LSN_FORMAT_ARGS(xlogreader->latestPagePtr), + offset)); record = NULL; } @@ -3429,14 +3429,14 @@ retry: errno = save_errno; ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen), (errcode_for_file_access(), - errmsg("could not read from WAL segment %s, LSN %X/%X, offset %u: %m", + errmsg("could not read from WAL segment %s, LSN %X/%08X, offset %u: %m", fname, LSN_FORMAT_ARGS(targetPagePtr), readOff))); } else ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen), (errcode(ERRCODE_DATA_CORRUPTED), - errmsg("could not read from WAL segment %s, LSN %X/%X, offset %u: read %d of %zu", + errmsg("could not read from WAL segment %s, LSN %X/%08X, offset %u: read %d of %zu", fname, LSN_FORMAT_ARGS(targetPagePtr), readOff, r, (Size) XLOG_BLCKSZ))); goto next_record_is_invalid; @@ -3718,7 +3718,7 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, wait_time = wal_retrieve_retry_interval - TimestampDifferenceMilliseconds(last_fail_time, now); - elog(LOG, "waiting for WAL to become available at %X/%X", + elog(LOG, "waiting for WAL to become available at %X/%08X", LSN_FORMAT_ARGS(RecPtr)); /* Do background tasks that might benefit us later. */ @@ -3864,7 +3864,7 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, tli = tliOfPointInHistory(tliRecPtr, expectedTLEs); if (curFileTLI > 0 && tli < curFileTLI) - elog(ERROR, "according to history file, WAL location %X/%X belongs to timeline %u, but previous recovered WAL file came from timeline %u", + elog(ERROR, "according to history file, WAL location %X/%08X belongs to timeline %u, but previous recovered WAL file came from timeline %u", LSN_FORMAT_ARGS(tliRecPtr), tli, curFileTLI); } @@ -4177,10 +4177,10 @@ rescanLatestTimeLine(TimeLineID replayTLI, XLogRecPtr replayLSN) if (currentTle->end < replayLSN) { ereport(LOG, - (errmsg("new timeline %u forked off current database system timeline %u before current recovery point %X/%X", - newtarget, - replayTLI, - LSN_FORMAT_ARGS(replayLSN)))); + errmsg("new timeline %u forked off current database system timeline %u before current recovery point %X/%08X", + newtarget, + replayTLI, + LSN_FORMAT_ARGS(replayLSN))); return false; } @@ -4994,13 +4994,25 @@ check_recovery_target_timeline(char **newval, void **extra, GucSource source) rttg = RECOVERY_TARGET_TIMELINE_LATEST; else { + char *endp; + uint64 timeline; + rttg = RECOVERY_TARGET_TIMELINE_NUMERIC; errno = 0; - strtoul(*newval, NULL, 0); - if (errno == EINVAL || errno == ERANGE) + timeline = strtou64(*newval, &endp, 0); + + if (*endp != '\0' || errno == EINVAL || errno == ERANGE) + { + GUC_check_errdetail("\"%s\" is not a valid number.", + "recovery_target_timeline"); + return false; + } + + if (timeline < 1 || timeline > PG_UINT32_MAX) { - GUC_check_errdetail("\"recovery_target_timeline\" is not a valid number."); + GUC_check_errdetail("\"%s\" must be between %u and %u.", + "recovery_target_timeline", 1, UINT_MAX); return false; } } diff --git a/src/backend/access/transam/xlogutils.c b/src/backend/access/transam/xlogutils.c index c389b27f77d..27ea52fdfee 100644 --- a/src/backend/access/transam/xlogutils.c +++ b/src/backend/access/transam/xlogutils.c @@ -795,7 +795,7 @@ XLogReadDetermineTimeline(XLogReaderState *state, XLogRecPtr wantPage, list_free_deep(timelineHistory); - elog(DEBUG3, "switched to timeline %u valid until %X/%X", + elog(DEBUG3, "switched to timeline %u valid until %X/%08X", state->currTLI, LSN_FORMAT_ARGS(state->currTLIValidUntil)); } |