diff options
Diffstat (limited to 'src')
79 files changed, 1269 insertions, 418 deletions
diff --git a/src/backend/access/brin/brin_minmax_multi.c b/src/backend/access/brin/brin_minmax_multi.c index 0d1507a2a36..a5a414182ca 100644 --- a/src/backend/access/brin/brin_minmax_multi.c +++ b/src/backend/access/brin/brin_minmax_multi.c @@ -624,7 +624,7 @@ brin_range_serialize(Ranges *range) for (i = 0; i < nvalues; i++) { - len += VARSIZE_ANY(range->values[i]); + len += VARSIZE_ANY(DatumGetPointer(range->values[i])); } } else if (typlen == -2) /* cstring */ @@ -2032,7 +2032,7 @@ brin_minmax_multi_distance_numeric(PG_FUNCTION_ARGS) d = DirectFunctionCall2(numeric_sub, a2, a1); /* a2 - a1 */ - PG_RETURN_FLOAT8(DirectFunctionCall1(numeric_float8, d)); + PG_RETURN_DATUM(DirectFunctionCall1(numeric_float8, d)); } /* diff --git a/src/backend/access/common/heaptuple.c b/src/backend/access/common/heaptuple.c index 969d1028cae..a410b5eb99b 100644 --- a/src/backend/access/common/heaptuple.c +++ b/src/backend/access/common/heaptuple.c @@ -189,7 +189,7 @@ getmissingattr(TupleDesc tupleDesc, if (att->attlen > 0) key.len = att->attlen; else - key.len = VARSIZE_ANY(attrmiss->am_value); + key.len = VARSIZE_ANY(DatumGetPointer(attrmiss->am_value)); key.value = attrmiss->am_value; entry = hash_search(missing_cache, &key, HASH_ENTER, &found); @@ -901,9 +901,9 @@ expand_tuple(HeapTuple *targetHeapTuple, att->attlen, attrmiss[attnum].am_value); - targetDataLen = att_addlength_pointer(targetDataLen, - att->attlen, - attrmiss[attnum].am_value); + targetDataLen = att_addlength_datum(targetDataLen, + att->attlen, + attrmiss[attnum].am_value); } else { diff --git a/src/backend/access/common/printsimple.c b/src/backend/access/common/printsimple.c index f346ab3e812..a09c8fcd332 100644 --- a/src/backend/access/common/printsimple.c +++ b/src/backend/access/common/printsimple.c @@ -123,7 +123,7 @@ printsimple(TupleTableSlot *slot, DestReceiver *self) case OIDOID: { - Oid num = ObjectIdGetDatum(value); + Oid num = DatumGetObjectId(value); char str[10]; /* 10 digits */ int len; diff --git a/src/backend/access/common/printtup.c b/src/backend/access/common/printtup.c index 830a3d883aa..6d3045e2332 100644 --- a/src/backend/access/common/printtup.c +++ b/src/backend/access/common/printtup.c @@ -350,7 +350,7 @@ printtup(TupleTableSlot *slot, DestReceiver *self) */ if (thisState->typisvarlena) VALGRIND_CHECK_MEM_IS_DEFINED(DatumGetPointer(attr), - VARSIZE_ANY(attr)); + VARSIZE_ANY(DatumGetPointer(attr))); if (thisState->format == 0) { diff --git a/src/backend/access/common/reloptions.c b/src/backend/access/common/reloptions.c index 50747c16396..0af3fea68fa 100644 --- a/src/backend/access/common/reloptions.c +++ b/src/backend/access/common/reloptions.c @@ -1164,7 +1164,7 @@ add_local_string_reloption(local_relopts *relopts, const char *name, * but we declare them as Datums to avoid including array.h in reloptions.h. */ Datum -transformRelOptions(Datum oldOptions, List *defList, const char *namspace, +transformRelOptions(Datum oldOptions, List *defList, const char *nameSpace, const char *const validnsps[], bool acceptOidsOff, bool isReset) { Datum result; @@ -1190,8 +1190,8 @@ transformRelOptions(Datum oldOptions, List *defList, const char *namspace, for (i = 0; i < noldoptions; i++) { - char *text_str = VARDATA(oldoptions[i]); - int text_len = VARSIZE(oldoptions[i]) - VARHDRSZ; + char *text_str = VARDATA(DatumGetPointer(oldoptions[i])); + int text_len = VARSIZE(DatumGetPointer(oldoptions[i])) - VARHDRSZ; /* Search for a match in defList */ foreach(cell, defList) @@ -1200,14 +1200,14 @@ transformRelOptions(Datum oldOptions, List *defList, const char *namspace, int kw_len; /* ignore if not in the same namespace */ - if (namspace == NULL) + if (nameSpace == NULL) { if (def->defnamespace != NULL) continue; } else if (def->defnamespace == NULL) continue; - else if (strcmp(def->defnamespace, namspace) != 0) + else if (strcmp(def->defnamespace, nameSpace) != 0) continue; kw_len = strlen(def->defname); @@ -1277,14 +1277,14 @@ transformRelOptions(Datum oldOptions, List *defList, const char *namspace, } /* ignore if not in the same namespace */ - if (namspace == NULL) + if (nameSpace == NULL) { if (def->defnamespace != NULL) continue; } else if (def->defnamespace == NULL) continue; - else if (strcmp(def->defnamespace, namspace) != 0) + else if (strcmp(def->defnamespace, nameSpace) != 0) continue; /* @@ -1456,8 +1456,8 @@ parseRelOptionsInternal(Datum options, bool validate, for (i = 0; i < noptions; i++) { - char *text_str = VARDATA(optiondatums[i]); - int text_len = VARSIZE(optiondatums[i]) - VARHDRSZ; + char *text_str = VARDATA(DatumGetPointer(optiondatums[i])); + int text_len = VARSIZE(DatumGetPointer(optiondatums[i])) - VARHDRSZ; int j; /* Search for a match in reloptions */ diff --git a/src/backend/access/common/toast_internals.c b/src/backend/access/common/toast_internals.c index 7d8be8346ce..196e06115e9 100644 --- a/src/backend/access/common/toast_internals.c +++ b/src/backend/access/common/toast_internals.c @@ -144,7 +144,7 @@ toast_save_datum(Relation rel, Datum value, int num_indexes; int validIndex; - Assert(!VARATT_IS_EXTERNAL(value)); + Assert(!VARATT_IS_EXTERNAL(dval)); /* * Open the toast relation and its indexes. We can use the index to check diff --git a/src/backend/access/common/tupdesc.c b/src/backend/access/common/tupdesc.c index 020d00cd01c..be60005ae46 100644 --- a/src/backend/access/common/tupdesc.c +++ b/src/backend/access/common/tupdesc.c @@ -815,10 +815,10 @@ hashRowType(TupleDesc desc) uint32 s; int i; - s = hash_combine(0, hash_uint32(desc->natts)); - s = hash_combine(s, hash_uint32(desc->tdtypeid)); + s = hash_combine(0, hash_bytes_uint32(desc->natts)); + s = hash_combine(s, hash_bytes_uint32(desc->tdtypeid)); for (i = 0; i < desc->natts; ++i) - s = hash_combine(s, hash_uint32(TupleDescAttr(desc, i)->atttypid)); + s = hash_combine(s, hash_bytes_uint32(TupleDescAttr(desc, i)->atttypid)); return s; } diff --git a/src/backend/access/gin/gininsert.c b/src/backend/access/gin/gininsert.c index a65acd89104..47b1898a064 100644 --- a/src/backend/access/gin/gininsert.c +++ b/src/backend/access/gin/gininsert.c @@ -2233,7 +2233,7 @@ _gin_build_tuple(OffsetNumber attrnum, unsigned char category, else if (typlen > 0) keylen = typlen; else if (typlen == -1) - keylen = VARSIZE_ANY(key); + keylen = VARSIZE_ANY(DatumGetPointer(key)); else if (typlen == -2) keylen = strlen(DatumGetPointer(key)) + 1; else diff --git a/src/backend/access/nbtree/nbtcompare.c b/src/backend/access/nbtree/nbtcompare.c index 4da5a3c1d16..e1b52acd20d 100644 --- a/src/backend/access/nbtree/nbtcompare.c +++ b/src/backend/access/nbtree/nbtcompare.c @@ -555,7 +555,7 @@ btcharcmp(PG_FUNCTION_ARGS) static Datum char_decrement(Relation rel, Datum existing, bool *underflow) { - uint8 cexisting = UInt8GetDatum(existing); + uint8 cexisting = DatumGetUInt8(existing); if (cexisting == 0) { @@ -571,7 +571,7 @@ char_decrement(Relation rel, Datum existing, bool *underflow) static Datum char_increment(Relation rel, Datum existing, bool *overflow) { - uint8 cexisting = UInt8GetDatum(existing); + uint8 cexisting = DatumGetUInt8(existing); if (cexisting == UCHAR_MAX) { diff --git a/src/backend/access/spgist/spgutils.c b/src/backend/access/spgist/spgutils.c index 95fea74e296..9b86c016acb 100644 --- a/src/backend/access/spgist/spgutils.c +++ b/src/backend/access/spgist/spgutils.c @@ -785,7 +785,7 @@ SpGistGetInnerTypeSize(SpGistTypeDesc *att, Datum datum) else if (att->attlen > 0) size = att->attlen; else - size = VARSIZE_ANY(datum); + size = VARSIZE_ANY(DatumGetPointer(datum)); return MAXALIGN(size); } @@ -804,7 +804,7 @@ memcpyInnerDatum(void *target, SpGistTypeDesc *att, Datum datum) } else { - size = (att->attlen > 0) ? att->attlen : VARSIZE_ANY(datum); + size = (att->attlen > 0) ? att->attlen : VARSIZE_ANY(DatumGetPointer(datum)); memcpy(target, DatumGetPointer(datum), size); } } diff --git a/src/backend/access/table/toast_helper.c b/src/backend/access/table/toast_helper.c index b60fab0a4d2..11f97d65367 100644 --- a/src/backend/access/table/toast_helper.c +++ b/src/backend/access/table/toast_helper.c @@ -330,7 +330,7 @@ toast_delete_external(Relation rel, const Datum *values, const bool *isnull, if (isnull[i]) continue; - else if (VARATT_IS_EXTERNAL_ONDISK(value)) + else if (VARATT_IS_EXTERNAL_ONDISK(DatumGetPointer(value))) toast_delete_datum(rel, value, is_speculative); } } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 5553c20fee8..9a4de1616bc 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -9011,7 +9011,7 @@ do_pg_backup_start(const char *backupidstr, bool fast, List **tablespaces, * work correctly, it is critical that sessionBackupState is only updated * after this block is over. */ - PG_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, DatumGetBool(true)); + PG_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, BoolGetDatum(true)); { bool gotUniqueStartpoint = false; DIR *tblspcdir; @@ -9250,7 +9250,7 @@ do_pg_backup_start(const char *backupidstr, bool fast, List **tablespaces, state->starttime = (pg_time_t) time(NULL); } - PG_END_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, DatumGetBool(true)); + PG_END_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, BoolGetDatum(true)); state->started_in_recovery = backup_started_in_recovery; @@ -9590,7 +9590,7 @@ register_persistent_abort_backup_handler(void) if (already_done) return; - before_shmem_exit(do_pg_abort_backup, DatumGetBool(false)); + before_shmem_exit(do_pg_abort_backup, BoolGetDatum(false)); already_done = true; } diff --git a/src/backend/backup/basebackup.c b/src/backend/backup/basebackup.c index f0f88838dc2..bb7d90aa5d9 100644 --- a/src/backend/backup/basebackup.c +++ b/src/backend/backup/basebackup.c @@ -1048,7 +1048,7 @@ SendBaseBackup(BaseBackupCmd *cmd, IncrementalBackupInfo *ib) sink = bbsink_zstd_new(sink, &opt.compression_specification); /* Set up progress reporting. */ - sink = bbsink_progress_new(sink, opt.progress); + sink = bbsink_progress_new(sink, opt.progress, opt.incremental); /* * Perform the base backup, but make sure we clean up the bbsink even if diff --git a/src/backend/backup/basebackup_copy.c b/src/backend/backup/basebackup_copy.c index 18b0b5a52d3..eb45d3bcb66 100644 --- a/src/backend/backup/basebackup_copy.c +++ b/src/backend/backup/basebackup_copy.c @@ -143,7 +143,7 @@ bbsink_copystream_begin_backup(bbsink *sink) buf = palloc(mysink->base.bbs_buffer_length + MAXIMUM_ALIGNOF); mysink->msgbuffer = buf + (MAXIMUM_ALIGNOF - 1); mysink->base.bbs_buffer = buf + MAXIMUM_ALIGNOF; - mysink->msgbuffer[0] = 'd'; /* archive or manifest data */ + mysink->msgbuffer[0] = PqMsg_CopyData; /* archive or manifest data */ /* Tell client the backup start location. */ SendXlogRecPtrResult(state->startptr, state->starttli); @@ -170,7 +170,7 @@ bbsink_copystream_begin_archive(bbsink *sink, const char *archive_name) ti = list_nth(state->tablespaces, state->tablespace_num); pq_beginmessage(&buf, PqMsg_CopyData); - pq_sendbyte(&buf, 'n'); /* New archive */ + pq_sendbyte(&buf, PqBackupMsg_NewArchive); pq_sendstring(&buf, archive_name); pq_sendstring(&buf, ti->path == NULL ? "" : ti->path); pq_endmessage(&buf); @@ -191,7 +191,7 @@ bbsink_copystream_archive_contents(bbsink *sink, size_t len) if (mysink->send_to_client) { /* Add one because we're also sending a leading type byte. */ - pq_putmessage('d', mysink->msgbuffer, len + 1); + pq_putmessage(PqMsg_CopyData, mysink->msgbuffer, len + 1); } /* Consider whether to send a progress report to the client. */ @@ -221,7 +221,7 @@ bbsink_copystream_archive_contents(bbsink *sink, size_t len) mysink->last_progress_report_time = now; pq_beginmessage(&buf, PqMsg_CopyData); - pq_sendbyte(&buf, 'p'); /* Progress report */ + pq_sendbyte(&buf, PqBackupMsg_ProgressReport); pq_sendint64(&buf, state->bytes_done); pq_endmessage(&buf); pq_flush_if_writable(); @@ -247,7 +247,7 @@ bbsink_copystream_end_archive(bbsink *sink) mysink->bytes_done_at_last_time_check = state->bytes_done; mysink->last_progress_report_time = GetCurrentTimestamp(); pq_beginmessage(&buf, PqMsg_CopyData); - pq_sendbyte(&buf, 'p'); /* Progress report */ + pq_sendbyte(&buf, PqBackupMsg_ProgressReport); pq_sendint64(&buf, state->bytes_done); pq_endmessage(&buf); pq_flush_if_writable(); @@ -262,7 +262,7 @@ bbsink_copystream_begin_manifest(bbsink *sink) StringInfoData buf; pq_beginmessage(&buf, PqMsg_CopyData); - pq_sendbyte(&buf, 'm'); /* Manifest */ + pq_sendbyte(&buf, PqBackupMsg_Manifest); pq_endmessage(&buf); } @@ -277,7 +277,7 @@ bbsink_copystream_manifest_contents(bbsink *sink, size_t len) if (mysink->send_to_client) { /* Add one because we're also sending a leading type byte. */ - pq_putmessage('d', mysink->msgbuffer, len + 1); + pq_putmessage(PqMsg_CopyData, mysink->msgbuffer, len + 1); } } diff --git a/src/backend/backup/basebackup_progress.c b/src/backend/backup/basebackup_progress.c index 1d22b541f89..dac20593622 100644 --- a/src/backend/backup/basebackup_progress.c +++ b/src/backend/backup/basebackup_progress.c @@ -56,7 +56,7 @@ static const bbsink_ops bbsink_progress_ops = { * forwards data to a successor sink. */ bbsink * -bbsink_progress_new(bbsink *next, bool estimate_backup_size) +bbsink_progress_new(bbsink *next, bool estimate_backup_size, bool incremental) { bbsink *sink; @@ -69,10 +69,15 @@ bbsink_progress_new(bbsink *next, bool estimate_backup_size) /* * Report that a base backup is in progress, and set the total size of the * backup to -1, which will get translated to NULL. If we're estimating - * the backup size, we'll insert the real estimate when we have it. + * the backup size, we'll insert the real estimate when we have it. Also, + * the backup type is set. */ pgstat_progress_start_command(PROGRESS_COMMAND_BASEBACKUP, InvalidOid); pgstat_progress_update_param(PROGRESS_BASEBACKUP_BACKUP_TOTAL, -1); + pgstat_progress_update_param(PROGRESS_BASEBACKUP_BACKUP_TYPE, + incremental + ? PROGRESS_BASEBACKUP_BACKUP_TYPE_INCREMENTAL + : PROGRESS_BASEBACKUP_BACKUP_TYPE_FULL); return sink; } diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index f6eca09ee15..1b3c5a55882 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1327,7 +1327,10 @@ CREATE VIEW pg_stat_progress_basebackup AS CASE S.param2 WHEN -1 THEN NULL ELSE S.param2 END AS backup_total, S.param3 AS backup_streamed, S.param4 AS tablespaces_total, - S.param5 AS tablespaces_streamed + S.param5 AS tablespaces_streamed, + CASE S.param6 WHEN 1 THEN 'full' + WHEN 2 THEN 'incremental' + END AS backup_type FROM pg_stat_get_progress_info('BASEBACKUP') AS S; @@ -1399,6 +1402,7 @@ CREATE VIEW pg_stat_subscription_stats AS ss.confl_insert_exists, ss.confl_update_origin_differs, ss.confl_update_exists, + ss.confl_update_deleted, ss.confl_update_missing, ss.confl_delete_origin_differs, ss.confl_delete_missing, diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 7111d5d5334..40d66537ad7 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -690,8 +690,8 @@ do_analyze_rel(Relation onerel, const VacuumParams params, * only do it for inherited stats. (We're never called for not-inherited * stats on partitioned tables anyway.) * - * Reset the changes_since_analyze counter only if we analyzed all - * columns; otherwise, there is still work for auto-analyze to do. + * Reset the mod_since_analyze counter only if we analyzed all columns; + * otherwise, there is still work for auto-analyze to do. */ if (!inh) pgstat_report_analyze(onerel, totalrows, totaldeadrows, diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c index 502a45163c8..92a396b8406 100644 --- a/src/backend/commands/dbcommands.c +++ b/src/backend/commands/dbcommands.c @@ -1052,7 +1052,7 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt) dbctype = src_ctype; if (dblocprovider == '\0') dblocprovider = src_locprovider; - if (dblocale == NULL) + if (dblocale == NULL && dblocprovider == src_locprovider) dblocale = src_locale; if (dbicurules == NULL) dbicurules = src_icurules; diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 1bf7eaae5b3..803c26ab216 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -2113,20 +2113,20 @@ AlterPublicationOwner_oid(Oid pubid, Oid newOwnerId) static char defGetGeneratedColsOption(DefElem *def) { - char *sval; + char *sval = ""; /* - * If no parameter value given, assume "stored" is meant. + * A parameter value is required. */ - if (!def->arg) - return PUBLISH_GENCOLS_STORED; - - sval = defGetString(def); + if (def->arg) + { + sval = defGetString(def); - if (pg_strcasecmp(sval, "none") == 0) - return PUBLISH_GENCOLS_NONE; - if (pg_strcasecmp(sval, "stored") == 0) - return PUBLISH_GENCOLS_STORED; + if (pg_strcasecmp(sval, "none") == 0) + return PUBLISH_GENCOLS_NONE; + if (pg_strcasecmp(sval, "stored") == 0) + return PUBLISH_GENCOLS_STORED; + } ereport(ERROR, errcode(ERRCODE_SYNTAX_ERROR), diff --git a/src/backend/executor/execReplication.c b/src/backend/executor/execReplication.c index f262e7a66f7..68184f5d671 100644 --- a/src/backend/executor/execReplication.c +++ b/src/backend/executor/execReplication.c @@ -14,12 +14,14 @@ #include "postgres.h" +#include "access/commit_ts.h" #include "access/genam.h" #include "access/gist.h" #include "access/relscan.h" #include "access/tableam.h" #include "access/transam.h" #include "access/xact.h" +#include "access/heapam.h" #include "catalog/pg_am_d.h" #include "commands/trigger.h" #include "executor/executor.h" @@ -36,7 +38,7 @@ static bool tuples_equal(TupleTableSlot *slot1, TupleTableSlot *slot2, - TypeCacheEntry **eq); + TypeCacheEntry **eq, Bitmapset *columns); /* * Setup a ScanKey for a search in the relation 'rel' for a tuple 'key' that @@ -221,7 +223,7 @@ retry: if (eq == NULL) eq = palloc0(sizeof(*eq) * outslot->tts_tupleDescriptor->natts); - if (!tuples_equal(outslot, searchslot, eq)) + if (!tuples_equal(outslot, searchslot, eq, NULL)) continue; } @@ -277,10 +279,13 @@ retry: /* * Compare the tuples in the slots by checking if they have equal values. + * + * If 'columns' is not null, only the columns specified within it will be + * considered for the equality check, ignoring all other columns. */ static bool tuples_equal(TupleTableSlot *slot1, TupleTableSlot *slot2, - TypeCacheEntry **eq) + TypeCacheEntry **eq, Bitmapset *columns) { int attrnum; @@ -306,6 +311,14 @@ tuples_equal(TupleTableSlot *slot1, TupleTableSlot *slot2, continue; /* + * Ignore columns that are not listed for checking. + */ + if (columns && + !bms_is_member(att->attnum - FirstLowInvalidHeapAttributeNumber, + columns)) + continue; + + /* * If one value is NULL and other is not, then they are certainly not * equal */ @@ -380,7 +393,7 @@ retry: /* Try to find the tuple */ while (table_scan_getnextslot(scan, ForwardScanDirection, scanslot)) { - if (!tuples_equal(scanslot, searchslot, eq)) + if (!tuples_equal(scanslot, searchslot, eq, NULL)) continue; found = true; @@ -456,6 +469,236 @@ BuildConflictIndexInfo(ResultRelInfo *resultRelInfo, Oid conflictindex) } /* + * If the tuple is recently dead and was deleted by a transaction with a newer + * commit timestamp than previously recorded, update the associated transaction + * ID, commit time, and origin. This helps ensure that conflict detection uses + * the most recent and relevant deletion metadata. + */ +static void +update_most_recent_deletion_info(TupleTableSlot *scanslot, + TransactionId oldestxmin, + TransactionId *delete_xid, + TimestampTz *delete_time, + RepOriginId *delete_origin) +{ + BufferHeapTupleTableSlot *hslot; + HeapTuple tuple; + Buffer buf; + bool recently_dead = false; + TransactionId xmax; + TimestampTz localts; + RepOriginId localorigin; + + hslot = (BufferHeapTupleTableSlot *) scanslot; + + tuple = ExecFetchSlotHeapTuple(scanslot, false, NULL); + buf = hslot->buffer; + + LockBuffer(buf, BUFFER_LOCK_SHARE); + + /* + * We do not consider HEAPTUPLE_DEAD status because it indicates either + * tuples whose inserting transaction was aborted (meaning there is no + * commit timestamp or origin), or tuples deleted by a transaction older + * than oldestxmin, making it safe to ignore them during conflict + * detection (See comments atop worker.c for details). + */ + if (HeapTupleSatisfiesVacuum(tuple, oldestxmin, buf) == HEAPTUPLE_RECENTLY_DEAD) + recently_dead = true; + + LockBuffer(buf, BUFFER_LOCK_UNLOCK); + + if (!recently_dead) + return; + + xmax = HeapTupleHeaderGetUpdateXid(tuple->t_data); + if (!TransactionIdIsValid(xmax)) + return; + + /* Select the dead tuple with the most recent commit timestamp */ + if (TransactionIdGetCommitTsData(xmax, &localts, &localorigin) && + TimestampDifferenceExceeds(*delete_time, localts, 0)) + { + *delete_xid = xmax; + *delete_time = localts; + *delete_origin = localorigin; + } +} + +/* + * Searches the relation 'rel' for the most recently deleted tuple that matches + * the values in 'searchslot' and is not yet removable by VACUUM. The function + * returns the transaction ID, origin, and commit timestamp of the transaction + * that deleted this tuple. + * + * 'oldestxmin' acts as a cutoff transaction ID. Tuples deleted by transactions + * with IDs >= 'oldestxmin' are considered recently dead and are eligible for + * conflict detection. + * + * Instead of stopping at the first match, we scan all matching dead tuples to + * identify most recent deletion. This is crucial because only the latest + * deletion is relevant for resolving conflicts. + * + * For example, consider a scenario on the subscriber where a row is deleted, + * re-inserted, and then deleted again only on the subscriber: + * + * - (pk, 1) - deleted at 9:00, + * - (pk, 1) - deleted at 9:02, + * + * Now, a remote update arrives: (pk, 1) -> (pk, 2), timestamped at 9:01. + * + * If we mistakenly return the older deletion (9:00), the system may wrongly + * apply the remote update using a last-update-wins strategy. Instead, we must + * recognize the more recent deletion at 9:02 and skip the update. See + * comments atop worker.c for details. Note, as of now, conflict resolution + * is not implemented. Consequently, the system may incorrectly report the + * older tuple as the conflicted one, leading to misleading results. + * + * The commit timestamp of the deleting transaction is used to determine which + * tuple was deleted most recently. + */ +bool +RelationFindDeletedTupleInfoSeq(Relation rel, TupleTableSlot *searchslot, + TransactionId oldestxmin, + TransactionId *delete_xid, + RepOriginId *delete_origin, + TimestampTz *delete_time) +{ + TupleTableSlot *scanslot; + TableScanDesc scan; + TypeCacheEntry **eq; + Bitmapset *indexbitmap; + TupleDesc desc PG_USED_FOR_ASSERTS_ONLY = RelationGetDescr(rel); + + Assert(equalTupleDescs(desc, searchslot->tts_tupleDescriptor)); + + *delete_xid = InvalidTransactionId; + *delete_origin = InvalidRepOriginId; + *delete_time = 0; + + /* + * If the relation has a replica identity key or a primary key that is + * unusable for locating deleted tuples (see + * IsIndexUsableForFindingDeletedTuple), a full table scan becomes + * necessary. In such cases, comparing the entire tuple is not required, + * since the remote tuple might not include all column values. Instead, + * the indexed columns alone are suffcient to identify the target tuple + * (see logicalrep_rel_mark_updatable). + */ + indexbitmap = RelationGetIndexAttrBitmap(rel, + INDEX_ATTR_BITMAP_IDENTITY_KEY); + + /* fallback to PK if no replica identity */ + if (!indexbitmap) + indexbitmap = RelationGetIndexAttrBitmap(rel, + INDEX_ATTR_BITMAP_PRIMARY_KEY); + + eq = palloc0(sizeof(*eq) * searchslot->tts_tupleDescriptor->natts); + + /* + * Start a heap scan using SnapshotAny to identify dead tuples that are + * not visible under a standard MVCC snapshot. Tuples from transactions + * not yet committed or those just committed prior to the scan are + * excluded in update_most_recent_deletion_info(). + */ + scan = table_beginscan(rel, SnapshotAny, 0, NULL); + scanslot = table_slot_create(rel, NULL); + + table_rescan(scan, NULL); + + /* Try to find the tuple */ + while (table_scan_getnextslot(scan, ForwardScanDirection, scanslot)) + { + if (!tuples_equal(scanslot, searchslot, eq, indexbitmap)) + continue; + + update_most_recent_deletion_info(scanslot, oldestxmin, delete_xid, + delete_time, delete_origin); + } + + table_endscan(scan); + ExecDropSingleTupleTableSlot(scanslot); + + return *delete_time != 0; +} + +/* + * Similar to RelationFindDeletedTupleInfoSeq() but using index scan to locate + * the deleted tuple. + */ +bool +RelationFindDeletedTupleInfoByIndex(Relation rel, Oid idxoid, + TupleTableSlot *searchslot, + TransactionId oldestxmin, + TransactionId *delete_xid, + RepOriginId *delete_origin, + TimestampTz *delete_time) +{ + Relation idxrel; + ScanKeyData skey[INDEX_MAX_KEYS]; + int skey_attoff; + IndexScanDesc scan; + TupleTableSlot *scanslot; + TypeCacheEntry **eq = NULL; + bool isIdxSafeToSkipDuplicates; + TupleDesc desc PG_USED_FOR_ASSERTS_ONLY = RelationGetDescr(rel); + + Assert(equalTupleDescs(desc, searchslot->tts_tupleDescriptor)); + Assert(OidIsValid(idxoid)); + + *delete_xid = InvalidTransactionId; + *delete_time = 0; + *delete_origin = InvalidRepOriginId; + + isIdxSafeToSkipDuplicates = (GetRelationIdentityOrPK(rel) == idxoid); + + scanslot = table_slot_create(rel, NULL); + + idxrel = index_open(idxoid, RowExclusiveLock); + + /* Build scan key. */ + skey_attoff = build_replindex_scan_key(skey, rel, idxrel, searchslot); + + /* + * Start an index scan using SnapshotAny to identify dead tuples that are + * not visible under a standard MVCC snapshot. Tuples from transactions + * not yet committed or those just committed prior to the scan are + * excluded in update_most_recent_deletion_info(). + */ + scan = index_beginscan(rel, idxrel, SnapshotAny, NULL, skey_attoff, 0); + + index_rescan(scan, skey, skey_attoff, NULL, 0); + + /* Try to find the tuple */ + while (index_getnext_slot(scan, ForwardScanDirection, scanslot)) + { + /* + * Avoid expensive equality check if the index is primary key or + * replica identity index. + */ + if (!isIdxSafeToSkipDuplicates) + { + if (eq == NULL) + eq = palloc0(sizeof(*eq) * scanslot->tts_tupleDescriptor->natts); + + if (!tuples_equal(scanslot, searchslot, eq, NULL)) + continue; + } + + update_most_recent_deletion_info(scanslot, oldestxmin, delete_xid, + delete_time, delete_origin); + } + + index_endscan(scan); + + index_close(idxrel, NoLock); + + ExecDropSingleTupleTableSlot(scanslot); + + return *delete_time != 0; +} + +/* * Find the tuple that violates the passed unique index (conflictindex). * * If the conflicting tuple is found return true, otherwise false. diff --git a/src/backend/partitioning/partbounds.c b/src/backend/partitioning/partbounds.c index 4bdc2941efb..822cf4ec451 100644 --- a/src/backend/partitioning/partbounds.c +++ b/src/backend/partitioning/partbounds.c @@ -1007,9 +1007,6 @@ partition_bounds_copy(PartitionBoundInfo src, int ndatums; int nindexes; int partnatts; - bool hash_part; - int natts; - Datum *boundDatums; dest = (PartitionBoundInfo) palloc(sizeof(PartitionBoundInfoData)); @@ -1023,7 +1020,7 @@ partition_bounds_copy(PartitionBoundInfo src, dest->datums = (Datum **) palloc(sizeof(Datum *) * ndatums); - if (src->kind != NULL) + if (src->kind != NULL && ndatums > 0) { PartitionRangeDatumKind *boundKinds; @@ -1058,36 +1055,40 @@ partition_bounds_copy(PartitionBoundInfo src, * For hash partitioning, datums array will have two elements - modulus * and remainder. */ - hash_part = (key->strategy == PARTITION_STRATEGY_HASH); - natts = hash_part ? 2 : partnatts; - boundDatums = palloc(ndatums * natts * sizeof(Datum)); - - for (i = 0; i < ndatums; i++) + if (ndatums > 0) { - int j; - - dest->datums[i] = &boundDatums[i * natts]; + bool hash_part = (key->strategy == PARTITION_STRATEGY_HASH); + int natts = hash_part ? 2 : partnatts; + Datum *boundDatums = palloc(ndatums * natts * sizeof(Datum)); - for (j = 0; j < natts; j++) + for (i = 0; i < ndatums; i++) { - bool byval; - int typlen; + int j; - if (hash_part) - { - typlen = sizeof(int32); /* Always int4 */ - byval = true; /* int4 is pass-by-value */ - } - else + dest->datums[i] = &boundDatums[i * natts]; + + for (j = 0; j < natts; j++) { - byval = key->parttypbyval[j]; - typlen = key->parttyplen[j]; - } + if (dest->kind == NULL || + dest->kind[i][j] == PARTITION_RANGE_DATUM_VALUE) + { + bool byval; + int typlen; - if (dest->kind == NULL || - dest->kind[i][j] == PARTITION_RANGE_DATUM_VALUE) - dest->datums[i][j] = datumCopy(src->datums[i][j], - byval, typlen); + if (hash_part) + { + typlen = sizeof(int32); /* Always int4 */ + byval = true; /* int4 is pass-by-value */ + } + else + { + byval = key->parttypbyval[j]; + typlen = key->parttyplen[j]; + } + dest->datums[i][j] = datumCopy(src->datums[i][j], + byval, typlen); + } + } } } diff --git a/src/backend/replication/logical/applyparallelworker.c b/src/backend/replication/logical/applyparallelworker.c index 1fa931a7422..cd0e19176fd 100644 --- a/src/backend/replication/logical/applyparallelworker.c +++ b/src/backend/replication/logical/applyparallelworker.c @@ -778,10 +778,10 @@ LogicalParallelApplyLoop(shm_mq_handle *mqh) /* * The first byte of messages sent from leader apply worker to - * parallel apply workers can only be 'w'. + * parallel apply workers can only be PqReplMsg_WALData. */ c = pq_getmsgbyte(&s); - if (c != 'w') + if (c != PqReplMsg_WALData) elog(ERROR, "unexpected message \"%c\"", c); /* diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c index 97c4e26b586..2fd3e8bbda5 100644 --- a/src/backend/replication/logical/conflict.c +++ b/src/backend/replication/logical/conflict.c @@ -29,6 +29,7 @@ static const char *const ConflictTypeNames[] = { [CT_UPDATE_EXISTS] = "update_exists", [CT_UPDATE_MISSING] = "update_missing", [CT_DELETE_ORIGIN_DIFFERS] = "delete_origin_differs", + [CT_UPDATE_DELETED] = "update_deleted", [CT_DELETE_MISSING] = "delete_missing", [CT_MULTIPLE_UNIQUE_CONFLICTS] = "multiple_unique_conflicts" }; @@ -176,6 +177,7 @@ errcode_apply_conflict(ConflictType type) case CT_UPDATE_ORIGIN_DIFFERS: case CT_UPDATE_MISSING: case CT_DELETE_ORIGIN_DIFFERS: + case CT_UPDATE_DELETED: case CT_DELETE_MISSING: return errcode(ERRCODE_T_R_SERIALIZATION_FAILURE); } @@ -261,6 +263,26 @@ errdetail_apply_conflict(EState *estate, ResultRelInfo *relinfo, break; + case CT_UPDATE_DELETED: + if (localts) + { + if (localorigin == InvalidRepOriginId) + appendStringInfo(&err_detail, _("The row to be updated was deleted locally in transaction %u at %s."), + localxmin, timestamptz_to_str(localts)); + else if (replorigin_by_oid(localorigin, true, &origin_name)) + appendStringInfo(&err_detail, _("The row to be updated was deleted by a different origin \"%s\" in transaction %u at %s."), + origin_name, localxmin, timestamptz_to_str(localts)); + + /* The origin that modified this row has been removed. */ + else + appendStringInfo(&err_detail, _("The row to be updated was deleted by a non-existent origin in transaction %u at %s."), + localxmin, timestamptz_to_str(localts)); + } + else + appendStringInfo(&err_detail, _("The row to be updated was deleted.")); + + break; + case CT_UPDATE_MISSING: appendStringInfoString(&err_detail, _("Could not find the row to be updated.")); break; diff --git a/src/backend/replication/logical/proto.c b/src/backend/replication/logical/proto.c index 1a352b542dc..1b3d9eb49dd 100644 --- a/src/backend/replication/logical/proto.c +++ b/src/backend/replication/logical/proto.c @@ -809,7 +809,7 @@ logicalrep_write_tuple(StringInfo out, Relation rel, TupleTableSlot *slot, continue; } - if (att->attlen == -1 && VARATT_IS_EXTERNAL_ONDISK(values[i])) + if (att->attlen == -1 && VARATT_IS_EXTERNAL_ONDISK(DatumGetPointer(values[i]))) { /* * Unchanged toasted datum. (Note that we don't promise to detect diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 2f0c08b8fbd..37738440113 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -1059,14 +1059,14 @@ ValidateSlotSyncParams(int elevel) { /* * Logical slot sync/creation requires wal_level >= logical. - * - * Since altering the wal_level requires a server restart, so error out in - * this case regardless of elevel provided by caller. */ if (wal_level < WAL_LEVEL_LOGICAL) - ereport(ERROR, + { + ereport(elevel, errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("replication slot synchronization requires \"wal_level\" >= \"logical\"")); + return false; + } /* * A physical replication slot(primary_slot_name) is required on the diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index b59221c4d06..0fdc5de57ba 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -138,9 +138,9 @@ * Each apply worker that enabled retain_dead_tuples option maintains a * non-removable transaction ID (oldest_nonremovable_xid) in shared memory to * prevent dead rows from being removed prematurely when the apply worker still - * needs them to detect conflicts reliably. This helps to retain the required - * commit_ts module information, which further helps to detect - * update_origin_differs and delete_origin_differs conflicts reliably, as + * needs them to detect update_deleted conflicts. Additionally, this helps to + * retain the required commit_ts module information, which further helps to + * detect update_origin_differs and delete_origin_differs conflicts reliably, as * otherwise, vacuum freeze could remove the required information. * * The logical replication launcher manages an internal replication slot named @@ -185,10 +185,10 @@ * transactions that occurred concurrently with the tuple DELETE, any * subsequent UPDATE from a remote node should have a later timestamp. In such * cases, it is acceptable to detect an update_missing scenario and convert the - * UPDATE to an INSERT when applying it. But, detecting concurrent remote - * transactions with earlier timestamps than the DELETE is necessary, as the - * UPDATEs in remote transactions should be ignored if their timestamp is - * earlier than that of the dead tuples. + * UPDATE to an INSERT when applying it. But, for concurrent remote + * transactions with earlier timestamps than the DELETE, detecting + * update_deleted is necessary, as the UPDATEs in remote transactions should be + * ignored if their timestamp is earlier than that of the dead tuples. * * Note that advancing the non-removable transaction ID is not supported if the * publisher is also a physical standby. This is because the logical walsender @@ -576,6 +576,12 @@ static bool FindReplTupleInLocalRel(ApplyExecutionData *edata, Relation localrel Oid localidxoid, TupleTableSlot *remoteslot, TupleTableSlot **localslot); +static bool FindDeletedTupleInLocalRel(Relation localrel, + Oid localidxoid, + TupleTableSlot *remoteslot, + TransactionId *delete_xid, + RepOriginId *delete_origin, + TimestampTz *delete_time); static void apply_handle_tuple_routing(ApplyExecutionData *edata, TupleTableSlot *remoteslot, LogicalRepTupleData *newtup, @@ -2912,17 +2918,31 @@ apply_handle_update_internal(ApplyExecutionData *edata, } else { + ConflictType type; TupleTableSlot *newslot = localslot; + /* + * Detecting whether the tuple was recently deleted or never existed + * is crucial to avoid misleading the user during confict handling. + */ + if (FindDeletedTupleInLocalRel(localrel, localindexoid, remoteslot, + &conflicttuple.xmin, + &conflicttuple.origin, + &conflicttuple.ts) && + conflicttuple.origin != replorigin_session_origin) + type = CT_UPDATE_DELETED; + else + type = CT_UPDATE_MISSING; + /* Store the new tuple for conflict reporting */ slot_store_data(newslot, relmapentry, newtup); /* - * The tuple to be updated could not be found. Do nothing except for - * emitting a log message. + * The tuple to be updated could not be found or was deleted. Do + * nothing except for emitting a log message. */ - ReportApplyConflict(estate, relinfo, LOG, CT_UPDATE_MISSING, - remoteslot, newslot, list_make1(&conflicttuple)); + ReportApplyConflict(estate, relinfo, LOG, type, remoteslot, newslot, + list_make1(&conflicttuple)); } /* Cleanup. */ @@ -3143,6 +3163,112 @@ FindReplTupleInLocalRel(ApplyExecutionData *edata, Relation localrel, } /* + * Determine whether the index can reliably locate the deleted tuple in the + * local relation. + * + * An index may exclude deleted tuples if it was re-indexed or re-created during + * change application. Therefore, an index is considered usable only if the + * conflict detection slot.xmin (conflict_detection_xmin) is greater than the + * index tuple's xmin. This ensures that any tuples deleted prior to the index + * creation or re-indexing are not relevant for conflict detection in the + * current apply worker. + * + * Note that indexes may also be excluded if they were modified by other DDL + * operations, such as ALTER INDEX. However, this is acceptable, as the + * likelihood of such DDL changes coinciding with the need to scan dead + * tuples for the update_deleted is low. + */ +static bool +IsIndexUsableForFindingDeletedTuple(Oid localindexoid, + TransactionId conflict_detection_xmin) +{ + HeapTuple index_tuple; + TransactionId index_xmin; + + index_tuple = SearchSysCache1(INDEXRELID, ObjectIdGetDatum(localindexoid)); + + if (!HeapTupleIsValid(index_tuple)) /* should not happen */ + elog(ERROR, "cache lookup failed for index %u", localindexoid); + + /* + * No need to check for a frozen transaction ID, as + * TransactionIdPrecedes() manages it internally, treating it as falling + * behind the conflict_detection_xmin. + */ + index_xmin = HeapTupleHeaderGetXmin(index_tuple->t_data); + + ReleaseSysCache(index_tuple); + + return TransactionIdPrecedes(index_xmin, conflict_detection_xmin); +} + +/* + * Attempts to locate a deleted tuple in the local relation that matches the + * values of the tuple received from the publication side (in 'remoteslot'). + * The search is performed using either the replica identity index, primary + * key, other available index, or a sequential scan if necessary. + * + * Returns true if the deleted tuple is found. If found, the transaction ID, + * origin, and commit timestamp of the deletion are stored in '*delete_xid', + * '*delete_origin', and '*delete_time' respectively. + */ +static bool +FindDeletedTupleInLocalRel(Relation localrel, Oid localidxoid, + TupleTableSlot *remoteslot, + TransactionId *delete_xid, RepOriginId *delete_origin, + TimestampTz *delete_time) +{ + TransactionId oldestxmin; + ReplicationSlot *slot; + + /* + * Return false if either dead tuples are not retained or commit timestamp + * data is not available. + */ + if (!MySubscription->retaindeadtuples || !track_commit_timestamp) + return false; + + /* + * For conflict detection, we use the conflict slot's xmin value instead + * of invoking GetOldestNonRemovableTransactionId(). The slot.xmin acts as + * a threshold to identify tuples that were recently deleted. These tuples + * are not visible to concurrent transactions, but we log an + * update_deleted conflict if such a tuple matches the remote update being + * applied. + * + * Although GetOldestNonRemovableTransactionId() can return a value older + * than the slot's xmin, for our current purpose it is acceptable to treat + * tuples deleted by transactions prior to slot.xmin as update_missing + * conflicts. + * + * Ideally, we would use oldest_nonremovable_xid, which is directly + * maintained by the leader apply worker. However, this value is not + * available to table synchronization or parallel apply workers, making + * slot.xmin a practical alternative in those contexts. + */ + slot = SearchNamedReplicationSlot(CONFLICT_DETECTION_SLOT, true); + + Assert(slot); + + SpinLockAcquire(&slot->mutex); + oldestxmin = slot->data.xmin; + SpinLockRelease(&slot->mutex); + + Assert(TransactionIdIsValid(oldestxmin)); + + if (OidIsValid(localidxoid) && + IsIndexUsableForFindingDeletedTuple(localidxoid, oldestxmin)) + return RelationFindDeletedTupleInfoByIndex(localrel, localidxoid, + remoteslot, oldestxmin, + delete_xid, delete_origin, + delete_time); + else + return RelationFindDeletedTupleInfoSeq(localrel, remoteslot, + oldestxmin, delete_xid, + delete_origin, delete_time); +} + +/* * This handles insert, update, delete on a partitioned table. */ static void @@ -3260,18 +3386,35 @@ apply_handle_tuple_routing(ApplyExecutionData *edata, remoteslot_part, &localslot); if (!found) { + ConflictType type; TupleTableSlot *newslot = localslot; + /* + * Detecting whether the tuple was recently deleted or + * never existed is crucial to avoid misleading the user + * during confict handling. + */ + if (FindDeletedTupleInLocalRel(partrel, + part_entry->localindexoid, + remoteslot_part, + &conflicttuple.xmin, + &conflicttuple.origin, + &conflicttuple.ts) && + conflicttuple.origin != replorigin_session_origin) + type = CT_UPDATE_DELETED; + else + type = CT_UPDATE_MISSING; + /* Store the new tuple for conflict reporting */ slot_store_data(newslot, part_entry, newtup); /* - * The tuple to be updated could not be found. Do nothing - * except for emitting a log message. + * The tuple to be updated could not be found or was + * deleted. Do nothing except for emitting a log message. */ ReportApplyConflict(estate, partrelinfo, LOG, - CT_UPDATE_MISSING, remoteslot_part, - newslot, list_make1(&conflicttuple)); + type, remoteslot_part, newslot, + list_make1(&conflicttuple)); return; } @@ -3851,7 +3994,7 @@ LogicalRepApplyLoop(XLogRecPtr last_received) c = pq_getmsgbyte(&s); - if (c == 'w') + if (c == PqReplMsg_WALData) { XLogRecPtr start_lsn; XLogRecPtr end_lsn; @@ -3873,7 +4016,7 @@ LogicalRepApplyLoop(XLogRecPtr last_received) maybe_advance_nonremovable_xid(&rdt_data, false); } - else if (c == 'k') + else if (c == PqReplMsg_Keepalive) { XLogRecPtr end_lsn; TimestampTz timestamp; @@ -3892,7 +4035,7 @@ LogicalRepApplyLoop(XLogRecPtr last_received) UpdateWorkerStats(last_received, timestamp, true); } - else if (c == 's') /* Primary status update */ + else if (c == PqReplMsg_PrimaryStatusUpdate) { rdt_data.remote_lsn = pq_getmsgint64(&s); rdt_data.remote_oldestxid = FullTransactionIdFromU64((uint64) pq_getmsgint64(&s)); @@ -4124,7 +4267,7 @@ send_feedback(XLogRecPtr recvpos, bool force, bool requestReply) else resetStringInfo(reply_message); - pq_sendbyte(reply_message, 'r'); + pq_sendbyte(reply_message, PqReplMsg_StandbyStatusUpdate); pq_sendint64(reply_message, recvpos); /* write */ pq_sendint64(reply_message, flushpos); /* flush */ pq_sendint64(reply_message, writepos); /* apply */ @@ -4172,8 +4315,8 @@ can_advance_nonremovable_xid(RetainDeadTuplesData *rdt_data) { /* * It is sufficient to manage non-removable transaction ID for a - * subscription by the main apply worker to detect conflicts reliably even - * for table sync or parallel apply workers. + * subscription by the main apply worker to detect update_deleted reliably + * even for table sync or parallel apply workers. */ if (!am_leader_apply_worker()) return false; @@ -4295,7 +4438,7 @@ request_publisher_status(RetainDeadTuplesData *rdt_data) * Send the current time to update the remote walsender's latest reply * message received time. */ - pq_sendbyte(request_message, 'p'); + pq_sendbyte(request_message, PqReplMsg_PrimaryStatusRequest); pq_sendint64(request_message, GetCurrentTimestamp()); elog(DEBUG2, "sending publisher status request message"); @@ -4374,10 +4517,11 @@ wait_for_local_flush(RetainDeadTuplesData *rdt_data) * We expect the publisher and subscriber clocks to be in sync using time * sync service like NTP. Otherwise, we will advance this worker's * oldest_nonremovable_xid prematurely, leading to the removal of rows - * required to detect conflicts reliably. This check primarily addresses - * scenarios where the publisher's clock falls behind; if the publisher's - * clock is ahead, subsequent transactions will naturally bear later - * commit timestamps, conforming to the design outlined atop worker.c. + * required to detect update_deleted reliably. This check primarily + * addresses scenarios where the publisher's clock falls behind; if the + * publisher's clock is ahead, subsequent transactions will naturally bear + * later commit timestamps, conforming to the design outlined atop + * worker.c. * * XXX Consider waiting for the publisher's clock to catch up with the * subscriber's before proceeding to the next phase. diff --git a/src/backend/replication/pgoutput/pgoutput.c b/src/backend/replication/pgoutput/pgoutput.c index f4c977262c5..80540c017bd 100644 --- a/src/backend/replication/pgoutput/pgoutput.c +++ b/src/backend/replication/pgoutput/pgoutput.c @@ -1374,8 +1374,8 @@ pgoutput_row_filter(Relation relation, TupleTableSlot *old_slot, * VARTAG_INDIRECT. See ReorderBufferToastReplace. */ if (att->attlen == -1 && - VARATT_IS_EXTERNAL_ONDISK(new_slot->tts_values[i]) && - !VARATT_IS_EXTERNAL_ONDISK(old_slot->tts_values[i])) + VARATT_IS_EXTERNAL_ONDISK(DatumGetPointer(new_slot->tts_values[i])) && + !VARATT_IS_EXTERNAL_ONDISK(DatumGetPointer(old_slot->tts_values[i]))) { if (!tmp_new_slot) { diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index b6281101711..7361ffc9dcf 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -826,7 +826,7 @@ XLogWalRcvProcessMsg(unsigned char type, char *buf, Size len, TimeLineID tli) switch (type) { - case 'w': /* WAL records */ + case PqReplMsg_WALData: { StringInfoData incoming_message; @@ -850,7 +850,7 @@ XLogWalRcvProcessMsg(unsigned char type, char *buf, Size len, TimeLineID tli) XLogWalRcvWrite(buf, len, dataStart, tli); break; } - case 'k': /* Keepalive */ + case PqReplMsg_Keepalive: { StringInfoData incoming_message; @@ -1130,7 +1130,7 @@ XLogWalRcvSendReply(bool force, bool requestReply) applyPtr = GetXLogReplayRecPtr(NULL); resetStringInfo(&reply_message); - pq_sendbyte(&reply_message, 'r'); + pq_sendbyte(&reply_message, PqReplMsg_StandbyStatusUpdate); pq_sendint64(&reply_message, writePtr); pq_sendint64(&reply_message, flushPtr); pq_sendint64(&reply_message, applyPtr); @@ -1234,7 +1234,7 @@ XLogWalRcvSendHSFeedback(bool immed) /* Construct the message and send it. */ resetStringInfo(&reply_message); - pq_sendbyte(&reply_message, 'h'); + pq_sendbyte(&reply_message, PqReplMsg_HotStandbyFeedback); pq_sendint64(&reply_message, GetCurrentTimestamp()); pq_sendint32(&reply_message, xmin); pq_sendint32(&reply_message, xmin_epoch); diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index ee911394a23..0855bae3535 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1534,7 +1534,7 @@ WalSndPrepareWrite(LogicalDecodingContext *ctx, XLogRecPtr lsn, TransactionId xi resetStringInfo(ctx->out); - pq_sendbyte(ctx->out, 'w'); + pq_sendbyte(ctx->out, PqReplMsg_WALData); pq_sendint64(ctx->out, lsn); /* dataStart */ pq_sendint64(ctx->out, lsn); /* walEnd */ @@ -2292,7 +2292,8 @@ ProcessRepliesIfAny(void) switch (firstchar) { /* - * 'd' means a standby reply wrapped in a CopyData packet. + * PqMsg_CopyData means a standby reply wrapped in a CopyData + * packet. */ case PqMsg_CopyData: ProcessStandbyMessage(); @@ -2300,8 +2301,9 @@ ProcessRepliesIfAny(void) break; /* - * CopyDone means the standby requested to finish streaming. - * Reply with CopyDone, if we had not sent that already. + * PqMsg_CopyDone means the standby requested to finish + * streaming. Reply with CopyDone, if we had not sent that + * already. */ case PqMsg_CopyDone: if (!streamingDoneSending) @@ -2315,7 +2317,8 @@ ProcessRepliesIfAny(void) break; /* - * 'X' means that the standby is closing down the socket. + * PqMsg_Terminate means that the standby is closing down the + * socket. */ case PqMsg_Terminate: proc_exit(0); @@ -2350,15 +2353,15 @@ ProcessStandbyMessage(void) switch (msgtype) { - case 'r': + case PqReplMsg_StandbyStatusUpdate: ProcessStandbyReplyMessage(); break; - case 'h': + case PqReplMsg_HotStandbyFeedback: ProcessStandbyHSFeedbackMessage(); break; - case 'p': + case PqReplMsg_PrimaryStatusRequest: ProcessStandbyPSRequestMessage(); break; @@ -2752,7 +2755,7 @@ ProcessStandbyPSRequestMessage(void) /* construct the message... */ resetStringInfo(&output_message); - pq_sendbyte(&output_message, 's'); + pq_sendbyte(&output_message, PqReplMsg_PrimaryStatusUpdate); pq_sendint64(&output_message, lsn); pq_sendint64(&output_message, (int64) U64FromFullTransactionId(fullOldestXidInCommit)); pq_sendint64(&output_message, (int64) U64FromFullTransactionId(nextFullXid)); @@ -3364,7 +3367,7 @@ XLogSendPhysical(void) * OK to read and send the slice. */ resetStringInfo(&output_message); - pq_sendbyte(&output_message, 'w'); + pq_sendbyte(&output_message, PqReplMsg_WALData); pq_sendint64(&output_message, startptr); /* dataStart */ pq_sendint64(&output_message, SendRqstPtr); /* walEnd */ @@ -4135,7 +4138,7 @@ WalSndKeepalive(bool requestReply, XLogRecPtr writePtr) /* construct the message... */ resetStringInfo(&output_message); - pq_sendbyte(&output_message, 'k'); + pq_sendbyte(&output_message, PqReplMsg_Keepalive); pq_sendint64(&output_message, XLogRecPtrIsInvalid(writePtr) ? sentPtr : writePtr); pq_sendint64(&output_message, GetCurrentTimestamp()); pq_sendbyte(&output_message, requestReply ? 1 : 0); diff --git a/src/backend/statistics/mcv.c b/src/backend/statistics/mcv.c index d98cda698d9..f59fb821543 100644 --- a/src/backend/statistics/mcv.c +++ b/src/backend/statistics/mcv.c @@ -767,7 +767,7 @@ statext_mcv_serialize(MCVList *mcvlist, VacAttrStats **stats) values[dim][i] = PointerGetDatum(PG_DETOAST_DATUM(values[dim][i])); /* serialized length (uint32 length + data) */ - len = VARSIZE_ANY_EXHDR(values[dim][i]); + len = VARSIZE_ANY_EXHDR(DatumGetPointer(values[dim][i])); info[dim].nbytes += sizeof(uint32); /* length */ info[dim].nbytes += len; /* value (no header) */ diff --git a/src/backend/storage/file/fileset.c b/src/backend/storage/file/fileset.c index 64141c7cb91..4d5ee353fd7 100644 --- a/src/backend/storage/file/fileset.c +++ b/src/backend/storage/file/fileset.c @@ -185,7 +185,7 @@ FileSetPath(char *path, FileSet *fileset, Oid tablespace) static Oid ChooseTablespace(const FileSet *fileset, const char *name) { - uint32 hash = hash_any((const unsigned char *) name, strlen(name)); + uint32 hash = hash_bytes((const unsigned char *) name, strlen(name)); return fileset->tablespaces[hash % fileset->ntablespaces]; } diff --git a/src/backend/storage/large_object/inv_api.c b/src/backend/storage/large_object/inv_api.c index 68b76f2cc18..a874000c8ca 100644 --- a/src/backend/storage/large_object/inv_api.c +++ b/src/backend/storage/large_object/inv_api.c @@ -561,7 +561,7 @@ inv_write(LargeObjectDesc *obj_desc, const char *buf, int nbytes) char data[LOBLKSIZE + VARHDRSZ]; /* ensure union is aligned well enough: */ int32 align_it; - } workbuf; + } workbuf = {0}; char *workb = VARDATA(&workbuf.hdr); HeapTuple newtup; Datum values[Natts_pg_largeobject]; @@ -752,7 +752,7 @@ inv_truncate(LargeObjectDesc *obj_desc, int64 len) char data[LOBLKSIZE + VARHDRSZ]; /* ensure union is aligned well enough: */ int32 align_it; - } workbuf; + } workbuf = {0}; char *workb = VARDATA(&workbuf.hdr); HeapTuple newtup; Datum values[Natts_pg_largeobject]; diff --git a/src/backend/tsearch/ts_selfuncs.c b/src/backend/tsearch/ts_selfuncs.c index 0c1d2bc1109..453a5e5c2ea 100644 --- a/src/backend/tsearch/ts_selfuncs.c +++ b/src/backend/tsearch/ts_selfuncs.c @@ -233,7 +233,7 @@ mcelem_tsquery_selec(TSQuery query, Datum *mcelem, int nmcelem, * The text Datums came from an array, so it cannot be compressed or * stored out-of-line -- it's safe to use VARSIZE_ANY*. */ - Assert(!VARATT_IS_COMPRESSED(mcelem[i]) && !VARATT_IS_EXTERNAL(mcelem[i])); + Assert(!VARATT_IS_COMPRESSED(DatumGetPointer(mcelem[i])) && !VARATT_IS_EXTERNAL(DatumGetPointer(mcelem[i]))); lookup[i].element = (text *) DatumGetPointer(mcelem[i]); lookup[i].frequency = numbers[i]; } diff --git a/src/backend/utils/adt/jsonb_gin.c b/src/backend/utils/adt/jsonb_gin.c index c1950792b5a..9b56248cf0b 100644 --- a/src/backend/utils/adt/jsonb_gin.c +++ b/src/backend/utils/adt/jsonb_gin.c @@ -896,8 +896,8 @@ gin_extract_jsonb_query(PG_FUNCTION_ARGS) continue; /* We rely on the array elements not being toasted */ entries[j++] = make_text_key(JGINFLAG_KEY, - VARDATA_ANY(key_datums[i]), - VARSIZE_ANY_EXHDR(key_datums[i])); + VARDATA_ANY(DatumGetPointer(key_datums[i])), + VARSIZE_ANY_EXHDR(DatumGetPointer(key_datums[i]))); } *nentries = j; diff --git a/src/backend/utils/adt/jsonb_op.c b/src/backend/utils/adt/jsonb_op.c index fa5603f26e1..51d38e321fb 100644 --- a/src/backend/utils/adt/jsonb_op.c +++ b/src/backend/utils/adt/jsonb_op.c @@ -63,8 +63,8 @@ jsonb_exists_any(PG_FUNCTION_ARGS) strVal.type = jbvString; /* We rely on the array elements not being toasted */ - strVal.val.string.val = VARDATA_ANY(key_datums[i]); - strVal.val.string.len = VARSIZE_ANY_EXHDR(key_datums[i]); + strVal.val.string.val = VARDATA_ANY(DatumGetPointer(key_datums[i])); + strVal.val.string.len = VARSIZE_ANY_EXHDR(DatumGetPointer(key_datums[i])); if (findJsonbValueFromContainer(&jb->root, JB_FOBJECT | JB_FARRAY, @@ -96,8 +96,8 @@ jsonb_exists_all(PG_FUNCTION_ARGS) strVal.type = jbvString; /* We rely on the array elements not being toasted */ - strVal.val.string.val = VARDATA_ANY(key_datums[i]); - strVal.val.string.len = VARSIZE_ANY_EXHDR(key_datums[i]); + strVal.val.string.val = VARDATA_ANY(DatumGetPointer(key_datums[i])); + strVal.val.string.len = VARSIZE_ANY_EXHDR(DatumGetPointer(key_datums[i])); if (findJsonbValueFromContainer(&jb->root, JB_FOBJECT | JB_FARRAY, diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index bcb1720b6cd..370456408bf 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -4766,8 +4766,8 @@ jsonb_delete_array(PG_FUNCTION_ARGS) continue; /* We rely on the array elements not being toasted */ - keyptr = VARDATA_ANY(keys_elems[i]); - keylen = VARSIZE_ANY_EXHDR(keys_elems[i]); + keyptr = VARDATA_ANY(DatumGetPointer(keys_elems[i])); + keylen = VARSIZE_ANY_EXHDR(DatumGetPointer(keys_elems[i])); if (keylen == v.val.string.len && memcmp(keyptr, v.val.string.val, keylen) == 0) { diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c index dbab24737ef..407041b14a1 100644 --- a/src/backend/utils/adt/jsonpath_exec.c +++ b/src/backend/utils/adt/jsonpath_exec.c @@ -3074,8 +3074,8 @@ JsonItemFromDatum(Datum val, Oid typid, int32 typmod, JsonbValue *res) case TEXTOID: case VARCHAROID: res->type = jbvString; - res->val.string.val = VARDATA_ANY(val); - res->val.string.len = VARSIZE_ANY_EXHDR(val); + res->val.string.val = VARDATA_ANY(DatumGetPointer(val)); + res->val.string.len = VARSIZE_ANY_EXHDR(DatumGetPointer(val)); break; case DATEOID: case TIMEOID: diff --git a/src/backend/utils/adt/multirangetypes.c b/src/backend/utils/adt/multirangetypes.c index cd84ced5b48..46f2ec0c29f 100644 --- a/src/backend/utils/adt/multirangetypes.c +++ b/src/backend/utils/adt/multirangetypes.c @@ -394,12 +394,13 @@ multirange_send(PG_FUNCTION_ARGS) for (int i = 0; i < range_count; i++) { Datum range; + bytea *outputbytes; range = RangeTypePGetDatum(ranges[i]); - range = PointerGetDatum(SendFunctionCall(&cache->typioproc, range)); + outputbytes = SendFunctionCall(&cache->typioproc, range); - pq_sendint32(buf, VARSIZE(range) - VARHDRSZ); - pq_sendbytes(buf, VARDATA(range), VARSIZE(range) - VARHDRSZ); + pq_sendint32(buf, VARSIZE(outputbytes) - VARHDRSZ); + pq_sendbytes(buf, VARDATA(outputbytes), VARSIZE(outputbytes) - VARHDRSZ); } PG_RETURN_BYTEA_P(pq_endtypsend(buf)); @@ -2833,7 +2834,7 @@ hash_multirange(PG_FUNCTION_ARGS) upper_hash = 0; /* Merge hashes of flags and bounds */ - range_hash = hash_uint32((uint32) flags); + range_hash = hash_bytes_uint32((uint32) flags); range_hash ^= lower_hash; range_hash = pg_rotate_left32(range_hash, 1); range_hash ^= upper_hash; diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 1c12ddbae49..c756c2bebaa 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -2171,7 +2171,7 @@ pg_stat_get_replication_slot(PG_FUNCTION_ARGS) Datum pg_stat_get_subscription_stats(PG_FUNCTION_ARGS) { -#define PG_STAT_GET_SUBSCRIPTION_STATS_COLS 11 +#define PG_STAT_GET_SUBSCRIPTION_STATS_COLS 12 Oid subid = PG_GETARG_OID(0); TupleDesc tupdesc; Datum values[PG_STAT_GET_SUBSCRIPTION_STATS_COLS] = {0}; @@ -2197,15 +2197,17 @@ pg_stat_get_subscription_stats(PG_FUNCTION_ARGS) INT8OID, -1, 0); TupleDescInitEntry(tupdesc, (AttrNumber) 6, "confl_update_exists", INT8OID, -1, 0); - TupleDescInitEntry(tupdesc, (AttrNumber) 7, "confl_update_missing", + TupleDescInitEntry(tupdesc, (AttrNumber) 7, "confl_update_deleted", INT8OID, -1, 0); - TupleDescInitEntry(tupdesc, (AttrNumber) 8, "confl_delete_origin_differs", + TupleDescInitEntry(tupdesc, (AttrNumber) 8, "confl_update_missing", INT8OID, -1, 0); - TupleDescInitEntry(tupdesc, (AttrNumber) 9, "confl_delete_missing", + TupleDescInitEntry(tupdesc, (AttrNumber) 9, "confl_delete_origin_differs", INT8OID, -1, 0); - TupleDescInitEntry(tupdesc, (AttrNumber) 10, "confl_multiple_unique_conflicts", + TupleDescInitEntry(tupdesc, (AttrNumber) 10, "confl_delete_missing", INT8OID, -1, 0); - TupleDescInitEntry(tupdesc, (AttrNumber) 11, "stats_reset", + TupleDescInitEntry(tupdesc, (AttrNumber) 11, "confl_multiple_unique_conflicts", + INT8OID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 12, "stats_reset", TIMESTAMPTZOID, -1, 0); BlessTupleDesc(tupdesc); diff --git a/src/backend/utils/adt/rangetypes.c b/src/backend/utils/adt/rangetypes.c index 66cc0acf4a7..c83b239b3bb 100644 --- a/src/backend/utils/adt/rangetypes.c +++ b/src/backend/utils/adt/rangetypes.c @@ -285,8 +285,7 @@ range_send(PG_FUNCTION_ARGS) if (RANGE_HAS_LBOUND(flags)) { - Datum bound = PointerGetDatum(SendFunctionCall(&cache->typioproc, - lower.val)); + bytea *bound = SendFunctionCall(&cache->typioproc, lower.val); uint32 bound_len = VARSIZE(bound) - VARHDRSZ; char *bound_data = VARDATA(bound); @@ -296,8 +295,7 @@ range_send(PG_FUNCTION_ARGS) if (RANGE_HAS_UBOUND(flags)) { - Datum bound = PointerGetDatum(SendFunctionCall(&cache->typioproc, - upper.val)); + bytea *bound = SendFunctionCall(&cache->typioproc, upper.val); uint32 bound_len = VARSIZE(bound) - VARHDRSZ; char *bound_data = VARDATA(bound); @@ -1444,7 +1442,7 @@ hash_range(PG_FUNCTION_ARGS) upper_hash = 0; /* Merge hashes of flags and bounds */ - result = hash_uint32((uint32) flags); + result = hash_bytes_uint32((uint32) flags); result ^= lower_hash; result = pg_rotate_left32(result, 1); result ^= upper_hash; diff --git a/src/backend/utils/adt/tsvector_op.c b/src/backend/utils/adt/tsvector_op.c index 1fa1275ca63..0625da9532f 100644 --- a/src/backend/utils/adt/tsvector_op.c +++ b/src/backend/utils/adt/tsvector_op.c @@ -329,8 +329,8 @@ tsvector_setweight_by_filter(PG_FUNCTION_ARGS) if (nulls[i]) continue; - lex = VARDATA(dlexemes[i]); - lex_len = VARSIZE(dlexemes[i]) - VARHDRSZ; + lex = VARDATA(DatumGetPointer(dlexemes[i])); + lex_len = VARSIZE(DatumGetPointer(dlexemes[i])) - VARHDRSZ; lex_pos = tsvector_bsearch(tsout, lex, lex_len); if (lex_pos >= 0 && (j = POSDATALEN(tsout, entry + lex_pos)) != 0) @@ -443,10 +443,10 @@ compare_text_lexemes(const void *va, const void *vb) { Datum a = *((const Datum *) va); Datum b = *((const Datum *) vb); - char *alex = VARDATA_ANY(a); - int alex_len = VARSIZE_ANY_EXHDR(a); - char *blex = VARDATA_ANY(b); - int blex_len = VARSIZE_ANY_EXHDR(b); + char *alex = VARDATA_ANY(DatumGetPointer(a)); + int alex_len = VARSIZE_ANY_EXHDR(DatumGetPointer(a)); + char *blex = VARDATA_ANY(DatumGetPointer(b)); + int blex_len = VARSIZE_ANY_EXHDR(DatumGetPointer(b)); return tsCompareString(alex, alex_len, blex, blex_len, false); } @@ -605,8 +605,8 @@ tsvector_delete_arr(PG_FUNCTION_ARGS) if (nulls[i]) continue; - lex = VARDATA(dlexemes[i]); - lex_len = VARSIZE(dlexemes[i]) - VARHDRSZ; + lex = VARDATA(DatumGetPointer(dlexemes[i])); + lex_len = VARSIZE(DatumGetPointer(dlexemes[i])) - VARHDRSZ; lex_pos = tsvector_bsearch(tsin, lex, lex_len); if (lex_pos >= 0) @@ -770,7 +770,7 @@ array_to_tsvector(PG_FUNCTION_ARGS) (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), errmsg("lexeme array may not contain nulls"))); - if (VARSIZE(dlexemes[i]) - VARHDRSZ == 0) + if (VARSIZE(DatumGetPointer(dlexemes[i])) - VARHDRSZ == 0) ereport(ERROR, (errcode(ERRCODE_ZERO_LENGTH_CHARACTER_STRING), errmsg("lexeme array may not contain empty strings"))); @@ -786,7 +786,7 @@ array_to_tsvector(PG_FUNCTION_ARGS) /* Calculate space needed for surviving lexemes. */ for (i = 0; i < nitems; i++) - datalen += VARSIZE(dlexemes[i]) - VARHDRSZ; + datalen += VARSIZE(DatumGetPointer(dlexemes[i])) - VARHDRSZ; tslen = CALCDATASIZE(nitems, datalen); /* Allocate and fill tsvector. */ @@ -798,8 +798,8 @@ array_to_tsvector(PG_FUNCTION_ARGS) cur = STRPTR(tsout); for (i = 0; i < nitems; i++) { - char *lex = VARDATA(dlexemes[i]); - int lex_len = VARSIZE(dlexemes[i]) - VARHDRSZ; + char *lex = VARDATA(DatumGetPointer(dlexemes[i])); + int lex_len = VARSIZE(DatumGetPointer(dlexemes[i])) - VARHDRSZ; memcpy(cur, lex, lex_len); arrout[i].haspos = 0; diff --git a/src/backend/utils/cache/catcache.c b/src/backend/utils/cache/catcache.c index d1b25214376..e2cd3feaf81 100644 --- a/src/backend/utils/cache/catcache.c +++ b/src/backend/utils/cache/catcache.c @@ -213,7 +213,7 @@ namehashfast(Datum datum) { char *key = NameStr(*DatumGetName(datum)); - return hash_any((unsigned char *) key, strlen(key)); + return hash_bytes((unsigned char *) key, strlen(key)); } static bool diff --git a/src/backend/utils/error/csvlog.c b/src/backend/utils/error/csvlog.c index fdac3c048e3..c3159ed7d97 100644 --- a/src/backend/utils/error/csvlog.c +++ b/src/backend/utils/error/csvlog.c @@ -120,7 +120,7 @@ write_csvlog(ErrorData *edata) appendStringInfoChar(&buf, ','); /* session id */ - appendStringInfo(&buf, INT64_HEX_FORMAT ".%x", MyStartTime, MyProcPid); + appendStringInfo(&buf, "%" PRIx64 ".%x", MyStartTime, MyProcPid); appendStringInfoChar(&buf, ','); /* Line number */ diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 47af743990f..b7b9692f8c8 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -1128,12 +1128,15 @@ set_backtrace(ErrorData *edata, int num_skip) nframes = backtrace(buf, lengthof(buf)); strfrms = backtrace_symbols(buf, nframes); - if (strfrms == NULL) - return; - - for (int i = num_skip; i < nframes; i++) - appendStringInfo(&errtrace, "\n%s", strfrms[i]); - free(strfrms); + if (strfrms != NULL) + { + for (int i = num_skip; i < nframes; i++) + appendStringInfo(&errtrace, "\n%s", strfrms[i]); + free(strfrms); + } + else + appendStringInfoString(&errtrace, + "insufficient memory for backtrace generation"); } #else appendStringInfoString(&errtrace, @@ -2956,12 +2959,12 @@ log_status_format(StringInfo buf, const char *format, ErrorData *edata) { char strfbuf[128]; - snprintf(strfbuf, sizeof(strfbuf) - 1, INT64_HEX_FORMAT ".%x", + snprintf(strfbuf, sizeof(strfbuf) - 1, "%" PRIx64 ".%x", MyStartTime, MyProcPid); appendStringInfo(buf, "%*s", padding, strfbuf); } else - appendStringInfo(buf, INT64_HEX_FORMAT ".%x", MyStartTime, MyProcPid); + appendStringInfo(buf, "%" PRIx64 ".%x", MyStartTime, MyProcPid); break; case 'p': if (padding != 0) diff --git a/src/backend/utils/error/jsonlog.c b/src/backend/utils/error/jsonlog.c index 519eacf17f8..2619f499042 100644 --- a/src/backend/utils/error/jsonlog.c +++ b/src/backend/utils/error/jsonlog.c @@ -168,7 +168,7 @@ write_jsonlog(ErrorData *edata) } /* Session id */ - appendJSONKeyValueFmt(&buf, "session_id", true, INT64_HEX_FORMAT ".%x", + appendJSONKeyValueFmt(&buf, "session_id", true, "%" PRIx64 ".%x", MyStartTime, MyProcPid); /* Line number */ diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 55621f35fb6..0a3ca4315de 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -35,6 +35,7 @@ #include "fe_utils/option_utils.h" #include "fe_utils/recovery_gen.h" #include "getopt_long.h" +#include "libpq/protocol.h" #include "receivelog.h" #include "streamutil.h" @@ -1338,7 +1339,7 @@ ReceiveArchiveStreamChunk(size_t r, char *copybuf, void *callback_data) /* Each CopyData message begins with a type byte. */ switch (GetCopyDataByte(r, copybuf, &cursor)) { - case 'n': + case PqBackupMsg_NewArchive: { /* New archive. */ char *archive_name; @@ -1410,7 +1411,7 @@ ReceiveArchiveStreamChunk(size_t r, char *copybuf, void *callback_data) break; } - case 'd': + case PqMsg_CopyData: { /* Archive or manifest data. */ if (state->manifest_buffer != NULL) @@ -1446,7 +1447,7 @@ ReceiveArchiveStreamChunk(size_t r, char *copybuf, void *callback_data) break; } - case 'p': + case PqBackupMsg_ProgressReport: { /* * Progress report. @@ -1465,7 +1466,7 @@ ReceiveArchiveStreamChunk(size_t r, char *copybuf, void *callback_data) break; } - case 'm': + case PqBackupMsg_Manifest: { /* * Manifest data will be sent next. This message is not diff --git a/src/bin/pg_basebackup/pg_recvlogical.c b/src/bin/pg_basebackup/pg_recvlogical.c index 8a5dd24e6c9..7a4d1a2d2ca 100644 --- a/src/bin/pg_basebackup/pg_recvlogical.c +++ b/src/bin/pg_basebackup/pg_recvlogical.c @@ -24,6 +24,7 @@ #include "getopt_long.h" #include "libpq-fe.h" #include "libpq/pqsignal.h" +#include "libpq/protocol.h" #include "pqexpbuffer.h" #include "streamutil.h" @@ -149,7 +150,7 @@ sendFeedback(PGconn *conn, TimestampTz now, bool force, bool replyRequested) LSN_FORMAT_ARGS(output_fsync_lsn), replication_slot); - replybuf[len] = 'r'; + replybuf[len] = PqReplMsg_StandbyStatusUpdate; len += 1; fe_sendint64(output_written_lsn, &replybuf[len]); /* write */ len += 8; @@ -454,7 +455,7 @@ StreamLogicalLog(void) } /* Check the message type. */ - if (copybuf[0] == 'k') + if (copybuf[0] == PqReplMsg_Keepalive) { int pos; bool replyRequested; @@ -466,7 +467,7 @@ StreamLogicalLog(void) * We just check if the server requested a reply, and ignore the * rest. */ - pos = 1; /* skip msgtype 'k' */ + pos = 1; /* skip msgtype PqReplMsg_Keepalive */ walEnd = fe_recvint64(©buf[pos]); output_written_lsn = Max(walEnd, output_written_lsn); @@ -509,7 +510,7 @@ StreamLogicalLog(void) continue; } - else if (copybuf[0] != 'w') + else if (copybuf[0] != PqReplMsg_WALData) { pg_log_error("unrecognized streaming header: \"%c\"", copybuf[0]); @@ -517,11 +518,11 @@ StreamLogicalLog(void) } /* - * Read the header of the XLogData message, enclosed in the CopyData + * Read the header of the WALData message, enclosed in the CopyData * message. We only need the WAL location field (dataStart), the rest * of the header is ignored. */ - hdr_len = 1; /* msgtype 'w' */ + hdr_len = 1; /* msgtype PqReplMsg_WALData */ hdr_len += 8; /* dataStart */ hdr_len += 8; /* walEnd */ hdr_len += 8; /* sendTime */ @@ -605,7 +606,7 @@ StreamLogicalLog(void) /* * We're doing a client-initiated clean exit and have sent CopyDone to * the server. Drain any messages, so we don't miss a last-minute - * ErrorResponse. The walsender stops generating XLogData records once + * ErrorResponse. The walsender stops generating WALData records once * it sees CopyDone, so expect this to finish quickly. After CopyDone, * it's too late for sendFeedback(), even if this were to take a long * time. Hence, use synchronous-mode PQgetCopyData(). diff --git a/src/bin/pg_basebackup/receivelog.c b/src/bin/pg_basebackup/receivelog.c index d6b7f117fa3..25b13c7f55c 100644 --- a/src/bin/pg_basebackup/receivelog.c +++ b/src/bin/pg_basebackup/receivelog.c @@ -21,6 +21,7 @@ #include "access/xlog_internal.h" #include "common/logging.h" #include "libpq-fe.h" +#include "libpq/protocol.h" #include "receivelog.h" #include "streamutil.h" @@ -38,8 +39,8 @@ static int CopyStreamReceive(PGconn *conn, long timeout, pgsocket stop_socket, char **buffer); static bool ProcessKeepaliveMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, XLogRecPtr blockpos, TimestampTz *last_status); -static bool ProcessXLogDataMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, - XLogRecPtr *blockpos); +static bool ProcessWALDataMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, + XLogRecPtr *blockpos); static PGresult *HandleEndOfCopyStream(PGconn *conn, StreamCtl *stream, char *copybuf, XLogRecPtr blockpos, XLogRecPtr *stoppos); static bool CheckCopyStreamStop(PGconn *conn, StreamCtl *stream, XLogRecPtr blockpos); @@ -338,7 +339,7 @@ sendFeedback(PGconn *conn, XLogRecPtr blockpos, TimestampTz now, bool replyReque char replybuf[1 + 8 + 8 + 8 + 8 + 1]; int len = 0; - replybuf[len] = 'r'; + replybuf[len] = PqReplMsg_StandbyStatusUpdate; len += 1; fe_sendint64(blockpos, &replybuf[len]); /* write */ len += 8; @@ -823,15 +824,15 @@ HandleCopyStream(PGconn *conn, StreamCtl *stream, } /* Check the message type. */ - if (copybuf[0] == 'k') + if (copybuf[0] == PqReplMsg_Keepalive) { if (!ProcessKeepaliveMsg(conn, stream, copybuf, r, blockpos, &last_status)) goto error; } - else if (copybuf[0] == 'w') + else if (copybuf[0] == PqReplMsg_WALData) { - if (!ProcessXLogDataMsg(conn, stream, copybuf, r, &blockpos)) + if (!ProcessWALDataMsg(conn, stream, copybuf, r, &blockpos)) goto error; /* @@ -1001,7 +1002,7 @@ ProcessKeepaliveMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, * Parse the keepalive message, enclosed in the CopyData message. We just * check if the server requested a reply, and ignore the rest. */ - pos = 1; /* skip msgtype 'k' */ + pos = 1; /* skip msgtype PqReplMsg_Keepalive */ pos += 8; /* skip walEnd */ pos += 8; /* skip sendTime */ @@ -1041,11 +1042,11 @@ ProcessKeepaliveMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, } /* - * Process XLogData message. + * Process WALData message. */ static bool -ProcessXLogDataMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, - XLogRecPtr *blockpos) +ProcessWALDataMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, + XLogRecPtr *blockpos) { int xlogoff; int bytes_left; @@ -1054,17 +1055,17 @@ ProcessXLogDataMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, /* * Once we've decided we don't want to receive any more, just ignore any - * subsequent XLogData messages. + * subsequent WALData messages. */ if (!(still_sending)) return true; /* - * Read the header of the XLogData message, enclosed in the CopyData + * Read the header of the WALData message, enclosed in the CopyData * message. We only need the WAL location field (dataStart), the rest of * the header is ignored. */ - hdr_len = 1; /* msgtype 'w' */ + hdr_len = 1; /* msgtype PqReplMsg_WALData */ hdr_len += 8; /* dataStart */ hdr_len += 8; /* walEnd */ hdr_len += 8; /* sendTime */ @@ -1162,7 +1163,7 @@ ProcessXLogDataMsg(PGconn *conn, StreamCtl *stream, char *copybuf, int len, return false; } still_sending = false; - return true; /* ignore the rest of this XLogData packet */ + return true; /* ignore the rest of this WALData packet */ } } } diff --git a/src/bin/pg_upgrade/t/002_pg_upgrade.pl b/src/bin/pg_upgrade/t/002_pg_upgrade.pl index 7d82593879d..0b15e38297e 100644 --- a/src/bin/pg_upgrade/t/002_pg_upgrade.pl +++ b/src/bin/pg_upgrade/t/002_pg_upgrade.pl @@ -375,6 +375,9 @@ SKIP: { my $dstnode = PostgreSQL::Test::Cluster->new('dst_node'); + skip "regress_dump_restore not enabled in PG_TEST_EXTRA" + if (!$ENV{PG_TEST_EXTRA} + || $ENV{PG_TEST_EXTRA} !~ /\bregress_dump_restore\b/); skip "different Postgres versions" if ($oldnode->pg_version != $dstnode->pg_version); skip "source node not using default install" diff --git a/src/include/access/reloptions.h b/src/include/access/reloptions.h index dfbb4c85460..a604a4702c3 100644 --- a/src/include/access/reloptions.h +++ b/src/include/access/reloptions.h @@ -233,7 +233,7 @@ extern void add_local_string_reloption(local_relopts *relopts, const char *name, fill_string_relopt filler, int offset); extern Datum transformRelOptions(Datum oldOptions, List *defList, - const char *namspace, const char *const validnsps[], + const char *nameSpace, const char *const validnsps[], bool acceptOidsOff, bool isReset); extern List *untransformRelOptions(Datum options); extern bytea *extractRelOptions(HeapTuple tuple, TupleDesc tupdesc, diff --git a/src/include/backup/basebackup_sink.h b/src/include/backup/basebackup_sink.h index 8a5ee996a45..310d92b8b9d 100644 --- a/src/include/backup/basebackup_sink.h +++ b/src/include/backup/basebackup_sink.h @@ -287,7 +287,8 @@ extern bbsink *bbsink_copystream_new(bool send_to_client); extern bbsink *bbsink_gzip_new(bbsink *next, pg_compress_specification *); extern bbsink *bbsink_lz4_new(bbsink *next, pg_compress_specification *); extern bbsink *bbsink_zstd_new(bbsink *next, pg_compress_specification *); -extern bbsink *bbsink_progress_new(bbsink *next, bool estimate_backup_size); +extern bbsink *bbsink_progress_new(bbsink *next, bool estimate_backup_size, + bool incremental); extern bbsink *bbsink_server_new(bbsink *next, char *pathname); extern bbsink *bbsink_throttle_new(bbsink *next, uint32 maxrate); diff --git a/src/include/c.h b/src/include/c.h index 6d4495bdd9f..bbdaa88c63a 100644 --- a/src/include/c.h +++ b/src/include/c.h @@ -530,8 +530,6 @@ typedef uint32 bits32; /* >= 32 bits */ /* snprintf format strings to use for 64-bit integers */ #define INT64_FORMAT "%" PRId64 #define UINT64_FORMAT "%" PRIu64 -#define INT64_HEX_FORMAT "%" PRIx64 -#define UINT64_HEX_FORMAT "%" PRIx64 /* * 128-bit signed and unsigned integers diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h index 5173d422d46..c4fe8b991af 100644 --- a/src/include/catalog/catversion.h +++ b/src/include/catalog/catversion.h @@ -57,6 +57,6 @@ */ /* yyyymmddN */ -#define CATALOG_VERSION_NO 202507231 +#define CATALOG_VERSION_NO 202508051 #endif diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 3ee8fed7e53..118d6da1ace 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -5688,9 +5688,9 @@ { oid => '6231', descr => 'statistics: information about subscription stats', proname => 'pg_stat_get_subscription_stats', provolatile => 's', proparallel => 'r', prorettype => 'record', proargtypes => 'oid', - proallargtypes => '{oid,oid,int8,int8,int8,int8,int8,int8,int8,int8,int8,timestamptz}', - proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o}', - proargnames => '{subid,subid,apply_error_count,sync_error_count,confl_insert_exists,confl_update_origin_differs,confl_update_exists,confl_update_missing,confl_delete_origin_differs,confl_delete_missing,confl_multiple_unique_conflicts,stats_reset}', + proallargtypes => '{oid,oid,int8,int8,int8,int8,int8,int8,int8,int8,int8,int8,timestamptz}', + proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o}', + proargnames => '{subid,subid,apply_error_count,sync_error_count,confl_insert_exists,confl_update_origin_differs,confl_update_exists,confl_update_deleted,confl_update_missing,confl_delete_origin_differs,confl_delete_missing,confl_multiple_unique_conflicts,stats_reset}', prosrc => 'pg_stat_get_subscription_stats' }, { oid => '6118', descr => 'statistics: information about subscription', proname => 'pg_stat_get_subscription', prorows => '10', proisstrict => 'f', diff --git a/src/include/commands/progress.h b/src/include/commands/progress.h index 7c736e7b03b..1cde4bd9bcf 100644 --- a/src/include/commands/progress.h +++ b/src/include/commands/progress.h @@ -130,6 +130,7 @@ #define PROGRESS_BASEBACKUP_BACKUP_STREAMED 2 #define PROGRESS_BASEBACKUP_TBLSPC_TOTAL 3 #define PROGRESS_BASEBACKUP_TBLSPC_STREAMED 4 +#define PROGRESS_BASEBACKUP_BACKUP_TYPE 5 /* Phases of pg_basebackup (as advertised via PROGRESS_BASEBACKUP_PHASE) */ #define PROGRESS_BASEBACKUP_PHASE_WAIT_CHECKPOINT 1 @@ -138,6 +139,10 @@ #define PROGRESS_BASEBACKUP_PHASE_WAIT_WAL_ARCHIVE 4 #define PROGRESS_BASEBACKUP_PHASE_TRANSFER_WAL 5 +/* Types of pg_basebackup (as advertised via PROGRESS_BASEBACKUP_BACKUP_TYPE) */ +#define PROGRESS_BASEBACKUP_BACKUP_TYPE_FULL 1 +#define PROGRESS_BASEBACKUP_BACKUP_TYPE_INCREMENTAL 2 + /* Progress parameters for PROGRESS_COPY */ #define PROGRESS_COPY_BYTES_PROCESSED 0 #define PROGRESS_COPY_BYTES_TOTAL 1 diff --git a/src/include/common/int128.h b/src/include/common/int128.h index a50f5709c29..8c300e56d9a 100644 --- a/src/include/common/int128.h +++ b/src/include/common/int128.h @@ -6,7 +6,7 @@ * We make use of the native int128 type if there is one, otherwise * implement things the hard way based on two int64 halves. * - * See src/tools/testint128.c for a simple test harness for this file. + * See src/test/modules/test_int128 for a simple test harness for this file. * * Copyright (c) 2017-2025, PostgreSQL Global Development Group * @@ -29,81 +29,21 @@ #endif #endif - -#if USE_NATIVE_INT128 - -typedef int128 INT128; - -/* - * Add an unsigned int64 value into an INT128 variable. - */ -static inline void -int128_add_uint64(INT128 *i128, uint64 v) -{ - *i128 += v; -} - /* - * Add a signed int64 value into an INT128 variable. - */ -static inline void -int128_add_int64(INT128 *i128, int64 v) -{ - *i128 += v; -} - -/* - * Add the 128-bit product of two int64 values into an INT128 variable. + * If native int128 support is enabled, INT128 is just int128. Otherwise, it + * is a structure with separate 64-bit high and low parts. * - * XXX with a stupid compiler, this could actually be less efficient than - * the other implementation; maybe we should do it by hand always? - */ -static inline void -int128_add_int64_mul_int64(INT128 *i128, int64 x, int64 y) -{ - *i128 += (int128) x * (int128) y; -} - -/* - * Compare two INT128 values, return -1, 0, or +1. - */ -static inline int -int128_compare(INT128 x, INT128 y) -{ - if (x < y) - return -1; - if (x > y) - return 1; - return 0; -} - -/* - * Widen int64 to INT128. - */ -static inline INT128 -int64_to_int128(int64 v) -{ - return (INT128) v; -} - -/* - * Convert INT128 to int64 (losing any high-order bits). - * This also works fine for casting down to uint64. - */ -static inline int64 -int128_to_int64(INT128 val) -{ - return (int64) val; -} - -#else /* !USE_NATIVE_INT128 */ - -/* * We lay out the INT128 structure with the same content and byte ordering * that a native int128 type would (probably) have. This makes no difference * for ordinary use of INT128, but allows union'ing INT128 with int128 for * testing purposes. */ +#if USE_NATIVE_INT128 + +typedef int128 INT128; + +#else + typedef struct { #ifdef WORDS_BIGENDIAN @@ -115,12 +55,17 @@ typedef struct #endif } INT128; +#endif + /* * Add an unsigned int64 value into an INT128 variable. */ static inline void int128_add_uint64(INT128 *i128, uint64 v) { +#if USE_NATIVE_INT128 + *i128 += v; +#else /* * First add the value to the .lo part, then check to see if a carry needs * to be propagated into the .hi part. A carry is needed if both inputs @@ -134,6 +79,7 @@ int128_add_uint64(INT128 *i128, uint64 v) if (((int64) v < 0 && (int64) oldlo < 0) || (((int64) v < 0 || (int64) oldlo < 0) && (int64) i128->lo >= 0)) i128->hi++; +#endif } /* @@ -142,6 +88,9 @@ int128_add_uint64(INT128 *i128, uint64 v) static inline void int128_add_int64(INT128 *i128, int64 v) { +#if USE_NATIVE_INT128 + *i128 += v; +#else /* * This is much like the above except that the carry logic differs for * negative v. Ordinarily we'd need to subtract 1 from the .hi part @@ -161,6 +110,7 @@ int128_add_int64(INT128 *i128, int64 v) if (!((int64) oldlo < 0 || (int64) i128->lo >= 0)) i128->hi--; } +#endif } /* @@ -176,6 +126,13 @@ int128_add_int64(INT128 *i128, int64 v) static inline void int128_add_int64_mul_int64(INT128 *i128, int64 x, int64 y) { +#if USE_NATIVE_INT128 + /* + * XXX with a stupid compiler, this could actually be less efficient than + * the non-native implementation; maybe we should do it by hand always? + */ + *i128 += (int128) x * (int128) y; +#else /* INT64_AU32 must use arithmetic right shift */ StaticAssertDecl(((int64) -1 >> 1) == (int64) -1, "arithmetic right shift is needed"); @@ -229,6 +186,7 @@ int128_add_int64_mul_int64(INT128 *i128, int64 x, int64 y) /* the fourth term: always unsigned */ int128_add_uint64(i128, x_l32 * y_l32); } +#endif } /* @@ -237,6 +195,13 @@ int128_add_int64_mul_int64(INT128 *i128, int64 x, int64 y) static inline int int128_compare(INT128 x, INT128 y) { +#if USE_NATIVE_INT128 + if (x < y) + return -1; + if (x > y) + return 1; + return 0; +#else if (x.hi < y.hi) return -1; if (x.hi > y.hi) @@ -246,6 +211,7 @@ int128_compare(INT128 x, INT128 y) if (x.lo > y.lo) return 1; return 0; +#endif } /* @@ -254,11 +220,15 @@ int128_compare(INT128 x, INT128 y) static inline INT128 int64_to_int128(int64 v) { +#if USE_NATIVE_INT128 + return (INT128) v; +#else INT128 val; val.lo = (uint64) v; val.hi = (v < 0) ? -INT64CONST(1) : INT64CONST(0); return val; +#endif } /* @@ -268,9 +238,11 @@ int64_to_int128(int64 v) static inline int64 int128_to_int64(INT128 val) { +#if USE_NATIVE_INT128 + return (int64) val; +#else return (int64) val.lo; +#endif } -#endif /* USE_NATIVE_INT128 */ - #endif /* INT128_H */ diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h index 104b059544d..a71502efeed 100644 --- a/src/include/executor/executor.h +++ b/src/include/executor/executor.h @@ -14,6 +14,7 @@ #ifndef EXECUTOR_H #define EXECUTOR_H +#include "datatype/timestamp.h" #include "executor/execdesc.h" #include "fmgr.h" #include "nodes/lockoptions.h" @@ -759,7 +760,18 @@ extern bool RelationFindReplTupleByIndex(Relation rel, Oid idxoid, TupleTableSlot *outslot); extern bool RelationFindReplTupleSeq(Relation rel, LockTupleMode lockmode, TupleTableSlot *searchslot, TupleTableSlot *outslot); - +extern bool RelationFindDeletedTupleInfoSeq(Relation rel, + TupleTableSlot *searchslot, + TransactionId oldestxmin, + TransactionId *delete_xid, + RepOriginId *delete_origin, + TimestampTz *delete_time); +extern bool RelationFindDeletedTupleInfoByIndex(Relation rel, Oid idxoid, + TupleTableSlot *searchslot, + TransactionId oldestxmin, + TransactionId *delete_xid, + RepOriginId *delete_origin, + TimestampTz *delete_time); extern void ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo, EState *estate, TupleTableSlot *slot); extern void ExecSimpleRelationUpdate(ResultRelInfo *resultRelInfo, diff --git a/src/include/libpq/protocol.h b/src/include/libpq/protocol.h index b0bcb3cdc26..c64e628628d 100644 --- a/src/include/libpq/protocol.h +++ b/src/include/libpq/protocol.h @@ -69,6 +69,27 @@ #define PqMsg_Progress 'P' +/* Replication codes sent by the primary (wrapped in CopyData messages). */ + +#define PqReplMsg_Keepalive 'k' +#define PqReplMsg_PrimaryStatusUpdate 's' +#define PqReplMsg_WALData 'w' + + +/* Replication codes sent by the standby (wrapped in CopyData messages). */ + +#define PqReplMsg_HotStandbyFeedback 'h' +#define PqReplMsg_PrimaryStatusRequest 'p' +#define PqReplMsg_StandbyStatusUpdate 'r' + + +/* Codes used for backups via COPY OUT (wrapped in CopyData messages). */ + +#define PqBackupMsg_Manifest 'm' +#define PqBackupMsg_NewArchive 'n' +#define PqBackupMsg_ProgressReport 'p' + + /* These are the authentication request codes sent by the backend. */ #define AUTH_REQ_OK 0 /* User is authenticated */ diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h index 6c59125f256..ff3cb8416ec 100644 --- a/src/include/replication/conflict.h +++ b/src/include/replication/conflict.h @@ -32,6 +32,9 @@ typedef enum /* The updated row value violates unique constraint */ CT_UPDATE_EXISTS, + /* The row to be updated was concurrently deleted by a different origin */ + CT_UPDATE_DELETED, + /* The row to be updated is missing */ CT_UPDATE_MISSING, diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index 0c7b8440a61..7c0204dd6f4 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -87,8 +87,9 @@ typedef struct LogicalRepWorker bool parallel_apply; /* - * The changes made by this and later transactions must be retained to - * ensure reliable conflict detection during the apply phase. + * Changes made by this transaction and subsequent ones must be preserved. + * This ensures that update_deleted conflicts can be accurately detected + * during the apply phase of logical replication by this worker. * * The logical replication launcher manages an internal replication slot * named "pg_conflict_detection". It asynchronously collects this ID to diff --git a/src/include/varatt.h b/src/include/varatt.h index 2e8564d4998..aeeabf9145b 100644 --- a/src/include/varatt.h +++ b/src/include/varatt.h @@ -89,20 +89,35 @@ typedef enum vartag_external VARTAG_ONDISK = 18 } vartag_external; +/* Is a TOAST pointer either type of expanded-object pointer? */ /* this test relies on the specific tag values above */ -#define VARTAG_IS_EXPANDED(tag) \ - (((tag) & ~1) == VARTAG_EXPANDED_RO) +static inline bool +VARTAG_IS_EXPANDED(vartag_external tag) +{ + return ((tag & ~1) == VARTAG_EXPANDED_RO); +} -#define VARTAG_SIZE(tag) \ - ((tag) == VARTAG_INDIRECT ? sizeof(varatt_indirect) : \ - VARTAG_IS_EXPANDED(tag) ? sizeof(varatt_expanded) : \ - (tag) == VARTAG_ONDISK ? sizeof(varatt_external) : \ - (AssertMacro(false), 0)) +/* Size of the data part of a "TOAST pointer" datum */ +static inline Size +VARTAG_SIZE(vartag_external tag) +{ + if (tag == VARTAG_INDIRECT) + return sizeof(varatt_indirect); + else if (VARTAG_IS_EXPANDED(tag)) + return sizeof(varatt_expanded); + else if (tag == VARTAG_ONDISK) + return sizeof(varatt_external); + else + { + Assert(false); + return 0; + } +} /* * These structs describe the header of a varlena object that may have been * TOASTed. Generally, don't reference these structs directly, but use the - * macros below. + * functions and macros below. * * We use separate structs for the aligned and unaligned cases because the * compiler might otherwise think it could generate code that assumes @@ -166,7 +181,9 @@ typedef struct /* * Endian-dependent macros. These are considered internal --- use the - * external macros below instead of using these directly. + * external functions below instead of using these directly. All of these + * expect an argument that is a pointer, not a Datum. Some of them have + * multiple-evaluation hazards, too. * * Note: IS_1B is true for external toast records but VARSIZE_1B will return 0 * for such records. Hence you should usually check for IS_EXTERNAL before @@ -194,7 +211,7 @@ typedef struct #define VARSIZE_1B(PTR) \ (((varattrib_1b *) (PTR))->va_header & 0x7F) #define VARTAG_1B_E(PTR) \ - (((varattrib_1b_e *) (PTR))->va_tag) + ((vartag_external) ((varattrib_1b_e *) (PTR))->va_tag) #define SET_VARSIZE_4B(PTR,len) \ (((varattrib_4b *) (PTR))->va_4byte.va_header = (len) & 0x3FFFFFFF) @@ -227,7 +244,7 @@ typedef struct #define VARSIZE_1B(PTR) \ ((((varattrib_1b *) (PTR))->va_header >> 1) & 0x7F) #define VARTAG_1B_E(PTR) \ - (((varattrib_1b_e *) (PTR))->va_tag) + ((vartag_external) ((varattrib_1b_e *) (PTR))->va_tag) #define SET_VARSIZE_4B(PTR,len) \ (((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2)) @@ -247,19 +264,19 @@ typedef struct #define VARDATA_1B_E(PTR) (((varattrib_1b_e *) (PTR))->va_data) /* - * Externally visible TOAST macros begin here. + * Externally visible TOAST functions and macros begin here. All of these + * were originally macros, accounting for the upper-case naming. + * + * Most of these functions accept a pointer to a value of a toastable data + * type. The caller's variable might be declared "text *" or the like, + * so we use "void *" here. Callers that are working with a Datum variable + * must apply DatumGetPointer before calling these functions. */ #define VARHDRSZ_EXTERNAL offsetof(varattrib_1b_e, va_data) #define VARHDRSZ_COMPRESSED offsetof(varattrib_4b, va_compressed.va_data) #define VARHDRSZ_SHORT offsetof(varattrib_1b, va_data) - #define VARATT_SHORT_MAX 0x7F -#define VARATT_CAN_MAKE_SHORT(PTR) \ - (VARATT_IS_4B_U(PTR) && \ - (VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT) <= VARATT_SHORT_MAX) -#define VARATT_CONVERTED_SHORT_SIZE(PTR) \ - (VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT) /* * In consumers oblivious to data alignment, call PG_DETOAST_DATUM_PACKED(), @@ -272,70 +289,234 @@ typedef struct * Code assembling a new datum should call VARDATA() and SET_VARSIZE(). * (Datums begin life untoasted.) * - * Other macros here should usually be used only by tuple assembly/disassembly + * Other functions here should usually be used only by tuple assembly/disassembly * code and code that specifically wants to work with still-toasted Datums. */ -#define VARDATA(PTR) VARDATA_4B(PTR) -#define VARSIZE(PTR) VARSIZE_4B(PTR) - -#define VARSIZE_SHORT(PTR) VARSIZE_1B(PTR) -#define VARDATA_SHORT(PTR) VARDATA_1B(PTR) - -#define VARTAG_EXTERNAL(PTR) VARTAG_1B_E(PTR) -#define VARSIZE_EXTERNAL(PTR) (VARHDRSZ_EXTERNAL + VARTAG_SIZE(VARTAG_EXTERNAL(PTR))) -#define VARDATA_EXTERNAL(PTR) VARDATA_1B_E(PTR) - -#define VARATT_IS_COMPRESSED(PTR) VARATT_IS_4B_C(PTR) -#define VARATT_IS_EXTERNAL(PTR) VARATT_IS_1B_E(PTR) -#define VARATT_IS_EXTERNAL_ONDISK(PTR) \ - (VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_ONDISK) -#define VARATT_IS_EXTERNAL_INDIRECT(PTR) \ - (VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_INDIRECT) -#define VARATT_IS_EXTERNAL_EXPANDED_RO(PTR) \ - (VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RO) -#define VARATT_IS_EXTERNAL_EXPANDED_RW(PTR) \ - (VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RW) -#define VARATT_IS_EXTERNAL_EXPANDED(PTR) \ - (VARATT_IS_EXTERNAL(PTR) && VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR))) -#define VARATT_IS_EXTERNAL_NON_EXPANDED(PTR) \ - (VARATT_IS_EXTERNAL(PTR) && !VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR))) -#define VARATT_IS_SHORT(PTR) VARATT_IS_1B(PTR) -#define VARATT_IS_EXTENDED(PTR) (!VARATT_IS_4B_U(PTR)) - -#define SET_VARSIZE(PTR, len) SET_VARSIZE_4B(PTR, len) -#define SET_VARSIZE_SHORT(PTR, len) SET_VARSIZE_1B(PTR, len) -#define SET_VARSIZE_COMPRESSED(PTR, len) SET_VARSIZE_4B_C(PTR, len) - -#define SET_VARTAG_EXTERNAL(PTR, tag) SET_VARTAG_1B_E(PTR, tag) - -#define VARSIZE_ANY(PTR) \ - (VARATT_IS_1B_E(PTR) ? VARSIZE_EXTERNAL(PTR) : \ - (VARATT_IS_1B(PTR) ? VARSIZE_1B(PTR) : \ - VARSIZE_4B(PTR))) - -/* Size of a varlena data, excluding header */ -#define VARSIZE_ANY_EXHDR(PTR) \ - (VARATT_IS_1B_E(PTR) ? VARSIZE_EXTERNAL(PTR)-VARHDRSZ_EXTERNAL : \ - (VARATT_IS_1B(PTR) ? VARSIZE_1B(PTR)-VARHDRSZ_SHORT : \ - VARSIZE_4B(PTR)-VARHDRSZ)) +/* Size of a known-not-toasted varlena datum, including header */ +static inline Size +VARSIZE(const void *PTR) +{ + return VARSIZE_4B(PTR); +} + +/* Start of data area of a known-not-toasted varlena datum */ +static inline char * +VARDATA(const void *PTR) +{ + return VARDATA_4B(PTR); +} + +/* Size of a known-short-header varlena datum, including header */ +static inline Size +VARSIZE_SHORT(const void *PTR) +{ + return VARSIZE_1B(PTR); +} + +/* Start of data area of a known-short-header varlena datum */ +static inline char * +VARDATA_SHORT(const void *PTR) +{ + return VARDATA_1B(PTR); +} + +/* Type tag of a "TOAST pointer" datum */ +static inline vartag_external +VARTAG_EXTERNAL(const void *PTR) +{ + return VARTAG_1B_E(PTR); +} + +/* Size of a "TOAST pointer" datum, including header */ +static inline Size +VARSIZE_EXTERNAL(const void *PTR) +{ + return VARHDRSZ_EXTERNAL + VARTAG_SIZE(VARTAG_EXTERNAL(PTR)); +} + +/* Start of data area of a "TOAST pointer" datum */ +static inline char * +VARDATA_EXTERNAL(const void *PTR) +{ + return VARDATA_1B_E(PTR); +} + +/* Is varlena datum in inline-compressed format? */ +static inline bool +VARATT_IS_COMPRESSED(const void *PTR) +{ + return VARATT_IS_4B_C(PTR); +} + +/* Is varlena datum a "TOAST pointer" datum? */ +static inline bool +VARATT_IS_EXTERNAL(const void *PTR) +{ + return VARATT_IS_1B_E(PTR); +} + +/* Is varlena datum a pointer to on-disk toasted data? */ +static inline bool +VARATT_IS_EXTERNAL_ONDISK(const void *PTR) +{ + return VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_ONDISK; +} + +/* Is varlena datum an indirect pointer? */ +static inline bool +VARATT_IS_EXTERNAL_INDIRECT(const void *PTR) +{ + return VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_INDIRECT; +} + +/* Is varlena datum a read-only pointer to an expanded object? */ +static inline bool +VARATT_IS_EXTERNAL_EXPANDED_RO(const void *PTR) +{ + return VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RO; +} + +/* Is varlena datum a read-write pointer to an expanded object? */ +static inline bool +VARATT_IS_EXTERNAL_EXPANDED_RW(const void *PTR) +{ + return VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RW; +} + +/* Is varlena datum either type of pointer to an expanded object? */ +static inline bool +VARATT_IS_EXTERNAL_EXPANDED(const void *PTR) +{ + return VARATT_IS_EXTERNAL(PTR) && VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR)); +} + +/* Is varlena datum a "TOAST pointer", but not for an expanded object? */ +static inline bool +VARATT_IS_EXTERNAL_NON_EXPANDED(const void *PTR) +{ + return VARATT_IS_EXTERNAL(PTR) && !VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR)); +} + +/* Is varlena datum a short-header datum? */ +static inline bool +VARATT_IS_SHORT(const void *PTR) +{ + return VARATT_IS_1B(PTR); +} + +/* Is varlena datum not in traditional (4-byte-header, uncompressed) format? */ +static inline bool +VARATT_IS_EXTENDED(const void *PTR) +{ + return !VARATT_IS_4B_U(PTR); +} + +/* Is varlena datum short enough to convert to short-header format? */ +static inline bool +VARATT_CAN_MAKE_SHORT(const void *PTR) +{ + return VARATT_IS_4B_U(PTR) && + (VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT) <= VARATT_SHORT_MAX; +} + +/* Size that datum will have in short-header format, including header */ +static inline Size +VARATT_CONVERTED_SHORT_SIZE(const void *PTR) +{ + return VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT; +} + +/* Set the size (including header) of a 4-byte-header varlena datum */ +static inline void +SET_VARSIZE(void *PTR, Size len) +{ + SET_VARSIZE_4B(PTR, len); +} + +/* Set the size (including header) of a short-header varlena datum */ +static inline void +SET_VARSIZE_SHORT(void *PTR, Size len) +{ + SET_VARSIZE_1B(PTR, len); +} + +/* Set the size (including header) of an inline-compressed varlena datum */ +static inline void +SET_VARSIZE_COMPRESSED(void *PTR, Size len) +{ + SET_VARSIZE_4B_C(PTR, len); +} + +/* Set the type tag of a "TOAST pointer" datum */ +static inline void +SET_VARTAG_EXTERNAL(void *PTR, vartag_external tag) +{ + SET_VARTAG_1B_E(PTR, tag); +} + +/* Size of a varlena datum of any format, including header */ +static inline Size +VARSIZE_ANY(const void *PTR) +{ + if (VARATT_IS_1B_E(PTR)) + return VARSIZE_EXTERNAL(PTR); + else if (VARATT_IS_1B(PTR)) + return VARSIZE_1B(PTR); + else + return VARSIZE_4B(PTR); +} + +/* Size of a varlena datum of any format, excluding header */ +static inline Size +VARSIZE_ANY_EXHDR(const void *PTR) +{ + if (VARATT_IS_1B_E(PTR)) + return VARSIZE_EXTERNAL(PTR) - VARHDRSZ_EXTERNAL; + else if (VARATT_IS_1B(PTR)) + return VARSIZE_1B(PTR) - VARHDRSZ_SHORT; + else + return VARSIZE_4B(PTR) - VARHDRSZ; +} + +/* Start of data area of a plain or short-header varlena datum */ /* caution: this will not work on an external or compressed-in-line Datum */ /* caution: this will return a possibly unaligned pointer */ -#define VARDATA_ANY(PTR) \ - (VARATT_IS_1B(PTR) ? VARDATA_1B(PTR) : VARDATA_4B(PTR)) +static inline char * +VARDATA_ANY(const void *PTR) +{ + return VARATT_IS_1B(PTR) ? VARDATA_1B(PTR) : VARDATA_4B(PTR); +} -/* Decompressed size and compression method of a compressed-in-line Datum */ -#define VARDATA_COMPRESSED_GET_EXTSIZE(PTR) \ - (((varattrib_4b *) (PTR))->va_compressed.va_tcinfo & VARLENA_EXTSIZE_MASK) -#define VARDATA_COMPRESSED_GET_COMPRESS_METHOD(PTR) \ - (((varattrib_4b *) (PTR))->va_compressed.va_tcinfo >> VARLENA_EXTSIZE_BITS) +/* Decompressed size of a compressed-in-line varlena datum */ +static inline Size +VARDATA_COMPRESSED_GET_EXTSIZE(const void *PTR) +{ + return ((varattrib_4b *) PTR)->va_compressed.va_tcinfo & VARLENA_EXTSIZE_MASK; +} + +/* Compression method of a compressed-in-line varlena datum */ +static inline uint32 +VARDATA_COMPRESSED_GET_COMPRESS_METHOD(const void *PTR) +{ + return ((varattrib_4b *) PTR)->va_compressed.va_tcinfo >> VARLENA_EXTSIZE_BITS; +} /* Same for external Datums; but note argument is a struct varatt_external */ -#define VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) \ - ((toast_pointer).va_extinfo & VARLENA_EXTSIZE_MASK) -#define VARATT_EXTERNAL_GET_COMPRESS_METHOD(toast_pointer) \ - ((toast_pointer).va_extinfo >> VARLENA_EXTSIZE_BITS) +static inline Size +VARATT_EXTERNAL_GET_EXTSIZE(struct varatt_external toast_pointer) +{ + return toast_pointer.va_extinfo & VARLENA_EXTSIZE_MASK; +} +static inline uint32 +VARATT_EXTERNAL_GET_COMPRESS_METHOD(struct varatt_external toast_pointer) +{ + return toast_pointer.va_extinfo >> VARLENA_EXTSIZE_BITS; +} + +/* Set size and compress method of an externally-stored varlena datum */ +/* This has to remain a macro; beware multiple evaluations! */ #define VARATT_EXTERNAL_SET_SIZE_AND_COMPRESS_METHOD(toast_pointer, len, cm) \ do { \ Assert((cm) == TOAST_PGLZ_COMPRESSION_ID || \ @@ -351,8 +532,11 @@ typedef struct * VARHDRSZ overhead, the former doesn't. We never use compression unless it * actually saves space, so we expect either equality or less-than. */ -#define VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer) \ - (VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) < \ - (toast_pointer).va_rawsize - VARHDRSZ) +static inline bool +VARATT_EXTERNAL_IS_COMPRESSED(struct varatt_external toast_pointer) +{ + return VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) < + (Size) (toast_pointer.va_rawsize - VARHDRSZ); +} #endif diff --git a/src/interfaces/ecpg/compatlib/informix.c b/src/interfaces/ecpg/compatlib/informix.c index e829d722f22..ca11a81f1bc 100644 --- a/src/interfaces/ecpg/compatlib/informix.c +++ b/src/interfaces/ecpg/compatlib/informix.c @@ -807,8 +807,10 @@ rfmtlong(long lng_val, const char *fmt, char *outbuf) if (strchr(fmt, (int) '(') && strchr(fmt, (int) ')')) brackets_ok = 1; - /* get position of the right-most dot in the format-string */ - /* and fill the temp-string wit '0's up to there. */ + /* + * get position of the right-most dot in the format-string and fill the + * temp-string with '0's up to there. + */ dotpos = getRightMostDot(fmt); /* start to parse the format-string */ diff --git a/src/test/modules/Makefile b/src/test/modules/Makefile index 7d3d3d52b45..903a8ac151a 100644 --- a/src/test/modules/Makefile +++ b/src/test/modules/Makefile @@ -25,6 +25,7 @@ SUBDIRS = \ test_escape \ test_extensions \ test_ginpostinglist \ + test_int128 \ test_integerset \ test_json_parser \ test_lfind \ diff --git a/src/test/modules/meson.build b/src/test/modules/meson.build index dd5cd065ba1..93be0f57289 100644 --- a/src/test/modules/meson.build +++ b/src/test/modules/meson.build @@ -24,6 +24,7 @@ subdir('test_dsm_registry') subdir('test_escape') subdir('test_extensions') subdir('test_ginpostinglist') +subdir('test_int128') subdir('test_integerset') subdir('test_json_parser') subdir('test_lfind') diff --git a/src/test/modules/test_int128/.gitignore b/src/test/modules/test_int128/.gitignore new file mode 100644 index 00000000000..277fec6ed2c --- /dev/null +++ b/src/test/modules/test_int128/.gitignore @@ -0,0 +1,2 @@ +/tmp_check/ +/test_int128 diff --git a/src/test/modules/test_int128/Makefile b/src/test/modules/test_int128/Makefile new file mode 100644 index 00000000000..2e86ee93a9d --- /dev/null +++ b/src/test/modules/test_int128/Makefile @@ -0,0 +1,23 @@ +# src/test/modules/test_int128/Makefile + +PGFILEDESC = "test_int128 - test 128-bit integer arithmetic" + +PROGRAM = test_int128 +OBJS = $(WIN32RES) test_int128.o + +PG_CPPFLAGS = -I$(libpq_srcdir) +PG_LIBS_INTERNAL += $(libpq_pgport) + +NO_INSTALL = 1 +TAP_TESTS = 1 + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/test/modules/test_int128 +top_builddir = ../../../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/contrib/contrib-global.mk +endif diff --git a/src/test/modules/test_int128/meson.build b/src/test/modules/test_int128/meson.build new file mode 100644 index 00000000000..4c2be7a0326 --- /dev/null +++ b/src/test/modules/test_int128/meson.build @@ -0,0 +1,33 @@ +# Copyright (c) 2025, PostgreSQL Global Development Group + +test_int128_sources = files( + 'test_int128.c', +) + +if host_system == 'windows' + test_int128_sources += rc_bin_gen.process(win32ver_rc, extra_args: [ + '--NAME', 'test_int128', + '--FILEDESC', 'test int128 program',]) +endif + +test_int128 = executable('test_int128', + test_int128_sources, + dependencies: [frontend_code, libpq], + kwargs: default_bin_args + { + 'install': false, + }, +) +testprep_targets += test_int128 + + +tests += { + 'name': 'test_int128', + 'sd': meson.current_source_dir(), + 'bd': meson.current_build_dir(), + 'tap': { + 'tests': [ + 't/001_test_int128.pl', + ], + 'deps': [test_int128], + }, +} diff --git a/src/test/modules/test_int128/t/001_test_int128.pl b/src/test/modules/test_int128/t/001_test_int128.pl new file mode 100644 index 00000000000..0c683869f34 --- /dev/null +++ b/src/test/modules/test_int128/t/001_test_int128.pl @@ -0,0 +1,27 @@ +# Copyright (c) 2025, PostgreSQL Global Development Group + +# Test 128-bit integer arithmetic code in int128.h + +use strict; +use warnings FATAL => 'all'; + +use PostgreSQL::Test::Utils; +use Test::More; + +# Run the test program with 1M iterations +my $exe = "test_int128"; +my $size = 1_000_000; + +note "testing executable $exe"; + +my ($stdout, $stderr) = run_command([ $exe, $size ]); + +SKIP: +{ + skip "no native int128 type", 2 if $stdout =~ /skipping tests/; + + is($stdout, "", "test_int128: no stdout"); + is($stderr, "", "test_int128: no stderr"); +} + +done_testing(); diff --git a/src/tools/testint128.c b/src/test/modules/test_int128/test_int128.c index a25631e277d..caa06541a1f 100644 --- a/src/tools/testint128.c +++ b/src/test/modules/test_int128/test_int128.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * testint128.c + * test_int128.c * Testbed for roll-our-own 128-bit integer arithmetic. * * This is a standalone test program that compares the behavior of an @@ -10,13 +10,18 @@ * * * IDENTIFICATION - * src/tools/testint128.c + * src/test/modules/test_int128/test_int128.c * *------------------------------------------------------------------------- */ #include "postgres_fe.h" +#include <time.h> + +/* Require a native int128 type */ +#ifdef HAVE_INT128 + /* * By default, we test the non-native implementation in int128.h; but * by predefining USE_NATIVE_INT128 to 1, you can test the native @@ -36,7 +41,7 @@ typedef union { int128 i128; INT128 I128; - union + struct { #ifdef WORDS_BIGENDIAN int64 hi; @@ -48,6 +53,7 @@ typedef union } hl; } test128; +#define INT128_HEX_FORMAT "%016" PRIx64 "%016" PRIx64 /* * Control version of comparator. @@ -75,7 +81,7 @@ main(int argc, char **argv) { long count; - pg_prng_seed(&pg_global_prng_state, 0); + pg_prng_seed(&pg_global_prng_state, (uint64) time(NULL)); if (argc >= 2) count = strtol(argv[1], NULL, 0); @@ -99,9 +105,9 @@ main(int argc, char **argv) if (t1.hl.hi != t2.hl.hi || t1.hl.lo != t2.hl.lo) { - printf("%016lX%016lX + unsigned %lX\n", x, y, z); - printf("native = %016lX%016lX\n", t1.hl.hi, t1.hl.lo); - printf("result = %016lX%016lX\n", t2.hl.hi, t2.hl.lo); + printf(INT128_HEX_FORMAT " + unsigned %016" PRIx64 "\n", x, y, z); + printf("native = " INT128_HEX_FORMAT "\n", t1.hl.hi, t1.hl.lo); + printf("result = " INT128_HEX_FORMAT "\n", t2.hl.hi, t2.hl.lo); return 1; } @@ -114,9 +120,9 @@ main(int argc, char **argv) if (t1.hl.hi != t2.hl.hi || t1.hl.lo != t2.hl.lo) { - printf("%016lX%016lX + signed %lX\n", x, y, z); - printf("native = %016lX%016lX\n", t1.hl.hi, t1.hl.lo); - printf("result = %016lX%016lX\n", t2.hl.hi, t2.hl.lo); + printf(INT128_HEX_FORMAT " + signed %016" PRIx64 "\n", x, y, z); + printf("native = " INT128_HEX_FORMAT "\n", t1.hl.hi, t1.hl.lo); + printf("result = " INT128_HEX_FORMAT "\n", t2.hl.hi, t2.hl.lo); return 1; } @@ -128,9 +134,9 @@ main(int argc, char **argv) if (t1.hl.hi != t2.hl.hi || t1.hl.lo != t2.hl.lo) { - printf("%lX * %lX\n", x, y); - printf("native = %016lX%016lX\n", t1.hl.hi, t1.hl.lo); - printf("result = %016lX%016lX\n", t2.hl.hi, t2.hl.lo); + printf("%016" PRIx64 " * %016" PRIx64 "\n", x, y); + printf("native = " INT128_HEX_FORMAT "\n", t1.hl.hi, t1.hl.lo); + printf("result = " INT128_HEX_FORMAT "\n", t2.hl.hi, t2.hl.lo); return 1; } @@ -146,8 +152,8 @@ main(int argc, char **argv) printf("comparison failure: %d vs %d\n", my_int128_compare(t1.i128, t2.i128), int128_compare(t1.I128, t2.I128)); - printf("arg1 = %016lX%016lX\n", t1.hl.hi, t1.hl.lo); - printf("arg2 = %016lX%016lX\n", t2.hl.hi, t2.hl.lo); + printf("arg1 = " INT128_HEX_FORMAT "\n", t1.hl.hi, t1.hl.lo); + printf("arg2 = " INT128_HEX_FORMAT "\n", t2.hl.hi, t2.hl.lo); return 1; } @@ -160,11 +166,25 @@ main(int argc, char **argv) printf("comparison failure: %d vs %d\n", my_int128_compare(t1.i128, t2.i128), int128_compare(t1.I128, t2.I128)); - printf("arg1 = %016lX%016lX\n", t1.hl.hi, t1.hl.lo); - printf("arg2 = %016lX%016lX\n", t2.hl.hi, t2.hl.lo); + printf("arg1 = " INT128_HEX_FORMAT "\n", t1.hl.hi, t1.hl.lo); + printf("arg2 = " INT128_HEX_FORMAT "\n", t2.hl.hi, t2.hl.lo); return 1; } } return 0; } + +#else /* ! HAVE_INT128 */ + +/* + * For now, do nothing if we don't have a native int128 type. + */ +int +main(int argc, char **argv) +{ + printf("skipping tests: no native int128 type\n"); + return 0; +} + +#endif diff --git a/src/test/modules/test_radixtree/test_radixtree.c b/src/test/modules/test_radixtree/test_radixtree.c index 32de6a3123e..80ad0296164 100644 --- a/src/test/modules/test_radixtree/test_radixtree.c +++ b/src/test/modules/test_radixtree/test_radixtree.c @@ -44,7 +44,7 @@ uint64 _expected = (expected_expr); \ if (_result != _expected) \ elog(ERROR, \ - "%s yielded " UINT64_HEX_FORMAT ", expected " UINT64_HEX_FORMAT " (%s) in file \"%s\" line %u", \ + "%s yielded %" PRIx64 ", expected %" PRIx64 " (%s) in file \"%s\" line %u", \ #result_expr, _result, _expected, #expected_expr, __FILE__, __LINE__); \ } while (0) diff --git a/src/test/recovery/t/035_standby_logical_decoding.pl b/src/test/recovery/t/035_standby_logical_decoding.pl index 921813483e3..c9c182892cf 100644 --- a/src/test/recovery/t/035_standby_logical_decoding.pl +++ b/src/test/recovery/t/035_standby_logical_decoding.pl @@ -8,6 +8,7 @@ use warnings FATAL => 'all'; use PostgreSQL::Test::Cluster; use PostgreSQL::Test::Utils; +use Time::HiRes qw(usleep); use Test::More; if ($ENV{enable_injection_points} ne 'yes') @@ -623,7 +624,7 @@ ok( $stderr =~ /ERROR: cannot copy invalidated replication slot "vacuum_full_inactiveslot"/, "invalidated slot cannot be copied"); -# Turn hot_standby_feedback back on +# Set hot_standby_feedback to on change_hot_standby_feedback_and_wait_for_xmins(1, 1); ################################################## @@ -754,12 +755,12 @@ wait_until_vacuum_can_remove( # message should not be issued ok( !$node_standby->log_contains( - "invalidating obsolete slot \"no_conflict_inactiveslot\"", $logstart), + "invalidating obsolete replication slot \"no_conflict_inactiveslot\"", $logstart), 'inactiveslot slot invalidation is not logged with vacuum on conflict_test' ); ok( !$node_standby->log_contains( - "invalidating obsolete slot \"no_conflict_activeslot\"", $logstart), + "invalidating obsolete replication slot \"no_conflict_activeslot\"", $logstart), 'activeslot slot invalidation is not logged with vacuum on conflict_test' ); diff --git a/src/test/regress/expected/create_index.out b/src/test/regress/expected/create_index.out index 9ade7b835e6..98e68e972be 100644 --- a/src/test/regress/expected/create_index.out +++ b/src/test/regress/expected/create_index.out @@ -1624,8 +1624,8 @@ DROP TABLE cwi_test; -- CREATE TABLE syscol_table (a INT); -- System columns cannot be indexed -CREATE INDEX ON syscolcol_table (ctid); -ERROR: relation "syscolcol_table" does not exist +CREATE INDEX ON syscol_table (ctid); +ERROR: index creation on system columns is not supported -- nor used in expressions CREATE INDEX ON syscol_table ((ctid >= '(1000,0)')); ERROR: index creation on system columns is not supported diff --git a/src/test/regress/expected/publication.out b/src/test/regress/expected/publication.out index 1ec3fa34a2d..53268059142 100644 --- a/src/test/regress/expected/publication.out +++ b/src/test/regress/expected/publication.out @@ -36,6 +36,9 @@ LINE 1: ...pub_xxx WITH (publish_generated_columns = stored, publish_ge... CREATE PUBLICATION testpub_xxx WITH (publish_generated_columns = foo); ERROR: invalid value for publication parameter "publish_generated_columns": "foo" DETAIL: Valid values are "none" and "stored". +CREATE PUBLICATION testpub_xxx WITH (publish_generated_columns); +ERROR: invalid value for publication parameter "publish_generated_columns": "" +DETAIL: Valid values are "none" and "stored". \dRp List of publications Name | Owner | All tables | Inserts | Updates | Deletes | Truncates | Generated columns | Via root @@ -1844,8 +1847,7 @@ DROP SCHEMA sch1 cascade; DROP SCHEMA sch2 cascade; -- ====================================================== -- Test the 'publish_generated_columns' parameter with the following values: --- 'stored', 'none', and the default (no value specified), which defaults to --- 'stored'. +-- 'stored', 'none'. SET client_min_messages = 'ERROR'; CREATE PUBLICATION pub1 FOR ALL TABLES WITH (publish_generated_columns = stored); \dRp+ pub1 @@ -1863,17 +1865,8 @@ CREATE PUBLICATION pub2 FOR ALL TABLES WITH (publish_generated_columns = none); regress_publication_user | t | t | t | t | t | none | f (1 row) -CREATE PUBLICATION pub3 FOR ALL TABLES WITH (publish_generated_columns); -\dRp+ pub3 - Publication pub3 - Owner | All tables | Inserts | Updates | Deletes | Truncates | Generated columns | Via root ---------------------------+------------+---------+---------+---------+-----------+-------------------+---------- - regress_publication_user | t | t | t | t | t | stored | f -(1 row) - DROP PUBLICATION pub1; DROP PUBLICATION pub2; -DROP PUBLICATION pub3; -- Test the 'publish_generated_columns' parameter as 'none' and 'stored' for -- different scenarios with/without generated columns in column lists. CREATE TABLE gencols (a int, gen1 int GENERATED ALWAYS AS (a * 2) STORED); diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index dce8c672b40..35e8aad7701 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1977,7 +1977,12 @@ pg_stat_progress_basebackup| SELECT pid, END AS backup_total, param3 AS backup_streamed, param4 AS tablespaces_total, - param5 AS tablespaces_streamed + param5 AS tablespaces_streamed, + CASE param6 + WHEN 1 THEN 'full'::text + WHEN 2 THEN 'incremental'::text + ELSE NULL::text + END AS backup_type FROM pg_stat_get_progress_info('BASEBACKUP'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20); pg_stat_progress_cluster| SELECT s.pid, s.datid, @@ -2179,13 +2184,14 @@ pg_stat_subscription_stats| SELECT ss.subid, ss.confl_insert_exists, ss.confl_update_origin_differs, ss.confl_update_exists, + ss.confl_update_deleted, ss.confl_update_missing, ss.confl_delete_origin_differs, ss.confl_delete_missing, ss.confl_multiple_unique_conflicts, ss.stats_reset FROM pg_subscription s, - LATERAL pg_stat_get_subscription_stats(s.oid) ss(subid, apply_error_count, sync_error_count, confl_insert_exists, confl_update_origin_differs, confl_update_exists, confl_update_missing, confl_delete_origin_differs, confl_delete_missing, confl_multiple_unique_conflicts, stats_reset); + LATERAL pg_stat_get_subscription_stats(s.oid) ss(subid, apply_error_count, sync_error_count, confl_insert_exists, confl_update_origin_differs, confl_update_exists, confl_update_deleted, confl_update_missing, confl_delete_origin_differs, confl_delete_missing, confl_multiple_unique_conflicts, stats_reset); pg_stat_sys_indexes| SELECT relid, indexrelid, schemaname, diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out index 1bfd33de3f3..ba302da51e7 100644 --- a/src/test/regress/expected/strings.out +++ b/src/test/regress/expected/strings.out @@ -2091,6 +2091,40 @@ SELECT c FROM toasttest; (1 row) DROP TABLE toasttest; +-- test with short varlenas (up to 126 data bytes reduced to a 1-byte header) +-- being toasted. +CREATE TABLE toasttest (f1 text, f2 text); +ALTER TABLE toasttest SET (toast_tuple_target = 128); +ALTER TABLE toasttest ALTER COLUMN f1 SET STORAGE EXTERNAL; +ALTER TABLE toasttest ALTER COLUMN f2 SET STORAGE EXTERNAL; +-- Here, the first value is a varlena large enough to make it toasted and +-- stored uncompressed. The second value is a short varlena, toasted +-- and stored uncompressed. +INSERT INTO toasttest values(repeat('1234', 1000), repeat('5678', 30)); +SELECT reltoastrelid::regclass AS reltoastname FROM pg_class + WHERE oid = 'toasttest'::regclass \gset +-- There should be two values inserted in the toast relation. +SELECT count(*) FROM :reltoastname WHERE chunk_seq = 0; + count +------- + 2 +(1 row) + +SELECT substr(f1, 5, 10) AS f1_data, substr(f2, 5, 10) AS f2_data + FROM toasttest; + f1_data | f2_data +------------+------------ + 1234123412 | 5678567856 +(1 row) + +SELECT pg_column_compression(f1) AS f1_comp, pg_column_compression(f2) AS f2_comp + FROM toasttest; + f1_comp | f2_comp +---------+--------- + | +(1 row) + +DROP TABLE toasttest; -- -- test length -- diff --git a/src/test/regress/sql/create_index.sql b/src/test/regress/sql/create_index.sql index e21ff426519..eabc9623b20 100644 --- a/src/test/regress/sql/create_index.sql +++ b/src/test/regress/sql/create_index.sql @@ -635,7 +635,7 @@ DROP TABLE cwi_test; CREATE TABLE syscol_table (a INT); -- System columns cannot be indexed -CREATE INDEX ON syscolcol_table (ctid); +CREATE INDEX ON syscol_table (ctid); -- nor used in expressions CREATE INDEX ON syscol_table ((ctid >= '(1000,0)')); diff --git a/src/test/regress/sql/publication.sql b/src/test/regress/sql/publication.sql index 2585f083181..deddf0da844 100644 --- a/src/test/regress/sql/publication.sql +++ b/src/test/regress/sql/publication.sql @@ -26,6 +26,7 @@ CREATE PUBLICATION testpub_xxx WITH (publish = 'cluster, vacuum'); CREATE PUBLICATION testpub_xxx WITH (publish_via_partition_root = 'true', publish_via_partition_root = '0'); CREATE PUBLICATION testpub_xxx WITH (publish_generated_columns = stored, publish_generated_columns = none); CREATE PUBLICATION testpub_xxx WITH (publish_generated_columns = foo); +CREATE PUBLICATION testpub_xxx WITH (publish_generated_columns); \dRp @@ -1183,19 +1184,15 @@ DROP SCHEMA sch2 cascade; -- ====================================================== -- Test the 'publish_generated_columns' parameter with the following values: --- 'stored', 'none', and the default (no value specified), which defaults to --- 'stored'. +-- 'stored', 'none'. SET client_min_messages = 'ERROR'; CREATE PUBLICATION pub1 FOR ALL TABLES WITH (publish_generated_columns = stored); \dRp+ pub1 CREATE PUBLICATION pub2 FOR ALL TABLES WITH (publish_generated_columns = none); \dRp+ pub2 -CREATE PUBLICATION pub3 FOR ALL TABLES WITH (publish_generated_columns); -\dRp+ pub3 DROP PUBLICATION pub1; DROP PUBLICATION pub2; -DROP PUBLICATION pub3; -- Test the 'publish_generated_columns' parameter as 'none' and 'stored' for -- different scenarios with/without generated columns in column lists. diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql index 92c445c2439..b94004cc08c 100644 --- a/src/test/regress/sql/strings.sql +++ b/src/test/regress/sql/strings.sql @@ -650,6 +650,26 @@ SELECT length(c), c::text FROM toasttest; SELECT c FROM toasttest; DROP TABLE toasttest; +-- test with short varlenas (up to 126 data bytes reduced to a 1-byte header) +-- being toasted. +CREATE TABLE toasttest (f1 text, f2 text); +ALTER TABLE toasttest SET (toast_tuple_target = 128); +ALTER TABLE toasttest ALTER COLUMN f1 SET STORAGE EXTERNAL; +ALTER TABLE toasttest ALTER COLUMN f2 SET STORAGE EXTERNAL; +-- Here, the first value is a varlena large enough to make it toasted and +-- stored uncompressed. The second value is a short varlena, toasted +-- and stored uncompressed. +INSERT INTO toasttest values(repeat('1234', 1000), repeat('5678', 30)); +SELECT reltoastrelid::regclass AS reltoastname FROM pg_class + WHERE oid = 'toasttest'::regclass \gset +-- There should be two values inserted in the toast relation. +SELECT count(*) FROM :reltoastname WHERE chunk_seq = 0; +SELECT substr(f1, 5, 10) AS f1_data, substr(f2, 5, 10) AS f2_data + FROM toasttest; +SELECT pg_column_compression(f1) AS f1_comp, pg_column_compression(f2) AS f2_comp + FROM toasttest; +DROP TABLE toasttest; + -- -- test length -- diff --git a/src/test/subscription/t/035_conflicts.pl b/src/test/subscription/t/035_conflicts.pl index 976d53a870e..36aeb14c563 100644 --- a/src/test/subscription/t/035_conflicts.pl +++ b/src/test/subscription/t/035_conflicts.pl @@ -150,7 +150,9 @@ pass('multiple_unique_conflicts detected on a leaf partition during insert'); # Setup a bidirectional logical replication between node_A & node_B ############################################################################### -# Initialize nodes. +# Initialize nodes. Enable the track_commit_timestamp on both nodes to detect +# the conflict when attempting to update a row that was previously modified by +# a different origin. # node_A. Increase the log_min_messages setting to DEBUG2 to debug test # failures. Disable autovacuum to avoid generating xid that could affect the @@ -158,7 +160,8 @@ pass('multiple_unique_conflicts detected on a leaf partition during insert'); my $node_A = $node_publisher; $node_A->append_conf( 'postgresql.conf', - qq{autovacuum = off + qq{track_commit_timestamp = on + autovacuum = off log_min_messages = 'debug2'}); $node_A->restart; @@ -270,6 +273,8 @@ $node_A->psql('postgres', ############################################################################### # Check that dead tuples on node A cannot be cleaned by VACUUM until the # concurrent transactions on Node B have been applied and flushed on Node A. +# Also, check that an update_deleted conflict is detected when updating a row +# that was deleted by a different origin. ############################################################################### # Insert a record @@ -288,6 +293,8 @@ $node_A->poll_query_until('postgres', "SELECT count(*) = 0 FROM pg_stat_activity WHERE backend_type = 'logical replication apply worker'" ); +my $log_location = -s $node_B->logfile; + $node_B->safe_psql('postgres', "UPDATE tab SET b = 3 WHERE a = 1;"); $node_A->safe_psql('postgres', "DELETE FROM tab WHERE a = 1;"); @@ -299,10 +306,30 @@ ok( $stderr =~ qr/1 are dead but not yet removable/, 'the deleted column is non-removable'); +# Ensure the DELETE is replayed on Node B +$node_A->wait_for_catchup($subname_BA); + +# Check the conflict detected on Node B +my $logfile = slurp_file($node_B->logfile(), $log_location); +ok( $logfile =~ + qr/conflict detected on relation "public.tab": conflict=delete_origin_differs.* +.*DETAIL:.* Deleting the row that was modified locally in transaction [0-9]+ at .* +.*Existing local tuple \(1, 3\); replica identity \(a\)=\(1\)/, + 'delete target row was modified in tab'); + +$log_location = -s $node_A->logfile; + $node_A->safe_psql( 'postgres', "ALTER SUBSCRIPTION $subname_AB ENABLE;"); $node_B->wait_for_catchup($subname_AB); +$logfile = slurp_file($node_A->logfile(), $log_location); +ok( $logfile =~ + qr/conflict detected on relation "public.tab": conflict=update_deleted.* +.*DETAIL:.* The row to be updated was deleted locally in transaction [0-9]+ at .* +.*Remote tuple \(1, 3\); replica identity \(a\)=\(1\)/, + 'update target row was deleted in tab'); + # Remember the next transaction ID to be assigned my $next_xid = $node_A->safe_psql('postgres', "SELECT txid_current() + 1;"); @@ -325,6 +352,41 @@ ok( $stderr =~ 'the deleted column is removed'); ############################################################################### +# Ensure that the deleted tuple needed to detect an update_deleted conflict is +# accessible via a sequential table scan. +############################################################################### + +# Drop the primary key from tab on node A and set REPLICA IDENTITY to FULL to +# enforce sequential scanning of the table. +$node_A->safe_psql('postgres', "ALTER TABLE tab REPLICA IDENTITY FULL"); +$node_B->safe_psql('postgres', "ALTER TABLE tab REPLICA IDENTITY FULL"); +$node_A->safe_psql('postgres', "ALTER TABLE tab DROP CONSTRAINT tab_pkey;"); + +# Disable the logical replication from node B to node A +$node_A->safe_psql('postgres', "ALTER SUBSCRIPTION $subname_AB DISABLE"); + +# Wait for the apply worker to stop +$node_A->poll_query_until('postgres', + "SELECT count(*) = 0 FROM pg_stat_activity WHERE backend_type = 'logical replication apply worker'" +); + +$node_B->safe_psql('postgres', "UPDATE tab SET b = 4 WHERE a = 2;"); +$node_A->safe_psql('postgres', "DELETE FROM tab WHERE a = 2;"); + +$log_location = -s $node_A->logfile; + +$node_A->safe_psql( + 'postgres', "ALTER SUBSCRIPTION $subname_AB ENABLE;"); +$node_B->wait_for_catchup($subname_AB); + +$logfile = slurp_file($node_A->logfile(), $log_location); +ok( $logfile =~ + qr/conflict detected on relation "public.tab": conflict=update_deleted.* +.*DETAIL:.* The row to be updated was deleted locally in transaction [0-9]+ at .* +.*Remote tuple \(2, 4\); replica identity full \(2, 2\)/, + 'update target row was deleted in tab'); + +############################################################################### # Check that the replication slot pg_conflict_detection is dropped after # removing all the subscriptions. ############################################################################### |