Index: doc/src/sgml/catalogs.sgml =================================================================== RCS file: /home/alvherre/cvs/pgsql/doc/src/sgml/catalogs.sgml,v retrieving revision 2.122 diff -c -r2.122 catalogs.sgml *** doc/src/sgml/catalogs.sgml 2 May 2006 22:25:09 -0000 2.122 --- doc/src/sgml/catalogs.sgml 5 May 2006 01:54:38 -0000 *************** *** 1633,1638 **** --- 1633,1662 ---- + relminxid + xid + + + The minimum transaction ID present in all rows in this table. This + value is used to determine the database-global + pg_database.datminxid value. + + + + + relvacuumxid + xid + + + The transaction ID that was used as cleaning point as of the last vacuum + operation. All rows inserted, updated or deleted in this table by + transactions whose IDs are below this one have been marked as known good + or deleted. This is used to determine the database-global + pg_database.datvacuumxid value. + + + + relacl aclitem[] *************** *** 2004,2024 **** xid ! All rows inserted or deleted by transaction IDs before this one ! have been marked as known committed or known aborted in this database. ! This is used to determine when commit-log space can be recycled. ! datfrozenxid xid All rows inserted by transaction IDs before this one have been relabeled with a permanent (frozen) transaction ID in this ! database. This is useful to check whether a database must be vacuumed ! soon to avoid transaction ID wrap-around problems. --- 2028,2054 ---- xid ! The transaction ID that was used as cleaning point as of the last vacuum ! operation. All rows inserted or deleted by transaction IDs before this one ! have been marked as known good or deleted. This ! is used to determine when commit-log space can be recycled. ! If InvalidTransactionId, then the minimum is unknown and can be ! determined by scanning pg_class.relvacuumxid. ! datminxid xid + The minimum transaction ID present in all tables in this database. All rows inserted by transaction IDs before this one have been relabeled with a permanent (frozen) transaction ID in this ! database. This is useful to check whether a database must be ! vacuumed soon to avoid transaction ID wrap-around problems. ! If InvalidTransactionId, then the minimum is unknown and can be ! determined by scanning pg_class.relminxid. Index: src/backend/access/heap/heapam.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/access/heap/heapam.c,v retrieving revision 1.212 diff -c -r1.212 heapam.c *** src/backend/access/heap/heapam.c 10 May 2006 23:18:39 -0000 1.212 --- src/backend/access/heap/heapam.c 25 May 2006 23:09:00 -0000 *************** *** 51,61 **** --- 51,72 ---- #include "storage/procarray.h" #include "utils/inval.h" #include "utils/relcache.h" + #include "utils/syscache.h" static XLogRecPtr log_heap_update(Relation reln, Buffer oldbuf, ItemPointerData from, Buffer newbuf, HeapTuple newtup, bool move); + /* + * There are some situations in which we want to acquire strong locks on + * relations, but we know there is no need to unfreeze them; for example, + * during VACUUM. Any such caller sets this variable to true, which turns + * heap_unfreeze into a no-op. + * + * It's advisable to do this in a PG_TRY block so that it won't "forget" to + * reset the variable in case of error. + */ + bool disable_heap_unfreeze = false; /* ---------------------------------------------------------------- * heap support routines *************** *** 2673,2678 **** --- 2684,2767 ---- return HeapTupleMayBeUpdated; } + /* + * heap_unfreeze + * Mark a table as no longer frozen in pg_class. + * + * This routine updates the pg_class.relminxid and relvacuumxid columns so that + * they no longer appear as frozen. + */ + void + heap_unfreeze(Relation rel) + { + Relation classRel; + Form_pg_class classForm; + HeapTuple tuple; + Oid relid = RelationGetRelid(rel); + bool dirty = false; + + /* early exit if somebody decided to disable us */ + if (disable_heap_unfreeze) + return; + + /* + * Under normal conditions, we should have a snapshot already, but in some + * cases there may not be one. Getting a snapshot guarantees we will have + * a valid RecentXmin to use. + */ + if (!TransactionIdIsValid(RecentXmin)) + ActiveSnapshot = CopySnapshot(GetTransactionSnapshot()); + Assert(TransactionIdIsValid(RecentXmin)); + + PG_TRY(); + { + /* Disable ourselves so that we don't recurse on unfreezing pg_class */ + disable_heap_unfreeze = true; + + classRel = heap_open(RelationRelationId, RowExclusiveLock); + + /* Fetch a copy to scribble on */ + tuple = SearchSysCacheCopy(RELOID, + ObjectIdGetDatum(relid), + 0, 0, 0); + if (!HeapTupleIsValid(tuple)) + elog(ERROR, "cache lookup failed for relation %u", relid); + + classForm = (Form_pg_class) GETSTRUCT(tuple); + + if (TransactionIdEquals(classForm->relminxid, FrozenTransactionId)) + { + classForm->relminxid = RecentXmin; + dirty = true; + } + if (TransactionIdEquals(classForm->relvacuumxid, FrozenTransactionId)) + { + classForm->relvacuumxid = RecentXmin; + dirty = true; + } + if (dirty) + { + elog(NOTICE, "unfreezing %s", RelationGetRelationName(rel)); + heap_inplace_update(classRel, tuple); + } + + heap_close(classRel, RowExclusiveLock); + + /* + * Increment our own command counter to get the inval message, so that + * we don't unfreeze this relation again. + */ + if (dirty) + CommandCounterIncrement(); + } + PG_CATCH(); + { + disable_heap_unfreeze = false; + PG_RE_THROW(); + } + PG_END_TRY(); + disable_heap_unfreeze = false; + } /* * heap_inplace_update - update a tuple "in place" (ie, overwrite it) Index: src/backend/access/transam/varsup.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/access/transam/varsup.c,v retrieving revision 1.70 diff -c -r1.70 varsup.c *** src/backend/access/transam/varsup.c 5 Mar 2006 15:58:22 -0000 1.70 --- src/backend/access/transam/varsup.c 19 May 2006 22:39:10 -0000 *************** *** 168,178 **** /* * Determine the last safe XID to allocate given the currently oldest ! * datfrozenxid (ie, the oldest XID that might exist in any database * of our cluster). */ void ! SetTransactionIdLimit(TransactionId oldest_datfrozenxid, Name oldest_datname) { TransactionId xidWarnLimit; --- 168,178 ---- /* * Determine the last safe XID to allocate given the currently oldest ! * datminxid (ie, the oldest XID that might exist in any database * of our cluster). */ void ! SetTransactionIdLimit(TransactionId oldest_datminxid, Name oldest_datname) { TransactionId xidWarnLimit; *************** *** 180,195 **** TransactionId xidWrapLimit; TransactionId curXid; ! Assert(TransactionIdIsValid(oldest_datfrozenxid)); /* * The place where we actually get into deep trouble is halfway around ! * from the oldest potentially-existing XID. (This calculation is ! * probably off by one or two counts, because the special XIDs reduce the ! * size of the loop a little bit. But we throw in plenty of slop below, ! * so it doesn't matter.) */ ! xidWrapLimit = oldest_datfrozenxid + (MaxTransactionId >> 1); if (xidWrapLimit < FirstNormalTransactionId) xidWrapLimit += FirstNormalTransactionId; --- 180,195 ---- TransactionId xidWrapLimit; TransactionId curXid; ! Assert(TransactionIdIsValid(oldest_datminxid)); /* * The place where we actually get into deep trouble is halfway around ! * from the oldest existing XID. (This calculation is probably off by one ! * or two counts, because the special XIDs reduce the size of the loop a ! * little bit. But we throw in plenty of slop below, so it doesn't ! * matter.) */ ! xidWrapLimit = oldest_datminxid + (MaxTransactionId >> 1); if (xidWrapLimit < FirstNormalTransactionId) xidWrapLimit += FirstNormalTransactionId; Index: src/backend/catalog/heap.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/catalog/heap.c,v retrieving revision 1.299 diff -c -r1.299 heap.c *** src/backend/catalog/heap.c 10 May 2006 23:18:39 -0000 1.299 --- src/backend/catalog/heap.c 19 May 2006 22:39:10 -0000 *************** *** 568,573 **** --- 568,592 ---- */ new_rel_reltup = new_rel_desc->rd_rel; + /* Initialize relminxid */ + if (relkind == RELKIND_RELATION || + relkind == RELKIND_TOASTVALUE) + { + /* + * Only real tables have Xids stored in them; initialize our known + * value to the minimum Xid that could put tuples in the new table. + */ + new_rel_reltup->relminxid = RecentXmin; + } + else + { + /* + * Other relations will not have Xids in them, so set the initial value + * to InvalidTransactionId. + */ + new_rel_reltup->relminxid = InvalidTransactionId; + } + switch (relkind) { case RELKIND_RELATION: Index: src/backend/commands/analyze.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/commands/analyze.c,v retrieving revision 1.93 diff -c -r1.93 analyze.c *** src/backend/commands/analyze.c 23 Mar 2006 00:19:28 -0000 1.93 --- src/backend/commands/analyze.c 19 May 2006 22:39:10 -0000 *************** *** 424,431 **** { vac_update_relstats(RelationGetRelid(onerel), RelationGetNumberOfBlocks(onerel), ! totalrows, ! hasindex); for (ind = 0; ind < nindexes; ind++) { AnlIndexData *thisdata = &indexdata[ind]; --- 424,432 ---- { vac_update_relstats(RelationGetRelid(onerel), RelationGetNumberOfBlocks(onerel), ! totalrows, hasindex, ! InvalidTransactionId, InvalidTransactionId); ! for (ind = 0; ind < nindexes; ind++) { AnlIndexData *thisdata = &indexdata[ind]; *************** *** 434,441 **** totalindexrows = ceil(thisdata->tupleFract * totalrows); vac_update_relstats(RelationGetRelid(Irel[ind]), RelationGetNumberOfBlocks(Irel[ind]), ! totalindexrows, ! false); } /* report results to the stats collector, too */ --- 435,442 ---- totalindexrows = ceil(thisdata->tupleFract * totalrows); vac_update_relstats(RelationGetRelid(Irel[ind]), RelationGetNumberOfBlocks(Irel[ind]), ! totalindexrows, false, ! InvalidTransactionId, InvalidTransactionId); } /* report results to the stats collector, too */ Index: src/backend/commands/dbcommands.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/commands/dbcommands.c,v retrieving revision 1.181 diff -c -r1.181 dbcommands.c *** src/backend/commands/dbcommands.c 4 May 2006 16:07:29 -0000 1.181 --- src/backend/commands/dbcommands.c 19 May 2006 22:39:10 -0000 *************** *** 46,51 **** --- 46,52 ---- #include "utils/flatfiles.h" #include "utils/fmgroids.h" #include "utils/guc.h" + #include "utils/inval.h" #include "utils/lsyscache.h" #include "utils/syscache.h" *************** *** 55,61 **** Oid *dbIdP, Oid *ownerIdP, int *encodingP, bool *dbIsTemplateP, bool *dbAllowConnP, Oid *dbLastSysOidP, ! TransactionId *dbVacuumXidP, TransactionId *dbFrozenXidP, Oid *dbTablespace); static bool have_createdb_privilege(void); static void remove_dbtablespaces(Oid db_id); --- 56,62 ---- Oid *dbIdP, Oid *ownerIdP, int *encodingP, bool *dbIsTemplateP, bool *dbAllowConnP, Oid *dbLastSysOidP, ! TransactionId *dbVacuumXidP, TransactionId *dbMinXidP, Oid *dbTablespace); static bool have_createdb_privilege(void); static void remove_dbtablespaces(Oid db_id); *************** *** 76,82 **** bool src_allowconn; Oid src_lastsysoid; TransactionId src_vacuumxid; ! TransactionId src_frozenxid; Oid src_deftablespace; volatile Oid dst_deftablespace; Relation pg_database_rel; --- 77,83 ---- bool src_allowconn; Oid src_lastsysoid; TransactionId src_vacuumxid; ! TransactionId src_minxid; Oid src_deftablespace; volatile Oid dst_deftablespace; Relation pg_database_rel; *************** *** 228,234 **** if (!get_db_info(dbtemplate, ShareLock, &src_dboid, &src_owner, &src_encoding, &src_istemplate, &src_allowconn, &src_lastsysoid, ! &src_vacuumxid, &src_frozenxid, &src_deftablespace)) ereport(ERROR, (errcode(ERRCODE_UNDEFINED_DATABASE), errmsg("template database \"%s\" does not exist", --- 229,235 ---- if (!get_db_info(dbtemplate, ShareLock, &src_dboid, &src_owner, &src_encoding, &src_istemplate, &src_allowconn, &src_lastsysoid, ! &src_vacuumxid, &src_minxid, &src_deftablespace)) ereport(ERROR, (errcode(ERRCODE_UNDEFINED_DATABASE), errmsg("template database \"%s\" does not exist", *************** *** 327,340 **** } /* ! * Normally we mark the new database with the same datvacuumxid and ! * datfrozenxid as the source. However, if the source is not allowing ! * connections then we assume it is fully frozen, and we can set the ! * current transaction ID as the xid limits. This avoids immediately ! * starting to generate warnings after cloning template0. ! */ ! if (!src_allowconn) ! src_vacuumxid = src_frozenxid = GetCurrentTransactionId(); /* * Check for db name conflict. This is just to give a more friendly --- 328,342 ---- } /* ! * Normally we mark the new database with the same datminxid as the source. ! * However, if the source is fully frozen, we must not mark the new ! * database as frozen because of the new pg_database tuple, which will be ! * marked with our transaction ID. ! */ ! if (TransactionIdEquals(src_minxid, FrozenTransactionId)) ! src_minxid = GetCurrentTransactionId(); ! if (TransactionIdEquals(src_vacuumxid, FrozenTransactionId)) ! src_vacuumxid = GetCurrentTransactionId(); /* * Check for db name conflict. This is just to give a more friendly *************** *** 367,373 **** new_record[Anum_pg_database_datconnlimit - 1] = Int32GetDatum(dbconnlimit); new_record[Anum_pg_database_datlastsysoid - 1] = ObjectIdGetDatum(src_lastsysoid); new_record[Anum_pg_database_datvacuumxid - 1] = TransactionIdGetDatum(src_vacuumxid); ! new_record[Anum_pg_database_datfrozenxid - 1] = TransactionIdGetDatum(src_frozenxid); new_record[Anum_pg_database_dattablespace - 1] = ObjectIdGetDatum(dst_deftablespace); /* --- 369,375 ---- new_record[Anum_pg_database_datconnlimit - 1] = Int32GetDatum(dbconnlimit); new_record[Anum_pg_database_datlastsysoid - 1] = ObjectIdGetDatum(src_lastsysoid); new_record[Anum_pg_database_datvacuumxid - 1] = TransactionIdGetDatum(src_vacuumxid); ! new_record[Anum_pg_database_datminxid - 1] = TransactionIdGetDatum(src_minxid); new_record[Anum_pg_database_dattablespace - 1] = ObjectIdGetDatum(dst_deftablespace); /* *************** *** 1050,1055 **** --- 1052,1119 ---- */ } + /* + * UnfreezeDatabase + * Unfreezes a database + * + * Unfreezing a database is to set datminxid and datvacuumxid to a current + * normal Xid. Currently, we do this anytime somebody connects to a database + * that is currently marked as frozen (datminxid = FrozenTransactionId). + * + * NB --- this is called early during backend initialization. + */ + void + UnfreezeDatabase(Oid dbid, TransactionId unfreezeXid) + { + Relation dbRel; + HeapTuple tuple; + Form_pg_database dbForm; + bool dirty = false; + + PG_TRY(); + { + disable_heap_unfreeze = true; + + dbRel = heap_open(DatabaseRelationId, RowExclusiveLock); + + /* fetch a copy of the tuple to scribble on */ + tuple = SearchSysCacheCopy(DATABASEOID, + dbid, + 0, 0, 0); + + if (!HeapTupleIsValid(tuple)) + elog(ERROR, + "cache lookup failed for database %u", dbid); + + dbForm = (Form_pg_database) GETSTRUCT(tuple); + + /* make sure no one did it while we weren't looking */ + if (TransactionIdEquals(dbForm->datminxid, FrozenTransactionId)) + { + dbForm->datminxid = unfreezeXid; + dirty = true; + } + if (TransactionIdEquals(dbForm->datvacuumxid, FrozenTransactionId)) + { + dbForm->datvacuumxid = unfreezeXid; + dirty = true; + } + + if (dirty) + heap_inplace_update(dbRel, tuple); + + heap_close(dbRel, RowExclusiveLock); + } + PG_CATCH(); + { + disable_heap_unfreeze = false; + PG_RE_THROW(); + }; + PG_END_TRY(); + + /* reenable heap unfreezing */ + disable_heap_unfreeze = false; + } /* * Helper functions *************** *** 1066,1072 **** Oid *dbIdP, Oid *ownerIdP, int *encodingP, bool *dbIsTemplateP, bool *dbAllowConnP, Oid *dbLastSysOidP, ! TransactionId *dbVacuumXidP, TransactionId *dbFrozenXidP, Oid *dbTablespace) { bool result = false; --- 1130,1136 ---- Oid *dbIdP, Oid *ownerIdP, int *encodingP, bool *dbIsTemplateP, bool *dbAllowConnP, Oid *dbLastSysOidP, ! TransactionId *dbVacuumXidP, TransactionId *dbMinXidP, Oid *dbTablespace) { bool result = false; *************** *** 1155,1163 **** /* limit of vacuumed XIDs */ if (dbVacuumXidP) *dbVacuumXidP = dbform->datvacuumxid; ! /* limit of frozen XIDs */ ! if (dbFrozenXidP) ! *dbFrozenXidP = dbform->datfrozenxid; /* default tablespace for this database */ if (dbTablespace) *dbTablespace = dbform->dattablespace; --- 1219,1227 ---- /* limit of vacuumed XIDs */ if (dbVacuumXidP) *dbVacuumXidP = dbform->datvacuumxid; ! /* limit of min XIDs */ ! if (dbMinXidP) ! *dbMinXidP = dbform->datminxid; /* default tablespace for this database */ if (dbTablespace) *dbTablespace = dbform->dattablespace; Index: src/backend/commands/vacuum.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/commands/vacuum.c,v retrieving revision 1.330 diff -c -r1.330 vacuum.c *** src/backend/commands/vacuum.c 10 May 2006 23:18:39 -0000 1.330 --- src/backend/commands/vacuum.c 20 May 2006 00:36:13 -0000 *************** *** 127,132 **** --- 127,133 ---- Size min_tlen; Size max_tlen; bool hasindex; + TransactionId minxid; /* Minimum Xid present anywhere on table */ /* vtlinks array for tuple chain following - sorted by new_tid */ int num_vtlinks; VTupleLink vtlinks; *************** *** 194,218 **** static int elevel = -1; - static TransactionId OldestXmin; - static TransactionId FreezeLimit; - /* non-export function prototypes */ static List *get_rel_oids(List *relids, const RangeVar *vacrel, const char *stmttype); ! static void vac_update_dbstats(Oid dbid, ! TransactionId vacuumXID, ! TransactionId frozenXID); ! static void vac_truncate_clog(TransactionId vacuumXID, ! TransactionId frozenXID); ! static bool vacuum_rel(Oid relid, VacuumStmt *vacstmt, char expected_relkind); static void full_vacuum_rel(Relation onerel, VacuumStmt *vacstmt); static void scan_heap(VRelStats *vacrelstats, Relation onerel, ! VacPageList vacuum_pages, VacPageList fraged_pages); static void repair_frag(VRelStats *vacrelstats, Relation onerel, VacPageList vacuum_pages, VacPageList fraged_pages, ! int nindexes, Relation *Irel); static void move_chain_tuple(Relation rel, Buffer old_buf, Page old_page, HeapTuple old_tup, Buffer dst_buf, Page dst_page, VacPage dst_vacpage, --- 195,214 ---- static int elevel = -1; /* non-export function prototypes */ static List *get_rel_oids(List *relids, const RangeVar *vacrel, const char *stmttype); ! static void vac_update_dbminxid(Oid dbid); ! static void vac_truncate_clog(void); ! static void vacuum_rel(Oid relid, VacuumStmt *vacstmt, char expected_relkind); static void full_vacuum_rel(Relation onerel, VacuumStmt *vacstmt); static void scan_heap(VRelStats *vacrelstats, Relation onerel, ! VacPageList vacuum_pages, VacPageList fraged_pages, ! TransactionId FreezeLimit, TransactionId OldestXmin); static void repair_frag(VRelStats *vacrelstats, Relation onerel, VacPageList vacuum_pages, VacPageList fraged_pages, ! int nindexes, Relation *Irel, TransactionId OldestXmin); static void move_chain_tuple(Relation rel, Buffer old_buf, Page old_page, HeapTuple old_tup, Buffer dst_buf, Page dst_page, VacPage dst_vacpage, *************** *** 268,275 **** vacuum(VacuumStmt *vacstmt, List *relids) { const char *stmttype = vacstmt->vacuum ? "VACUUM" : "ANALYZE"; - TransactionId initialOldestXmin = InvalidTransactionId; - TransactionId initialFreezeLimit = InvalidTransactionId; volatile MemoryContext anl_context = NULL; volatile bool all_rels, in_outer_xact, --- 264,269 ---- *************** *** 352,383 **** */ relations = get_rel_oids(relids, vacstmt->relation, stmttype); - if (vacstmt->vacuum && all_rels) - { - /* - * It's a database-wide VACUUM. - * - * Compute the initially applicable OldestXmin and FreezeLimit XIDs, - * so that we can record these values at the end of the VACUUM. Note - * that individual tables may well be processed with newer values, but - * we can guarantee that no (non-shared) relations are processed with - * older ones. - * - * It is okay to record non-shared values in pg_database, even though - * we may vacuum shared relations with older cutoffs, because only the - * minimum of the values present in pg_database matters. We can be - * sure that shared relations have at some time been vacuumed with - * cutoffs no worse than the global minimum; for, if there is a - * backend in some other DB with xmin = OLDXMIN that's determining the - * cutoff with which we vacuum shared relations, it is not possible - * for that database to have a cutoff newer than OLDXMIN recorded in - * pg_database. - */ - vacuum_set_xid_limits(vacstmt, false, - &initialOldestXmin, - &initialFreezeLimit); - } - /* * Decide whether we need to start/commit our own transactions. * --- 346,351 ---- *************** *** 438,443 **** --- 406,421 ---- VacuumCostBalance = 0; /* + * During vacuum, we are going to lock the relation with a writer's + * lock, but if it's already frozen, we won't do any writing on it, so + * disable the unfreezing for the duration of this VACUUM operation. + * However, if this a FULL vacuum, we may mark some tuples with our + * Xid even if the table is frozen, so skip this step. + */ + if (!vacstmt->full) + disable_heap_unfreeze = true; + + /* * Loop to process each selected relation. */ foreach(cur, relations) *************** *** 445,454 **** Oid relid = lfirst_oid(cur); if (vacstmt->vacuum) ! { ! if (!vacuum_rel(relid, vacstmt, RELKIND_RELATION)) ! all_rels = false; /* forget about updating dbstats */ ! } if (vacstmt->analyze) { MemoryContext old_context = NULL; --- 423,430 ---- Oid relid = lfirst_oid(cur); if (vacstmt->vacuum) ! vacuum_rel(relid, vacstmt, RELKIND_RELATION); ! if (vacstmt->analyze) { MemoryContext old_context = NULL; *************** *** 493,504 **** --- 469,484 ---- { /* Make sure cost accounting is turned off after error */ VacuumCostActive = false; + /* reenable heap unfreezing too */ + disable_heap_unfreeze = false; PG_RE_THROW(); } PG_END_TRY(); /* Turn off vacuum cost accounting */ VacuumCostActive = false; + /* reenable heap unfreezing too */ + disable_heap_unfreeze = false; /* * Finish up processing. *************** *** 531,547 **** if (all_rels) PrintFreeSpaceMapStatistics(elevel); ! /* ! * If we completed a database-wide VACUUM without skipping any ! * relations, update the database's pg_database row with info about ! * the transaction IDs used, and try to truncate pg_clog. ! */ ! if (all_rels) ! { ! vac_update_dbstats(MyDatabaseId, ! initialOldestXmin, initialFreezeLimit); ! vac_truncate_clog(initialOldestXmin, initialFreezeLimit); ! } } /* --- 511,521 ---- if (all_rels) PrintFreeSpaceMapStatistics(elevel); ! /* Update pg_database.datminxid and datvacuumxid */ ! vac_update_dbminxid(MyDatabaseId); ! ! /* Try to truncate pg_clog. */ ! vac_truncate_clog(); } /* *************** *** 687,797 **** */ void vac_update_relstats(Oid relid, BlockNumber num_pages, double num_tuples, ! bool hasindex) { Relation rd; HeapTuple ctup; Form_pg_class pgcform; bool dirty; ! rd = heap_open(RelationRelationId, RowExclusiveLock); ! ! /* Fetch a copy of the tuple to scribble on */ ! ctup = SearchSysCacheCopy(RELOID, ! ObjectIdGetDatum(relid), ! 0, 0, 0); ! if (!HeapTupleIsValid(ctup)) ! elog(ERROR, "pg_class entry for relid %u vanished during vacuuming", ! relid); ! pgcform = (Form_pg_class) GETSTRUCT(ctup); ! /* Apply required updates, if any, to copied tuple */ ! dirty = false; ! if (pgcform->relpages != (int32) num_pages) ! { ! pgcform->relpages = (int32) num_pages; ! dirty = true; ! } ! if (pgcform->reltuples != (float4) num_tuples) ! { ! pgcform->reltuples = (float4) num_tuples; ! dirty = true; ! } ! if (pgcform->relhasindex != hasindex) ! { ! pgcform->relhasindex = hasindex; ! dirty = true; ! } ! /* ! * If we have discovered that there are no indexes, then there's no ! * primary key either. This could be done more thoroughly... ! */ ! if (!hasindex) ! { ! if (pgcform->relhaspkey) { ! pgcform->relhaspkey = false; dirty = true; } - } ! /* ! * If anything changed, write out the tuple ! */ ! if (dirty) ! heap_inplace_update(rd, ctup); ! heap_close(rd, RowExclusiveLock); } /* ! * vac_update_dbstats() -- update statistics for one database * ! * Update the whole-database statistics that are kept in its pg_database ! * row, and the flat-file copy of pg_database. * * We violate transaction semantics here by overwriting the database's ! * existing pg_database tuple with the new values. This is reasonably ! * safe since the new values are correct whether or not this transaction * commits. As with vac_update_relstats, this avoids leaving dead tuples * behind after a VACUUM. * ! * This routine is shared by full and lazy VACUUM. Note that it is only ! * applied after a database-wide VACUUM operation. */ static void ! vac_update_dbstats(Oid dbid, ! TransactionId vacuumXID, ! TransactionId frozenXID) { - Relation relation; HeapTuple tuple; Form_pg_database dbform; ! relation = heap_open(DatabaseRelationId, RowExclusiveLock); ! /* Fetch a copy of the tuple to scribble on */ ! tuple = SearchSysCacheCopy(DATABASEOID, ! ObjectIdGetDatum(dbid), ! 0, 0, 0); ! if (!HeapTupleIsValid(tuple)) ! elog(ERROR, "could not find tuple for database %u", dbid); ! dbform = (Form_pg_database) GETSTRUCT(tuple); ! ! /* overwrite the existing statistics in the tuple */ ! dbform->datvacuumxid = vacuumXID; ! dbform->datfrozenxid = frozenXID; ! heap_inplace_update(relation, tuple); ! heap_close(relation, RowExclusiveLock); ! /* Mark the flat-file copy of pg_database for update at commit */ ! database_file_update_needed(); ! } /* * vac_truncate_clog() -- attempt to truncate the commit log --- 661,919 ---- */ void vac_update_relstats(Oid relid, BlockNumber num_pages, double num_tuples, ! bool hasindex, TransactionId minxid, ! TransactionId vacuumxid) { Relation rd; HeapTuple ctup; Form_pg_class pgcform; bool dirty; ! PG_TRY(); ! { ! /* Don't unfreeze pg_class by doing this */ ! disable_heap_unfreeze = true; ! rd = heap_open(RelationRelationId, RowExclusiveLock); ! /* Fetch a copy of the tuple to scribble on */ ! ctup = SearchSysCacheCopy(RELOID, ! ObjectIdGetDatum(relid), ! 0, 0, 0); ! if (!HeapTupleIsValid(ctup)) ! elog(ERROR, "pg_class entry for relid %u vanished during vacuuming", ! relid); ! pgcform = (Form_pg_class) GETSTRUCT(ctup); ! ! /* Apply required updates, if any, to copied tuple */ ! dirty = false; ! if (pgcform->relpages != (int32) num_pages) { ! pgcform->relpages = (int32) num_pages; ! dirty = true; ! } ! if (pgcform->reltuples != (float4) num_tuples) ! { ! pgcform->reltuples = (float4) num_tuples; ! dirty = true; ! } ! if (pgcform->relhasindex != hasindex) ! { ! pgcform->relhasindex = hasindex; ! dirty = true; ! } ! if (pgcform->relminxid != minxid) ! { ! pgcform->relminxid = minxid; ! dirty = true; ! } ! /* ! * If relminxid is Frozen (i.e. the table is truly frozen), it's more ! * useful to mark it as having vacuumxid frozen as well. This means ! * that this table does not impose any particular limit to pg_clog ! * truncation. ! * ! * It seems a bit of a hack to be doing this here, but it would be ! * even uglier to have all the callers do it. ! */ ! if (TransactionIdEquals(pgcform->relminxid, FrozenTransactionId)) ! vacuumxid = FrozenTransactionId; ! if (pgcform->relvacuumxid != vacuumxid) ! { ! pgcform->relvacuumxid = vacuumxid; dirty = true; } ! /* ! * If we have discovered that there are no indexes, then there's no ! * primary key either. This could be done more thoroughly... ! */ ! if (!hasindex) ! { ! if (pgcform->relhaspkey) ! { ! pgcform->relhaspkey = false; ! dirty = true; ! } ! } ! ! /* ! * If anything changed, write out the tuple ! */ ! if (dirty) ! heap_inplace_update(rd, ctup); ! ! heap_close(rd, RowExclusiveLock); ! ! } ! PG_CATCH(); ! { ! disable_heap_unfreeze = false; ! PG_RE_THROW(); ! } ! PG_END_TRY(); ! disable_heap_unfreeze = false; } /* ! * vac_update_dbminxid() -- update the minimum Xid present in one database * ! * Update pg_database's datminxid and datvacuumxid, and the flat-file copy ! * of it. datminxid is updated to the minimum of all relminxid found in ! * pg_class. The value is also returned in minXID. * * We violate transaction semantics here by overwriting the database's ! * existing pg_database tuple with the new value. This is reasonably ! * safe since the new value is correct whether or not this transaction * commits. As with vac_update_relstats, this avoids leaving dead tuples * behind after a VACUUM. * ! * This routine is shared by full and lazy VACUUM. */ static void ! vac_update_dbminxid(Oid dbid) { HeapTuple tuple; Form_pg_database dbform; + Relation relation; + SysScanDesc scan; + HeapTuple classTup; + TransactionId newMinXid = InvalidTransactionId; + TransactionId newVacXid = InvalidTransactionId; + bool dirty = false; + + PG_TRY(); + { + /* + * Disable heap unfreezing of pg_database, since we are going + * to update the tuple in-place and won't be writing our Xid on it. + */ + disable_heap_unfreeze = true; ! /* ! * We must seqscan pg_class to find the minimum Xid, because there ! * is no index that can help us here. ! */ ! relation = heap_open(RelationRelationId, AccessShareLock); ! scan = systable_beginscan(relation, InvalidOid, false, ! SnapshotNow, 0, NULL); ! while ((classTup = systable_getnext(scan)) != NULL) ! { ! Form_pg_class classForm; ! classForm = (Form_pg_class) GETSTRUCT(classTup); ! /* ! * Only consider heap and TOAST tables (anything else should have ! * InvalidTransactionId in both fields anyway.) ! */ ! if (classForm->relkind != RELKIND_RELATION && ! classForm->relkind != RELKIND_TOASTVALUE) ! continue; ! ! /* ! * Compute the minimum relminxid in all the tables in the database. ! * We consider only normal Xids --- this means in particular we ! * avoid setting the minimum to FrozenTransactionId here. If all ! * tables turn out to be frozen, we will exit the loop with the ! * value set to InvalidTransactionId. We cannot allow newMinXid to ! * be set to FrozenTransactionId --- that messes us up because of ! * the semantics of TransactionIdPrecedes. ! * ! * Other values we are ignoring here are InvalidTransactionId ! * (which is set for some bootstrap tables) and ! * BootstrapTransactionId. This doesn't cause any problems because ! * for all practical purposes they behave exactly like ! * FrozenTransactionId. ! */ ! if (TransactionIdIsNormal(classForm->relminxid) && ! (!TransactionIdIsValid(newMinXid) || ! TransactionIdPrecedes(classForm->relminxid, newMinXid))) ! newMinXid = classForm->relminxid; ! ! /* ditto, for relvacuumxid */ ! if (TransactionIdIsNormal(classForm->relvacuumxid) && ! (!TransactionIdIsValid(newVacXid) || ! TransactionIdPrecedes(classForm->relvacuumxid, newVacXid))) ! newVacXid = classForm->relvacuumxid; ! } ! ! /* we're done with pg_class */ ! systable_endscan(scan); ! heap_close(relation, AccessShareLock); ! ! /* ! * If we got InvalidTransactionId, then all tables must be frozen. As ! * a special protection, we only allow a database to be wholly marked ! * as "frozen" if this is a standalone backend. Otherwise, some other ! * backend may be modifying a table behind our back; we can't safely ! * assume that the database is truly frozen. So if we detect that all ! * tables are frozen but we're running on a regular backend, fall back ! * to storing RecentXmin in datminxid (the minimum Xid which could be ! * unfreezing a table simultaneously.) ! */ ! if (!TransactionIdIsValid(newMinXid)) ! newMinXid = IsPostmasterEnvironment ? RecentXmin : ! FrozenTransactionId; ! ! /* ! * In datvacuumxid, if we got InvalidTransactionId we use ! * FrozenTransactionId in pg_database. This case is not valid as ! * truncation point for pg_clog, but it's handled specially in ! * vac_truncate_clog() because it's useful as a permanent sign ! * that this database doesn't have a true lower limit on truncation. ! */ ! if (!TransactionIdIsValid(newVacXid)) ! newVacXid = FrozenTransactionId; ! ! /* Now fetch the pg_database tuple we need to update. */ ! relation = heap_open(DatabaseRelationId, RowExclusiveLock); ! ! /* Fetch a copy of the tuple to scribble on */ ! tuple = SearchSysCacheCopy(DATABASEOID, ! ObjectIdGetDatum(dbid), ! 0, 0, 0); ! ! if (!HeapTupleIsValid(tuple)) ! elog(ERROR, "could not find tuple for database %u", dbid); ! ! dbform = (Form_pg_database) GETSTRUCT(tuple); ! ! if (TransactionIdPrecedes(dbform->datminxid, newMinXid) || ! TransactionIdEquals(newMinXid, FrozenTransactionId)) ! { ! dbform->datminxid = newMinXid; ! dirty = true; ! } ! if (TransactionIdPrecedes(dbform->datvacuumxid, newVacXid) || ! TransactionIdEquals(newVacXid, FrozenTransactionId)) ! { ! dbform->datvacuumxid = newVacXid; ! dirty = true; ! } ! ! if (dirty) ! heap_inplace_update(relation, tuple); ! ! heap_freetuple(tuple); ! ! heap_close(relation, RowExclusiveLock); ! } ! PG_CATCH(); ! { ! /* Make sure to reenable heap unfreezing in case of error */ ! disable_heap_unfreeze = false; ! PG_RE_THROW(); ! } ! PG_END_TRY(); + /* reenable heap unfreezing */ + disable_heap_unfreeze = false; + } /* * vac_truncate_clog() -- attempt to truncate the commit log *************** *** 806,833 **** * will generate more-annoying warnings, and ultimately refuse to issue * any more new XIDs. * - * The passed XIDs are simply the ones I just wrote into my pg_database - * entry. They're used to initialize the "min" calculations. - * * This routine is shared by full and lazy VACUUM. Note that it is only * applied after a database-wide VACUUM operation. */ static void ! vac_truncate_clog(TransactionId vacuumXID, TransactionId frozenXID) { TransactionId myXID = GetCurrentTransactionId(); Relation relation; HeapScanDesc scan; HeapTuple tuple; int32 age; NameData oldest_datname; bool vacuumAlreadyWrapped = false; ! bool frozenAlreadyWrapped = false; ! /* init oldest_datname to sync with my frozenXID */ namestrcpy(&oldest_datname, get_database_name(MyDatabaseId)); /* * Note: the "already wrapped" cases should now be impossible due to the * defenses in GetNewTransactionId, but we keep them anyway. */ --- 928,963 ---- * will generate more-annoying warnings, and ultimately refuse to issue * any more new XIDs. * * This routine is shared by full and lazy VACUUM. Note that it is only * applied after a database-wide VACUUM operation. */ static void ! vac_truncate_clog(void) { TransactionId myXID = GetCurrentTransactionId(); + TransactionId minXID; + TransactionId vacuumXID; Relation relation; HeapScanDesc scan; HeapTuple tuple; int32 age; NameData oldest_datname; bool vacuumAlreadyWrapped = false; ! bool minAlreadyWrapped = false; ! /* ! * Initialize the minimum values to a recent value. ! */ ! minXID = vacuumXID = RecentXmin; namestrcpy(&oldest_datname, get_database_name(MyDatabaseId)); /* + * Note we don't initialize the oldest database name here. This is because + * the name will only be used if myXID - minXID is some positive quantity, + * and if that happens, we will also initialize the name in the loop below. + */ + + /* * Note: the "already wrapped" cases should now be impossible due to the * defenses in GetNewTransactionId, but we keep them anyway. */ *************** *** 839,849 **** { Form_pg_database dbform = (Form_pg_database) GETSTRUCT(tuple); ! /* Ignore non-connectable databases (eg, template0) */ ! /* It's assumed that these have been frozen correctly */ ! if (!dbform->datallowconn) ! continue; ! if (TransactionIdIsNormal(dbform->datvacuumxid)) { if (TransactionIdPrecedes(myXID, dbform->datvacuumxid)) --- 969,984 ---- { Form_pg_database dbform = (Form_pg_database) GETSTRUCT(tuple); ! /* ! * Note we ignore FrozenTransactionId here for both values. If all ! * databases turn out to be frozen, the values will end up as the ! * current XID, which is the correct truncation point for pg_clog and ! * also the correct value for the varsup.c limit. ! * ! * Also note that the all-databases-are-frozen case is pretty rare. ! * It can only happen if the user VACUUM FREEZEs all databases using ! * standalone backends. ! */ if (TransactionIdIsNormal(dbform->datvacuumxid)) { if (TransactionIdPrecedes(myXID, dbform->datvacuumxid)) *************** *** 851,867 **** else if (TransactionIdPrecedes(dbform->datvacuumxid, vacuumXID)) vacuumXID = dbform->datvacuumxid; } ! if (TransactionIdIsNormal(dbform->datfrozenxid)) { ! if (TransactionIdPrecedes(myXID, dbform->datfrozenxid)) ! frozenAlreadyWrapped = true; ! else if (TransactionIdPrecedes(dbform->datfrozenxid, frozenXID)) { ! frozenXID = dbform->datfrozenxid; namecpy(&oldest_datname, &dbform->datname); } } } heap_endscan(scan); --- 986,1003 ---- else if (TransactionIdPrecedes(dbform->datvacuumxid, vacuumXID)) vacuumXID = dbform->datvacuumxid; } ! if (TransactionIdIsNormal(dbform->datminxid)) { ! if (TransactionIdPrecedes(myXID, dbform->datminxid)) ! minAlreadyWrapped = true; ! else if (TransactionIdPrecedes(dbform->datminxid, minXID)) { ! minXID = dbform->datminxid; namecpy(&oldest_datname, &dbform->datname); } } } + elog(NOTICE, "clog truncation: %u, varsup.c limit: %u", vacuumXID, minXID); heap_endscan(scan); *************** *** 886,892 **** * Do not update varsup.c if we seem to have suffered wraparound already; * the computed XID might be bogus. */ ! if (frozenAlreadyWrapped) { ereport(WARNING, (errmsg("some databases have not been vacuumed in over 1 billion transactions"), --- 1022,1028 ---- * Do not update varsup.c if we seem to have suffered wraparound already; * the computed XID might be bogus. */ ! if (minAlreadyWrapped) { ereport(WARNING, (errmsg("some databases have not been vacuumed in over 1 billion transactions"), *************** *** 895,904 **** } /* Update the wrap limit for GetNewTransactionId */ ! SetTransactionIdLimit(frozenXID, &oldest_datname); /* Give warning about impending wraparound problems */ ! age = (int32) (myXID - frozenXID); if (age > (int32) ((MaxTransactionId >> 3) * 3)) ereport(WARNING, (errmsg("database \"%s\" must be vacuumed within %u transactions", --- 1031,1040 ---- } /* Update the wrap limit for GetNewTransactionId */ ! SetTransactionIdLimit(minXID, &oldest_datname); /* Give warning about impending wraparound problems */ ! age = (int32) (myXID - minXID); if (age > (int32) ((MaxTransactionId >> 3) * 3)) ereport(WARNING, (errmsg("database \"%s\" must be vacuumed within %u transactions", *************** *** 920,930 **** /* * vacuum_rel() -- vacuum one heap relation * - * Returns TRUE if we actually processed the relation (or can ignore it - * for some reason), FALSE if we failed to process it due to permissions - * or other reasons. (A FALSE result really means that some data - * may have been left unvacuumed, so we can't update XID stats.) - * * Doing one heap at a time incurs extra overhead, since we need to * check that the heap exists again just before we vacuum it. The * reason that we do this is so that vacuuming can be spread across --- 1056,1061 ---- *************** *** 933,946 **** * * At entry and exit, we are not inside a transaction. */ ! static bool vacuum_rel(Oid relid, VacuumStmt *vacstmt, char expected_relkind) { LOCKMODE lmode; Relation onerel; LockRelId onerelid; Oid toast_relid; - bool result; /* Begin a transaction for vacuuming this relation */ StartTransactionCommand(); --- 1064,1076 ---- * * At entry and exit, we are not inside a transaction. */ ! static void vacuum_rel(Oid relid, VacuumStmt *vacstmt, char expected_relkind) { LOCKMODE lmode; Relation onerel; LockRelId onerelid; Oid toast_relid; /* Begin a transaction for vacuuming this relation */ StartTransactionCommand(); *************** *** 969,983 **** { StrategyHintVacuum(false); CommitTransactionCommand(); ! return true; /* okay 'cause no data there */ } /* * Determine the type of lock we want --- hard exclusive lock for a FULL ! * vacuum, but just ShareUpdateExclusiveLock for concurrent vacuum. Either ! * way, we can be sure that no other backend is vacuuming the same table. */ ! lmode = vacstmt->full ? AccessExclusiveLock : ShareUpdateExclusiveLock; /* * Open the class, get an appropriate lock on it, and check permissions. --- 1099,1115 ---- { StrategyHintVacuum(false); CommitTransactionCommand(); ! return; } /* * Determine the type of lock we want --- hard exclusive lock for a FULL ! * vacuum, ExclusiveLock for VACUUM FREEZE, but just ! * ShareUpdateExclusiveLock for concurrent vacuum. Either way, we can be ! * sure that no other backend is vacuuming the same table. */ ! lmode = vacstmt->full ? AccessExclusiveLock : ! vacstmt->freeze ? ExclusiveLock : ShareUpdateExclusiveLock; /* * Open the class, get an appropriate lock on it, and check permissions. *************** *** 1000,1006 **** relation_close(onerel, lmode); StrategyHintVacuum(false); CommitTransactionCommand(); ! return false; } /* --- 1132,1138 ---- relation_close(onerel, lmode); StrategyHintVacuum(false); CommitTransactionCommand(); ! return; } /* *************** *** 1015,1021 **** relation_close(onerel, lmode); StrategyHintVacuum(false); CommitTransactionCommand(); ! return false; } /* --- 1147,1153 ---- relation_close(onerel, lmode); StrategyHintVacuum(false); CommitTransactionCommand(); ! return; } /* *************** *** 1030,1036 **** relation_close(onerel, lmode); StrategyHintVacuum(false); CommitTransactionCommand(); ! return true; /* assume no long-lived data in temp tables */ } /* --- 1162,1168 ---- relation_close(onerel, lmode); StrategyHintVacuum(false); CommitTransactionCommand(); ! return; /* assume no long-lived data in temp tables */ } /* *************** *** 1059,1066 **** else lazy_vacuum_rel(onerel, vacstmt); - result = true; /* did the vacuum */ - /* all done with this class, but hold lock until commit */ relation_close(onerel, NoLock); --- 1191,1196 ---- *************** *** 1073,1094 **** /* * If the relation has a secondary toast rel, vacuum that too while we * still hold the session lock on the master table. Note however that ! * "analyze" will not get done on the toast table. This is good, because ! * the toaster always uses hardcoded index access and statistics are ! * totally unimportant for toast relations. */ if (toast_relid != InvalidOid) ! { ! if (!vacuum_rel(toast_relid, vacstmt, RELKIND_TOASTVALUE)) ! result = false; /* failed to vacuum the TOAST table? */ ! } /* * Now release the session-level lock on the master table. */ UnlockRelationForSession(&onerelid, lmode); - - return result; } --- 1203,1219 ---- /* * If the relation has a secondary toast rel, vacuum that too while we * still hold the session lock on the master table. Note however that ! * "analyze" will not get done on the toast table. This is good, ! * because the toaster always uses hardcoded index access and ! * statistics are totally unimportant for toast relations. */ if (toast_relid != InvalidOid) ! vacuum_rel(toast_relid, vacstmt, RELKIND_TOASTVALUE); /* * Now release the session-level lock on the master table. */ UnlockRelationForSession(&onerelid, lmode); } *************** *** 1120,1125 **** --- 1245,1252 ---- int nindexes, i; VRelStats *vacrelstats; + TransactionId FreezeLimit, + OldestXmin; vacuum_set_xid_limits(vacstmt, onerel->rd_rel->relisshared, &OldestXmin, &FreezeLimit); *************** *** 1132,1140 **** vacrelstats->rel_tuples = 0; vacrelstats->hasindex = false; /* scan the heap */ vacuum_pages.num_pages = fraged_pages.num_pages = 0; ! scan_heap(vacrelstats, onerel, &vacuum_pages, &fraged_pages); /* Now open all indexes of the relation */ vac_open_indexes(onerel, AccessExclusiveLock, &nindexes, &Irel); --- 1259,1279 ---- vacrelstats->rel_tuples = 0; vacrelstats->hasindex = false; + /* + * Set initial minimum Xid, which will be updated if a smaller Xid is found + * in the relation by scan_heap. + * + * We use RecentXmin here (the minimum Xid that belongs to a transaction + * that is still open according to our snapshot), because it is the + * earliest transaction that could insert new tuples in the table after our + * VACUUM is done. + */ + vacrelstats->minxid = RecentXmin; + /* scan the heap */ vacuum_pages.num_pages = fraged_pages.num_pages = 0; ! scan_heap(vacrelstats, onerel, &vacuum_pages, &fraged_pages, FreezeLimit, ! OldestXmin); /* Now open all indexes of the relation */ vac_open_indexes(onerel, AccessExclusiveLock, &nindexes, &Irel); *************** *** 1162,1168 **** { /* Try to shrink heap */ repair_frag(vacrelstats, onerel, &vacuum_pages, &fraged_pages, ! nindexes, Irel); vac_close_indexes(nindexes, Irel, NoLock); } else --- 1301,1307 ---- { /* Try to shrink heap */ repair_frag(vacrelstats, onerel, &vacuum_pages, &fraged_pages, ! nindexes, Irel, OldestXmin); vac_close_indexes(nindexes, Irel, NoLock); } else *************** *** 1180,1186 **** /* update statistics in pg_class */ vac_update_relstats(RelationGetRelid(onerel), vacrelstats->rel_pages, ! vacrelstats->rel_tuples, vacrelstats->hasindex); /* report results to the stats collector, too */ pgstat_report_vacuum(RelationGetRelid(onerel), onerel->rd_rel->relisshared, --- 1319,1326 ---- /* update statistics in pg_class */ vac_update_relstats(RelationGetRelid(onerel), vacrelstats->rel_pages, ! vacrelstats->rel_tuples, vacrelstats->hasindex, ! vacrelstats->minxid, OldestXmin); /* report results to the stats collector, too */ pgstat_report_vacuum(RelationGetRelid(onerel), onerel->rd_rel->relisshared, *************** *** 1194,1209 **** * This routine sets commit status bits, constructs vacuum_pages (list * of pages we need to compact free space on and/or clean indexes of * deleted tuples), constructs fraged_pages (list of pages with free ! * space that tuples could be moved into), and calculates statistics ! * on the number of live tuples in the heap. */ static void scan_heap(VRelStats *vacrelstats, Relation onerel, ! VacPageList vacuum_pages, VacPageList fraged_pages) { BlockNumber nblocks, blkno; - HeapTupleData tuple; char *relname; VacPage vacpage; BlockNumber empty_pages, --- 1334,1350 ---- * This routine sets commit status bits, constructs vacuum_pages (list * of pages we need to compact free space on and/or clean indexes of * deleted tuples), constructs fraged_pages (list of pages with free ! * space that tuples could be moved into), calculates statistics on the ! * number of live tuples in the heap, and figures out the minimum normal ! * Xid present anywhere on the table. */ static void scan_heap(VRelStats *vacrelstats, Relation onerel, ! VacPageList vacuum_pages, VacPageList fraged_pages, ! TransactionId FreezeLimit, TransactionId OldestXmin) { BlockNumber nblocks, blkno; char *relname; VacPage vacpage; BlockNumber empty_pages, *************** *** 1317,1322 **** --- 1458,1464 ---- { ItemId itemid = PageGetItemId(page, offnum); bool tupgone = false; + HeapTupleData tuple; /* * Collect un-used items too - it's possible to have indexes *************** *** 1458,1463 **** --- 1600,1628 ---- min_tlen = tuple.t_len; if (tuple.t_len > max_tlen) max_tlen = tuple.t_len; + + /* + * Checks for pg_class.relminxid: determine the earliest + * Xid in any tuple of any table. + */ + if (TransactionIdIsNormal(HeapTupleHeaderGetXmin(tuple.t_data)) && + TransactionIdPrecedes(HeapTupleHeaderGetXmin(tuple.t_data), + vacrelstats->minxid)) + vacrelstats->minxid = HeapTupleHeaderGetXmin(tuple.t_data); + + /* + * If XMAX is not marked INVALID, we assume it's valid without + * making any check on it --- it must be recently obsoleted or + * still running, else HeapTupleSatisfiesVacuum would have + * deemed it removable. + */ + if (!(tuple.t_data->t_infomask | HEAP_XMAX_INVALID)) + { + if (TransactionIdIsNormal(HeapTupleHeaderGetXmax(tuple.t_data)) && + TransactionIdPrecedes(HeapTupleHeaderGetXmax(tuple.t_data), + vacrelstats->minxid)) + vacrelstats->minxid = HeapTupleHeaderGetXmax(tuple.t_data); + } } } /* scan along page */ *************** *** 1597,1603 **** static void repair_frag(VRelStats *vacrelstats, Relation onerel, VacPageList vacuum_pages, VacPageList fraged_pages, ! int nindexes, Relation *Irel) { TransactionId myXID = GetCurrentTransactionId(); Buffer dst_buffer = InvalidBuffer; --- 1762,1768 ---- static void repair_frag(VRelStats *vacrelstats, Relation onerel, VacPageList vacuum_pages, VacPageList fraged_pages, ! int nindexes, Relation *Irel, TransactionId OldestXmin) { TransactionId myXID = GetCurrentTransactionId(); Buffer dst_buffer = InvalidBuffer; *************** *** 2940,2946 **** /* now update statistics in pg_class */ vac_update_relstats(RelationGetRelid(indrel), stats->num_pages, stats->num_index_tuples, ! false); ereport(elevel, (errmsg("index \"%s\" now contains %.0f row versions in %u pages", --- 3105,3111 ---- /* now update statistics in pg_class */ vac_update_relstats(RelationGetRelid(indrel), stats->num_pages, stats->num_index_tuples, ! false, InvalidTransactionId, InvalidTransactionId); ereport(elevel, (errmsg("index \"%s\" now contains %.0f row versions in %u pages", *************** *** 3009,3015 **** /* now update statistics in pg_class */ vac_update_relstats(RelationGetRelid(indrel), stats->num_pages, stats->num_index_tuples, ! false); ereport(elevel, (errmsg("index \"%s\" now contains %.0f row versions in %u pages", --- 3174,3180 ---- /* now update statistics in pg_class */ vac_update_relstats(RelationGetRelid(indrel), stats->num_pages, stats->num_index_tuples, ! false, InvalidTransactionId, InvalidTransactionId); ereport(elevel, (errmsg("index \"%s\" now contains %.0f row versions in %u pages", Index: src/backend/commands/vacuumlazy.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/commands/vacuumlazy.c,v retrieving revision 1.70 diff -c -r1.70 vacuumlazy.c *** src/backend/commands/vacuumlazy.c 2 May 2006 22:25:10 -0000 1.70 --- src/backend/commands/vacuumlazy.c 19 May 2006 22:39:10 -0000 *************** *** 42,47 **** --- 42,48 ---- #include "access/genam.h" #include "access/heapam.h" #include "access/xlog.h" + #include "catalog/catalog.h" #include "commands/vacuum.h" #include "miscadmin.h" #include "pgstat.h" *************** *** 72,77 **** --- 73,79 ---- double tuples_deleted; BlockNumber nonempty_pages; /* actually, last nonempty page + 1 */ Size threshold; /* minimum interesting free space */ + TransactionId minxid; /* minimum Xid present anywhere in table */ /* List of TIDs of tuples we intend to delete */ /* NB: this list is ordered by TID address */ int num_dead_tuples; /* current # of entries */ *************** *** 88,100 **** static int elevel = -1; - static TransactionId OldestXmin; - static TransactionId FreezeLimit; - /* non-export function prototypes */ static void lazy_scan_heap(Relation onerel, LVRelStats *vacrelstats, ! Relation *Irel, int nindexes); static void lazy_vacuum_heap(Relation onerel, LVRelStats *vacrelstats); static void lazy_vacuum_index(Relation indrel, IndexBulkDeleteResult **stats, --- 90,100 ---- static int elevel = -1; /* non-export function prototypes */ static void lazy_scan_heap(Relation onerel, LVRelStats *vacrelstats, ! Relation *Irel, int nindexes, TransactionId FreezeLimit, ! TransactionId OldestXmin); static void lazy_vacuum_heap(Relation onerel, LVRelStats *vacrelstats); static void lazy_vacuum_index(Relation indrel, IndexBulkDeleteResult **stats, *************** *** 104,112 **** LVRelStats *vacrelstats); static int lazy_vacuum_page(Relation onerel, BlockNumber blkno, Buffer buffer, int tupindex, LVRelStats *vacrelstats); ! static void lazy_truncate_heap(Relation onerel, LVRelStats *vacrelstats); static BlockNumber count_nondeletable_pages(Relation onerel, ! LVRelStats *vacrelstats); static void lazy_space_alloc(LVRelStats *vacrelstats, BlockNumber relblocks); static void lazy_record_dead_tuple(LVRelStats *vacrelstats, ItemPointer itemptr); --- 104,113 ---- LVRelStats *vacrelstats); static int lazy_vacuum_page(Relation onerel, BlockNumber blkno, Buffer buffer, int tupindex, LVRelStats *vacrelstats); ! static void lazy_truncate_heap(Relation onerel, LVRelStats *vacrelstats, ! TransactionId OldestXmin); static BlockNumber count_nondeletable_pages(Relation onerel, ! LVRelStats *vacrelstats, TransactionId OldestXmin); static void lazy_space_alloc(LVRelStats *vacrelstats, BlockNumber relblocks); static void lazy_record_dead_tuple(LVRelStats *vacrelstats, ItemPointer itemptr); *************** *** 122,128 **** * lazy_vacuum_rel() -- perform LAZY VACUUM for one heap relation * * This routine vacuums a single heap, cleans out its indexes, and ! * updates its num_pages and num_tuples statistics. * * At entry, we have already established a transaction and opened * and locked the relation. --- 123,130 ---- * lazy_vacuum_rel() -- perform LAZY VACUUM for one heap relation * * This routine vacuums a single heap, cleans out its indexes, and ! * updates its relpages and reltuples statistics, as well as the ! * relminxid and relvacuumxid information. * * At entry, we have already established a transaction and opened * and locked the relation. *************** *** 135,146 **** --- 137,164 ---- int nindexes; bool hasindex; BlockNumber possibly_freeable; + TransactionId OldestXmin, + FreezeLimit; if (vacstmt->verbose) elevel = INFO; else elevel = DEBUG2; + /* + * We can skip vacuuming a frozen table, since we know nobody has touched + * it since the last VACUUM. XXX Do it only in regular backends though, + * just to make sure we won't be skipping vacuums in standalone backends + * due to strange sinval behavior. + */ + if (onerel->rd_rel->relminxid == FrozenTransactionId && IsUnderPostmaster) + { + elog(LOG, "skipping VACUUM to frozen relation \"%s\"", + RelationGetRelationName(onerel)); + + return; + } + vacuum_set_xid_limits(vacstmt, onerel->rd_rel->relisshared, &OldestXmin, &FreezeLimit); *************** *** 150,161 **** /* XXX should we scale it up or down? Adjust vacuum.c too, if so */ vacrelstats->threshold = GetAvgFSMRequestSize(&onerel->rd_node); /* Open all indexes of the relation */ vac_open_indexes(onerel, ShareUpdateExclusiveLock, &nindexes, &Irel); hasindex = (nindexes > 0); /* Do the vacuuming */ ! lazy_scan_heap(onerel, vacrelstats, Irel, nindexes); /* Done with indexes */ vac_close_indexes(nindexes, Irel, NoLock); --- 168,201 ---- /* XXX should we scale it up or down? Adjust vacuum.c too, if so */ vacrelstats->threshold = GetAvgFSMRequestSize(&onerel->rd_node); + /* + * Set initial minimum Xid, which will be updated if a smaller Xid is found + * in the relation by lazy_scan_heap. + * + * In VACUUM FREEZE, we use FrozenTransactionId here. This is safe + * because we acquired ExclusiveLock above, so no one can be inserting + * newer tuples in pages earlier to those we have scanned. If there's any + * tuple whose Xid we can't change, the lower bound will be raised. + * + * In the non-FREEZE case, we use RecentXmin here (the minimum Xid that + * belongs to a transaction that is still open according to our snapshot), + * because it is the earliest transaction that could concurrently insert + * new tuples in the table. + * + * The FREEZE case doesn't have an equivalent in VACUUM FULL because FULL + * in combination with FREEZE is verboten. + */ + if (vacstmt->freeze) + vacrelstats->minxid = FrozenTransactionId; + else + vacrelstats->minxid = RecentXmin; + /* Open all indexes of the relation */ vac_open_indexes(onerel, ShareUpdateExclusiveLock, &nindexes, &Irel); hasindex = (nindexes > 0); /* Do the vacuuming */ ! lazy_scan_heap(onerel, vacrelstats, Irel, nindexes, FreezeLimit, OldestXmin); /* Done with indexes */ vac_close_indexes(nindexes, Irel, NoLock); *************** *** 169,184 **** possibly_freeable = vacrelstats->rel_pages - vacrelstats->nonempty_pages; if (possibly_freeable >= REL_TRUNCATE_MINIMUM || possibly_freeable >= vacrelstats->rel_pages / REL_TRUNCATE_FRACTION) ! lazy_truncate_heap(onerel, vacrelstats); /* Update shared free space map with final free space info */ lazy_update_fsm(onerel, vacrelstats); /* Update statistics in pg_class */ ! vac_update_relstats(RelationGetRelid(onerel), ! vacrelstats->rel_pages, ! vacrelstats->rel_tuples, ! hasindex); /* report results to the stats collector, too */ pgstat_report_vacuum(RelationGetRelid(onerel), onerel->rd_rel->relisshared, --- 209,223 ---- possibly_freeable = vacrelstats->rel_pages - vacrelstats->nonempty_pages; if (possibly_freeable >= REL_TRUNCATE_MINIMUM || possibly_freeable >= vacrelstats->rel_pages / REL_TRUNCATE_FRACTION) ! lazy_truncate_heap(onerel, vacrelstats, OldestXmin); /* Update shared free space map with final free space info */ lazy_update_fsm(onerel, vacrelstats); /* Update statistics in pg_class */ ! vac_update_relstats(RelationGetRelid(onerel), vacrelstats->rel_pages, ! vacrelstats->rel_tuples, hasindex, ! vacrelstats->minxid, OldestXmin); /* report results to the stats collector, too */ pgstat_report_vacuum(RelationGetRelid(onerel), onerel->rd_rel->relisshared, *************** *** 193,202 **** * and pages with free space, and calculates statistics on the number * of live tuples in the heap. When done, or when we run low on space * for dead-tuple TIDs, invoke vacuuming of indexes and heap. */ static void lazy_scan_heap(Relation onerel, LVRelStats *vacrelstats, ! Relation *Irel, int nindexes) { BlockNumber nblocks, blkno; --- 232,245 ---- * and pages with free space, and calculates statistics on the number * of live tuples in the heap. When done, or when we run low on space * for dead-tuple TIDs, invoke vacuuming of indexes and heap. + * + * It also updates the minimum Xid found anywhere on the table, for + * pg_class.relminxid. */ static void lazy_scan_heap(Relation onerel, LVRelStats *vacrelstats, ! Relation *Irel, int nindexes, TransactionId FreezeLimit, ! TransactionId OldestXmin) { BlockNumber nblocks, blkno; *************** *** 408,413 **** --- 451,470 ---- { num_tuples += 1; hastup = true; + + /* + * If the tuple is alive, we consider it for the "minxid" + * calculations. + */ + if (TransactionIdIsNormal(HeapTupleHeaderGetXmin(tuple.t_data)) && + TransactionIdPrecedes(HeapTupleHeaderGetXmin(tuple.t_data), + vacrelstats->minxid)) + vacrelstats->minxid = HeapTupleHeaderGetXmin(tuple.t_data); + + if (TransactionIdIsNormal(HeapTupleHeaderGetXmax(tuple.t_data)) && + TransactionIdPrecedes(HeapTupleHeaderGetXmax(tuple.t_data), + vacrelstats->minxid)) + vacrelstats->minxid = HeapTupleHeaderGetXmax(tuple.t_data); } } /* scan along page */ *************** *** 668,676 **** /* now update statistics in pg_class */ vac_update_relstats(RelationGetRelid(indrel), ! stats->num_pages, ! stats->num_index_tuples, ! false); ereport(elevel, (errmsg("index \"%s\" now contains %.0f row versions in %u pages", --- 725,732 ---- /* now update statistics in pg_class */ vac_update_relstats(RelationGetRelid(indrel), ! stats->num_pages, stats->num_index_tuples, ! false, InvalidTransactionId, InvalidTransactionId); ereport(elevel, (errmsg("index \"%s\" now contains %.0f row versions in %u pages", *************** *** 691,697 **** * lazy_truncate_heap - try to truncate off any empty pages at the end */ static void ! lazy_truncate_heap(Relation onerel, LVRelStats *vacrelstats) { BlockNumber old_rel_pages = vacrelstats->rel_pages; BlockNumber new_rel_pages; --- 747,754 ---- * lazy_truncate_heap - try to truncate off any empty pages at the end */ static void ! lazy_truncate_heap(Relation onerel, LVRelStats *vacrelstats, ! TransactionId OldestXmin) { BlockNumber old_rel_pages = vacrelstats->rel_pages; BlockNumber new_rel_pages; *************** *** 732,738 **** * because other backends could have added tuples to these pages whilst we * were vacuuming. */ ! new_rel_pages = count_nondeletable_pages(onerel, vacrelstats); if (new_rel_pages >= old_rel_pages) { --- 789,795 ---- * because other backends could have added tuples to these pages whilst we * were vacuuming. */ ! new_rel_pages = count_nondeletable_pages(onerel, vacrelstats, OldestXmin); if (new_rel_pages >= old_rel_pages) { *************** *** 787,793 **** * Returns number of nondeletable pages (last nonempty page + 1). */ static BlockNumber ! count_nondeletable_pages(Relation onerel, LVRelStats *vacrelstats) { BlockNumber blkno; HeapTupleData tuple; --- 844,851 ---- * Returns number of nondeletable pages (last nonempty page + 1). */ static BlockNumber ! count_nondeletable_pages(Relation onerel, LVRelStats *vacrelstats, ! TransactionId OldestXmin) { BlockNumber blkno; HeapTupleData tuple; Index: src/backend/libpq/hba.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/libpq/hba.c,v retrieving revision 1.151 diff -c -r1.151 hba.c *** src/backend/libpq/hba.c 6 Mar 2006 17:41:43 -0000 1.151 --- src/backend/libpq/hba.c 19 May 2006 23:58:26 -0000 *************** *** 1005,1011 **** * dbname: gets database name (must be of size NAMEDATALEN bytes) * dboid: gets database OID * dbtablespace: gets database's default tablespace's OID ! * dbfrozenxid: gets database's frozen XID * dbvacuumxid: gets database's vacuum XID * * This is not much related to the other functions in hba.c, but we put it --- 1005,1011 ---- * dbname: gets database name (must be of size NAMEDATALEN bytes) * dboid: gets database OID * dbtablespace: gets database's default tablespace's OID ! * dbminxid: gets database's minimum XID * dbvacuumxid: gets database's vacuum XID * * This is not much related to the other functions in hba.c, but we put it *************** *** 1013,1019 **** */ bool read_pg_database_line(FILE *fp, char *dbname, Oid *dboid, ! Oid *dbtablespace, TransactionId *dbfrozenxid, TransactionId *dbvacuumxid) { char buf[MAX_TOKEN]; --- 1013,1019 ---- */ bool read_pg_database_line(FILE *fp, char *dbname, Oid *dboid, ! Oid *dbtablespace, TransactionId *dbminxid, TransactionId *dbvacuumxid) { char buf[MAX_TOKEN]; *************** *** 1036,1042 **** next_token(fp, buf, sizeof(buf)); if (!isdigit((unsigned char) buf[0])) elog(FATAL, "bad data in flat pg_database file"); ! *dbfrozenxid = atoxid(buf); next_token(fp, buf, sizeof(buf)); if (!isdigit((unsigned char) buf[0])) elog(FATAL, "bad data in flat pg_database file"); --- 1036,1042 ---- next_token(fp, buf, sizeof(buf)); if (!isdigit((unsigned char) buf[0])) elog(FATAL, "bad data in flat pg_database file"); ! *dbminxid = atoxid(buf); next_token(fp, buf, sizeof(buf)); if (!isdigit((unsigned char) buf[0])) elog(FATAL, "bad data in flat pg_database file"); Index: src/backend/postmaster/autovacuum.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/postmaster/autovacuum.c,v retrieving revision 1.19 diff -c -r1.19 autovacuum.c *** src/backend/postmaster/autovacuum.c 19 May 2006 15:15:37 -0000 1.19 --- src/backend/postmaster/autovacuum.c 19 May 2006 23:57:09 -0000 *************** *** 79,85 **** { Oid oid; char *name; ! TransactionId frozenxid; TransactionId vacuumxid; PgStat_StatDBEntry *entry; int32 age; --- 79,85 ---- { Oid oid; char *name; ! TransactionId minxid; TransactionId vacuumxid; PgStat_StatDBEntry *entry; int32 age; *************** *** 349,355 **** { autovac_dbase *tmp = lfirst(cell); bool this_whole_db; ! int32 freeze_age, vacuum_age; /* --- 349,355 ---- { autovac_dbase *tmp = lfirst(cell); bool this_whole_db; ! int32 true_age, vacuum_age; /* *************** *** 362,370 **** * Unlike vacuum.c, we also look at vacuumxid. This is so that * pg_clog can be kept trimmed to a reasonable size. */ ! freeze_age = (int32) (nextXid - tmp->frozenxid); vacuum_age = (int32) (nextXid - tmp->vacuumxid); ! tmp->age = Max(freeze_age, vacuum_age); this_whole_db = (tmp->age > (int32) ((MaxTransactionId >> 3) * 3 - 100000)); --- 362,370 ---- * Unlike vacuum.c, we also look at vacuumxid. This is so that * pg_clog can be kept trimmed to a reasonable size. */ ! true_age = (int32) (nextXid - tmp->minxid); vacuum_age = (int32) (nextXid - tmp->vacuumxid); ! tmp->age = Max(true_age, vacuum_age); this_whole_db = (tmp->age > (int32) ((MaxTransactionId >> 3) * 3 - 100000)); *************** *** 455,461 **** FILE *db_file; Oid db_id; Oid db_tablespace; ! TransactionId db_frozenxid; TransactionId db_vacuumxid; filename = database_getflatfilename(); --- 455,461 ---- FILE *db_file; Oid db_id; Oid db_tablespace; ! TransactionId db_minxid; TransactionId db_vacuumxid; filename = database_getflatfilename(); *************** *** 466,472 **** errmsg("could not open file \"%s\": %m", filename))); while (read_pg_database_line(db_file, thisname, &db_id, ! &db_tablespace, &db_frozenxid, &db_vacuumxid)) { autovac_dbase *db; --- 466,472 ---- errmsg("could not open file \"%s\": %m", filename))); while (read_pg_database_line(db_file, thisname, &db_id, ! &db_tablespace, &db_minxid, &db_vacuumxid)) { autovac_dbase *db; *************** *** 475,481 **** db->oid = db_id; db->name = pstrdup(thisname); ! db->frozenxid = db_frozenxid; db->vacuumxid = db_vacuumxid; /* these get set later: */ db->entry = NULL; --- 475,481 ---- db->oid = db_id; db->name = pstrdup(thisname); ! db->minxid = db_minxid; db->vacuumxid = db_vacuumxid; /* these get set later: */ db->entry = NULL; Index: src/backend/storage/lmgr/lmgr.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/storage/lmgr/lmgr.c,v retrieving revision 1.83 diff -c -r1.83 lmgr.c *** src/backend/storage/lmgr/lmgr.c 4 May 2006 16:07:29 -0000 1.83 --- src/backend/storage/lmgr/lmgr.c 19 May 2006 22:39:10 -0000 *************** *** 15,20 **** --- 15,21 ---- #include "postgres.h" + #include "access/heapam.h" #include "access/subtrans.h" #include "access/transam.h" #include "access/xact.h" *************** *** 53,58 **** --- 54,67 ---- LOCKTAG tag; LockAcquireResult res; + /* + * If the relation was frozen and somebody tries to lock it for more than + * a simple SELECT, unfreeze it. + */ + if (relation->rd_rel->relminxid == FrozenTransactionId && + lockmode > AccessShareLock) + heap_unfreeze(relation); + SET_LOCKTAG_RELATION(tag, relation->rd_lockInfo.lockRelId.dbId, relation->rd_lockInfo.lockRelId.relId); *************** *** 89,94 **** --- 98,111 ---- LOCKTAG tag; LockAcquireResult res; + /* + * If the relation was frozen and somebody tries to lock it for more than + * a simple SELECT, unfreeze it. + */ + if (relation->rd_rel->relminxid == FrozenTransactionId && + lockmode > AccessShareLock) + heap_unfreeze(relation); + SET_LOCKTAG_RELATION(tag, relation->rd_lockInfo.lockRelId.dbId, relation->rd_lockInfo.lockRelId.relId); Index: src/backend/utils/init/flatfiles.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/utils/init/flatfiles.c,v retrieving revision 1.18 diff -c -r1.18 flatfiles.c *** src/backend/utils/init/flatfiles.c 4 May 2006 16:07:29 -0000 1.18 --- src/backend/utils/init/flatfiles.c 20 May 2006 01:06:40 -0000 *************** *** 163,169 **** /* * write_database_file: update the flat database file * ! * A side effect is to determine the oldest database's datfrozenxid * so we can set or update the XID wrap limit. */ static void --- 163,169 ---- /* * write_database_file: update the flat database file * ! * A side effect is to determine the oldest database's datminxid * so we can set or update the XID wrap limit. */ static void *************** *** 177,183 **** HeapScanDesc scan; HeapTuple tuple; NameData oldest_datname; ! TransactionId oldest_datfrozenxid = InvalidTransactionId; /* * Create a temporary filename to be renamed later. This prevents the --- 177,183 ---- HeapScanDesc scan; HeapTuple tuple; NameData oldest_datname; ! TransactionId oldest_datminxid = InvalidTransactionId; /* * Create a temporary filename to be renamed later. This prevents the *************** *** 208,234 **** char *datname; Oid datoid; Oid dattablespace; ! TransactionId datfrozenxid, datvacuumxid; datname = NameStr(dbform->datname); datoid = HeapTupleGetOid(tuple); dattablespace = dbform->dattablespace; ! datfrozenxid = dbform->datfrozenxid; datvacuumxid = dbform->datvacuumxid; /* ! * Identify the oldest datfrozenxid, ignoring databases that are not * connectable (we assume they are safely frozen). This must match * the logic in vac_truncate_clog() in vacuum.c. */ if (dbform->datallowconn && ! TransactionIdIsNormal(datfrozenxid)) { ! if (oldest_datfrozenxid == InvalidTransactionId || ! TransactionIdPrecedes(datfrozenxid, oldest_datfrozenxid)) { ! oldest_datfrozenxid = datfrozenxid; namestrcpy(&oldest_datname, datname); } } --- 208,234 ---- char *datname; Oid datoid; Oid dattablespace; ! TransactionId datminxid, datvacuumxid; datname = NameStr(dbform->datname); datoid = HeapTupleGetOid(tuple); dattablespace = dbform->dattablespace; ! datminxid = dbform->datminxid; datvacuumxid = dbform->datvacuumxid; /* ! * Identify the oldest datminxid, ignoring databases that are not * connectable (we assume they are safely frozen). This must match * the logic in vac_truncate_clog() in vacuum.c. */ if (dbform->datallowconn && ! TransactionIdIsNormal(datminxid)) { ! if (oldest_datminxid == InvalidTransactionId || ! TransactionIdPrecedes(datminxid, oldest_datminxid)) { ! oldest_datminxid = datminxid; namestrcpy(&oldest_datname, datname); } } *************** *** 244,257 **** } /* ! * The file format is: "dbname" oid tablespace frozenxid vacuumxid * * The xids are not needed for backend startup, but are of use to * autovacuum, and might also be helpful for forensic purposes. */ fputs_quote(datname, fp); fprintf(fp, " %u %u %u %u\n", ! datoid, dattablespace, datfrozenxid, datvacuumxid); } heap_endscan(scan); --- 244,257 ---- } /* ! * The file format is: "dbname" oid tablespace minxid vacuumxid * * The xids are not needed for backend startup, but are of use to * autovacuum, and might also be helpful for forensic purposes. */ fputs_quote(datname, fp); fprintf(fp, " %u %u %u %u\n", ! datoid, dattablespace, datminxid, datvacuumxid); } heap_endscan(scan); *************** *** 272,281 **** tempname, filename))); /* ! * Set the transaction ID wrap limit using the oldest datfrozenxid */ ! if (oldest_datfrozenxid != InvalidTransactionId) ! SetTransactionIdLimit(oldest_datfrozenxid, &oldest_datname); } --- 272,281 ---- tempname, filename))); /* ! * Set the transaction ID wrap limit using the oldest datminxid */ ! if (oldest_datminxid != InvalidTransactionId) ! SetTransactionIdLimit(oldest_datminxid, &oldest_datname); } Index: src/backend/utils/init/postinit.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/backend/utils/init/postinit.c,v retrieving revision 1.167 diff -c -r1.167 postinit.c *** src/backend/utils/init/postinit.c 4 May 2006 18:51:36 -0000 1.167 --- src/backend/utils/init/postinit.c 19 May 2006 23:59:14 -0000 *************** *** 24,29 **** --- 24,30 ---- #include "catalog/pg_authid.h" #include "catalog/pg_database.h" #include "catalog/pg_tablespace.h" + #include "commands/dbcommands.h" #include "libpq/hba.h" #include "mb/pg_wchar.h" #include "miscadmin.h" *************** *** 193,198 **** --- 194,210 ---- PGC_BACKEND, PGC_S_DEFAULT); /* + * If the database is marked as frozen, unfreeze it to make sure we won't + * leave non-vacuumed tuples hidden behind a frozen pg_database entry. + * + * This is more paranoid than it needs to be -- if we had a way of + * declaring a session as being guaranteed-read-only, we could skip doing + * this for such sessions. In the meantime, be safe. + */ + if (TransactionIdEquals(dbform->datminxid, FrozenTransactionId)) + UnfreezeDatabase(MyDatabaseId, GetCurrentTransactionId()); + + /* * Lastly, set up any database-specific configuration variables. */ if (IsUnderPostmaster) Index: src/bin/initdb/initdb.c =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/bin/initdb/initdb.c,v retrieving revision 1.114 diff -c -r1.114 initdb.c *** src/bin/initdb/initdb.c 21 Mar 2006 17:54:28 -0000 1.114 --- src/bin/initdb/initdb.c 7 May 2006 04:59:58 -0000 *************** *** 184,189 **** --- 184,190 ---- static void setup_schema(void); static void vacuum_db(void); static void make_template0(void); + static void freeze_template0(void); static void make_postgres(void); static void trapsig(int signum); static void check_ok(void); *************** *** 2014,2019 **** --- 2015,2054 ---- } /* + * freeze template0 + * + * Note that this routine connects to template0, not template1 like all the + * rest. + */ + static void + freeze_template0(void) + { + PG_CMD_DECL; + char **line; + static char *template_freeze[] = { + "VACUUM FREEZE;\n", + NULL + }; + + fputs(_("freezing template0 ... "), stdout); + fflush(stdout); + + snprintf(cmd, sizeof(cmd), + "\"%s\" %s template0 >%s", + backend_exec, backend_options, + DEVNULL); + + PG_CMD_OPEN; + + for (line = template_freeze; *line; line++) + PG_CMD_PUTS(*line); + + PG_CMD_CLOSE; + + check_ok(); + } + + /* * copy template1 to postgres */ static void *************** *** 2946,2951 **** --- 2981,2988 ---- make_template0(); + freeze_template0(); + make_postgres(); if (authwarning != NULL) Index: src/include/access/heapam.h =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/include/access/heapam.h,v retrieving revision 1.111 diff -c -r1.111 heapam.h *** src/include/access/heapam.h 10 May 2006 23:18:39 -0000 1.111 --- src/include/access/heapam.h 13 May 2006 18:16:25 -0000 *************** *** 122,127 **** --- 122,129 ---- /* heapam.c */ + extern bool disable_heap_unfreeze; + typedef enum { LockTupleShared, *************** *** 168,173 **** --- 170,176 ---- Buffer *buffer, ItemPointer ctid, TransactionId *update_xmax, CommandId cid, LockTupleMode mode, bool nowait); + extern void heap_unfreeze(Relation rel); extern void heap_inplace_update(Relation relation, HeapTuple tuple); extern Oid simple_heap_insert(Relation relation, HeapTuple tup); Index: src/include/access/transam.h =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/include/access/transam.h,v retrieving revision 1.57 diff -c -r1.57 transam.h *** src/include/access/transam.h 5 Mar 2006 15:58:53 -0000 1.57 --- src/include/access/transam.h 5 May 2006 01:54:39 -0000 *************** *** 123,129 **** /* in transam/varsup.c */ extern TransactionId GetNewTransactionId(bool isSubXact); extern TransactionId ReadNewTransactionId(void); ! extern void SetTransactionIdLimit(TransactionId oldest_datfrozenxid, Name oldest_datname); extern Oid GetNewObjectId(void); --- 123,129 ---- /* in transam/varsup.c */ extern TransactionId GetNewTransactionId(bool isSubXact); extern TransactionId ReadNewTransactionId(void); ! extern void SetTransactionIdLimit(TransactionId oldest_datminxid, Name oldest_datname); extern Oid GetNewObjectId(void); Index: src/include/catalog/pg_attribute.h =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/include/catalog/pg_attribute.h,v retrieving revision 1.120 diff -c -r1.120 pg_attribute.h *** src/include/catalog/pg_attribute.h 5 Mar 2006 15:58:54 -0000 1.120 --- src/include/catalog/pg_attribute.h 14 May 2006 13:35:35 -0000 *************** *** 404,410 **** { 1259, {"relhaspkey"}, 16, -1, 1, 22, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \ { 1259, {"relhasrules"}, 16, -1, 1, 23, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \ { 1259, {"relhassubclass"},16, -1, 1, 24, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \ ! { 1259, {"relacl"}, 1034, -1, -1, 25, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 } DATA(insert ( 1259 relname 19 -1 NAMEDATALEN 1 0 -1 -1 f p i t f f t 0)); DATA(insert ( 1259 relnamespace 26 -1 4 2 0 -1 -1 t p i t f f t 0)); --- 404,412 ---- { 1259, {"relhaspkey"}, 16, -1, 1, 22, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \ { 1259, {"relhasrules"}, 16, -1, 1, 23, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \ { 1259, {"relhassubclass"},16, -1, 1, 24, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \ ! { 1259, {"relminxid"}, 28, -1, 4, 25, 0, -1, -1, true, 'p', 'i', true, false, false, true, 0 }, \ ! { 1259, {"relvacuumxid"}, 28, -1, 4, 26, 0, -1, -1, true, 'p', 'i', true, false, false, true, 0 }, \ ! { 1259, {"relacl"}, 1034, -1, -1, 27, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 } DATA(insert ( 1259 relname 19 -1 NAMEDATALEN 1 0 -1 -1 f p i t f f t 0)); DATA(insert ( 1259 relnamespace 26 -1 4 2 0 -1 -1 t p i t f f t 0)); *************** *** 430,436 **** DATA(insert ( 1259 relhaspkey 16 -1 1 22 0 -1 -1 t p c t f f t 0)); DATA(insert ( 1259 relhasrules 16 -1 1 23 0 -1 -1 t p c t f f t 0)); DATA(insert ( 1259 relhassubclass 16 -1 1 24 0 -1 -1 t p c t f f t 0)); ! DATA(insert ( 1259 relacl 1034 -1 -1 25 1 -1 -1 f x i f f f t 0)); DATA(insert ( 1259 ctid 27 0 6 -1 0 -1 -1 f p s t f f t 0)); DATA(insert ( 1259 oid 26 0 4 -2 0 -1 -1 t p i t f f t 0)); DATA(insert ( 1259 xmin 28 0 4 -3 0 -1 -1 t p i t f f t 0)); --- 432,440 ---- DATA(insert ( 1259 relhaspkey 16 -1 1 22 0 -1 -1 t p c t f f t 0)); DATA(insert ( 1259 relhasrules 16 -1 1 23 0 -1 -1 t p c t f f t 0)); DATA(insert ( 1259 relhassubclass 16 -1 1 24 0 -1 -1 t p c t f f t 0)); ! DATA(insert ( 1259 relminxid 28 -1 4 25 0 -1 -1 t p i t f f t 0)); ! DATA(insert ( 1259 relvacuumxid 28 -1 4 26 0 -1 -1 t p i t f f t 0)); ! DATA(insert ( 1259 relacl 1034 -1 -1 27 1 -1 -1 f x i f f f t 0)); DATA(insert ( 1259 ctid 27 0 6 -1 0 -1 -1 f p s t f f t 0)); DATA(insert ( 1259 oid 26 0 4 -2 0 -1 -1 t p i t f f t 0)); DATA(insert ( 1259 xmin 28 0 4 -3 0 -1 -1 t p i t f f t 0)); Index: src/include/catalog/pg_class.h =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/include/catalog/pg_class.h,v retrieving revision 1.91 diff -c -r1.91 pg_class.h *** src/include/catalog/pg_class.h 5 Mar 2006 15:58:54 -0000 1.91 --- src/include/catalog/pg_class.h 14 May 2006 13:36:58 -0000 *************** *** 74,79 **** --- 74,81 ---- bool relhaspkey; /* has PRIMARY KEY index */ bool relhasrules; /* has associated rules */ bool relhassubclass; /* has derived classes */ + TransactionId relminxid; /* minimum Xid present in table */ + TransactionId relvacuumxid; /* Xid used as last vacuum OldestXmin */ /* * relacl may or may not be present, see note above! *************** *** 83,89 **** /* Size of fixed part of pg_class tuples, not counting relacl or padding */ #define CLASS_TUPLE_SIZE \ ! (offsetof(FormData_pg_class,relhassubclass) + sizeof(bool)) /* ---------------- * Form_pg_class corresponds to a pointer to a tuple with --- 85,91 ---- /* Size of fixed part of pg_class tuples, not counting relacl or padding */ #define CLASS_TUPLE_SIZE \ ! (offsetof(FormData_pg_class,relvacuumxid) + sizeof(TransactionId)) /* ---------------- * Form_pg_class corresponds to a pointer to a tuple with *************** *** 103,110 **** * relacl field. This is a kluge. * ---------------- */ ! #define Natts_pg_class_fixed 24 ! #define Natts_pg_class 25 #define Anum_pg_class_relname 1 #define Anum_pg_class_relnamespace 2 #define Anum_pg_class_reltype 3 --- 105,112 ---- * relacl field. This is a kluge. * ---------------- */ ! #define Natts_pg_class_fixed 26 ! #define Natts_pg_class 27 #define Anum_pg_class_relname 1 #define Anum_pg_class_relnamespace 2 #define Anum_pg_class_reltype 3 *************** *** 129,135 **** #define Anum_pg_class_relhaspkey 22 #define Anum_pg_class_relhasrules 23 #define Anum_pg_class_relhassubclass 24 ! #define Anum_pg_class_relacl 25 /* ---------------- * initial contents of pg_class --- 131,139 ---- #define Anum_pg_class_relhaspkey 22 #define Anum_pg_class_relhasrules 23 #define Anum_pg_class_relhassubclass 24 ! #define Anum_pg_class_relminxid 25 ! #define Anum_pg_class_relvacuumxid 26 ! #define Anum_pg_class_relacl 27 /* ---------------- * initial contents of pg_class *************** *** 139,151 **** * ---------------- */ ! DATA(insert OID = 1247 ( pg_type PGNSP 71 PGUID 0 1247 0 0 0 0 0 f f r 23 0 0 0 0 0 t f f f _null_ )); DESCR(""); ! DATA(insert OID = 1249 ( pg_attribute PGNSP 75 PGUID 0 1249 0 0 0 0 0 f f r 17 0 0 0 0 0 f f f f _null_ )); DESCR(""); ! DATA(insert OID = 1255 ( pg_proc PGNSP 81 PGUID 0 1255 0 0 0 0 0 f f r 18 0 0 0 0 0 t f f f _null_ )); DESCR(""); ! DATA(insert OID = 1259 ( pg_class PGNSP 83 PGUID 0 1259 0 0 0 0 0 f f r 25 0 0 0 0 0 t f f f _null_ )); DESCR(""); #define RELKIND_INDEX 'i' /* secondary index */ --- 143,155 ---- * ---------------- */ ! DATA(insert OID = 1247 ( pg_type PGNSP 71 PGUID 0 1247 0 0 0 0 0 f f r 23 0 0 0 0 0 t f f f 0 0 _null_ )); DESCR(""); ! DATA(insert OID = 1249 ( pg_attribute PGNSP 75 PGUID 0 1249 0 0 0 0 0 f f r 17 0 0 0 0 0 f f f f 0 0 _null_ )); DESCR(""); ! DATA(insert OID = 1255 ( pg_proc PGNSP 81 PGUID 0 1255 0 0 0 0 0 f f r 18 0 0 0 0 0 t f f f 0 0 _null_ )); DESCR(""); ! DATA(insert OID = 1259 ( pg_class PGNSP 83 PGUID 0 1259 0 0 0 0 0 f f r 27 0 0 0 0 0 t f f f 0 0 _null_ )); DESCR(""); #define RELKIND_INDEX 'i' /* secondary index */ Index: src/include/catalog/pg_database.h =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/include/catalog/pg_database.h,v retrieving revision 1.40 diff -c -r1.40 pg_database.h *** src/include/catalog/pg_database.h 5 Mar 2006 15:58:54 -0000 1.40 --- src/include/catalog/pg_database.h 14 May 2006 13:39:36 -0000 *************** *** 43,49 **** int4 datconnlimit; /* max connections allowed (-1=no limit) */ Oid datlastsysoid; /* highest OID to consider a system OID */ TransactionId datvacuumxid; /* all XIDs before this are vacuumed */ ! TransactionId datfrozenxid; /* all XIDs before this are frozen */ Oid dattablespace; /* default table space for this DB */ text datconfig[1]; /* database-specific GUC (VAR LENGTH) */ aclitem datacl[1]; /* access permissions (VAR LENGTH) */ --- 43,49 ---- int4 datconnlimit; /* max connections allowed (-1=no limit) */ Oid datlastsysoid; /* highest OID to consider a system OID */ TransactionId datvacuumxid; /* all XIDs before this are vacuumed */ ! TransactionId datminxid; /* minimum XID present anywhere in the DB */ Oid dattablespace; /* default table space for this DB */ text datconfig[1]; /* database-specific GUC (VAR LENGTH) */ aclitem datacl[1]; /* access permissions (VAR LENGTH) */ *************** *** 60,66 **** * compiler constants for pg_database * ---------------- */ ! #define Natts_pg_database 12 #define Anum_pg_database_datname 1 #define Anum_pg_database_datdba 2 #define Anum_pg_database_encoding 3 --- 60,66 ---- * compiler constants for pg_database * ---------------- */ ! #define Natts_pg_database 13 #define Anum_pg_database_datname 1 #define Anum_pg_database_datdba 2 #define Anum_pg_database_encoding 3 *************** *** 69,75 **** #define Anum_pg_database_datconnlimit 6 #define Anum_pg_database_datlastsysoid 7 #define Anum_pg_database_datvacuumxid 8 ! #define Anum_pg_database_datfrozenxid 9 #define Anum_pg_database_dattablespace 10 #define Anum_pg_database_datconfig 11 #define Anum_pg_database_datacl 12 --- 69,75 ---- #define Anum_pg_database_datconnlimit 6 #define Anum_pg_database_datlastsysoid 7 #define Anum_pg_database_datvacuumxid 8 ! #define Anum_pg_database_datminxid 9 #define Anum_pg_database_dattablespace 10 #define Anum_pg_database_datconfig 11 #define Anum_pg_database_datacl 12 Index: src/include/commands/dbcommands.h =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/include/commands/dbcommands.h,v retrieving revision 1.45 diff -c -r1.45 dbcommands.h *** src/include/commands/dbcommands.h 24 Mar 2006 04:32:13 -0000 1.45 --- src/include/commands/dbcommands.h 19 May 2006 23:53:54 -0000 *************** *** 58,63 **** --- 58,64 ---- extern void AlterDatabase(AlterDatabaseStmt *stmt); extern void AlterDatabaseSet(AlterDatabaseSetStmt *stmt); extern void AlterDatabaseOwner(const char *dbname, Oid newOwnerId); + extern void UnfreezeDatabase(Oid dbid, TransactionId unfreezeXid); extern Oid get_database_oid(const char *dbname); extern char *get_database_name(Oid dbid); Index: src/include/commands/vacuum.h =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/include/commands/vacuum.h,v retrieving revision 1.63 diff -c -r1.63 vacuum.h *** src/include/commands/vacuum.h 5 Mar 2006 15:58:55 -0000 1.63 --- src/include/commands/vacuum.h 14 May 2006 13:47:49 -0000 *************** *** 114,123 **** extern void vac_open_indexes(Relation relation, LOCKMODE lockmode, int *nindexes, Relation **Irel); extern void vac_close_indexes(int nindexes, Relation *Irel, LOCKMODE lockmode); ! extern void vac_update_relstats(Oid relid, ! BlockNumber num_pages, ! double num_tuples, ! bool hasindex); extern void vacuum_set_xid_limits(VacuumStmt *vacstmt, bool sharedRel, TransactionId *oldestXmin, TransactionId *freezeLimit); --- 114,122 ---- extern void vac_open_indexes(Relation relation, LOCKMODE lockmode, int *nindexes, Relation **Irel); extern void vac_close_indexes(int nindexes, Relation *Irel, LOCKMODE lockmode); ! extern void vac_update_relstats(Oid relid, BlockNumber num_pages, ! double num_tuples, bool hasindex, ! TransactionId minxid, TransactionId vacuumxid); extern void vacuum_set_xid_limits(VacuumStmt *vacstmt, bool sharedRel, TransactionId *oldestXmin, TransactionId *freezeLimit); Index: src/include/libpq/hba.h =================================================================== RCS file: /home/alvherre/cvs/pgsql/src/include/libpq/hba.h,v retrieving revision 1.42 diff -c -r1.42 hba.h *** src/include/libpq/hba.h 6 Mar 2006 17:41:44 -0000 1.42 --- src/include/libpq/hba.h 19 May 2006 23:54:41 -0000 *************** *** 40,46 **** extern int hba_getauthmethod(hbaPort *port); extern int authident(hbaPort *port); extern bool read_pg_database_line(FILE *fp, char *dbname, Oid *dboid, ! Oid *dbtablespace, TransactionId *dbfrozenxid, TransactionId *dbvacuumxid); #endif /* HBA_H */ --- 40,46 ---- extern int hba_getauthmethod(hbaPort *port); extern int authident(hbaPort *port); extern bool read_pg_database_line(FILE *fp, char *dbname, Oid *dboid, ! Oid *dbtablespace, TransactionId *dbminxid, TransactionId *dbvacuumxid); #endif /* HBA_H */