Improve vacuum code to track minimum Xids per table instead of per database.

To this end, add a couple of columns to pg_class, relminxid and relvacuumxid,
based on which we calculate the pg_database columns after each vacuum.

We now force all databases to be vacuumed, even template ones.  A backend
noticing too old a database (meaning pg_database.datminxid is in danger of
falling behind Xid wraparound) will signal the postmaster, which in turn will
start an autovacuum iteration to process the offending database.  In principle
this is only there to cope with frozen (non-connectable) databases without
forcing users to set them to connectable, but it could force regular user
database to go through a database-wide vacuum at any time.  Maybe we should
warn users about this somehow.  Of course the real solution will be to use
autovacuum all the time ;-)

There are some additional improvements we could have in this area: for example
the vacuum code could be smarter about not updating pg_database for each table
when called by autovacuum, and do it only once the whole autovacuum iteration
is done.

I updated the system catalogs documentation, but I didn't modify the
maintenance section.  Also having some regression tests for this would be nice
but it's not really a very straightforward thing to do.

Catalog version bumped due to system catalog changes.

Author: alvherre

doc/src/sgml/catalogs.sgml

@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.125 2006/07/03 22:45:36 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.126 2006/07/10 16:20:49 alvherre Exp $ -->
 <!--
  Documentation of the system catalogs, directed toward PostgreSQL developers
  -->
@@ -1639,6 +1639,30 @@
       <entry>True if table has (or once had) any inheritance children</entry>
      </row>
 
+     <row>
+      <entry><structfield>relminxid</structfield></entry>
+      <entry><type>xid</type></entry>
+      <entry></entry>
+      <entry>
+       The minimum transaction ID present in all rows in this table.  This
+       value is used to determine the database-global
+       <structname>pg_database</>.<structfield>datminxid</> value.
+      </entry>
+     </row>
+
+     <row>
+      <entry><structfield>relvacuumxid</structfield></entry>
+      <entry><type>xid</type></entry>
+      <entry></entry>
+      <entry>
+       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
+       <structname>pg_database</>.<structfield>datvacuumxid</> value.
+      </entry>
+     </row>
+
      <row>
       <entry><structfield>relacl</structfield></entry>
       <entry><type>aclitem[]</type></entry>
@@ -2022,21 +2046,27 @@
       <entry><type>xid</type></entry>
       <entry></entry>
       <entry>
-       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.
+       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 <structname>pg_class</>.<structfield>relvacuumxid</>.
       </entry>
      </row>
 
      <row>
-      <entry><structfield>datfrozenxid</structfield></entry>
+      <entry><structfield>datminxid</structfield></entry>
       <entry><type>xid</type></entry>
       <entry></entry>
       <entry>
+       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 (<quote>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.
+       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 <structname>pg_class</>.<structfield>relminxid</>.
       </entry>
      </row>
 

src/backend/access/transam/varsup.c

@@ -6,7 +6,7 @@
  * Copyright (c) 2000-2006, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/transam/varsup.c,v 1.70 2006/03/05 15:58:22 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/transam/varsup.c,v 1.71 2006/07/10 16:20:49 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -168,28 +168,28 @@ ReadNewTransactionId(void)
 
 /*
  * Determine the last safe XID to allocate given the currently oldest
- * datfrozenxid (ie, the oldest XID that might exist in any database
+ * datminxid (ie, the oldest XID that might exist in any database
  * of our cluster).
  */
 void
-SetTransactionIdLimit(TransactionId oldest_datfrozenxid,
+SetTransactionIdLimit(TransactionId oldest_datminxid,
 					  Name oldest_datname)
 {
 	TransactionId xidWarnLimit;
 	TransactionId xidStopLimit;
 	TransactionId xidWrapLimit;
 	TransactionId curXid;
 
-	Assert(TransactionIdIsValid(oldest_datfrozenxid));
+	Assert(TransactionIdIsValid(oldest_datminxid));
 
 	/*
 	 * 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.)
+	 * 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_datfrozenxid + (MaxTransactionId >> 1);
+	xidWrapLimit = oldest_datminxid + (MaxTransactionId >> 1);
 	if (xidWrapLimit < FirstNormalTransactionId)
 		xidWrapLimit += FirstNormalTransactionId;
 

src/backend/catalog/heap.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/catalog/heap.c,v 1.305 2006/07/08 20:45:38 alvherre Exp $
+ *	  $PostgreSQL: pgsql/src/backend/catalog/heap.c,v 1.306 2006/07/10 16:20:49 alvherre Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -597,6 +597,8 @@ InsertPgClassTuple(Relation pg_class_desc,
 	values[Anum_pg_class_relhaspkey - 1] = BoolGetDatum(rd_rel->relhaspkey);
 	values[Anum_pg_class_relhasrules - 1] = BoolGetDatum(rd_rel->relhasrules);
 	values[Anum_pg_class_relhassubclass - 1] = BoolGetDatum(rd_rel->relhassubclass);
+	values[Anum_pg_class_relminxid - 1] = TransactionIdGetDatum(rd_rel->relminxid);
+	values[Anum_pg_class_relvacuumxid - 1] = TransactionIdGetDatum(rd_rel->relvacuumxid);
 	/* start out with empty permissions */
 	nulls[Anum_pg_class_relacl - 1] = 'n';
 	if (reloptions != (Datum) 0)
@@ -644,6 +646,35 @@ AddNewRelationTuple(Relation pg_class_desc,
 	 */
 	new_rel_reltup = new_rel_desc->rd_rel;
 
+	/* Initialize relminxid and relvacuumxid */
+	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.
+		 */
+		if (!IsBootstrapProcessingMode())
+		{
+			new_rel_reltup->relminxid = RecentXmin;
+			new_rel_reltup->relvacuumxid = RecentXmin;
+		}
+		else
+		{
+			new_rel_reltup->relminxid = FirstNormalTransactionId;
+			new_rel_reltup->relvacuumxid = FirstNormalTransactionId;
+		}
+	}
+	else
+	{
+		/*
+		 * Other relations will not have Xids in them, so set the initial value
+		 * to InvalidTransactionId.
+		 */
+		new_rel_reltup->relminxid = InvalidTransactionId;
+		new_rel_reltup->relvacuumxid = InvalidTransactionId;
+	}
+
 	switch (relkind)
 	{
 		case RELKIND_RELATION:

src/backend/commands/analyze.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.93 2006/03/23 00:19:28 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.94 2006/07/10 16:20:50 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -424,8 +424,9 @@ analyze_rel(Oid relid, VacuumStmt *vacstmt)
 	{
 		vac_update_relstats(RelationGetRelid(onerel),
 							RelationGetNumberOfBlocks(onerel),
-							totalrows,
-							hasindex);
+							totalrows, hasindex,
+							InvalidTransactionId, InvalidTransactionId);
+
 		for (ind = 0; ind < nindexes; ind++)
 		{
 			AnlIndexData *thisdata = &indexdata[ind];
@@ -434,8 +435,8 @@ analyze_rel(Oid relid, VacuumStmt *vacstmt)
 			totalindexrows = ceil(thisdata->tupleFract * totalrows);
 			vac_update_relstats(RelationGetRelid(Irel[ind]),
 								RelationGetNumberOfBlocks(Irel[ind]),
-								totalindexrows,
-								false);
+								totalindexrows, false,
+								InvalidTransactionId, InvalidTransactionId);
 		}
 
 		/* report results to the stats collector, too */

src/backend/commands/dbcommands.c

@@ -13,7 +13,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/dbcommands.c,v 1.181 2006/05/04 16:07:29 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/dbcommands.c,v 1.182 2006/07/10 16:20:50 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -55,7 +55,7 @@ static bool get_db_info(const char *name, LOCKMODE lockmode,
 			Oid *dbIdP, Oid *ownerIdP,
 			int *encodingP, bool *dbIsTemplateP, bool *dbAllowConnP,
 			Oid *dbLastSysOidP,
-			TransactionId *dbVacuumXidP, TransactionId *dbFrozenXidP,
+			TransactionId *dbVacuumXidP, TransactionId *dbMinXidP,
 			Oid *dbTablespace);
 static bool have_createdb_privilege(void);
 static void remove_dbtablespaces(Oid db_id);
@@ -76,7 +76,7 @@ createdb(const CreatedbStmt *stmt)
 	bool		src_allowconn;
 	Oid			src_lastsysoid;
 	TransactionId src_vacuumxid;
-	TransactionId src_frozenxid;
+	TransactionId src_minxid;
 	Oid			src_deftablespace;
 	volatile Oid dst_deftablespace;
 	Relation	pg_database_rel;
@@ -228,7 +228,7 @@ createdb(const CreatedbStmt *stmt)
 	if (!get_db_info(dbtemplate, ShareLock,
 					 &src_dboid, &src_owner, &src_encoding,
 					 &src_istemplate, &src_allowconn, &src_lastsysoid,
-					 &src_vacuumxid, &src_frozenxid, &src_deftablespace))
+					 &src_vacuumxid, &src_minxid, &src_deftablespace))
 		ereport(ERROR,
 				(errcode(ERRCODE_UNDEFINED_DATABASE),
 				 errmsg("template database \"%s\" does not exist",
@@ -326,16 +326,6 @@ createdb(const CreatedbStmt *stmt)
 		/* Note there is no additional permission check in this path */
 	}
 
-	/*
-	 * 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
 	 * error message than "unique index violation".  There's a race condition
@@ -367,7 +357,7 @@ createdb(const CreatedbStmt *stmt)
 	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_datminxid - 1] = TransactionIdGetDatum(src_minxid);
 	new_record[Anum_pg_database_dattablespace - 1] = ObjectIdGetDatum(dst_deftablespace);
 
 	/*
@@ -1066,7 +1056,7 @@ get_db_info(const char *name, LOCKMODE lockmode,
 			Oid *dbIdP, Oid *ownerIdP,
 			int *encodingP, bool *dbIsTemplateP, bool *dbAllowConnP,
 			Oid *dbLastSysOidP,
-			TransactionId *dbVacuumXidP, TransactionId *dbFrozenXidP,
+			TransactionId *dbVacuumXidP, TransactionId *dbMinXidP,
 			Oid *dbTablespace)
 {
 	bool		result = false;
@@ -1155,9 +1145,9 @@ get_db_info(const char *name, LOCKMODE lockmode,
 				/* limit of vacuumed XIDs */
 				if (dbVacuumXidP)
 					*dbVacuumXidP = dbform->datvacuumxid;
-				/* limit of frozen XIDs */
-				if (dbFrozenXidP)
-					*dbFrozenXidP = dbform->datfrozenxid;
+				/* limit of min XIDs */
+				if (dbMinXidP)
+					*dbMinXidP = dbform->datminxid;
 				/* default tablespace for this database */
 				if (dbTablespace)
 					*dbTablespace = dbform->dattablespace;