Clean up a number of autovacuum loose ends. Make the stats collector

track shared relations in a separate hashtable, so that operations done
from different databases are counted correctly.  Add proper support for
anti-XID-wraparound vacuuming, even in databases that are never connected
to and so have no stats entries.  Miscellaneous other bug fixes.
Alvaro Herrera, some additional fixes by Tom Lane.

Author: tglsfdc

src/backend/access/transam/xlog.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.212 2005/07/29 03:25:53 momjian Exp $
+ * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.213 2005/07/29 19:29:59 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -4913,6 +4913,36 @@ GetRedoRecPtr(void)
 	return RedoRecPtr;
 }
 
+/*
+ * GetRecentNextXid - get the nextXid value saved by the most recent checkpoint
+ *
+ * This is currently used only by the autovacuum daemon.  To check for
+ * impending XID wraparound, autovac needs an approximate idea of the current
+ * XID counter, and it needs it before choosing which DB to attach to, hence
+ * before it sets up a PGPROC, hence before it can take any LWLocks.  But it
+ * has attached to shared memory, and so we can let it reach into the shared
+ * ControlFile structure and pull out the last checkpoint nextXID.
+ *
+ * Since we don't take any sort of lock, we have to assume that reading a
+ * TransactionId is atomic ... but that assumption is made elsewhere, too,
+ * and in any case the worst possible consequence of a bogus result is that
+ * autovac issues an unnecessary database-wide VACUUM.
+ *
+ * Note: we could also choose to read ShmemVariableCache->nextXid in an
+ * unlocked fashion, thus getting a more up-to-date result; but since that
+ * changes far more frequently than the controlfile checkpoint copy, it would
+ * pose a far higher risk of bogus result if we did have a nonatomic-read
+ * problem.
+ *
+ * A (theoretically) completely safe answer is to read the actual pg_control
+ * file into local process memory, but that certainly seems like overkill.
+ */
+TransactionId
+GetRecentNextXid(void)
+{
+	return ControlFile->checkPointCopy.nextXid;
+}
+
 /*
  * This must be called ONCE during postmaster or standalone-backend shutdown
  */

src/backend/commands/analyze.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.87 2005/07/14 05:13:39 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.88 2005/07/29 19:30:03 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -317,7 +317,9 @@ analyze_rel(Oid relid, VacuumStmt *vacstmt)
 		 * a zero-column table.
 		 */
 		if (!vacstmt->vacuum)
-			pgstat_report_analyze(RelationGetRelid(onerel), 0, 0);
+			pgstat_report_analyze(RelationGetRelid(onerel),
+								  onerel->rd_rel->relisshared,
+				   				  0, 0);
 
 		vac_close_indexes(nindexes, Irel, AccessShareLock);
 		relation_close(onerel, AccessShareLock);
@@ -436,8 +438,9 @@ analyze_rel(Oid relid, VacuumStmt *vacstmt)
 		}
 
 		/* report results to the stats collector, too */
-		pgstat_report_analyze(RelationGetRelid(onerel), totalrows,
-							  totaldeadrows);
+		pgstat_report_analyze(RelationGetRelid(onerel),
+							  onerel->rd_rel->relisshared,
+			   				  totalrows, totaldeadrows);
 	}
 
 	/* Done with indexes */

src/backend/commands/vacuum.c

@@ -13,7 +13,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/vacuum.c,v 1.311 2005/07/14 05:13:39 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/vacuum.c,v 1.312 2005/07/29 19:30:03 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -41,6 +41,7 @@
 #include "tcop/pquery.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/flatfiles.h"
 #include "utils/fmgroids.h"
 #include "utils/inval.h"
 #include "utils/lsyscache.h"
@@ -490,7 +491,7 @@ vacuum(VacuumStmt *vacstmt, List *relids)
 		 * If it was a database-wide VACUUM, print FSM usage statistics
 		 * (we don't make you be superuser to see these).
 		 */
-		if (vacstmt->relation == NULL)
+		if (all_rels)
 			PrintFreeSpaceMapStatistics(elevel);
 
 		/*
@@ -712,7 +713,7 @@ vac_update_relstats(Oid relid, BlockNumber num_pages, double num_tuples,
  *	vac_update_dbstats() -- update statistics for one database
  *
  *		Update the whole-database statistics that are kept in its pg_database
- *		row.
+ *		row, and the flat-file copy of pg_database.
  *
  *		We violate no-overwrite semantics here by storing new values for the
  *		statistics columns directly into the tuple that's already on the page.
@@ -721,8 +722,6 @@ vac_update_relstats(Oid relid, BlockNumber num_pages, double num_tuples,
  *
  *		This routine is shared by full and lazy VACUUM.  Note that it is only
  *		applied after a database-wide VACUUM operation.
- *
- *		Note that we don't bother to update the flat-file copy of pg_database.
  */
 static void
 vac_update_dbstats(Oid dbid,
@@ -768,6 +767,9 @@ vac_update_dbstats(Oid dbid,
 	heap_endscan(scan);
 
 	heap_close(relation, RowExclusiveLock);
+
+	/* Mark the flat-file copy of pg_database for update at commit */
+	database_file_update_needed();
 }
 
 
@@ -1165,8 +1167,8 @@ full_vacuum_rel(Relation onerel, VacuumStmt *vacstmt)
 						vacrelstats->rel_tuples, vacrelstats->hasindex);
 
 	/* report results to the stats collector, too */
-	pgstat_report_vacuum(RelationGetRelid(onerel), vacstmt->analyze,
-						 vacrelstats->rel_tuples);
+	pgstat_report_vacuum(RelationGetRelid(onerel), onerel->rd_rel->relisshared,
+		   				 vacstmt->analyze, vacrelstats->rel_tuples);
 }
 
 

src/backend/commands/vacuumlazy.c

@@ -31,7 +31,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/vacuumlazy.c,v 1.55 2005/07/14 05:13:40 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/vacuumlazy.c,v 1.56 2005/07/29 19:30:03 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -182,8 +182,8 @@ lazy_vacuum_rel(Relation onerel, VacuumStmt *vacstmt)
 						hasindex);
 
 	/* report results to the stats collector, too */
-	pgstat_report_vacuum(RelationGetRelid(onerel), vacstmt->analyze,
-						 vacrelstats->rel_tuples);
+	pgstat_report_vacuum(RelationGetRelid(onerel), onerel->rd_rel->relisshared,
+		   				 vacstmt->analyze, vacrelstats->rel_tuples);
 }
 
 

src/backend/libpq/hba.c

@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/libpq/hba.c,v 1.145 2005/07/28 15:30:55 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/libpq/hba.c,v 1.146 2005/07/29 19:30:04 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -39,6 +39,7 @@
 
 
 #define atooid(x)  ((Oid) strtoul((x), NULL, 10))
+#define atoxid(x)  ((TransactionId) strtoul((x), NULL, 10))
 
 /* Max size of username ident server can return */
 #define IDENT_USERNAME_MAX 512
@@ -999,13 +1000,14 @@ load_hba(void)
  *	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
  *
  * This is not much related to the other functions in hba.c, but we put it
  * here because it uses the next_token() infrastructure.
  */
 bool
-read_pg_database_line(FILE *fp, char *dbname,
-					  Oid *dboid, Oid *dbtablespace)
+read_pg_database_line(FILE *fp, char *dbname, Oid *dboid,
+					  Oid *dbtablespace, TransactionId *dbfrozenxid)
 {
 	char		buf[MAX_TOKEN];
 
@@ -1024,10 +1026,10 @@ read_pg_database_line(FILE *fp, char *dbname,
 	if (!isdigit((unsigned char) buf[0]))
 		elog(FATAL, "bad data in flat pg_database file");
 	*dbtablespace = atooid(buf);
-	/* discard datfrozenxid */
 	next_token(fp, buf, sizeof(buf));
 	if (!isdigit((unsigned char) buf[0]))
 		elog(FATAL, "bad data in flat pg_database file");
+	*dbfrozenxid = atoxid(buf);
 	/* expect EOL next */
 	if (next_token(fp, buf, sizeof(buf)))
 		elog(FATAL, "bad data in flat pg_database file");