Create a "relation mapping" infrastructure to support changing the relfilenodes

of shared or nailed system catalogs.  This has two key benefits:

* The new CLUSTER-based VACUUM FULL can be applied safely to all catalogs.

* We no longer have to use an unsafe reindex-in-place approach for reindexing
  shared catalogs.

CLUSTER on nailed catalogs now works too, although I left it disabled on
shared catalogs because the resulting pg_index.indisclustered update would
only be visible in one database.

Since reindexing shared system catalogs is now fully transactional and
crash-safe, the former special cases in REINDEX behavior have been removed;
shared catalogs are treated the same as non-shared.

This commit does not do anything about the recently-discussed problem of
deadlocks between VACUUM FULL/CLUSTER on a system catalog and other
concurrent queries; will address that in a separate patch.  As a stopgap,
parallel_schedule has been tweaked to run vacuum.sql by itself, to avoid
such failures during the regression tests.

4 files changed, 40 insertions, 15 deletions

diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index ddc3f6b4f96..bd280360879 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/index/genam.c,v 1.79 2010/01/02 16:57:35 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/index/genam.c,v 1.80 2010/02/07 20:48:09 tgl Exp $
  *
  * NOTES
  *	  many of the old access method routines have been turned into
@@ -21,6 +21,7 @@
 
 #include "access/relscan.h"
 #include "access/transam.h"
+#include "catalog/index.h"
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "storage/bufmgr.h"
@@ -419,7 +420,7 @@ systable_beginscan_ordered(Relation heapRelation,
 
 	/* REINDEX can probably be a hard error here ... */
 	if (ReindexIsProcessingIndex(RelationGetRelid(indexRelation)))
-		elog(ERROR, "cannot do ordered scan on index \"%s\", because it is the current REINDEX target",
+		elog(ERROR, "cannot do ordered scan on index \"%s\", because it is being reindexed",
 			 RelationGetRelationName(indexRelation));
 	/* ... but we only throw a warning about violating IgnoreSystemIndexes */
 	if (IgnoreSystemIndexes)
diff --git a/src/backend/access/transam/rmgr.c b/src/backend/access/transam/rmgr.c
index 7e1e0f60fc3..8038b25d1d0 100644
--- a/src/backend/access/transam/rmgr.c
+++ b/src/backend/access/transam/rmgr.c
@@ -3,7 +3,7 @@
  *
  * Resource managers definition
  *
- * $PostgreSQL: pgsql/src/backend/access/transam/rmgr.c,v 1.28 2009/12/19 01:32:33 sriggs Exp $
+ * $PostgreSQL: pgsql/src/backend/access/transam/rmgr.c,v 1.29 2010/02/07 20:48:09 tgl Exp $
  */
 #include "postgres.h"
 
@@ -22,6 +22,7 @@
 #include "commands/tablespace.h"
 #include "storage/freespace.h"
 #include "storage/standby.h"
+#include "utils/relmapper.h"
 
 
 const RmgrData RmgrTable[RM_MAX_ID + 1] = {
@@ -32,7 +33,7 @@ const RmgrData RmgrTable[RM_MAX_ID + 1] = {
 	{"Database", dbase_redo, dbase_desc, NULL, NULL, NULL},
 	{"Tablespace", tblspc_redo, tblspc_desc, NULL, NULL, NULL},
 	{"MultiXact", multixact_redo, multixact_desc, NULL, NULL, NULL},
-	{"Reserved 7", NULL, NULL, NULL, NULL, NULL},
+	{"RelMap", relmap_redo, relmap_desc, NULL, NULL, NULL},
 	{"Standby", standby_redo, standby_desc, NULL, NULL, NULL},
 	{"Heap2", heap2_redo, heap2_desc, NULL, NULL, NULL},
 	{"Heap", heap_redo, heap_desc, NULL, NULL, NULL},
diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index f74a941f66e..156ed5c47be 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/transam/xact.c,v 1.282 2010/01/24 21:49:17 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/transam/xact.c,v 1.283 2010/02/07 20:48:09 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -48,6 +48,7 @@
 #include "utils/inval.h"
 #include "utils/memutils.h"
 #include "utils/relcache.h"
+#include "utils/relmapper.h"
 #include "utils/snapmgr.h"
 #include "pg_trace.h"
 
@@ -250,7 +251,7 @@ static void AbortTransaction(void);
 static void AtAbort_Memory(void);
 static void AtCleanup_Memory(void);
 static void AtAbort_ResourceOwner(void);
-static void AtCommit_LocalCache(void);
+static void AtCCI_LocalCache(void);
 static void AtCommit_Memory(void);
 static void AtStart_Cache(void);
 static void AtStart_Memory(void);
@@ -703,7 +704,7 @@ CommandCounterIncrement(void)
 		 * read-only command.  (But see hacks in inval.c to make real sure we
 		 * don't think a command that queued inval messages was read-only.)
 		 */
-		AtCommit_LocalCache();
+		AtCCI_LocalCache();
 	}
 
 	/*
@@ -1095,12 +1096,20 @@ cleanup:
 
 
 /*
- *	AtCommit_LocalCache
+ *	AtCCI_LocalCache
  */
 static void
-AtCommit_LocalCache(void)
+AtCCI_LocalCache(void)
 {
 	/*
+	 * Make any pending relation map changes visible.  We must do this
+	 * before processing local sinval messages, so that the map changes
+	 * will get reflected into the relcache when relcache invals are
+	 * processed.
+	 */
+	AtCCI_RelationMap();
+
+	/*
 	 * Make catalog changes visible to me for the next command.
 	 */
 	CommandEndInvalidationMessages();
@@ -1734,6 +1743,9 @@ CommitTransaction(void)
 	/* Prevent cancel/die interrupt while cleaning up */
 	HOLD_INTERRUPTS();
 
+	/* Commit updates to the relation map --- do this as late as possible */
+	AtEOXact_RelationMap(true);
+
 	/*
 	 * set the current transaction state information appropriately during
 	 * commit processing
@@ -1980,6 +1992,7 @@ PrepareTransaction(void)
 	AtPrepare_Locks();
 	AtPrepare_PgStat();
 	AtPrepare_MultiXact();
+	AtPrepare_RelationMap();
 
 	/*
 	 * Here is where we really truly prepare.
@@ -2148,10 +2161,11 @@ AbortTransaction(void)
 	/*
 	 * do abort processing
 	 */
-	AfterTriggerEndXact(false);
+	AfterTriggerEndXact(false);			/* 'false' means it's abort */
 	AtAbort_Portals();
-	AtEOXact_LargeObject(false);	/* 'false' means it's abort */
+	AtEOXact_LargeObject(false);
 	AtAbort_Notify();
+	AtEOXact_RelationMap(false);
 
 	/*
 	 * Advertise the fact that we aborted in pg_clog (assuming that we got as
@@ -4625,11 +4639,18 @@ xact_desc_commit(StringInfo buf, xl_xact_commit *xlrec)
 			SharedInvalidationMessage *msg = &msgs[i];
 
 			if (msg->id >= 0)
-				appendStringInfo(buf,  "catcache id%d ", msg->id);
+				appendStringInfo(buf, " catcache %d", msg->id);
+			else if (msg->id == SHAREDINVALCATALOG_ID)
+				appendStringInfo(buf, " catalog %u", msg->cat.catId);
 			else if (msg->id == SHAREDINVALRELCACHE_ID)
-				appendStringInfo(buf,  "relcache ");
+				appendStringInfo(buf, " relcache %u", msg->rc.relId);
+			/* remaining cases not expected, but print something anyway */
 			else if (msg->id == SHAREDINVALSMGR_ID)
-				appendStringInfo(buf,  "smgr ");
+				appendStringInfo(buf, " smgr");
+			else if (msg->id == SHAREDINVALRELMAP_ID)
+				appendStringInfo(buf, " relmap");
+			else
+				appendStringInfo(buf, " unknown id %d", msg->id);
 		}
 	}
 }
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 49adda12f9a..f4b03f4c1be 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2010, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.366 2010/02/01 13:40:28 sriggs Exp $
+ * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.367 2010/02/07 20:48:09 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,7 @@
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
+#include "utils/relmapper.h"
 #include "pg_trace.h"
 
 
@@ -7123,6 +7124,7 @@ CheckPointGuts(XLogRecPtr checkPointRedo, int flags)
 	CheckPointCLOG();
 	CheckPointSUBTRANS();
 	CheckPointMultiXact();
+	CheckPointRelationMap();
 	CheckPointBuffers(flags);	/* performs all required fsyncs */
 	/* We deliberately delay 2PC checkpointing as long as possible */
 	CheckPointTwoPhase(checkPointRedo);