Add new block-by-block strategy for CREATE DATABASE.

Because this strategy logs changes on a block-by-block basis, it
avoids the need to checkpoint before and after the operation.
However, because it logs each changed block individually, it might
generate a lot of extra write-ahead logging if the template database
is large. Therefore, the older strategy remains available via a new
STRATEGY parameter to CREATE DATABASE, and a corresponding --strategy
option to createdb.

Somewhat controversially, this patch assembles the list of relations
to be copied to the new database by reading the pg_class relation of
the template database. Cross-database access like this isn't normally
possible, but it can be made to work here because there can't be any
connections to the database being copied, nor can it contain any
in-doubt transactions. Even so, we have to use lower-level interfaces
than normal, since the table scan and relcache interfaces will not
work for a database to which we're not connected. The advantage of
this approach is that we do not need to rely on the filesystem to
determine what ought to be copied, but instead on PostgreSQL's own
knowledge of the database structure. This avoids, for example,
copying stray files that happen to be located in the source database
directory.

Dilip Kumar, with a fairly large number of cosmetic changes by me.
Reviewed and tested by Ashutosh Sharma, Andres Freund, John Naylor,
Greg Nancarrow, Neha Sharma. Additional feedback from Bruce Momjian,
Heikki Linnakangas, Julien Rouhaud, Adam Brusselback, Kyotaro
Horiguchi, Tomas Vondra, Andrew Dunstan, Álvaro Herrera, and others.

Discussion: http://postgr.es/m/CA+TgmoYtcdxBjLh31DLxUXHxFVMPGzrU5_T=CYCvRyFHywSBUQ@mail.gmail.com

6 files changed, 33 insertions, 8 deletions

diff --git a/src/include/catalog/storage.h b/src/include/catalog/storage.h
index 9ffc7419131..844a023b2ce 100644
--- a/src/include/catalog/storage.h
+++ b/src/include/catalog/storage.h
@@ -22,7 +22,9 @@
 /* GUC variables */
 extern int	wal_skip_threshold;
 
-extern SMgrRelation RelationCreateStorage(RelFileNode rnode, char relpersistence);
+extern SMgrRelation RelationCreateStorage(RelFileNode rnode,
+										  char relpersistence,
+										  bool register_delete);
 extern void RelationDropStorage(Relation rel);
 extern void RelationPreserveStorage(RelFileNode rnode, bool atCommit);
 extern void RelationPreTruncate(Relation rel);
diff --git a/src/include/commands/dbcommands_xlog.h b/src/include/commands/dbcommands_xlog.h
index 593a8578a41..0ee2452feba 100644
--- a/src/include/commands/dbcommands_xlog.h
+++ b/src/include/commands/dbcommands_xlog.h
@@ -18,17 +18,32 @@
 #include "lib/stringinfo.h"
 
 /* record types */
-#define XLOG_DBASE_CREATE		0x00
-#define XLOG_DBASE_DROP			0x10
+#define XLOG_DBASE_CREATE_FILE_COPY		0x00
+#define XLOG_DBASE_CREATE_WAL_LOG		0x10
+#define XLOG_DBASE_DROP					0x20
 
-typedef struct xl_dbase_create_rec
+/*
+ * Single WAL record for an entire CREATE DATABASE operation. This is used
+ * by the FILE_COPY strategy.
+ */
+typedef struct xl_dbase_create_file_copy_rec
 {
-	/* Records copying of a single subdirectory incl. contents */
 	Oid			db_id;
 	Oid			tablespace_id;
 	Oid			src_db_id;
 	Oid			src_tablespace_id;
-} xl_dbase_create_rec;
+} xl_dbase_create_file_copy_rec;
+
+/*
+ * WAL record for the beginning of a CREATE DATABASE operation, when the
+ * WAL_LOG strategy is used. Each individual block will be logged separately
+ * afterward.
+ */
+typedef struct xl_dbase_create_wal_log_rec
+{
+	Oid			db_id;
+	Oid			tablespace_id;
+} xl_dbase_create_wal_log_rec;
 
 typedef struct xl_dbase_drop_rec
 {
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index dd01841c300..a6b657f0ba5 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -184,7 +184,8 @@ extern Buffer ReadBufferExtended(Relation reln, ForkNumber forkNum,
 								 BufferAccessStrategy strategy);
 extern Buffer ReadBufferWithoutRelcache(RelFileNode rnode,
 										ForkNumber forkNum, BlockNumber blockNum,
-										ReadBufferMode mode, BufferAccessStrategy strategy);
+										ReadBufferMode mode, BufferAccessStrategy strategy,
+										bool permanent);
 extern void ReleaseBuffer(Buffer buffer);
 extern void UnlockReleaseBuffer(Buffer buffer);
 extern void MarkBufferDirty(Buffer buffer);
@@ -203,6 +204,9 @@ extern BlockNumber RelationGetNumberOfBlocksInFork(Relation relation,
 extern void FlushOneBuffer(Buffer buffer);
 extern void FlushRelationBuffers(Relation rel);
 extern void FlushRelationsAllBuffers(struct SMgrRelationData **smgrs, int nrels);
+extern void CreateAndCopyRelationData(RelFileNode src_rnode,
+									  RelFileNode dst_rnode,
+									  bool permanent);
 extern void FlushDatabaseBuffers(Oid dbid);
 extern void DropRelFileNodeBuffers(struct SMgrRelationData *smgr_reln, ForkNumber *forkNum,
 								   int nforks, BlockNumber *firstDelBlock);
diff --git a/src/include/storage/lmgr.h b/src/include/storage/lmgr.h
index 49edbcc81be..be1d2c99a95 100644
--- a/src/include/storage/lmgr.h
+++ b/src/include/storage/lmgr.h
@@ -38,6 +38,7 @@ extern void RelationInitLockInfo(Relation relation);
 
 /* Lock a relation */
 extern void LockRelationOid(Oid relid, LOCKMODE lockmode);
+extern void LockRelationId(LockRelId *relid, LOCKMODE lockmode);
 extern bool ConditionalLockRelationOid(Oid relid, LOCKMODE lockmode);
 extern void UnlockRelationId(LockRelId *relid, LOCKMODE lockmode);
 extern void UnlockRelationOid(Oid relid, LOCKMODE lockmode);
diff --git a/src/include/utils/relmapper.h b/src/include/utils/relmapper.h
index 9fbb5a7f9b5..f10353e1390 100644
--- a/src/include/utils/relmapper.h
+++ b/src/include/utils/relmapper.h
@@ -38,7 +38,9 @@ typedef struct xl_relmap_update
 extern Oid	RelationMapOidToFilenode(Oid relationId, bool shared);
 
 extern Oid	RelationMapFilenodeToOid(Oid relationId, bool shared);
-
+extern Oid RelationMapOidToFilenodeForDatabase(char *dbpath, Oid relationId);
+extern void RelationMapCopy(Oid dbid, Oid tsid, char *srcdbpath,
+							char *dstdbpath);
 extern void RelationMapUpdateMap(Oid relationId, Oid fileNode, bool shared,
 								 bool immediate);
 
diff --git a/src/include/utils/wait_event.h b/src/include/utils/wait_event.h
index 1c39ce031a7..d870c592632 100644
--- a/src/include/utils/wait_event.h
+++ b/src/include/utils/wait_event.h
@@ -218,6 +218,7 @@ typedef enum
 	WAIT_EVENT_TWOPHASE_FILE_READ,
 	WAIT_EVENT_TWOPHASE_FILE_SYNC,
 	WAIT_EVENT_TWOPHASE_FILE_WRITE,
+	WAIT_EVENT_VERSION_FILE_WRITE,
 	WAIT_EVENT_WALSENDER_TIMELINE_HISTORY_READ,
 	WAIT_EVENT_WAL_BOOTSTRAP_SYNC,
 	WAIT_EVENT_WAL_BOOTSTRAP_WRITE,