Provide for parallel restoration from a custom format archive. Each data and

post-data step is run in a separate worker child (a thread on Windows, a child
process elsewhere) up to the concurrent number specified by the new pg_restore
command-line --multi-thread | -m switch.

Andrew Dunstan, with some editing by Tom Lane.

Author: adunstan

doc/src/sgml/ref/pg_restore.sgml

@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/ref/pg_restore.sgml,v 1.77 2009/01/05 16:54:36 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/ref/pg_restore.sgml,v 1.78 2009/02/02 20:07:36 adunstan Exp $ -->
 
 <refentry id="APP-PGRESTORE">
  <refmeta>
@@ -241,6 +241,28 @@
       </listitem>
      </varlistentry>
 
+     <varlistentry>
+      <term><option>-m <replaceable class="parameter">number-of-threads</replaceable></option></term>
+      <term><option>--multi-thread=<replaceable class="parameter">number-of-threads</replaceable></option></term>
+      <listitem>
+       <para>
+        Run the most time-consuming parts of <application>pg_restore</>
+        &mdash; those which load data, create indexes, or create
+        constraints &mdash; using multiple concurrent connections to the
+        database. This option can dramatically reduce the time to restore a
+        large database to a server running on a multi-processor machine.
+       </para>
+
+       <para>
+        This option is ignored when emitting a script rather than connecting
+        directly to a database server.  Multiple threads cannot be used
+        together with <option>--single-transaction</option>.  Also, the input
+        must be a plain file (not, for example, a pipe), and at present only
+        the custom archive format is supported.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry>
       <term><option>-n <replaceable class="parameter">namespace</replaceable></option></term>
       <term><option>--schema=<replaceable class="parameter">schema</replaceable></option></term>

src/bin/pg_dump/pg_backup.h

@@ -15,7 +15,7 @@
  *
  *
  * IDENTIFICATION
- *		$PostgreSQL: pgsql/src/bin/pg_dump/pg_backup.h,v 1.48 2009/01/05 16:54:36 tgl Exp $
+ *		$PostgreSQL: pgsql/src/bin/pg_dump/pg_backup.h,v 1.49 2009/02/02 20:07:36 adunstan Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,14 @@ typedef enum _archiveMode
 	archModeRead
 } ArchiveMode;
 
+typedef enum _teSection
+{
+	SECTION_NONE = 1,			/* COMMENTs, ACLs, etc; can be anywhere */
+	SECTION_PRE_DATA,			/* stuff to be processed before data */
+	SECTION_DATA,				/* TABLE DATA, BLOBS, BLOB COMMENTS */
+	SECTION_POST_DATA			/* stuff to be processed after data */
+} teSection;
+
 /*
  *	We may want to have some more user-readable data, but in the mean
  *	time this gives us some abstraction and type checking.
@@ -124,6 +132,7 @@ typedef struct _restoreOptions
 	int			suppressDumpWarnings;	/* Suppress output of WARNING entries
 										 * to stderr */
 	bool		single_txn;
+	int			number_of_threads;
 
 	bool	   *idWanted;		/* array showing which dump IDs to emit */
 } RestoreOptions;
@@ -152,7 +161,8 @@ extern void ArchiveEntry(Archive *AHX,
 			 const char *tag,
 			 const char *namespace, const char *tablespace,
 			 const char *owner, bool withOids,
-			 const char *desc, const char *defn,
+			 const char *desc, teSection section,
+			 const char *defn,
 			 const char *dropStmt, const char *copyStmt,
 			 const DumpId *deps, int nDeps,
 			 DataDumperPtr dumpFn, void *dumpArg);