Add a GUC variable "synchronize_seqscans" to allow clients to disable the new

synchronized-scanning behavior, and make pg_dump disable sync scans so that
it will reliably preserve row ordering.  Per recent discussions.

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 30ca1c219c94232c13d2440806b1258225c4d9c1..05996b491088328fa0579ddbbdfc1123e6e999e5 100644 (file)
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -1,4 +1,4 @@
-
+
 
 
   Server Configuration
@@ -4611,6 +4611,28 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
       
      
 
+     
+      synchronize_seqscans (boolean)
+      
+       synchronize_seqscans configuration parameter
+      
+      
+       
+        This allows sequential scans of large tables to synchronize with each
+        other, so that concurrent scans read the same block at about the
+        same time and hence share the I/O workload.  When this is enabled,
+        a scan might start in the middle of the table and then wrap
+        around the end to cover all rows, so as to synchronize with the
+        activity of scans already in progress.  This can result in
+        unpredictable changes in the row ordering returned by queries that
+        have no ORDER BY clause.  Setting this parameter to
+        off ensures the pre-8.3 behavior in which a sequential
+        scan always starts from the beginning of the table.  The default
+        is on.
+       
+      
+     
+
      
     
 

diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 7134581333a6b550881c565b738b5b9e45ba5b13..c3a45b98db5bda0a96cf00cba0fa0d0fab0048c5 100644 (file)
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/heap/heapam.c,v 1.248 2008/01/14 01:39:09 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/heap/heapam.c,v 1.249 2008/01/30 18:35:55 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -59,6 +59,10 @@
 #include "utils/syscache.h"
 
 
+/* GUC variable */
+bool   synchronize_seqscans = true;
+
+
 static HeapScanDesc heap_beginscan_internal(Relation relation,
                        Snapshot snapshot,
                        int nkeys, ScanKey key,
@@ -104,7 +108,8 @@ initscan(HeapScanDesc scan, ScanKey key)
     * the thresholds for these features could be different, we make them the
     * same so that there are only two behaviors to tune rather than four.
     * (However, some callers need to be able to disable one or both of
-    * these behaviors, independently of the size of the table.)
+    * these behaviors, independently of the size of the table; also there
+    * is a GUC variable that can disable synchronized scanning.)
     *
     * During a rescan, don't make a new strategy object if we don't have to.
     */
@@ -129,7 +134,7 @@ initscan(HeapScanDesc scan, ScanKey key)
        scan->rs_strategy = NULL;
    }
 
-   if (allow_sync)
+   if (allow_sync && synchronize_seqscans)
    {
        scan->rs_syncscan = true;
        scan->rs_startblock = ss_get_location(scan->rs_rd, scan->rs_nblocks);

diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index e3e04f4d3418244fe6cf036978062aa937214035..1dbffbfb4825bdb3eadc46af06c2f373728487e8 100644 (file)
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -10,7 +10,7 @@
  * Written by Peter Eisentraut .
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.431 2008/01/27 19:12:28 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.432 2008/01/30 18:35:55 tgl Exp $
  *
  *--------------------------------------------------------------------
  */
@@ -110,6 +110,7 @@ extern int  CommitDelay;
 extern int CommitSiblings;
 extern char *default_tablespace;
 extern char *temp_tablespaces;
+extern bool synchronize_seqscans;
 extern bool fullPageWrites;
 
 #ifdef TRACE_SORT
@@ -1052,6 +1053,15 @@ static struct config_bool ConfigureNamesBool[] =
        false, NULL, NULL
    },
 
+   {
+       {"synchronize_seqscans", PGC_USERSET, COMPAT_OPTIONS_PREVIOUS,
+           gettext_noop("Enable synchronized sequential scans."),
+           NULL
+       },
+       &synchronize_seqscans,
+       true, NULL, NULL
+   },
+
    {
        {"archive_mode", PGC_POSTMASTER, WAL_SETTINGS,
            gettext_noop("Allows archiving of WAL files using archive_command."),

diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index d9b9532395ea9c287cf6f22a6816f138e1c637d3..258a7d1a4f519942d23b3eef13ea54be9fbaf5d2 100644 (file)
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -476,9 +476,10 @@
 #backslash_quote = safe_encoding   # on, off, or safe_encoding
 #default_with_oids = off
 #escape_string_warning = on
-#standard_conforming_strings = off
 #regex_flavor = advanced       # advanced, extended, or basic
 #sql_inheritance = on
+#standard_conforming_strings = off
+#synchronize_seqscans = on
 
 # - Other Platforms and Clients -
 

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 3e53a64cd461c70e07f1c3d8314c77d54d00bbcd..c284bbb2da9637cd61ff252a237769b13760ad28 100644 (file)
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -12,7 +12,7 @@
  * by PostgreSQL
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.c,v 1.481 2008/01/01 19:45:55 momjian Exp $
+ *   $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.c,v 1.482 2008/01/30 18:35:55 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -552,6 +552,20 @@ main(int argc, char **argv)
    /* Set the datestyle to ISO to ensure the dump's portability */
    do_sql_command(g_conn, "SET DATESTYLE = ISO");
 
+   /*
+    * If supported, set extra_float_digits so that we can dump float data
+    * exactly (given correctly implemented float I/O code, anyway)
+    */
+   if (g_fout->remoteVersion >= 70400)
+       do_sql_command(g_conn, "SET extra_float_digits TO 2");
+
+   /*
+    * If synchronized scanning is supported, disable it, to prevent
+    * unpredictable changes in row ordering across a dump and reload.
+    */
+   if (g_fout->remoteVersion >= 80300)
+       do_sql_command(g_conn, "SET synchronize_seqscans TO off");
+
    /*
     * Start serializable transaction to dump consistent data.
     */
@@ -567,13 +581,6 @@ main(int argc, char **argv)
    else
        username_subquery = "SELECT usename FROM pg_user WHERE usesysid =";
 
-   /*
-    * If supported, set extra_float_digits so that we can dump float data
-    * exactly (given correctly implemented float I/O code, anyway)
-    */
-   if (g_fout->remoteVersion >= 70400)
-       do_sql_command(g_conn, "SET extra_float_digits TO 2");
-
    /* Find the last built-in OID, if needed */
    if (g_fout->remoteVersion < 70300)
    {