Make pg_basebackup skip temporary statistics files.

The temporary statistics files don't need to be included in the backup
because they are always reset at the beginning of the archive recovery.
This patch changes pg_basebackup so that it skips all files located in
$PGDATA/pg_stat_tmp or the directory specified by stats_temp_directory
parameter.

diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c
index 3c6e84d0c40b865ffd71e92c4e758f884073ab88..97f171d68edfdf4c8526531f705243f5e4fbe868 100644 (file)
--- a/contrib/pg_stat_statements/pg_stat_statements.c
+++ b/contrib/pg_stat_statements/pg_stat_statements.c
@@ -68,6 +68,7 @@
 #include "parser/analyze.h"
 #include "parser/parsetree.h"
 #include "parser/scanner.h"
+#include "pgstat.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/spin.h"
@@ -89,7 +90,7 @@ PG_MODULE_MAGIC;
  * race conditions.  Besides, we only expect modest, infrequent I/O for query
  * strings, so placing the file on a faster filesystem is not compelling.
  */
-#define PGSS_TEXT_FILE "pg_stat_tmp/pgss_query_texts.stat"
+#define PGSS_TEXT_FILE PG_STAT_TMP_DIR "/pgss_query_texts.stat"
 
 /* Magic number identifying the stats file format */
 static const uint32 PGSS_FILE_HEADER = 0x20140125;

diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c
index 781f678097d4c6dc5d000703f30fe7bbffe2a43f..06e54bc530e2e6133c3b0008cd9c71b1fedd5470 100644 (file)
--- a/src/backend/replication/basebackup.c
+++ b/src/backend/replication/basebackup.c
@@ -25,6 +25,7 @@
 #include "libpq/pqformat.h"
 #include "miscadmin.h"
 #include "nodes/pg_list.h"
+#include "pgstat.h"
 #include "replication/basebackup.h"
 #include "replication/walsender.h"
 #include "replication/walsender_private.h"
@@ -63,6 +64,9 @@ static int    compareWalFileNames(const void *a, const void *b);
 /* Was the backup currently in-progress initiated in recovery mode? */
 static bool backup_started_in_recovery = false;
 
+/* Relative path of temporary statistics directory */
+static char *statrelpath = NULL;
+
 /*
  * Size of each block sent into the tar stream for larger files.
  */
@@ -111,6 +115,18 @@ perform_base_backup(basebackup_options *opt, DIR *tblspcdir)
                                  &labelfile);
    SendXlogRecPtrResult(startptr, starttli);
 
+   /*
+    * Calculate the relative path of temporary statistics directory
+    * in order to skip the files which are located in that directory later.
+    */
+   if (is_absolute_path(pgstat_stat_directory) &&
+       strncmp(pgstat_stat_directory, DataDir, datadirpathlen) == 0)
+       statrelpath = psprintf("./%s", pgstat_stat_directory + datadirpathlen + 1);
+   else if (strncmp(pgstat_stat_directory, "./", 2) != 0)
+       statrelpath = psprintf("./%s", pgstat_stat_directory);
+   else
+       statrelpath = pgstat_stat_directory;
+
    PG_ENSURE_ERROR_CLEANUP(base_backup_cleanup, (Datum) 0);
    {
        List       *tablespaces = NIL;
@@ -838,7 +854,6 @@ sendDir(char *path, int basepathlen, bool sizeonly, List *tablespaces)
                    sizeof(PG_AUTOCONF_FILENAME) + 4) == 0)
            continue;
 
-
        /*
         * If there's a backup_label file, it belongs to a backup started by
         * the user with pg_start_backup(). It is *not* correct for this
@@ -891,6 +906,20 @@ sendDir(char *path, int basepathlen, bool sizeonly, List *tablespaces)
            continue;
        }
 
+       /*
+        * Skip temporary statistics files. PG_STAT_TMP_DIR must be skipped
+        * even when stats_temp_directory is set because PGSS_TEXT_FILE is
+        * always created there.
+        */
+       if ((statrelpath != NULL && strcmp(pathbuf, statrelpath) == 0) ||
+           strncmp(de->d_name, PG_STAT_TMP_DIR, strlen(PG_STAT_TMP_DIR)) == 0)
+       {
+           if (!sizeonly)
+               _tarWriteHeader(pathbuf + basepathlen + 1, NULL, &statbuf);
+           size += 512;
+           continue;
+       }
+
        /*
         * We can skip pg_xlog, the WAL segments need to be fetched from the
         * WAL archive anyway. But include it as an empty directory anyway, so

diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 70d73d9898ee02a32db20d1806bf79538b1ffc0a..2812a73d5454bd3cb13b83c06b3a980218b27ace 100644 (file)
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -3174,7 +3174,7 @@ static struct config_string ConfigureNamesString[] =
            GUC_SUPERUSER_ONLY
        },
        &pgstat_temp_directory,
-       "pg_stat_tmp",
+       PG_STAT_TMP_DIR,
        check_canonical_path, assign_pgstat_temp_directory, NULL
    },
 

diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 2024b7994a4c9e55474de09db70de71150f75ca7..5b2e4609f65c6dfc7a1a2a1de1b8b6d35f3b9390 100644 (file)
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -20,6 +20,9 @@
 #include "utils/relcache.h"
 
 
+/* Default directory to store temporary statistics data in */
+#define PG_STAT_TMP_DIR        "pg_stat_tmp"
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {