Add pg_stat_archiver statistics view.

This view shows the statistics about the WAL archiver process's activity.

Gabriele Bartolini, reviewed by Michael Paquier, refactored a bit by me.

Author: MasaoFujii

doc/src/sgml/monitoring.sgml

@@ -269,6 +269,14 @@ postgres: <replaceable>user</> <replaceable>database</> <replaceable>host</> <re
       </entry>
      </row>
 
+     <row>
+      <entry><structname>pg_stat_archiver</><indexterm><primary>pg_stat_archiver</primary></indexterm></entry>
+      <entry>One row only, showing statistics about the
+       WAL archiver process's activity. See
+       <xref linkend="pg-stat-archiver-view"> for details.
+      </entry>
+     </row>
+
      <row>
       <entry><structname>pg_stat_bgwriter</><indexterm><primary>pg_stat_bgwriter</primary></indexterm></entry>
       <entry>One row only, showing statistics about the
@@ -648,6 +656,63 @@ postgres: <replaceable>user</> <replaceable>database</> <replaceable>host</> <re
    </para>
   </note>
 
+  <table id="pg-stat-archiver-view" xreflabel="pg_stat_archiver">
+   <title><structname>pg_stat_archiver</structname> View</title>
+
+   <tgroup cols="3">
+    <thead>
+     <row>
+      <entry>Column</entry>
+      <entry>Type</entry>
+      <entry>Description</entry>
+     </row>
+    </thead>
+
+    <tbody>
+     <row>
+      <entry><structfield>archived_count</></entry>
+      <entry><type>bigint</type></entry>
+      <entry>Number of WAL files that have been successfully archived</entry>
+     </row>
+     <row>
+      <entry><structfield>last_archived_wal</></entry>
+      <entry><type>text</type></entry>
+      <entry>Name of the last WAL file successfully archived</entry>
+     </row>
+     <row>
+      <entry><structfield>last_archived_time</></entry>
+      <entry><type>timestamp with time zone</type></entry>
+      <entry>Time of the last successful archive operation</entry>
+     </row>
+     <row>
+      <entry><structfield>failed_count</></entry>
+      <entry><type>bigint</type></entry>
+      <entry>Number of failed attempts for archiving WAL files</entry>
+     </row>
+     <row>
+      <entry><structfield>last_failed_wal</></entry>
+      <entry><type>text</type></entry>
+      <entry>Name of the WAL file of the last failed archival operation</entry>
+     </row>
+     <row>
+      <entry><structfield>last_failed_time</></entry>
+      <entry><type>timestamp with time zone</type></entry>
+      <entry>Time of the last failed archival operation</entry>
+     </row>
+     <row>
+      <entry><structfield>stats_reset</></entry>
+      <entry><type>timestamp with time zone</type></entry>
+      <entry>Time at which these statistics were last reset</entry>
+     </row>
+    </tbody>
+   </tgroup>
+  </table>
+
+  <para>
+   The <structname>pg_stat_archiver</structname> view will always have a
+   single row, containing data about the archiver process of the cluster.
+  </para>
+
   <table id="pg-stat-bgwriter-view" xreflabel="pg_stat_bgwriter">
    <title><structname>pg_stat_bgwriter</structname> View</title>
 
@@ -1613,6 +1678,8 @@ postgres: <replaceable>user</> <replaceable>database</> <replaceable>host</> <re
        argument (requires superuser privileges).
        Calling <literal>pg_stat_reset_shared('bgwriter')</> will zero all the
        counters shown in the <structname>pg_stat_bgwriter</> view.
+       Calling <literal>pg_stat_reset_shared('archiver')</> will zero all the
+       counters shown in the <structname>pg_stat_archiver</> view.
       </entry>
      </row>
 

src/backend/catalog/system_views.sql

@@ -672,6 +672,17 @@ CREATE VIEW pg_stat_xact_user_functions AS
     WHERE P.prolang != 12  -- fast check to eliminate built-in functions
           AND pg_stat_get_xact_function_calls(P.oid) IS NOT NULL;
 
+CREATE VIEW pg_stat_archiver AS
+    SELECT
+        s.archived_count,
+        s.last_archived_wal,
+        s.last_archived_time,
+        s.failed_count,
+        s.last_failed_wal,
+        s.last_failed_time,
+        s.stats_reset
+    FROM pg_stat_get_archiver() s;
+
 CREATE VIEW pg_stat_bgwriter AS
     SELECT
         pg_stat_get_bgwriter_timed_checkpoints() AS checkpoints_timed,

src/backend/postmaster/pgarch.c

@@ -36,6 +36,7 @@
 #include "access/xlog_internal.h"
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "postmaster/fork_process.h"
 #include "postmaster/pgarch.h"
 #include "postmaster/postmaster.h"
@@ -58,19 +59,6 @@
 #define PGARCH_RESTART_INTERVAL 10		/* How often to attempt to restart a
 										 * failed archiver; in seconds. */
 
-/* ----------
- * Archiver control info.
- *
- * We expect that archivable files within pg_xlog will have names between
- * MIN_XFN_CHARS and MAX_XFN_CHARS in length, consisting only of characters
- * appearing in VALID_XFN_CHARS.  The status files in archive_status have
- * corresponding names with ".ready" or ".done" appended.
- * ----------
- */
-#define MIN_XFN_CHARS	16
-#define MAX_XFN_CHARS	40
-#define VALID_XFN_CHARS "0123456789ABCDEF.history.backup"
-
 #define NUM_ARCHIVE_RETRIES 3
 
 
@@ -496,10 +484,17 @@ pgarch_ArchiverCopyLoop(void)
 			{
 				/* successful */
 				pgarch_archiveDone(xlog);
+
+				/* Tell the collector about the WAL file that we successfully archived */
+				pgstat_send_archiver(xlog, false);
+
 				break;			/* out of inner retry loop */
 			}
 			else
 			{
+				/* Tell the collector about the WAL file that we failed to archive */
+				pgstat_send_archiver(xlog, true);
+
 				if (++failures >= NUM_ARCHIVE_RETRIES)
 				{
 					ereport(WARNING,

src/backend/postmaster/pgstat.c

@@ -221,6 +221,7 @@ static int	localNumBackends = 0;
  * Contains statistics that are not collected per database
  * or per table.
  */
+static PgStat_ArchiverStats archiverStats;
 static PgStat_GlobalStats globalStats;
 
 /* Write request info for each database */
@@ -292,6 +293,7 @@ static void pgstat_recv_resetsinglecounter(PgStat_MsgResetsinglecounter *msg, in
 static void pgstat_recv_autovac(PgStat_MsgAutovacStart *msg, int len);
 static void pgstat_recv_vacuum(PgStat_MsgVacuum *msg, int len);
 static void pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len);
+static void pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len);
 static void pgstat_recv_bgwriter(PgStat_MsgBgWriter *msg, int len);
 static void pgstat_recv_funcstat(PgStat_MsgFuncstat *msg, int len);
 static void pgstat_recv_funcpurge(PgStat_MsgFuncpurge *msg, int len);
@@ -1257,13 +1259,15 @@ pgstat_reset_shared_counters(const char *target)
 				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
 				 errmsg("must be superuser to reset statistics counters")));
 
-	if (strcmp(target, "bgwriter") == 0)
+	if (strcmp(target, "archiver") == 0)
+		msg.m_resettarget = RESET_ARCHIVER;
+	else if (strcmp(target, "bgwriter") == 0)
 		msg.m_resettarget = RESET_BGWRITER;
 	else
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 				 errmsg("unrecognized reset target: \"%s\"", target),
-				 errhint("Target must be \"bgwriter\".")));
+				 errhint("Target must be \"archiver\" or \"bgwriter\".")));
 
 	pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETSHAREDCOUNTER);
 	pgstat_send(&msg, sizeof(msg));
@@ -2321,6 +2325,23 @@ pgstat_fetch_stat_numbackends(void)
 	return localNumBackends;
 }
 
+/*
+ * ---------
+ * pgstat_fetch_stat_archiver() -
+ *
+ *	Support function for the SQL-callable pgstat* functions. Returns
+ *	a pointer to the archiver statistics struct.
+ * ---------
+ */
+PgStat_ArchiverStats *
+pgstat_fetch_stat_archiver(void)
+{
+	backend_read_statsfile();
+
+	return &archiverStats;
+}
+
+
 /*
  * ---------
  * pgstat_fetch_global() -
@@ -3035,6 +3056,28 @@ pgstat_send(void *msg, int len)
 #endif
 }
 
+/* ----------
+ * pgstat_send_archiver() -
+ *
+ *	Tell the collector about the WAL file that we successfully
+ *	archived or failed to archive.
+ * ----------
+ */
+void
+pgstat_send_archiver(const char *xlog, bool failed)
+{
+	PgStat_MsgArchiver	msg;
+
+	/*
+	 * Prepare and send the message
+	 */
+	pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_ARCHIVER);
+	msg.m_failed = failed;
+	strncpy(msg.m_xlog, xlog, sizeof(msg.m_xlog));
+	msg.m_timestamp = GetCurrentTimestamp();
+	pgstat_send(&msg, sizeof(msg));
+}
+
 /* ----------
  * pgstat_send_bgwriter() -
  *
@@ -3278,6 +3321,10 @@ PgstatCollectorMain(int argc, char *argv[])
 					pgstat_recv_analyze((PgStat_MsgAnalyze *) &msg, len);
 					break;
 
+				case PGSTAT_MTYPE_ARCHIVER:
+					pgstat_recv_archiver((PgStat_MsgArchiver *) &msg, len);
+					break;
+
 				case PGSTAT_MTYPE_BGWRITER:
 					pgstat_recv_bgwriter((PgStat_MsgBgWriter *) &msg, len);
 					break;
@@ -3562,6 +3609,12 @@ pgstat_write_statsfiles(bool permanent, bool allDbs)
 	rc = fwrite(&globalStats, sizeof(globalStats), 1, fpout);
 	(void) rc;					/* we'll check for error with ferror */
 
+	/*
+	 * Write archiver stats struct
+	 */
+	rc = fwrite(&archiverStats, sizeof(archiverStats), 1, fpout);
+	(void) rc;					/* we'll check for error with ferror */
+
 	/*
 	 * Walk through the database table.
 	 */
@@ -3828,16 +3881,18 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep)
 						 HASH_ELEM | HASH_FUNCTION | HASH_CONTEXT);
 
 	/*
-	 * Clear out global statistics so they start from zero in case we can't
-	 * load an existing statsfile.
+	 * Clear out global and archiver statistics so they start from zero
+	 * in case we can't load an existing statsfile.
 	 */
 	memset(&globalStats, 0, sizeof(globalStats));
+	memset(&archiverStats, 0, sizeof(archiverStats));
 
 	/*
 	 * Set the current timestamp (will be kept only in case we can't load an
 	 * existing statsfile).
 	 */
 	globalStats.stat_reset_timestamp = GetCurrentTimestamp();
+	archiverStats.stat_reset_timestamp = globalStats.stat_reset_timestamp;
 
 	/*
 	 * Try to open the stats file. If it doesn't exist, the backends simply
@@ -3879,6 +3934,16 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep)
 		goto done;
 	}
 
+	/*
+	 * Read archiver stats struct
+	 */
+	if (fread(&archiverStats, 1, sizeof(archiverStats), fpin) != sizeof(archiverStats))
+	{
+		ereport(pgStatRunningInCollector ? LOG : WARNING,
+				(errmsg("corrupted statistics file \"%s\"", statfile)));
+		goto done;
+	}
+
 	/*
 	 * We found an existing collector stats file. Read it and put all the
 	 * hashtable entries into place.
@@ -4159,7 +4224,7 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash,
  *	stats_timestamp value.
  *
  *	- if there's no db stat entry (e.g. for a new or inactive database),
- *	there's no stat_timestamp value, but also nothing to write so we return
+ *	there's no stats_timestamp value, but also nothing to write so we return
  *	the timestamp of the global statfile.
  * ----------
  */
@@ -4169,6 +4234,7 @@ pgstat_read_db_statsfile_timestamp(Oid databaseid, bool permanent,
 {
 	PgStat_StatDBEntry dbentry;
 	PgStat_GlobalStats myGlobalStats;
+	PgStat_ArchiverStats myArchiverStats;
 	FILE	   *fpin;
 	int32		format_id;
 	const char *statfile = permanent ? PGSTAT_STAT_PERMANENT_FILENAME : pgstat_stat_filename;
@@ -4211,6 +4277,18 @@ pgstat_read_db_statsfile_timestamp(Oid databaseid, bool permanent,
 		return false;
 	}
 
+	/*
+	 * Read archiver stats struct
+	 */
+	if (fread(&myArchiverStats, 1, sizeof(myArchiverStats),
+			  fpin) != sizeof(myArchiverStats))
+	{
+		ereport(pgStatRunningInCollector ? LOG : WARNING,
+				(errmsg("corrupted statistics file \"%s\"", statfile)));
+		FreeFile(fpin);
+		return false;
+	}
+
 	/* By default, we're going to return the timestamp of the global file. */
 	*ts = myGlobalStats.stats_timestamp;
 
@@ -4738,6 +4816,12 @@ pgstat_recv_resetsharedcounter(PgStat_MsgResetsharedcounter *msg, int len)
 		memset(&globalStats, 0, sizeof(globalStats));
 		globalStats.stat_reset_timestamp = GetCurrentTimestamp();
 	}
+	else if (msg->m_resettarget == RESET_ARCHIVER)
+	{
+		/* Reset the archiver statistics for the cluster. */
+		memset(&archiverStats, 0, sizeof(archiverStats));
+		archiverStats.stat_reset_timestamp = GetCurrentTimestamp();
+	}
 
 	/*
 	 * Presumably the sender of this message validated the target, don't
@@ -4867,6 +4951,33 @@ pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len)
 }
 
 
+/* ----------
+ * pgstat_recv_archiver() -
+ *
+ *	Process a ARCHIVER message.
+ * ----------
+ */
+static void
+pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len)
+{
+	if (msg->m_failed)
+	{
+		/* Failed archival attempt */
+		++archiverStats.failed_count;
+		memcpy(archiverStats.last_failed_wal, msg->m_xlog,
+			sizeof(archiverStats.last_failed_wal));
+		archiverStats.last_failed_timestamp = msg->m_timestamp;
+	}
+	else
+	{
+		/* Successful archival operation */
+		++archiverStats.archived_count;
+		memcpy(archiverStats.last_archived_wal, msg->m_xlog,
+			sizeof(archiverStats.last_archived_wal));
+		archiverStats.last_archived_timestamp = msg->m_timestamp;
+	}
+}
+
 /* ----------
  * pgstat_recv_bgwriter() -
  *