pgstat: split reporting/fetching of bgwriter and checkpointer stats.

These have been unrelated since bgwriter and checkpointer were split into two
processes in 806a2ae. As there several pending patches (shared memory
stats, extending the set of tracked IO / buffer statistics) that are made a
bit more awkward by the grouping, split them. Done separately to make
reviewing easier.

This does *not* change the contents of pg_stat_bgwriter or move fields out of
bgwriter/checkpointer stats that arguably do not belong in either. However
pgstat_fetch_global() was renamed and split into
pgstat_fetch_stat_checkpointer() and pgstat_fetch_stat_bgwriter().

Author: Andres Freund <andres@anarazel.de>
Discussion: https://postgr.es/m/20210405092914.mmxqe7j56lsjfsej@alap3.anarazel.de

Author: anarazel

src/backend/access/transam/xlog.c

@@ -8721,8 +8721,8 @@ LogCheckpointEnd(bool restartpoint)
 												 CheckpointStats.ckpt_sync_end_t);
 
 	/* Accumulate checkpoint timing summary data, in milliseconds. */
-	BgWriterStats.m_checkpoint_write_time += write_msecs;
-	BgWriterStats.m_checkpoint_sync_time += sync_msecs;
+	PendingCheckpointerStats.m_checkpoint_write_time += write_msecs;
+	PendingCheckpointerStats.m_checkpoint_sync_time += sync_msecs;
 
 	/*
 	 * All of the published timing statistics are accounted for.  Only

src/backend/postmaster/checkpointer.c

@@ -357,7 +357,7 @@ CheckpointerMain(void)
 		if (((volatile CheckpointerShmemStruct *) CheckpointerShmem)->ckpt_flags)
 		{
 			do_checkpoint = true;
-			BgWriterStats.m_requested_checkpoints++;
+			PendingCheckpointerStats.m_requested_checkpoints++;
 		}
 
 		/*
@@ -371,7 +371,7 @@ CheckpointerMain(void)
 		if (elapsed_secs >= CheckPointTimeout)
 		{
 			if (!do_checkpoint)
-				BgWriterStats.m_timed_checkpoints++;
+				PendingCheckpointerStats.m_timed_checkpoints++;
 			do_checkpoint = true;
 			flags |= CHECKPOINT_CAUSE_TIME;
 		}
@@ -493,13 +493,9 @@ CheckpointerMain(void)
 		CheckArchiveTimeout();
 
 		/*
-		 * Send off activity statistics to the stats collector.  (The reason
-		 * why we re-use bgwriter-related code for this is that the bgwriter
-		 * and checkpointer used to be just one process.  It's probably not
-		 * worth the trouble to split the stats support into two independent
-		 * stats message types.)
+		 * Send off activity statistics to the stats collector.
 		 */
-		pgstat_send_bgwriter();
+		pgstat_send_checkpointer();
 
 		/* Send WAL statistics to the stats collector. */
 		pgstat_send_wal(true);
@@ -577,9 +573,9 @@ HandleCheckpointerInterrupts(void)
 		 * updates the statistics, increment the checkpoint request and send
 		 * the statistics to the stats collector.
 		 */
-		BgWriterStats.m_requested_checkpoints++;
+		PendingCheckpointerStats.m_requested_checkpoints++;
 		ShutdownXLOG(0, 0);
-		pgstat_send_bgwriter();
+		pgstat_send_checkpointer();
 		pgstat_send_wal(true);
 
 		/* Normal exit from the checkpointer is here */
@@ -719,9 +715,9 @@ CheckpointWriteDelay(int flags, double progress)
 		CheckArchiveTimeout();
 
 		/*
-		 * Report interim activity statistics to the stats collector.
+		 * Report interim activity statistics.
 		 */
-		pgstat_send_bgwriter();
+		pgstat_send_checkpointer();
 
 		/*
 		 * This sleep used to be connected to bgwriter_delay, typically 200ms.
@@ -1265,8 +1261,10 @@ AbsorbSyncRequests(void)
 	LWLockAcquire(CheckpointerCommLock, LW_EXCLUSIVE);
 
 	/* Transfer stats counts into pending pgstats message */
-	BgWriterStats.m_buf_written_backend += CheckpointerShmem->num_backend_writes;
-	BgWriterStats.m_buf_fsync_backend += CheckpointerShmem->num_backend_fsync;
+	PendingCheckpointerStats.m_buf_written_backend
+		+= CheckpointerShmem->num_backend_writes;
+	PendingCheckpointerStats.m_buf_fsync_backend
+		+= CheckpointerShmem->num_backend_fsync;
 
 	CheckpointerShmem->num_backend_writes = 0;
 	CheckpointerShmem->num_backend_fsync = 0;

src/backend/postmaster/pgstat.c

@@ -128,7 +128,8 @@ char	   *pgstat_stat_tmpname = NULL;
  * Stored directly in a stats message structure so they can be sent
  * without needing to copy things around.  We assume these init to zeroes.
  */
-PgStat_MsgBgWriter BgWriterStats;
+PgStat_MsgBgWriter PendingBgWriterStats;
+PgStat_MsgCheckpointer PendingCheckpointerStats;
 PgStat_MsgWal WalStats;
 
 /*
@@ -348,6 +349,7 @@ static void pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len);
 static void pgstat_recv_anl_ancestors(PgStat_MsgAnlAncestors *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_checkpointer(PgStat_MsgCheckpointer *msg, int len);
 static void pgstat_recv_wal(PgStat_MsgWal *msg, int len);
 static void pgstat_recv_slru(PgStat_MsgSLRU *msg, int len);
 static void pgstat_recv_funcstat(PgStat_MsgFuncstat *msg, int len);
@@ -2830,6 +2832,37 @@ pgstat_fetch_stat_archiver(void)
 	return &archiverStats;
 }
 
+/*
+ * ---------
+ * pgstat_fetch_stat_bgwriter() -
+ *
+ *	Support function for the SQL-callable pgstat* functions. Returns
+ *	a pointer to the bgwriter statistics struct.
+ * ---------
+ */
+PgStat_BgWriterStats *
+pgstat_fetch_stat_bgwriter(void)
+{
+	backend_read_statsfile();
+
+	return &globalStats.bgwriter;
+}
+
+/*
+ * ---------
+ * pgstat_fetch_stat_checkpointer() -
+ *
+ *	Support function for the SQL-callable pgstat* functions. Returns
+ *	a pointer to the checkpointer statistics struct.
+ * ---------
+ */
+PgStat_CheckpointerStats *
+pgstat_fetch_stat_checkpointer(void)
+{
+	backend_read_statsfile();
+
+	return &globalStats.checkpointer;
+}
 
 /*
  * ---------
@@ -3025,19 +3058,51 @@ pgstat_send_bgwriter(void)
 	 * this case, avoid sending a completely empty message to the stats
 	 * collector.
 	 */
-	if (memcmp(&BgWriterStats, &all_zeroes, sizeof(PgStat_MsgBgWriter)) == 0)
+	if (memcmp(&PendingBgWriterStats, &all_zeroes, sizeof(PgStat_MsgBgWriter)) == 0)
+		return;
+
+	/*
+	 * Prepare and send the message
+	 */
+	pgstat_setheader(&PendingBgWriterStats.m_hdr, PGSTAT_MTYPE_BGWRITER);
+	pgstat_send(&PendingBgWriterStats, sizeof(PendingBgWriterStats));
+
+	/*
+	 * Clear out the statistics buffer, so it can be re-used.
+	 */
+	MemSet(&PendingBgWriterStats, 0, sizeof(PendingBgWriterStats));
+}
+
+/* ----------
+ * pgstat_send_checkpointer() -
+ *
+ *		Send checkpointer statistics to the collector
+ * ----------
+ */
+void
+pgstat_send_checkpointer(void)
+{
+	/* We assume this initializes to zeroes */
+	static const PgStat_MsgCheckpointer all_zeroes;
+
+	/*
+	 * This function can be called even if nothing at all has happened. In
+	 * this case, avoid sending a completely empty message to the stats
+	 * collector.
+	 */
+	if (memcmp(&PendingCheckpointerStats, &all_zeroes, sizeof(PgStat_MsgCheckpointer)) == 0)
 		return;
 
 	/*
 	 * Prepare and send the message
 	 */
-	pgstat_setheader(&BgWriterStats.m_hdr, PGSTAT_MTYPE_BGWRITER);
-	pgstat_send(&BgWriterStats, sizeof(BgWriterStats));
+	pgstat_setheader(&PendingCheckpointerStats.m_hdr, PGSTAT_MTYPE_CHECKPOINTER);
+	pgstat_send(&PendingCheckpointerStats, sizeof(PendingCheckpointerStats));
 
 	/*
 	 * Clear out the statistics buffer, so it can be re-used.
 	 */
-	MemSet(&BgWriterStats, 0, sizeof(BgWriterStats));
+	MemSet(&PendingCheckpointerStats, 0, sizeof(PendingCheckpointerStats));
 }
 
 /* ----------
@@ -3382,6 +3447,10 @@ PgstatCollectorMain(int argc, char *argv[])
 					pgstat_recv_bgwriter(&msg.msg_bgwriter, len);
 					break;
 
+				case PGSTAT_MTYPE_CHECKPOINTER:
+					pgstat_recv_checkpointer(&msg.msg_checkpointer, len);
+					break;
+
 				case PGSTAT_MTYPE_WAL:
 					pgstat_recv_wal(&msg.msg_wal, len);
 					break;
@@ -3934,6 +4003,7 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep)
 	bool		found;
 	const char *statfile = permanent ? PGSTAT_STAT_PERMANENT_FILENAME : pgstat_stat_filename;
 	int			i;
+	TimestampTz	ts;
 
 	/*
 	 * The tables will live in pgStatLocalContext.
@@ -3962,15 +4032,16 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep)
 	 * 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;
-	walStats.stat_reset_timestamp = globalStats.stat_reset_timestamp;
+	ts = GetCurrentTimestamp();
+	globalStats.bgwriter.stat_reset_timestamp = ts;
+	archiverStats.stat_reset_timestamp = ts;
+	walStats.stat_reset_timestamp = ts;
 
 	/*
 	 * Set the same reset timestamp for all SLRU items too.
 	 */
 	for (i = 0; i < SLRU_NUM_ELEMENTS; i++)
-		slruStats[i].stat_reset_timestamp = globalStats.stat_reset_timestamp;
+		slruStats[i].stat_reset_timestamp = ts;
 
 	/*
 	 * Try to open the stats file. If it doesn't exist, the backends simply
@@ -5055,9 +5126,9 @@ pgstat_recv_resetsharedcounter(PgStat_MsgResetsharedcounter *msg, int len)
 {
 	if (msg->m_resettarget == RESET_BGWRITER)
 	{
-		/* Reset the global background writer statistics for the cluster. */
+		/* Reset the global, bgwriter and checkpointer statistics for the cluster. */
 		memset(&globalStats, 0, sizeof(globalStats));
-		globalStats.stat_reset_timestamp = GetCurrentTimestamp();
+		globalStats.bgwriter.stat_reset_timestamp = GetCurrentTimestamp();
 	}
 	else if (msg->m_resettarget == RESET_ARCHIVER)
 	{
@@ -5345,16 +5416,27 @@ pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len)
 static void
 pgstat_recv_bgwriter(PgStat_MsgBgWriter *msg, int len)
 {
-	globalStats.timed_checkpoints += msg->m_timed_checkpoints;
-	globalStats.requested_checkpoints += msg->m_requested_checkpoints;
-	globalStats.checkpoint_write_time += msg->m_checkpoint_write_time;
-	globalStats.checkpoint_sync_time += msg->m_checkpoint_sync_time;
-	globalStats.buf_written_checkpoints += msg->m_buf_written_checkpoints;
-	globalStats.buf_written_clean += msg->m_buf_written_clean;
-	globalStats.maxwritten_clean += msg->m_maxwritten_clean;
-	globalStats.buf_written_backend += msg->m_buf_written_backend;
-	globalStats.buf_fsync_backend += msg->m_buf_fsync_backend;
-	globalStats.buf_alloc += msg->m_buf_alloc;
+	globalStats.bgwriter.buf_written_clean += msg->m_buf_written_clean;
+	globalStats.bgwriter.maxwritten_clean += msg->m_maxwritten_clean;
+	globalStats.bgwriter.buf_alloc += msg->m_buf_alloc;
+}
+
+/* ----------
+ * pgstat_recv_checkpointer() -
+ *
+ *	Process a CHECKPOINTER message.
+ * ----------
+ */
+static void
+pgstat_recv_checkpointer(PgStat_MsgCheckpointer *msg, int len)
+{
+	globalStats.checkpointer.timed_checkpoints += msg->m_timed_checkpoints;
+	globalStats.checkpointer.requested_checkpoints += msg->m_requested_checkpoints;
+	globalStats.checkpointer.checkpoint_write_time += msg->m_checkpoint_write_time;
+	globalStats.checkpointer.checkpoint_sync_time += msg->m_checkpoint_sync_time;
+	globalStats.checkpointer.buf_written_checkpoints += msg->m_buf_written_checkpoints;
+	globalStats.checkpointer.buf_written_backend += msg->m_buf_written_backend;
+	globalStats.checkpointer.buf_fsync_backend += msg->m_buf_fsync_backend;
 }
 
 /* ----------

src/backend/storage/buffer/bufmgr.c

@@ -2137,7 +2137,7 @@ BufferSync(int flags)
 			if (SyncOneBuffer(buf_id, false, &wb_context) & BUF_WRITTEN)
 			{
 				TRACE_POSTGRESQL_BUFFER_SYNC_WRITTEN(buf_id);
-				BgWriterStats.m_buf_written_checkpoints++;
+				PendingCheckpointerStats.m_buf_written_checkpoints++;
 				num_written++;
 			}
 		}
@@ -2247,7 +2247,7 @@ BgBufferSync(WritebackContext *wb_context)
 	strategy_buf_id = StrategySyncStart(&strategy_passes, &recent_alloc);
 
 	/* Report buffer alloc counts to pgstat */
-	BgWriterStats.m_buf_alloc += recent_alloc;
+	PendingBgWriterStats.m_buf_alloc += recent_alloc;
 
 	/*
 	 * If we're not running the LRU scan, just stop after doing the stats
@@ -2437,15 +2437,15 @@ BgBufferSync(WritebackContext *wb_context)
 			reusable_buffers++;
 			if (++num_written >= bgwriter_lru_maxpages)
 			{
-				BgWriterStats.m_maxwritten_clean++;
+				PendingBgWriterStats.m_maxwritten_clean++;
 				break;
 			}
 		}
 		else if (sync_state & BUF_REUSABLE)
 			reusable_buffers++;
 	}
 
-	BgWriterStats.m_buf_written_clean += num_written;
+	PendingBgWriterStats.m_buf_written_clean += num_written;
 
 #ifdef BGW_DEBUG
 	elog(DEBUG1, "bgwriter: recent_alloc=%u smoothed=%.2f delta=%ld ahead=%d density=%.2f reusable_est=%d upcoming_est=%d scanned=%d wrote=%d reusable=%d",