Make walsender more responsive.

Per testing by Andres Freund, this improves replication performance
and reduces replication latency and latency jitter.  I was a bit
concerned about moving more work into XLogInsert, but testing seems
to show that it's not a problem in practice.

Along the way, improve comments for WaitLatchOrSocket.

Andres Freund.  Review and stylistic cleanup by me.

3 files changed, 18 insertions, 35 deletions

diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c
index e8fb78b3311..7f198c2e3e0 100644
--- a/src/backend/access/transam/twophase.c
+++ b/src/backend/access/transam/twophase.c
@@ -1042,13 +1042,6 @@ EndPrepare(GlobalTransaction gxact)
 
 	/* If we crash now, we have prepared: WAL replay will fix things */
 
-	/*
-	 * Wake up all walsenders to send WAL up to the PREPARE record immediately
-	 * if replication is enabled
-	 */
-	if (max_wal_senders > 0)
-		WalSndWakeup();
-
 	/* write correct CRC and close file */
 	if ((write(fd, &statefile_crc, sizeof(pg_crc32))) != sizeof(pg_crc32))
 	{
@@ -2045,13 +2038,6 @@ RecordTransactionCommitPrepared(TransactionId xid,
 	/* Flush XLOG to disk */
 	XLogFlush(recptr);
 
-	/*
-	 * Wake up all walsenders to send WAL up to the COMMIT PREPARED record
-	 * immediately if replication is enabled
-	 */
-	if (max_wal_senders > 0)
-		WalSndWakeup();
-
 	/* Mark the transaction committed in pg_clog */
 	TransactionIdCommitTree(xid, nchildren, children);
 
@@ -2133,13 +2119,6 @@ RecordTransactionAbortPrepared(TransactionId xid,
 	XLogFlush(recptr);
 
 	/*
-	 * Wake up all walsenders to send WAL up to the ABORT PREPARED record
-	 * immediately if replication is enabled
-	 */
-	if (max_wal_senders > 0)
-		WalSndWakeup();
-
-	/*
 	 * Mark the transaction aborted in clog.  This is not absolutely necessary
 	 * but we may as well do it while we are here.
 	 */
diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 4755ee6ee40..86b1afa80d9 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -1142,13 +1142,6 @@ RecordTransactionCommit(void)
 		XLogFlush(XactLastRecEnd);
 
 		/*
-		 * Wake up all walsenders to send WAL up to the COMMIT record
-		 * immediately if replication is enabled
-		 */
-		if (max_wal_senders > 0)
-			WalSndWakeup();
-
-		/*
 		 * Now we may update the CLOG, if we wrote a COMMIT record above
 		 */
 		if (markXidCommitted)
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index cbfa68a4e7b..a43e2eeaf30 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1025,6 +1025,8 @@ begin:;
 
 		END_CRIT_SECTION();
 
+		/* wakeup the WalSnd now that we released the WALWriteLock */
+		WalSndWakeupProcessRequests();
 		return RecPtr;
 	}
 
@@ -1208,6 +1210,9 @@ begin:;
 
 	END_CRIT_SECTION();
 
+	/* wakeup the WalSnd now that we outside contented locks */
+	WalSndWakeupProcessRequests();
+
 	return RecPtr;
 }
 
@@ -1792,6 +1797,10 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible, bool xlog_switch)
 			if (finishing_seg || (xlog_switch && last_iteration))
 			{
 				issue_xlog_fsync(openLogFile, openLogSegNo);
+
+				/* signal that we need to wakeup WalSnd later */
+				WalSndWakeupRequest();
+
 				LogwrtResult.Flush = LogwrtResult.Write;		/* end of page */
 
 				if (XLogArchivingActive())
@@ -1854,7 +1863,11 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible, bool xlog_switch)
 				openLogFile = XLogFileOpen(openLogSegNo);
 				openLogOff = 0;
 			}
+
 			issue_xlog_fsync(openLogFile, openLogSegNo);
+
+			/* signal that we need to wakeup WalSnd later */
+			WalSndWakeupRequest();
 		}
 		LogwrtResult.Flush = LogwrtResult.Write;
 	}
@@ -2120,6 +2133,9 @@ XLogFlush(XLogRecPtr record)
 
 	END_CRIT_SECTION();
 
+	/* wakeup the WalSnd now that we released the WALWriteLock */
+	WalSndWakeupProcessRequests();
+
 	/*
 	 * If we still haven't flushed to the request point then we have a
 	 * problem; most likely, the requested flush point is past end of XLOG.
@@ -2245,13 +2261,8 @@ XLogBackgroundFlush(void)
 
 	END_CRIT_SECTION();
 
-	/*
-	 * If we wrote something then we have something to send to standbys also,
-	 * otherwise the replication delay become around 7s with just async
-	 * commit.
-	 */
-	if (wrote_something)
-		WalSndWakeup();
+	/* wakeup the WalSnd now that we released the WALWriteLock */
+	WalSndWakeupProcessRequests();
 
 	return wrote_something;
 }