From c46d66f42d92f5d7c84f18ce62c892b3686f6745 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <daniel@yesql.se>
Date: Mon, 23 Aug 2021 13:25:26 +0200
Subject: [PATCH] Quick exit on log stream child exit in pg_basebackup

If the log streaming child process (thread on Windows) dies during
backup then the whole backup will be aborted at the end of the
backup.  Instead, trap ungraceful termination of the log streaming
child and exit early.
---
 src/bin/pg_basebackup/pg_basebackup.c | 40 ++++++++++++++++++++++++++-
 1 file changed, 39 insertions(+), 1 deletion(-)

diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c
index 7296eb97d0..e0dd9f868b 100644
--- a/src/bin/pg_basebackup/pg_basebackup.c
+++ b/src/bin/pg_basebackup/pg_basebackup.c
@@ -174,6 +174,8 @@ static int	bgpipe[2] = {-1, -1};
 /* Handle to child process */
 static pid_t bgchild = -1;
 static bool in_log_streamer = false;
+/* State of child process */
+static sig_atomic_t bgchild_exited = false;
 
 /* End position for xlog streaming, empty string if unknown yet */
 static XLogRecPtr xlogendptr;
@@ -267,6 +269,16 @@ disconnect_atexit(void)
 		PQfinish(conn);
 }
 
+/*
+ * If the bgchild exits prematurely we can abort processing rather than wait
+ * till the backup has finished and error out at that time.
+ */
+static void
+sigchld_handler(SIGNAL_ARGS)
+{
+	bgchild_exited = true;
+}
+
 #ifndef WIN32
 /*
  * On windows, our background thread dies along with the process. But on
@@ -562,17 +574,28 @@ LogStreamerMain(logstreamer_param *param)
 											  stream.do_sync);
 
 	if (!ReceiveXlogStream(param->bgconn, &stream))
-
+	{
 		/*
 		 * Any errors will already have been reported in the function process,
 		 * but we need to tell the parent that we didn't shutdown in a nice
 		 * way.
 		 */
+#ifdef WIN32
+		/*
+		 * In order to signal the main thread of an ungraceful exit we
+		 * set the flag used on Unix to signal SIGCHLD.
+		 */
+		bgchild_exited = true;
+#endif
 		return 1;
+	}
 
 	if (!stream.walmethod->finish())
 	{
 		pg_log_error("could not finish writing WAL files: %m");
+#ifdef WIN32
+		bgchild_exited = true;
+#endif
 		return 1;
 	}
 
@@ -985,6 +1008,12 @@ ReceiveCopyData(PGconn *conn, WriteDataCallback callback,
 			exit(1);
 		}
 
+		if (bgchild_exited)
+		{
+			pg_log_error("log streamer child terminated unexpectedly");
+			exit(1);
+		}
+
 		(*callback) (r, copybuf, callback_data);
 
 		PQfreemem(copybuf);
@@ -2600,6 +2629,15 @@ main(int argc, char **argv)
 	}
 	atexit(disconnect_atexit);
 
+#ifndef WIN32
+	/*
+	 * Trap SIGCHLD to be able to handle the WAL stream process exiting. There
+	 * is no SIGCHLD on Windows, there we rely on the background thread setting
+	 * the signal variable on ungraceful exit.
+	 */
+	pqsignal(SIGCHLD, sigchld_handler);
+#endif
+
 	/*
 	 * Set umask so that directories/files are created with the same
 	 * permissions as directories/files in the source data directory.
-- 
2.24.3 (Apple Git-128)