From d11eae09e48694ad6b4139bbb7d7b112833301f5 Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Sun, 12 Aug 2018 18:05:49 -0400
Subject: [PATCH] Fix bogus loop logic in 013_crash_restart test's pump_until
 subroutine.

The pump_nb() step might've already received the desired data, so we must
check for that at the top of the loop not the bottom.  Otherwise, the
call to pump() will sit with nothing to do until the timeout elapses.
pump_until then falls out with apparent success ... but the timeout has
been used up, causing the next call of pump_until to report a timeout
failure.  I believe this explains the intermittent timeout failures
we've seen in the buildfarm ever since this test went in.  I was able
to reproduce the problem on gaur semi-repeatably, and this appears to
fix it.

In passing, remove a duplicate assignment, fix one stdin-assignment to
look like the rest, and document the test's dependency on test_decoding.
---
 src/test/recovery/README                 | 2 ++
 src/test/recovery/t/013_crash_restart.pl | 5 ++---
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/src/test/recovery/README b/src/test/recovery/README
index a1e1aa1be1..632e720ebe 100644
--- a/src/test/recovery/README
+++ b/src/test/recovery/README
@@ -9,6 +9,8 @@ Running the tests
 =================
 
 NOTE: You must have given the --enable-tap-tests argument to configure.
+Also, to use "make installcheck", you must have built and installed
+contrib/test_decoding in addition to the core code.
 
 Run
     make check
diff --git a/src/test/recovery/t/013_crash_restart.pl b/src/test/recovery/t/013_crash_restart.pl
index 440ac097fc..c928e9201e 100644
--- a/src/test/recovery/t/013_crash_restart.pl
+++ b/src/test/recovery/t/013_crash_restart.pl
@@ -157,7 +157,6 @@ ok(pump_until($killme, \$killme_stdout, qr/[[:digit:]]+[\r\n]$/m),
 	"acquired pid for SIGKILL");
 $pid = $killme_stdout;
 chomp($pid);
-$pid           = $killme_stdout;
 $killme_stdout = '';
 $killme_stderr = '';
 
@@ -176,7 +175,7 @@ $killme_stderr = '';
 # signal that crash-restart has occurred.  The initial wait for the
 # trivial select is to be sure that psql successfully connected to
 # backend.
-$monitor_stdin = q[
+$monitor_stdin .= q[
 SELECT $$psql-connected$$;
 SELECT pg_sleep(3600);
 ];
@@ -252,6 +251,7 @@ sub pump_until
 	$proc->pump_nb();
 	while (1)
 	{
+		last if $$stream =~ /$untl/;
 		if ($psql_timeout->is_expired)
 		{
 			diag("aborting wait: program timed out");
@@ -269,7 +269,6 @@ sub pump_until
 			return 0;
 		}
 		$proc->pump();
-		last if $$stream =~ /$untl/;
 	}
 	return 1;