From e5040385f57e122c45bd911d4676a66230ff5db5 Mon Sep 17 00:00:00 2001
From: Joachim Wiberg <troglobit@gmail.com>
Date: Sat, 22 Aug 2026 07:47:20 +0200
Subject: [PATCH] test: fix flaky crashing.sh

Two races, both around the post:script Finit runs when it gives up on a
service.

Finit marks the service crashed before it forks post:script, so the file
the test greps for lands a moment later.  Waiting for the state is not
enough.

slay then takes the PID from initctl status, and service_post_script()
sets svc->pid to the script's PID, so once Finit has given up the PID
reported for the service is the post:script.  Killing that takes out the
script instead of the service and the file never arrives at all.  The
guard for this was already there, with a comment describing it, but
inside the loop that waits for a PID to appear, so it only covered the
case where there was none.  A PID that was already there went straight
to kill -9.  Hence the gcc leg killing once more at lap 13, after Finit
had stopped restarting, where clang stopped at 12.

Signed-off-by: Joachim Wiberg <troglobit@gmail.com>
---
 test/crashing.sh   |  5 ++---
 test/skel/bin/slay | 10 ++++++++++
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/test/crashing.sh b/test/crashing.sh
index 1322e502..0084feb1 100755
--- a/test/crashing.sh
+++ b/test/crashing.sh
@@ -8,7 +8,7 @@ TEST_DIR=$(dirname "$0")
 test_teardown()
 {
     say "Running test teardown."
-    run "rm -f $FINIT_CONF" "/tmp/post"
+    run "rm -f $FINIT_CONF /tmp/post"
 }
 
 crashit()
@@ -48,8 +48,7 @@ test_one()
     fi
 
     retry "assert_status $nm crashed" 500
-    run "cat /tmp/post"
-    assert_file_contains "/tmp/post" "POST"
+    retry "assert_file_contains /tmp/post POST" 100
     run "rm -f /tmp/post"
 }
 
diff --git a/test/skel/bin/slay b/test/skel/bin/slay
index 0bd7d025..91e2825a 100755
--- a/test/skel/bin/slay
+++ b/test/skel/bin/slay
@@ -58,5 +58,15 @@ done
 
 echo "$pid" > /tmp/oldpid
 
+# The check above only runs while waiting for a PID to appear.  Finit
+# reports the post:script's PID as the service's once it has given up
+# restarting, so a PID that was already there needs the same guard:
+# killing it would take out the script instead of the service, and the
+# side effects the test is waiting for never happen.
+st=$(initctl -p status "$nm" 2>/dev/null | awk '/Status/{print $3}')
+if [ "$st" = "crashed" ]; then
+    exit 1
+fi
+
 #echo "PID $pid, kill -9 ..."
 kill -9 "$pid" 2>/dev/null || true