mirror of
https://github.com/troglobit/finit.git
synced 2026-10-04 14:54:14 +07:00
Joachim Wiberg
e5040385f5
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>
73 lines
1.7 KiB
Bash
Executable File
73 lines
1.7 KiB
Bash
Executable File
#!/bin/sh
|
|
|
|
nm=$1
|
|
|
|
getpid()
|
|
{
|
|
initctl status "$1" |awk '/PID :/{ print $3; }'
|
|
}
|
|
|
|
pid=$(getpid "$nm")
|
|
if [ -f oldpid ]; then
|
|
oldpid=$(cat oldpid)
|
|
if [ "$oldpid" = "$pid" ]; then
|
|
echo "Looks bad, wait for it ..."
|
|
sleep 3
|
|
pid=$(getpid "$nm")
|
|
if [ "$oldpid" = "$pid" ]; then
|
|
echo "Finit did not deregister old PID $oldpid vs $pid"
|
|
initctl status "$nm"
|
|
ps
|
|
echo "Reloading finit ..."
|
|
initctl reload
|
|
sleep 1
|
|
initctl status "$nm"
|
|
exit 1
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
timeout=50
|
|
while [ "$pid" -le 1 ]; do
|
|
sleep 0.1
|
|
# Once Finit gives up on a service it forks the post:script and
|
|
# reports that PID as the service's, so a slay still waiting for
|
|
# the service to come back would kill the script instead.
|
|
st=$(initctl -p status "$nm" 2>/dev/null | awk '/Status/{print $3}')
|
|
if [ "$st" = "crashed" ]; then
|
|
exit 1
|
|
fi
|
|
pid=$(getpid "$nm")
|
|
if [ "$pid" -le 1 ]; then
|
|
timeout=$((timeout - 1))
|
|
if [ "$timeout" -gt 0 ]; then
|
|
continue
|
|
fi
|
|
|
|
if [ $pid -ne 0 ]; then
|
|
echo "Got a bad PID: $pid, aborting ..."
|
|
ps
|
|
sleep 1
|
|
initctl status "$nm"
|
|
ps
|
|
fi
|
|
exit 1
|
|
fi
|
|
break
|
|
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
|