# Script to check if OSPF is functioning.  It relies on the fact that each
# adjacent neighbor will be reachable via it's router-id, and that if we're
# unable to exchange routes for whatever reason, the router-id will be
# unreachable.  By default a router that comes up will not permit itself to be
# rebooted until OSPF has come up at least once.  The cases we've seen where it
# fails the failing side states neighbor state Full, but the working side says
# Exchange.  So this check should prevent rebooting core routers, but alas, I'm
# not 100% confident of that.
#
# The logic here reboots if we're in a bad state with at leats one peer.
# Possibly this should be negated to only reboot if no peers are in a good
# state and at least one is in a bad state (more complex though).
# Reboot possibility will get enabled once at least one peer has managed to
# come up successfully.
#
# In case of multiple OSPF instances, if any one of them is functioning we move
# towards the mayreboot state, but we will only restart non-functioning
# instances.
:if ([/file find name=ospfstatus.txt] = "") do={
	:put "ospf status file doesn't exist - creating."
	/file print file=ospfstatus
	/file set [/file find name="ospfstatus.txt"] contents="no"
	:put "Done, please re-run the script."
	# Continuing with the rest of the script is pointless as our view of /file is
	# a snapshot in spite of /file set ... which above sets it to some arbitrary
	# content (looks like a file list).
} else={
	:local mayreboot [/file get ospfstatus.txt contents]

	# After initial set the file content is completely bogus ...
	:if ($mayreboot != "yes" && $mayreboot != "no") do={
		:set mayreboot "no"
	}

	:put "Checking OSPF (mayreboot=$mayreboot) ..."

	:foreach n in=[/routing ospf neighbor find where state="Full"] do={
		:local loopback [/routing ospf neighbor get $n router-id]

		:put "Remote OSPF $loopback @ $remoteaddress"
		/ip route check $loopback once do={
			:if ($status != "failed") do={
				:put "OSPF is functioning correctly."
				:if ($mayreboot != "yes") do={
					:log info "OSPF restored - restoring"
					/file set ospfstatus.txt contents="yes"
					/tool fetch keep-result=no url="https://slack.com/api/chat.postMessage?token=xoxb-212578866007-F6mp189CQi8vHl1gPmeaxLLo&channel=wisp&text=OSPF%20on%20$[/system identity get name]%20restored&as_user=false&username=ospf-check"
				}
			} else={
				:put "OSPF is not functioning correctly."
				:if ($mayreboot = "yes") do={
					:local instancename [/routing ospf neighbor get $n instance]

					/file set ospfstatus.txt contents="no"
					:put "Restarting OSPF"
					:log error "OSPF malfunctioned - restarting."
					/routing ospf instance set [/routing ospf instance find name=$instancename] disabled=yes
					:delay 10
					/routing ospf instance set [/routing ospf instance find name=$instancename] disabled=no
				}
			}
		}
	}
}