From 6e24d335172b43286a284167c2d54d8f240fc9a0 Mon Sep 17 00:00:00 2001
From: Aaditya Bagga <aaditya_gnulinux@zoho.com>
Date: Tue, 6 Nov 2018 20:26:33 +0530
Subject: [runit integration] give a bit of time to start the service

Currently, we run sv start immediately after linking the service.
The runsv process may not be up at the moment, as a result of which
openrc will mark the service as stopped, even though it may be brought up
by runit at the next scan.

This is documented in the gentoo wiki:
https://wiki.gentoo.org/wiki/Runit#OpenRC.27s_runit_integration_feature

This PR adds a timeout so that correct process state can be reported.

Before:
 * Starting netdata-runit ...
fail: /run/openrc/sv/netdata: runsv not running
 * Failed to start netdata-runit

After:
 * Starting netdata-runit ...
fail: /run/openrc/sv/netdata: runsv not running
ok: run: /run/openrc/sv/netdata: (pid 9042) 0s

This fixes #253.
---
 sh/runit.sh | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

(limited to 'sh')

diff --git a/sh/runit.sh b/sh/runit.sh
index 3cef0f3a..5d82c9f6 100644
--- a/sh/runit.sh
+++ b/sh/runit.sh
@@ -20,8 +20,20 @@ runit_start()
 	service_link="${RC_SVCDIR}/sv/${service_path##*/}"
 	ebegin "Starting ${name:-$RC_SVCNAME}"
 	ln -snf "${service_path}" "${service_link}"
-	sv start "${service_link}" > /dev/null 2>&1
-	eend $? "Failed to start ${name:-$RC_SVCNAME}"
+	local i=0 retval=1
+	# it can take upto 5 seconds for runsv to start
+	while [ $i -lt 6 ] ; do
+		if sv start "${service_link}" > /dev/null 2>&1; then
+			retval=0
+			break
+		fi
+		sleep 1 && i=$(expr $i + 1)
+	done
+	if [ $retval -eq 1 ]; then
+		# clean up the link else sv will keep on trying
+		rm "${service_link}"
+	fi
+	eend $retval "Failed to start ${name:-$RC_SVCNAME}"
 }
 
 runit_stop()
-- 
cgit v1.2.3