common-ha: reliable grace using pacemaker notify actions

Using *-dead_ip-1 resources to track on which nodes the ganesha.nfsd
had died was found to be unreliable.

Running `pcs status` in the ganesha_grace monitor action was seen to
time out during failover; the HA devs opined that it was, generally,
not a good idea to run `pcs status` in a monitor action in any event.
They suggested using the notify feature, where the resources on all
the nodes are notified when a clone resource agent dies.

This change adds a notify action to the ganesha_grace RA. The ganesha_mon
RA monitors its ganesha.nfsd daemon. While the daemon is running, it
creates two attributes: ganesha-active and grace-active. When the daemon
stops for any reason, the attributes are deleted. Deleting the
ganesha-active attribute triggers the failover of the virtual IP (the
IPaddr RA) to another node where ganesha.nfsd is still running. The
ganesha_grace RA monitors the grace-active attribute. When the
grace-active attibute is deleted, the ganesha_grace RA stops, and will
not restart. This triggers pacemaker to trigger the notify action in
the ganesha_grace RAs on the other nodes in the cluster; which send a
DBUS message to their ganesha.nfsd.

(N.B. grace-active is a bit of a misnomer. while the grace-active
attribute exists, everything is normal and healthy. Deleting the
attribute triggers putting the surviving ganesha.nfsds into GRACE.)

To ensure that the remaining/surviving ganesha.nfsds are put into
NFS-GRACE before the IPaddr (virtual IP) fails over there is a short
delay (sleep) between deleting the grace-active attribute and the
ganesha-active attribute. To summarize:
  1. on node 2 ganesha_mon:monitor notices that ganesha.nfsd has died
  2. on node 2 ganesha_mon:monitor deletes its grace-active attribute
  3. on node 2 ganesha_grace:monitor notices that grace-active is gone
     and returns OCF_ERR_GENERIC, a.k.a. new error. When pacemaker
     tries to (re)start ganesha_grace, its start action will return
     OCF_NOT_RUNNING, a.k.a. known error, don't attempt further
     restarts.
  4. on nodes 1, 3, etc., ganesha_grace:notify receives a post-stop
     notification indicating that node 2 is gone, and sends a DBUS
     message to its ganesha.nfsd putting it into NFS-GRACE.
  5. on node 2 ganesha_mon:monitor waits a short period, then deletes
     its ganesha-active attribute. This triggers the IPaddr (virt IP)
     failover according to constraint location rules.

ganesha_nfsd modified to run for the duration, start action is invoked
to setup the /var/lib/nfs symlink, stop action is invoked to restore it.
ganesha-ha.sh modified accordingly to create it as a clone resource.

BUG: 1290865
Change-Id: I1ba24f38fa4338b3aeb17c65645e9f439387ff57
Signed-off-by: Kaleb S KEITHLEY <kkeithle@redhat.com>
Reviewed-on: http://review.gluster.org/12964
Smoke: Gluster Build System <jenkins@build.gluster.com>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.com>
Reviewed-on: http://review.gluster.org/13725

1 files changed, 47 insertions, 42 deletions

diff --git a/extras/ganesha/ocf/ganesha_nfsd b/extras/ganesha/ocf/ganesha_nfsd
index e064183daef..a9d3e4d860f 100644
--- a/extras/ganesha/ocf/ganesha_nfsd
+++ b/extras/ganesha/ocf/ganesha_nfsd
@@ -29,13 +29,16 @@
 : ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat}
 . ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs
 
-if [ -n "$OCF_DEBUG_LIBRARY" ]; then
-    . $OCF_DEBUG_LIBRARY
+if [ -n "${OCF_DEBUG_LIBRARY}" ]; then
+    . ${OCF_DEBUG_LIBRARY}
 else
     : ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat}
 . ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs
 fi
 
+OCF_RESKEY_ha_vol_mnt_default="/var/run/gluster/shared_storage"
+: ${OCF_RESKEY_ha_vol_mnt=${OCF_RESKEY_ha_vol_mnt_default}}
+
 ganesha_meta_data() {
         cat <<END
 <?xml version="1.0"?>
@@ -59,16 +62,16 @@ resource agent for nfs-ganesha.
 </parameters>
 
 <actions>
-<action name="start"   timeout="40s" />
-<action name="stop"    timeout="40s" />
-<action name="status" depth="0"  timeout="20s" interval="1m" />
-<action name="monitor" depth="0"  timeout="10s" interval="1m" />
+<action name="start"   timeout="5s" />
+<action name="stop"    timeout="5s" />
+<action name="status" depth="0"  timeout="5s" interval="0" />
+<action name="monitor" depth="0"  timeout="5s" interval="0" />
 <action name="meta-data"  timeout="20s" />
 </actions>
 </resource-agent>
 END
 
-return $OCF_SUCCESS
+return ${OCF_SUCCESS}
 }
 
 ganesha_nfsd_usage() {
@@ -78,10 +81,10 @@ ganesha_nfsd_usage() {
 # Make sure meta-data and usage always succeed
 case $__OCF_ACTION in
 	meta-data)	ganesha_meta_data
-			exit $OCF_SUCCESS
+			exit ${OCF_SUCCESS}
 			;;
 	usage|help)	ganesha_usage
-			exit $OCF_SUCCESS
+			exit ${OCF_SUCCESS}
 			;;
 	*)
 			;;
@@ -89,58 +92,60 @@ esac
 
 ganesha_nfsd_start()
 {
-	return $OCF_SUCCESS
+	local long_host=$(hostname)
+
+	if [[ -d /var/lib/nfs ]]; then
+		mv /var/lib/nfs /var/lib/nfs.backup
+		if [ $? -ne 0 ]; then
+			ocf_log notice "mv /var/lib/nfs /var/lib/nfs.backup failed"
+		fi
+		ln -s ${OCF_RESKEY_ha_vol_mnt}/nfs-ganesha/${long_host}/nfs /var/lib/nfs
+		if [ $? -ne 0 ]; then
+			ocf_log notice "ln -s ${OCF_RESKEY_ha_vol_mnt}/nfs-ganesha/${long_host}/nfs /var/lib/nfs failed"
+		fi
+	fi
+
+	return ${OCF_SUCCESS}
 }
 
 ganesha_nfsd_stop()
 {
-	local short_host=$(hostname -s)
-	local long_host=""
-
-	if [ "X${OCF_RESOURCE_INSTANCE:0:9}X" = "Xnfs_startX" ]; then
-
-		# if this is any nfs_start, go ahead. worst case we
-		# find the link already exists and do nothing
-		long_host=$(hostname)
-
-		if [ -d /var/lib/nfs ]; then
-			mv /var/lib/nfs /var/lib/nfs.backup
-			ln -s $OCF_RESKEY_ha_vol_mnt/nfs-ganesha/${long_host}/nfs /var/lib/nfs
-			if [ $? -ne 0 ]; then
-				logger "warning: ln -s $OCF_RESKEY_ha_vol_mnt/nfs-ganesha/${long_host}/nfs /var/lib/nfs failed"
-			fi
 
+	if [ -L /var/lib/nfs -a -d /var/lib/nfs.backup ]; then
+		rm -f /var/lib/nfs
+		if [ $? -ne 0 ]; then
+			ocf_log notice "rm -f /var/lib/nfs failed"
 		fi
-	else
-
-		# if this is a clone resource or is specific to this node
-		# remove the symlink and restore /var/lib/nfs
-
-		if [ "X${OCF_RESOURCE_INSTANCE}X" = "Xnfs_stopX" ] ||
-		   [ "X${OCF_RESOURCE_INSTANCE}X" = "Xnfs_stop-${short_host}X" ]; then
-			if [ -L /var/lib/nfs -a -d /var/lib/nfs.backup ]; then
-				rm -f /var/lib/nfs
-				mv /var/lib/nfs.backup /var/lib/nfs
-			fi
+		mv /var/lib/nfs.backup /var/lib/nfs
+		if [ $? -ne 0 ]; then
+			ocf_log notice "mv /var/lib/nfs.backup /var/lib/nfs failed"
 		fi
 	fi
 
-	return $OCF_SUCCESS
+	return ${OCF_SUCCESS}
 }
 
 ganesha_nfsd_monitor()
 {
-	return $OCF_SUCCESS
+	# pacemaker checks to see if RA is already running before starting it.
+	# if we return success, then it's presumed it's already running and
+	# doesn't need to be started, i.e. invoke the start action.
+	# return something other than success to make pacemaker invoke the
+	# start action
+	if [[ -L /var/lib/nfs ]]; then
+		return ${OCF_SUCCESS}
+	fi
+	return ${OCF_NOT_RUNNING}
 }
 
 ganesha_nfsd_validate()
 {
-	return $OCF_SUCCESS
+	return ${OCF_SUCCESS}
 }
 
 ganesha_nfsd_validate
 
-# logger "ganesha_nfsd ${OCF_RESOURCE_INSTANCE} $__OCF_ACTION"
+# ocf_log notice "ganesha_nfsd ${OCF_RESOURCE_INSTANCE} $__OCF_ACTION"
 
 # Translate each action into the appropriate function call
 case $__OCF_ACTION in
@@ -151,13 +156,13 @@ stop)           ganesha_nfsd_stop
 status|monitor) ganesha_nfsd_monitor
 		;;
 *)              ganesha_nfsd_usage
-                exit $OCF_ERR_UNIMPLEMENTED
+                exit ${OCF_ERR_UNIMPLEMENTED}
                 ;;
 esac
 
 rc=$?
 
 # The resource agent may optionally log a debug message
-ocf_log debug "${OCF_RESOURCE_INSTANCE} $__OCF_ACTION returned $rc"
+ocf_log debug "${OCF_RESOURCE_INSTANCE} ${__OCF_ACTION} returned $rc"
 exit $rc