Blob Blame History Raw
From 8b9c49fd965f73709d5a6e2c21987ba26af4856b Mon Sep 17 00:00:00 2001
From: Luca Miccini <lmiccini@redhat.com>
Date: Wed, 25 Sep 2019 17:12:39 +0200
Subject: [PATCH] Add a configurable delay to Nova Evacuate calls

In case /var/lib/nova/instances resides on NFS we have seen migrations
failing with 'Failed to get "write" lock - Is another process using the
image' errors.

This has been tracked down to grace/lease timeouts not having expired
before attempting the migration/evacuate, so in this cases it might be
desirable to delay the nova evacuate call to give the storage time to
release the locks.

Change-Id: Ie2fe784202d754eda38092479b1ab3ff4d02136a
Resolves: rhbz#1740069
---

diff --git a/heartbeat/NovaEvacuate b/heartbeat/NovaEvacuate
index 810f30a..596f520 100644
--- a/heartbeat/NovaEvacuate
+++ b/heartbeat/NovaEvacuate
@@ -125,6 +125,15 @@
 <content type="boolean" default="0" />
 </parameter>
 
+<parameter name="evacuate_delay" unique="0" required="0">
+<longdesc lang="en">
+Allows delaying the nova evacuate API call, e.g. to give a storage array time to clean
+up eventual locks/leases.
+</longdesc>
+<shortdesc lang="en">Nova evacuate delay</shortdesc>
+<content type="integer" default="0" />
+</parameter>
+
 </parameters>
 
 <actions>
@@ -216,6 +225,11 @@
 		fence_agent="fence_evacuate"
 	    fi
 
+            if [ ${OCF_RESKEY_evacuate_delay} != 0 ]; then
+                ocf_log info "Delaying nova evacuate by $OCF_RESKEY_evacuate_delay seconds"
+                sleep ${OCF_RESKEY_evacuate_delay}
+            fi
+
 	    ocf_log notice "Initiating evacuation of $node with $fence_agent"
 	    $fence_agent ${fence_options} -o status -n ${node}
 	    if [ $? = 1 ]; then