From e5d3d2269bb9b38bc5959895b4d302fb8f6f51a7 Mon Sep 17 00:00:00 2001
From: Luca Miccini <lmiccini@redhat.com>
Date: Wed, 25 Sep 2019 17:28:39 +0200
Subject: [PATCH] Add a configurable delay to Nova Evacuate calls

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.

Related resource-agents change: https://review.opendev.org/#/c/684777/

NB: cherry-pick not 100% clean due to missing I00d4f97cd24f7c36eeb0a29f9c91422cf7ded3ee
    (Add region support for instance HA). As there are no current plans
    to backport that, we chose to adapt this review instead

Change-Id: I5ec6a5b0c66579e068e811f49aae10a5f406158a
Resolves: rhbz#1740069
(cherry picked from commit 72487d804ef4c64d16889b1b474252f6963a18c2)
---
 manifests/profile/base/pacemaker/instance_ha.pp | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/manifests/profile/base/pacemaker/instance_ha.pp b/manifests/profile/base/pacemaker/instance_ha.pp
index 62546068a..ce8a2fa04 100644
--- a/manifests/profile/base/pacemaker/instance_ha.pp
+++ b/manifests/profile/base/pacemaker/instance_ha.pp
@@ -56,6 +56,10 @@
 #   Variable that defines the no_shared_storage for the nova evacuate resource
 #   Defaults to hiera('tripleo::instanceha::no_shared_storage', true)
 #
+# [*evacuate_delay*]
+#   (Optional) Integer, seconds to wait before starting the nova evacuate
+#   Defaults to hiera('tripleo::instanceha::evacuate_delay', 0)
+#
 class tripleo::profile::base::pacemaker::instance_ha (
   $step                  = Integer(hiera('step')),
   $pcs_tries             = hiera('pcs_tries', 20),
@@ -66,6 +70,7 @@ class tripleo::profile::base::pacemaker::instance_ha (
   $user_domain           = hiera('nova::keystone::authtoken::user_domain_name', 'Default'),
   $project_domain        = hiera('nova::keystone::authtoken::project_domain_name', 'Default'),
   $no_shared_storage     = hiera('tripleo::instanceha::no_shared_storage', true),
+  $evacuate_delay        = hiera('tripleo::instanceha::evacuate_delay', 0),
 ) {
   if $step >= 2 {
     class { '::pacemaker::resource_defaults':
@@ -111,10 +116,15 @@ class tripleo::profile::base::pacemaker::instance_ha (
     } else {
       $iha_no_shared_storage = 'no_shared_storage=false'
     }
+    if $evacuate_delay > 0 {
+      $evacuate_param = " evacuate_delay=${evacuate_delay}"
+    } else {
+      $evacuate_param = ''
+    }
     pacemaker::resource::ocf { 'nova-evacuate':
       ocf_agent_name  => 'openstack:NovaEvacuate',
       # lint:ignore:140chars
-      resource_params => "auth_url=${keystone_endpoint_url} username=${keystone_admin} password=${keystone_password} user_domain=${user_domain} project_domain=${project_domain} tenant_name=${keystone_admin} ${iha_no_shared_storage}",
+      resource_params => "auth_url=${keystone_endpoint_url} username=${keystone_admin} password=${keystone_password} user_domain=${user_domain} project_domain=${project_domain} tenant_name=${keystone_admin} ${iha_no_shared_storage}${evacuate_param}",
       # lint:endignore
       tries           => $pcs_tries,
       location_rule   => {