From 661757a16f485567403470b38b403cccaf60bdb2 Mon Sep 17 00:00:00 2001 From: Alex Schultz Date: Tue, 11 Jul 2017 15:14:00 -0600 Subject: Retry ceilometer-upgrade When the ceilometer-upgrade command is run in step5, it talks to gnocchi and keystone on all the controllers. Since these other nodes might have httpd restarted mid-upgrade we should retry if we get a failure. Change-Id: I874cf9c34b41d055a258704dabe9150eab0f7968 Closes-Bug: #1703444 --- manifests/profile/base/ceilometer/upgrade.pp | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'manifests/profile/base/ceilometer') diff --git a/manifests/profile/base/ceilometer/upgrade.pp b/manifests/profile/base/ceilometer/upgrade.pp index f192b48..0031b79 100644 --- a/manifests/profile/base/ceilometer/upgrade.pp +++ b/manifests/profile/base/ceilometer/upgrade.pp @@ -42,8 +42,16 @@ class tripleo::profile::base::ceilometer::upgrade ( # are created safely. if $step >= 5 and $sync_db { exec {'ceilometer-db-upgrade': - command => 'ceilometer-upgrade --skip-metering-database', - path => ['/usr/bin', '/usr/sbin'], + command => 'ceilometer-upgrade --skip-metering-database', + path => ['/usr/bin', '/usr/sbin'], + # LP#1703444 - When this runs, it talks to gnocchi on all controllers + # which then reaches out to keystone via haproxy. Since the deployment + # may restart httpd on these other nodes it can result in an intermittent + # 503 which fails this command. We should retry the upgrade in case of + # error since we cannot ensure that there might not be some other deploy + # process running on the other nodes. + try_sleep => 5, + tries => 10 } } } -- cgit 1.2.3-korg