From 61ff9941c3d1f9cbc6867205ffe83cb23ae8375e Mon Sep 17 00:00:00 2001 From: Luca Miccini Date: Fri, 29 Nov 2024 13:10:21 +0100 Subject: [PATCH] Configure keystonemiddleware to deal with memcached pods failures Whenever one of the mecached pods disappears, because of a rolling restart during a minor update or as result of a failure, APIs can take a long time to detect that the pod went away and keep trying to reconnect. From a quick round of tests we saw downtimes up to ~150s. By tuning memcache_pool_dead_retry and memcache_pool_conn_get_timeout the behavior seems much more acceptable. Jira: https://issues.redhat.com/browse/OSPRH-11935 --- templates/cinder/config/00-global-defaults.conf | 2 ++ 1 file changed, 2 insertions(+) diff --git a/templates/cinder/config/00-global-defaults.conf b/templates/cinder/config/00-global-defaults.conf index b9935da2..14a5a158 100644 --- a/templates/cinder/config/00-global-defaults.conf +++ b/templates/cinder/config/00-global-defaults.conf @@ -66,6 +66,8 @@ file_event_handler=/etc/cinder www_authenticate_uri={{ .KeystonePublicURL }} auth_url = {{ .KeystoneInternalURL }} memcached_servers = {{ .MemcachedServersWithInet }} +memcache_pool_dead_retry = 10 +memcache_pool_conn_get_timeout = 2 auth_type = password project_domain_name = Default user_domain_name = Default