Gehel has submitted this change and it was merged. Change subject: elasticsearch - check shards via the service, not via each individual node ......................................................................
elasticsearch - check shards via the service, not via each individual node Checking cluster state on each node is redundant and generate a lot of noise. Cluster wide checks are now done on the service only. The logstash cluster is left unchanged as it does not have LVS. The relforge cluster is at the moment left unmonitored. This will be fixed once a cleanup of the different elasticsearch roles is done (see https://gerrit.wikimedia.org/r/#/c/304067/). Bug: T133844 Change-Id: Ica721152c10d777003726e80fa03ed82c69c8a10 --- M manifests/role/icinga.pp M modules/elasticsearch/manifests/nagios/check.pp A modules/icinga/manifests/monitor/elasticsearch.pp M modules/role/manifests/elasticsearch/server.pp 4 files changed, 22 insertions(+), 2 deletions(-) Approvals: Gehel: Looks good to me, approved EBernhardson: Looks good to me, but someone else must approve jenkins-bot: Verified Objections: Faidon Liambotis: There's a problem with this change, please improve diff --git a/manifests/role/icinga.pp b/manifests/role/icinga.pp index 3e7977c..c40bf8a 100644 --- a/manifests/role/icinga.pp +++ b/manifests/role/icinga.pp @@ -24,6 +24,7 @@ include icinga::monitor::certs include icinga::monitor::gsb include icinga::monitor::commons + include icinga::monitor::elasticsearch include lvs::monitor include role::authdns::monitoring include netops::monitoring diff --git a/modules/elasticsearch/manifests/nagios/check.pp b/modules/elasticsearch/manifests/nagios/check.pp index bc19b24..ce651c7 100644 --- a/modules/elasticsearch/manifests/nagios/check.pp +++ b/modules/elasticsearch/manifests/nagios/check.pp @@ -1,4 +1,4 @@ -# == Class elasticsearch::notifications +# == Class elasticsearch::nagios::check # Sets up icinga alerts for an elasticsearch instance. # Make sure your Nagios/Icinga node has included # the elasticsearch::nagios::plugin class. diff --git a/modules/icinga/manifests/monitor/elasticsearch.pp b/modules/icinga/manifests/monitor/elasticsearch.pp new file mode 100644 index 0000000..164b180 --- /dev/null +++ b/modules/icinga/manifests/monitor/elasticsearch.pp @@ -0,0 +1,20 @@ +# monitor the different elasticsearch clusters +class icinga::monitor::elasticsearch { + + monitoring::service { 'elasticsearch shards - eqiad': + host => 'search.svc.eqiad.wmnet', + check_command => 'check_elasticsearch_shards', + description => 'ElasticSearch health check for shards', + critical => true, + contact_group => 'admins,team-discovery', + } + + monitoring::service { 'elasticsearch shards - codfw': + host => 'search.svc.codfw.wmnet', + check_command => 'check_elasticsearch_shards', + description => 'ElasticSearch health check for shards', + critical => true, + contact_group => 'admins,team-discovery', + } + +} diff --git a/modules/role/manifests/elasticsearch/server.pp b/modules/role/manifests/elasticsearch/server.pp index ac7db8c..fff8196 100644 --- a/modules/role/manifests/elasticsearch/server.pp +++ b/modules/role/manifests/elasticsearch/server.pp @@ -64,7 +64,6 @@ include ::elasticsearch::https include elasticsearch::monitor::diamond include ::elasticsearch::log::hot_threads - include ::elasticsearch::nagios::check file { '/etc/elasticsearch/scripts': ensure => absent, -- To view, visit https://gerrit.wikimedia.org/r/305519 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Ica721152c10d777003726e80fa03ed82c69c8a10 Gerrit-PatchSet: 3 Gerrit-Project: operations/puppet Gerrit-Branch: production Gerrit-Owner: Gehel <gleder...@wikimedia.org> Gerrit-Reviewer: DCausse <dcau...@wikimedia.org> Gerrit-Reviewer: EBernhardson <ebernhard...@wikimedia.org> Gerrit-Reviewer: Faidon Liambotis <fai...@wikimedia.org> Gerrit-Reviewer: Gehel <gleder...@wikimedia.org> Gerrit-Reviewer: jenkins-bot <> _______________________________________________ MediaWiki-commits mailing list MediaWiki-commits@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits