Filippo Giunchedi has uploaded a new change for review. https://gerrit.wikimedia.org/r/203102
Change subject: labs: update graphite checks with new metric names ...................................................................... labs: update graphite checks with new metric names Change-Id: Icaa113b13fd1c916b562f182ee1a502dc7bc6fcd --- M modules/beta/files/shinken.cfg M modules/shinken/files/labs/basic-instance-checks.cfg 2 files changed, 5 insertions(+), 5 deletions(-) git pull ssh://gerrit.wikimedia.org:29418/operations/puppet refs/changes/02/203102/1 diff --git a/modules/beta/files/shinken.cfg b/modules/beta/files/shinken.cfg index c98735a..8f6bba2 100644 --- a/modules/beta/files/shinken.cfg +++ b/modules/beta/files/shinken.cfg @@ -73,12 +73,12 @@ service_description HHVM Queue Size hostgroup_name role::mediawiki::appserver use generic-service - check_command check_graphite_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.hhvmHealthCollector.queued.value!10!80!10min!30!--over + check_command check_graphite_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.hhvmHealthCollector.queued!10!80!10min!30!--over } define service { service_description Long lived cherry-picks on puppetmaster host_name deployment-salt use generic-service - check_command check_graphite_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.puppetmaster.cherrypicked_commits.value!0!0!48h!100!--over + check_command check_graphite_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.puppetmaster.cherrypicked_commits!0!0!48h!100!--over } diff --git a/modules/shinken/files/labs/basic-instance-checks.cfg b/modules/shinken/files/labs/basic-instance-checks.cfg index 0f4cc24..6018aed 100644 --- a/modules/shinken/files/labs/basic-instance-checks.cfg +++ b/modules/shinken/files/labs/basic-instance-checks.cfg @@ -4,7 +4,7 @@ # Check that all mounts have at least 10% free space (for warn), 5% (for crit) define service { - check_command check_graphite_series_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.diskspace.*.byte_percentfree.value!15!10!10min!1!--under + check_command check_graphite_series_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.diskspace.*.byte_percentfree!15!10!10min!1!--under hostgroup_name role::labs::instance service_description Free space - all mounts use generic-service @@ -13,7 +13,7 @@ # Check for puppet failure events define service { - check_command check_graphite_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.puppetagent.failed_events.value!0!0!10min!1!--over + check_command check_graphite_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.puppetagent.failed_events!0!0!10min!1!--over hostgroup_name role::labs::instance service_description Puppet failure use generic-service @@ -42,7 +42,7 @@ # Check for puppet staleness define service { - check_command check_graphite_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.puppetagent.time_since_last_run.value!3600!43200!10min!1!--over + check_command check_graphite_threshold!http://labmon1001.eqiad.wmnet!10!$HOSTNOTES$.$HOSTNAME$.puppetagent.time_since_last_run!3600!43200!10min!1!--over hostgroup_name role::labs::instance service_description Puppet staleness use generic-service -- To view, visit https://gerrit.wikimedia.org/r/203102 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: newchange Gerrit-Change-Id: Icaa113b13fd1c916b562f182ee1a502dc7bc6fcd Gerrit-PatchSet: 1 Gerrit-Project: operations/puppet Gerrit-Branch: production Gerrit-Owner: Filippo Giunchedi <fgiunch...@wikimedia.org> _______________________________________________ MediaWiki-commits mailing list MediaWiki-commits@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits