diff --git a/ansible/install/roles/collectd-rhoso/templates/controlplane.collectd.conf.j2 b/ansible/install/roles/collectd-rhoso/templates/controlplane.collectd.conf.j2 index c46b2da3a..75ea2ca83 100644 --- a/ansible/install/roles/collectd-rhoso/templates/controlplane.collectd.conf.j2 +++ b/ansible/install/roles/collectd-rhoso/templates/controlplane.collectd.conf.j2 @@ -19,7 +19,7 @@ LoadPlugin dbi LoadPlugin exec LoadPlugin match_regex LoadPlugin mysql -LoadPlugin processes +# LoadPlugin processes Globals true @@ -35,7 +35,7 @@ LoadPlugin unixsock - Port "9104" + Port "8888" {% if db_conf %} @@ -422,164 +422,165 @@ LoadPlugin unixsock {% endif %} -# Including the version of OpenStack that the process was verified as running after -# OpenStack Installation with a comment at the end of each Process/ProcessMatch statement. -# A Minus before the version means the process was not found in that version. (Ex -10) - - # Ansible - ProcessMatch "ansible-playbook" "ansible-playbook" - ProcessMatch "ansible-runner" "ansible-runner" - - # Aodh (OpenStack Installed) - ProcessMatch "aodh-evaluator" "aodh-evaluator" # 10,11,12,13 - ProcessMatch "aodh-listener" "aodh-listener" # 10,11,12,13 - ProcessMatch "aodh-notifier" "aodh-notifier" # 10,11,12,13 - ProcessMatch "aodh_wsgi" "aodh_wsgi.*-DFOREGROUND" # 11,12,13 - - # Barbican (OpenStack Installed) - ProcessMatch "barbican_wsgi" "barbican_wsgi.*-DFOREGROUND" # 13 - ProcessMatch "barbican-keystone-listener" "python.+barbican-keystone-listener" # 13 - ProcessMatch "barbican-worker" "python.+barbican-worker" # 13 - - # Ceilometer (OpenStack Installed) - ProcessMatch "ceilometer-agent-notification" "ceilometer-agent-notification" # 10,11,12,13 - ProcessMatch "ceilometer-collector" "ceilometer-collector" # 10,11,-12,-13 - ProcessMatch "ceilometer-polling" "ceilometer-polling" # 10,11,12,13 - ProcessMatch "ceilometer_wsgi" "ceilometer_wsgi.*-DFOREGROUND" # 11,-12,-13 - - # Ceph (OpenStack Installed) - # When CephStorage nodes deployed - ProcessMatch "ceph-mon" "^/usr/bin/ceph-mon" # -10,-11,-12,-13 - - # Cinder (OpenStack Installed) - ProcessMatch "cinder-api" "python.+cinder-api" # 10,-11,-12 - ProcessMatch "cinder-scheduler" "python.+cinder-scheduler" # 10,11,12,13 - ProcessMatch "cinder-volume" "python.+cinder-volume" # 10,11,12,13 - ProcessMatch "cinder_wsgi" "cinder_wsgi.*-DFOREGROUND" # 11,12,13 - - # Collectd (Browbeat Installed) - ProcessMatch "collectd" "/usr/sbin/collectd" - - # Conmon (OpenStack Installed) - ProcessMatch "conmon" "/usr/bin/conmon" # 16 - - # Docker (OpenStack Installed) - ProcessMatch "dockerd-current" "dockerd-current" # 12,13 - - # Pacemaker / Corosync (OpenStack Installed) - ProcessMatch "attrd" "/usr/libexec/pacemaker/attrd" # 10,11,12,13 - ProcessMatch "cib" "/usr/libexec/pacemaker/cib" # 10,11,12,13 - Process "corosync" # 10,11,12,13 - ProcessMatch "crmd" "/usr/libexec/pacemaker/crmd" # 10,11,12,13 - ProcessMatch "lrmd" "/usr/libexec/pacemaker/lrmd" # 10,11,12,13 - ProcessMatch "pacemakerd" "/usr/sbin/pacemakerd" # 10,11,12,13 - ProcessMatch "pcsd" "^/usr/bin/ruby.+/usr/lib/pcsd" # 10,11,12,13 - ProcessMatch "pengine" "/usr/libexec/pacemaker/pengine" # 10,11,12,13 - ProcessMatch "stonithd" "/usr/libexec/pacemaker/stonithd" # 10,11,12,13 - - # Everything Else (OpenStack Installed) - # (Processes displayed under "Everything Else" on Grafana Dashboards) - ProcessMatch "dnsmasq" "^dnsmasq.+" # 10,11,12 - ProcessMatch "haproxy" "/usr/sbin/haproxy.+/etc/haproxy/haproxy.cfg" # 10,11,12,13 - Process "httpd" # 10,11,12,13 - Process "keepalived" # 10,11,12 - Process "memcached" # 10,11,12,13 - Process "mongod" # 10,11,-12,-13 - ProcessMatch "mysqld" "/usr/libexec/mysqld" # 10,11,12,13 - ProcessMatch "rabbitmq" "/usr/lib64/erlang/erts-.+/bin/beam.smp" # 10,11,12,13 - Process "redis-server" # 10,11,12,13 - ProcessMatch "karaf" "java.+karaf" # ODL Specific - - # Glance (OpenStack Installed) - ProcessMatch "glance-api" "python.+glance-api" # 10,11,12,13 - ProcessMatch "glance-registry" "python.+glance-registry" # 10,-11,-12,-13 - - # Gnocchi (OpenStack Installed) - ProcessMatch "gnocchi-metricd-master" "gnocchi-metricd.*master" # 11,12,13 - ProcessMatch "gnocchi-metricd-scheduler" "gnocchi-metricd.*scheduler" # 10,11,-12,-13 - ProcessMatch "gnocchi-metricd-processing" "gnocchi-metricd.*processing" # 10,11,12,13 - ProcessMatch "gnocchi-metricd-reporting" "gnocchi-metricd.*reporting" # 10,11,12,13 - ProcessMatch "gnocchi-metricd-janitor" "gnocchi-metricd.*janitor" # 10,11,12,13 - ProcessMatch "gnocchi-metricd" "gnocchi-metricd " # 10(Old proctitle) - ProcessMatch "gnocchi-statsd" "python.+gnocchi-statsd" # 10,11,12,13 - ProcessMatch "gnocchi_wsgi" "gnocchi_wsgi.*-DFOREGROUND" # 11,12,13 - - # Heat (OpenStack Installed) - ProcessMatch "heat-api" "python.+heat-api --config-file" # 10,11,-12,-13 - ProcessMatch "heat-api-cfn" "python.+heat-api-cfn" # 10,11,-12,-13 - ProcessMatch "heat-api-cloudwatch" "python.+heat-api-cloudwatch" # 10,11,-12,-123 - ProcessMatch "heat_api_cfn" "heat_api_cfn_ws" # 12,13 - ProcessMatch "heat_api_cloudwatch" "heat_api_cloudw" # 12,-13 - ProcessMatch "heat_api_wsgi" "heat_api_wsgi" # 12,13 - ProcessMatch "heat-engine" "python.+heat-engine" # 10,11,12,13 - - # Horizon (OpenStack Installed) - ProcessMatch "horizon" "horizon" # 13 - - # Keystone (OpenStack Installed) - ProcessMatch "keystone-admin" "keystone-admin.*-DFOREGROUND" # 10,11,12,13 - ProcessMatch "keystone-main" "keystone-main.*-DFOREGROUND" # 10,11,12,13 - ProcessMatch "keystone" "keystone.*-DFOREGROUND" # 16 - # Starting Pike, fernet tokens are default thus token_flush not needed - ProcessMatch "keystone-token-flush" "keystone-manage.*token_flush" # 10,11,-12,-13 - - # Neutron (OpenStack Installed) - ProcessMatch "neutron-dhcp-agent" "python.+neutron-dhcp-agent" # 10,11,12,13 - ProcessMatch "neutron-l3-agent" "python.+neutron-l3-agent" # 10,11,12,13 - ProcessMatch "neutron-metadata-agent" "python.+neutron-metadata-agent" # 10,11,12,13 - ProcessMatch "neutron-ns-metadata-proxy" "python.+neutron-ns-metadata-proxy" # 10,11 - ProcessMatch "neutron-openvswitch-agent" "python.+neutron-openvswitch-agent" # 10,11,12,13 - ProcessMatch "neutron-rootwrap-daemon" "python.+neutron-rootwrap-daemon" # 10,11,12,13 - ProcessMatch "neutron-server" "python.+neutron-server" # 10,11,12,13 - ProcessMatch "neutron-keepalived-state-change" "python.+neutron-keepalived-state-change" #For HA router - - # Nova (OpenStack Installed) - ProcessMatch "nova-api" "python.+nova-api$" # 10,11,-12,-13 - ProcessMatch "nova-api-metadata" "python.+nova-api-metadata" # 12,13 - ProcessMatch "nova_api_wsgi" "nova_api_wsgi" # 12,13 - ProcessMatch "nova-conductor" "python.+nova-conductor" # 10,11,12,13 - ProcessMatch "nova-consoleauth" "python.+nova-consoleauth" # 10,11,12,13 - ProcessMatch "nova-novncproxy" "python.+nova-novncproxy" # 10,11,12,13 - ProcessMatch "nova-scheduler" "python.+nova-scheduler" # 10,11,12,13 - ProcessMatch "placement_wsgi" "placement_wsgi.*-DFOREGROUND" # 11,12,13 - ProcessMatch "nova_metadata_w" "nova_metadata_w.*-DFOREGROUND" # 16 - - # Octavia (OpenStack Installed) - ProcessMatch "octavia-housekeeping" "python.+octavia-housekeeping" # 13 - ProcessMatch "octavia-health-manager" "python.+octavia-health-manager" # 13 - ProcessMatch "octavia-api" "python.+octavia-api" # 13 - ProcessMatch "octavia-worker" "octavia-worker --config-file" # 13 - ProcessMatch "octavia_wsgi" "octavia_wsgi.*-DFOREGROUND" # 16 - - # OVS (OpenStack Installed) - ProcessMatch "ovs-vswitchd" "ovs-vswitchd.+openvswitch" # 10,11,12,13 - ProcessMatch "ovsdb-client" "ovsdb-client" # 10,11,12,13 - ProcessMatch "ovsdb-server" "ovsdb-server.+openvswitch" # 10,11,12,13 - ProcessMatch "ovsdb-server-nb" "ovsdb-server.+ovsdb-server-nb" # 16 - ProcessMatch "ovsdb-server-sb" "ovsdb-server.+ovsdb-server-sb" # 16 - ProcessMatch "ovn-northd" "ovn-northd.+ovnnb_db" # 16 - ProcessMatch "ovn-controller" "ovn-controller.+openvswitch" # 9,10 - ProcessMatch "ovn-controller-vtep" "ovn-controller-vtep.+openvswitch" # 9,10 - - # Panko (OpenStack Installed) - ProcessMatch "panko_wsgi" "panko_wsgi.*-DFOREGROUND" # 11,12,13 - - # Swift (OpenStack Installed) - ProcessMatch "swift-account-auditor" "python.+swift-account-auditor" # 10,11,12,13 - ProcessMatch "swift-account-reaper" "python.+swift-account-reaper" # 10,11,12,13 - ProcessMatch "swift-account-replicator" "python.+swift-account-replicator" # 10,11,12,13 - ProcessMatch "swift-account-server" "python.+swift-account-server" # 10,11,12,13 - ProcessMatch "swift-container-auditor" "python.+swift-container-auditor" # 10,11,12,13 - ProcessMatch "swift-container-replicator" "python.+swift-container-replicator" # 10,11,12,13 - ProcessMatch "swift-container-server" "python.+swift-container-server" # 10,11,12,13 - ProcessMatch "swift-container-updater" "python.+swift-container-updater" # 10,11,12,13 - ProcessMatch "swift-object-auditor" "python.+swift-object-auditor" # 10,11,12,13 - ProcessMatch "swift-object-expirer" "python.+swift-object-expirer" # 11,12,13 - ProcessMatch "swift-object-replicator" "python.+swift-object-replicator" # 10,11,12,13 - ProcessMatch "swift-object-server" "python.+swift-object-server" # 10,11,12,13 - ProcessMatch "swift-object-updater" "python.+swift-object-updater" # 10,11,12,13 - ProcessMatch "swift-proxy-server" "python.+swift-proxy-server" # 10,11,12,13 - +# Commenting processes plugin as processes naming has changed in RHOSO +# # Including the version of OpenStack that the process was verified as running after +# # OpenStack Installation with a comment at the end of each Process/ProcessMatch statement. +# # A Minus before the version means the process was not found in that version. (Ex -10) +# +# # Ansible +# ProcessMatch "ansible-playbook" "ansible-playbook" +# ProcessMatch "ansible-runner" "ansible-runner" +# +# # Aodh (OpenStack Installed) +# ProcessMatch "aodh-evaluator" "aodh-evaluator" # 10,11,12,13 +# ProcessMatch "aodh-listener" "aodh-listener" # 10,11,12,13 +# ProcessMatch "aodh-notifier" "aodh-notifier" # 10,11,12,13 +# ProcessMatch "aodh_wsgi" "aodh_wsgi.*-DFOREGROUND" # 11,12,13 +# +# # Barbican (OpenStack Installed) +# ProcessMatch "barbican_wsgi" "barbican_wsgi.*-DFOREGROUND" # 13 +# ProcessMatch "barbican-keystone-listener" "python.+barbican-keystone-listener" # 13 +# ProcessMatch "barbican-worker" "python.+barbican-worker" # 13 +# +# # Ceilometer (OpenStack Installed) +# ProcessMatch "ceilometer-agent-notification" "ceilometer-agent-notification" # 10,11,12,13 +# ProcessMatch "ceilometer-collector" "ceilometer-collector" # 10,11,-12,-13 +# ProcessMatch "ceilometer-polling" "ceilometer-polling" # 10,11,12,13 +# ProcessMatch "ceilometer_wsgi" "ceilometer_wsgi.*-DFOREGROUND" # 11,-12,-13 +# +# # Ceph (OpenStack Installed) +# # When CephStorage nodes deployed +# ProcessMatch "ceph-mon" "^/usr/bin/ceph-mon" # -10,-11,-12,-13 +# +# # Cinder (OpenStack Installed) +# ProcessMatch "cinder-api" "python.+cinder-api" # 10,-11,-12 +# ProcessMatch "cinder-scheduler" "python.+cinder-scheduler" # 10,11,12,13 +# ProcessMatch "cinder-volume" "python.+cinder-volume" # 10,11,12,13 +# ProcessMatch "cinder_wsgi" "cinder_wsgi.*-DFOREGROUND" # 11,12,13 +# +# # Collectd (Browbeat Installed) +# ProcessMatch "collectd" "/usr/sbin/collectd" +# +# # Conmon (OpenStack Installed) +# ProcessMatch "conmon" "/usr/bin/conmon" # 16 +# +# # Docker (OpenStack Installed) +# ProcessMatch "dockerd-current" "dockerd-current" # 12,13 +# +# # Pacemaker / Corosync (OpenStack Installed) +# ProcessMatch "attrd" "/usr/libexec/pacemaker/attrd" # 10,11,12,13 +# ProcessMatch "cib" "/usr/libexec/pacemaker/cib" # 10,11,12,13 +# Process "corosync" # 10,11,12,13 +# ProcessMatch "crmd" "/usr/libexec/pacemaker/crmd" # 10,11,12,13 +# ProcessMatch "lrmd" "/usr/libexec/pacemaker/lrmd" # 10,11,12,13 +# ProcessMatch "pacemakerd" "/usr/sbin/pacemakerd" # 10,11,12,13 +# ProcessMatch "pcsd" "^/usr/bin/ruby.+/usr/lib/pcsd" # 10,11,12,13 +# ProcessMatch "pengine" "/usr/libexec/pacemaker/pengine" # 10,11,12,13 +# ProcessMatch "stonithd" "/usr/libexec/pacemaker/stonithd" # 10,11,12,13 +# +# # Everything Else (OpenStack Installed) +# # (Processes displayed under "Everything Else" on Grafana Dashboards) +# ProcessMatch "dnsmasq" "^dnsmasq.+" # 10,11,12 +# ProcessMatch "haproxy" "/usr/sbin/haproxy.+/etc/haproxy/haproxy.cfg" # 10,11,12,13 +# Process "httpd" # 10,11,12,13 +# Process "keepalived" # 10,11,12 +# Process "memcached" # 10,11,12,13 +# Process "mongod" # 10,11,-12,-13 +# ProcessMatch "mysqld" "/usr/libexec/mysqld" # 10,11,12,13 +# ProcessMatch "rabbitmq" "/usr/lib64/erlang/erts-.+/bin/beam.smp" # 10,11,12,13 +# Process "redis-server" # 10,11,12,13 +# ProcessMatch "karaf" "java.+karaf" # ODL Specific +# +# # Glance (OpenStack Installed) +# ProcessMatch "glance-api" "python.+glance-api" # 10,11,12,13 +# ProcessMatch "glance-registry" "python.+glance-registry" # 10,-11,-12,-13 +# +# # Gnocchi (OpenStack Installed) +# ProcessMatch "gnocchi-metricd-master" "gnocchi-metricd.*master" # 11,12,13 +# ProcessMatch "gnocchi-metricd-scheduler" "gnocchi-metricd.*scheduler" # 10,11,-12,-13 +# ProcessMatch "gnocchi-metricd-processing" "gnocchi-metricd.*processing" # 10,11,12,13 +# ProcessMatch "gnocchi-metricd-reporting" "gnocchi-metricd.*reporting" # 10,11,12,13 +# ProcessMatch "gnocchi-metricd-janitor" "gnocchi-metricd.*janitor" # 10,11,12,13 +# ProcessMatch "gnocchi-metricd" "gnocchi-metricd " # 10(Old proctitle) +# ProcessMatch "gnocchi-statsd" "python.+gnocchi-statsd" # 10,11,12,13 +# ProcessMatch "gnocchi_wsgi" "gnocchi_wsgi.*-DFOREGROUND" # 11,12,13 +# +# # Heat (OpenStack Installed) +# ProcessMatch "heat-api" "python.+heat-api --config-file" # 10,11,-12,-13 +# ProcessMatch "heat-api-cfn" "python.+heat-api-cfn" # 10,11,-12,-13 +# ProcessMatch "heat-api-cloudwatch" "python.+heat-api-cloudwatch" # 10,11,-12,-123 +# ProcessMatch "heat_api_cfn" "heat_api_cfn_ws" # 12,13 +# ProcessMatch "heat_api_cloudwatch" "heat_api_cloudw" # 12,-13 +# ProcessMatch "heat_api_wsgi" "heat_api_wsgi" # 12,13 +# ProcessMatch "heat-engine" "python.+heat-engine" # 10,11,12,13 +# +# # Horizon (OpenStack Installed) +# ProcessMatch "horizon" "horizon" # 13 +# +# # Keystone (OpenStack Installed) +# ProcessMatch "keystone-admin" "keystone-admin.*-DFOREGROUND" # 10,11,12,13 +# ProcessMatch "keystone-main" "keystone-main.*-DFOREGROUND" # 10,11,12,13 +# ProcessMatch "keystone" "keystone.*-DFOREGROUND" # 16 +# # Starting Pike, fernet tokens are default thus token_flush not needed +# ProcessMatch "keystone-token-flush" "keystone-manage.*token_flush" # 10,11,-12,-13 +# +# # Neutron (OpenStack Installed) +# ProcessMatch "neutron-dhcp-agent" "python.+neutron-dhcp-agent" # 10,11,12,13 +# ProcessMatch "neutron-l3-agent" "python.+neutron-l3-agent" # 10,11,12,13 +# ProcessMatch "neutron-metadata-agent" "python.+neutron-metadata-agent" # 10,11,12,13 +# ProcessMatch "neutron-ns-metadata-proxy" "python.+neutron-ns-metadata-proxy" # 10,11 +# ProcessMatch "neutron-openvswitch-agent" "python.+neutron-openvswitch-agent" # 10,11,12,13 +# ProcessMatch "neutron-rootwrap-daemon" "python.+neutron-rootwrap-daemon" # 10,11,12,13 +# ProcessMatch "neutron-server" "python.+neutron-server" # 10,11,12,13 +# ProcessMatch "neutron-keepalived-state-change" "python.+neutron-keepalived-state-change" #For HA router +# +# # Nova (OpenStack Installed) +# ProcessMatch "nova-api" "python.+nova-api$" # 10,11,-12,-13 +# ProcessMatch "nova-api-metadata" "python.+nova-api-metadata" # 12,13 +# ProcessMatch "nova_api_wsgi" "nova_api_wsgi" # 12,13 +# ProcessMatch "nova-conductor" "python.+nova-conductor" # 10,11,12,13 +# ProcessMatch "nova-consoleauth" "python.+nova-consoleauth" # 10,11,12,13 +# ProcessMatch "nova-novncproxy" "python.+nova-novncproxy" # 10,11,12,13 +# ProcessMatch "nova-scheduler" "python.+nova-scheduler" # 10,11,12,13 +# ProcessMatch "placement_wsgi" "placement_wsgi.*-DFOREGROUND" # 11,12,13 +# ProcessMatch "nova_metadata_w" "nova_metadata_w.*-DFOREGROUND" # 16 +# +# # Octavia (OpenStack Installed) +# ProcessMatch "octavia-housekeeping" "python.+octavia-housekeeping" # 13 +# ProcessMatch "octavia-health-manager" "python.+octavia-health-manager" # 13 +# ProcessMatch "octavia-api" "python.+octavia-api" # 13 +# ProcessMatch "octavia-worker" "octavia-worker --config-file" # 13 +# ProcessMatch "octavia_wsgi" "octavia_wsgi.*-DFOREGROUND" # 16 +# +# # OVS (OpenStack Installed) +# ProcessMatch "ovs-vswitchd" "ovs-vswitchd.+openvswitch" # 10,11,12,13 +# ProcessMatch "ovsdb-client" "ovsdb-client" # 10,11,12,13 +# ProcessMatch "ovsdb-server" "ovsdb-server.+openvswitch" # 10,11,12,13 +# ProcessMatch "ovsdb-server-nb" "ovsdb-server.+ovsdb-server-nb" # 16 +# ProcessMatch "ovsdb-server-sb" "ovsdb-server.+ovsdb-server-sb" # 16 +# ProcessMatch "ovn-northd" "ovn-northd.+ovnnb_db" # 16 +# ProcessMatch "ovn-controller" "ovn-controller.+openvswitch" # 9,10 +# ProcessMatch "ovn-controller-vtep" "ovn-controller-vtep.+openvswitch" # 9,10 +# +# # Panko (OpenStack Installed) +# ProcessMatch "panko_wsgi" "panko_wsgi.*-DFOREGROUND" # 11,12,13 +# +# # Swift (OpenStack Installed) +# ProcessMatch "swift-account-auditor" "python.+swift-account-auditor" # 10,11,12,13 +# ProcessMatch "swift-account-reaper" "python.+swift-account-reaper" # 10,11,12,13 +# ProcessMatch "swift-account-replicator" "python.+swift-account-replicator" # 10,11,12,13 +# ProcessMatch "swift-account-server" "python.+swift-account-server" # 10,11,12,13 +# ProcessMatch "swift-container-auditor" "python.+swift-container-auditor" # 10,11,12,13 +# ProcessMatch "swift-container-replicator" "python.+swift-container-replicator" # 10,11,12,13 +# ProcessMatch "swift-container-server" "python.+swift-container-server" # 10,11,12,13 +# ProcessMatch "swift-container-updater" "python.+swift-container-updater" # 10,11,12,13 +# ProcessMatch "swift-object-auditor" "python.+swift-object-auditor" # 10,11,12,13 +# ProcessMatch "swift-object-expirer" "python.+swift-object-expirer" # 11,12,13 +# ProcessMatch "swift-object-replicator" "python.+swift-object-replicator" # 10,11,12,13 +# ProcessMatch "swift-object-server" "python.+swift-object-server" # 10,11,12,13 +# ProcessMatch "swift-object-updater" "python.+swift-object-updater" # 10,11,12,13 +# ProcessMatch "swift-proxy-server" "python.+swift-proxy-server" # 10,11,12,13 +# {% if container_logs is not none and container_logs | length > 0 %} diff --git a/ansible/install/roles/index-ocp-data/templates/metrics.yaml b/ansible/install/roles/index-ocp-data/templates/metrics.yaml index 74e5f3c11..f48391e5e 100644 --- a/ansible/install/roles/index-ocp-data/templates/metrics.yaml +++ b/ansible/install/roles/index-ocp-data/templates/metrics.yaml @@ -1,6 +1,5 @@ # Containers & pod metrics -# -- query: (sum(irate(container_cpu_usage_seconds_total{name!="",container!~"POD|",namespace=~"openstack"}[2m]) * 100) by (container, pod, namespace, node)) > 0 +- query: sum(irate(container_cpu_usage_seconds_total{name!="",container!~"POD|",namespace=~"openstack"}[2m]) * 100) by (container, pod, namespace, node) metricName: containerCPU - query: sum(container_memory_rss{name!="",container!~"POD|",namespace=~"openstack"}) by (container, pod, namespace, node) @@ -12,6 +11,7 @@ - query: sum(irate(container_network_transmit_packets_total{cluster="",namespace=~"openstack", pod!=""}[2m])) by (pod, namespace, node, interface) metricName: containerTranPackets +# OCP Cluster details - query: cluster_version{type="completed"} metricName: clusterVersion instant: true @@ -39,3 +39,142 @@ - query: count(kube_statefulset_labels{namespace='openstack'}) metricName: ospStatefulsetCount instant: true + +# MYSQL Innodb data +- query: sum(irate(collectd_mysql_mysql_innodb_log_total[5m])) by (type) + metricName: ospMysqlInnodbLog + +- query: sum(irate(collectd_mysql_mysql_innodb_data_total[5m])) by (type) + metricName: ospMysqlInnodbData + +- query: sum(irate(collectd_mysql_mysql_innodb_dblwr_total[5m])) by (type) + metricName: ospMysqlInnodbDoubleWrite + +- query: sum(irate(collectd_mysql_mysql_innodb_pages_total[5m])) by (type) + metricName: ospMysqlInnodbPages + +- query: sum(irate(collectd_mysql_mysql_innodb_row_lock_total[5m])) by (type) + metricName: ospMysqlInnodbRowLock + +- query: sum(irate(collectd_mysql_mysql_innodb_rows_total[5m])) by (type) + metricName: ospMysqlInnodbRows + +# OVN DB Tables Row Counts +- query: sum(collectd_ovn_gauge) by (type) + metricName: ospOVNDBTableRowCount + +# OVN RAFT Monitoring +- query: sum(collectd_ovn_raft_monitoring_gauge) by (ovn_raft_monitoring) + metricName: ospOVNRAFTData + +# Tail info +- query: sum(increase(collectd_tail_counter_total[5m])) by (tail, type) + metricName: ospTailInfo + +# OSP DB Data +- query: sum(collectd_dbi_gauge) by (type, dbi) + metricName: ospDbResources + +# OSP resource response time +- query: sum(collectd_tail_response_time{tail=~".*_avg_response_time"}) by (tail, type) + metricName: ospResourceAvgRespTime + +- query: sum(collectd_tail_response_time{tail=~".*_min_response_time"}) by (tail, type) + metricName: ospResourceMinRespTime + +- query: sum(collectd_tail_response_time{tail=~".*_max_response_time"}) by (tail, type) + metricName: ospResourceMaxRespTime + +# Commenting processes plugin queries, as the processes naming has changed in RHOSO +# Collecting processes metrics from prometheus now. we can use these below queries +# once regex is corrected. + +# # OSP Process and Thread Counts +# - query: sum(collectd_processes_ps_count_processes) by (processes, instance) +# metricName: ospProcessCount +# +# - query: sum(collectd_processes_ps_count_threads) by (processes, instance) +# metricName: ospThreadsCount +# +# # OSP process CPU time +# - query: sum(irate(collectd_processes_ps_cputime_syst_total[2m]) / 10000) by (instance, processes) +# metricName: ospProcessCPUSys +# +# - query: sum(irate(collectd_processes_ps_cputime_syst_total[2m]) / 10000) by (instance, processes) +# metricName: ospProcessCPUUser +# +# # OSP Process Memory +# - query: sum(irate(collectd_processes_ps_rss[5m])) by (instance, processes) +# metricName: ospProcessMemRSS +# +# - query: sum(irate(collectd_processes_ps_vm[5m])) by (instance, processes) +# metricName: ospProcessMemVirt +# +# # OSP Process Pagefault +# - query: sum(increase(collectd_processes_ps_pagefaults_majflt_total[5m])) by (instance, processes) +# metricName: ospProcessPagefaultMax +# +# - query: sum(increase(collectd_processes_ps_pagefaults_minflt_total[5m])) by (instance, processes) +# metricName: ospProcessPagefaultMin +# +# # OSP process IOPs +# - query: sum(irate(collectd_processes_io_ops_write_total[5m])) by (instance, processes) +# metricName: ospProcessIOPsWrite +# +# - query: sum(irate(collectd_processes_io_ops_read_total[5m])) by (instance, processes) +# metricName: ospProcessIOPsRead +# +# # OSP Process IO Throughput +# - query: sum(irate(collectd_processes_io_octets_rx_total[5m])) by (instance, processes) +# metricName: ospProcessIORx +# +# - query: sum(irate(collectd_processes_io_octets_tx_total[5m])) by (instance, processes) +# metricName: ospProcessIOTx +# +# # OSP Process Disk IO +# - query: sum(irate(collectd_processes_disk_octets_read_total[5m])) by (instance, processes) +# metricName: ospProcessDiskRead +# +# - query: sum(irate(collectd_processes_disk_octets_write_total[5m])) by (instance, processes) +# metricName: ospProcessDiskWrite + +# MariaDB +- query: sum(collectd_mysql_threads) by (name, type) + metricName: ospMysqlThreads + +- query: sum(rate(collectd_mysql_mysql_octets_tx_total[2m])) by (name) + metricName: ospMysqlTrafficTx + +- query: sum(rate(collectd_mysql_mysql_octets_rx_total[2m])) by (name) + metricName: ospMysqlTrafficRx + +- query: sum(increase(collectd_mysql_cache_result_total[5m])) by (type) + metricName: ospMysqlQueryCache + +- query: sum(collectd_mysql_cache_size) by (type) + metricName: ospMysqlQueryCacheSize + +- query: sum(collectd_mysql_mysql_bpool_bytes) by (type) + metricName: ospMysqlBufferPoolData + +- query: sum(increase(collectd_mysql_mysql_bpool_counters_total[5m])) by (type) + metricName: ospMysqlBufferPool + +- query: sum(increase(collectd_mysql_mysql_commands_total[5m])) by (type) + metricName: ospMysqlCommands + +- query: sum(increase(collectd_mysql_mysql_handler_total[5m])) by (type) + metricName: ospMysqlHandlers + +- query: sum(increase(collectd_mysql_mysql_locks_total[5m])) by (type) + metricName: ospMysqlLocks + +- query: sum(increase(collectd_mysql_mysql_select_total[5m])) by (type) + metricName: ospMysqlSelect + +- query: sum(increase(collectd_mysql_mysql_sort_total[5m])) by (type) + metricName: ospMysqlSort + +# RabbitMQ +- query: sum(collectd_rabbitmq_monitoring_gauge) by (rabbitmq_monitoring) + metricName: ospRabbitmqQueueCounts