openstack
/
openstack-helm-infra
Code Issues Proposed changes

Prometheus: Render Rules as Templates 

This change allows us to substitute values into our rules files.

Example:

- alert: my_region_is_down
  expr: up{region="{{ $my_region }}"} == 0
  
To support this change, rule annotations that used the expansion
{{ $labels.foo }} had to be surrounded with "{{` ... `}}" to render
correctly.

Change-Id: Ia7ac891de8261acca62105a3e2636bd747a5fbea
This commit is contained in:
Steven Fitzpatrick 2020-08-10 08:31:59 -05:00
parent 3fa84d655f
commit fb7fc87d23
8 changed files with 223 additions and 241 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
prometheus/templates/configmap-etc.yaml
View File

@ -22,8 +22,9 @@ metadata:
type: Opaque type: Opaque
data: data:
{{- include "helm-toolkit.snippets.values_template_renderer" (dict "envAll" $envAll "template" .Values.conf.prometheus.scrape_configs.template "key" "prometheus.yml" "format" "Secret") | indent 2 }} {{- include "helm-toolkit.snippets.values_template_renderer" (dict "envAll" $envAll "template" .Values.conf.prometheus.scrape_configs.template "key" "prometheus.yml" "format" "Secret") | indent 2 }}
{{ range $key, $value := .Values.conf.prometheus.rules }} {{ range $name, $config := .Values.conf.prometheus.rules }}
{{ $key }}.rules: {{ toYaml $value | b64enc }} {{- $filename := printf "%s.rules" $name}}
{{- include "helm-toolkit.snippets.values_template_renderer" (dict "envAll" $envAll "template" $config "key" $filename "format" "Secret") | indent 2 }}
{{ end }} {{ end }}
# NOTE(srwilkers): this must be last, to work round helm ~2.7 bug. # NOTE(srwilkers): this must be last, to work round helm ~2.7 bug.
{{- include "helm-toolkit.snippets.values_template_renderer" (dict "envAll" $envAll "template" .Values.conf.httpd "key" "httpd.conf" "format" "Secret") | indent 2 }} {{- include "helm-toolkit.snippets.values_template_renderer" (dict "envAll" $envAll "template" .Values.conf.httpd "key" "httpd.conf" "format" "Secret") | indent 2 }}

6
prometheus/values_overrides/alertmanager.yaml
View File

@ -12,7 +12,7 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: The configuration of the instances of the Alertmanager cluster `{{$labels.service}}` are out of sync. description: "{{`The configuration of the instances of the Alertmanager cluster {{$labels.service}} are out of sync.`}}"
summary: Alertmanager configurations are inconsistent summary: Alertmanager configurations are inconsistent
- alert: AlertmanagerDownOrMissing - alert: AlertmanagerDownOrMissing
expr: label_replace(prometheus_operator_alertmanager_spec_replicas, "job", "alertmanager-$1", "alertmanager", "(.*)") / ON(job) GROUP_RIGHT() sum(up) BY (job) != 1 expr: label_replace(prometheus_operator_alertmanager_spec_replicas, "job", "alertmanager-$1", "alertmanager", "(.*)") / ON(job) GROUP_RIGHT() sum(up) BY (job) != 1
@ -20,7 +20,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: An unexpected number of Alertmanagers are scraped or Alertmanagers disappeared from discovery. description: "{{`An unexpected number of Alertmanagers are scraped or Alertmanagers disappeared from discovery.`}}"
summary: Alertmanager down or not discovered summary: Alertmanager down or not discovered
- alert: FailedReload - alert: FailedReload
expr: alertmanager_config_last_reload_successful == 0 expr: alertmanager_config_last_reload_successful == 0
@ -28,6 +28,6 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Reloading Alertmanager's configuration has failed for {{ $labels.namespace }}/{{ $labels.pod }}. description: "{{`Reloading Alertmanager's configuration has failed for {{ $labels.namespace }}/{{ $labels.pod }}.`}}"
summary: Alertmanager configuration reload has failed summary: Alertmanager configuration reload has failed
... ...

32
prometheus/values_overrides/ceph.yaml
View File

@ -29,56 +29,56 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'no ceph active mgr is present or all ceph mgr are down' description: "{{`no ceph active mgr is present or all ceph mgr are down`}}"
summary: 'no ceph active mgt is present' summary: "{{`no ceph active mgt is present`}}"
- alert: ceph_monitor_quorum_low - alert: ceph_monitor_quorum_low
expr: ceph_mon_quorum_count < 3 expr: ceph_mon_quorum_count < 3
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'ceph monitor quorum has been less than 3 for more than 5 minutes' description: "{{`ceph monitor quorum has been less than 3 for more than 5 minutes`}}"
summary: 'ceph high availability is at risk' summary: "{{`ceph high availability is at risk`}}"
- alert: ceph_monitor_quorum_absent - alert: ceph_monitor_quorum_absent
expr: absent(avg_over_time(ceph_mon_quorum_status[5m])) expr: absent(avg_over_time(ceph_mon_quorum_status[5m]))
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'ceph monitor quorum has been gone for more than 5 minutes' description: "{{`ceph monitor quorum has been gone for more than 5 minutes`}}"
summary: 'ceph high availability is at risk' summary: "{{`ceph high availability is at risk`}}"
- alert: ceph_cluster_usage_high - alert: ceph_cluster_usage_high
expr: avg_over_time(ceph_cluster_usage_percent[5m]) > 80 expr: avg_over_time(ceph_cluster_usage_percent[5m]) > 80
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'ceph cluster capacity usage more than 80 percent' description: "{{`ceph cluster capacity usage more than 80 percent`}}"
summary: 'ceph cluster usage is more than 80 percent' summary: "{{`ceph cluster usage is more than 80 percent`}}"
- alert: ceph_placement_group_degrade_pct_high - alert: ceph_placement_group_degrade_pct_high
expr: avg_over_time(ceph_placement_group_degrade_percent[5m]) > 80 expr: avg_over_time(ceph_placement_group_degrade_percent[5m]) > 80
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: 'ceph placement group degradation is more than 80 percent' description: "{{`ceph placement group degradation is more than 80 percent`}}"
summary: 'ceph placement groups degraded' summary: "{{`ceph placement groups degraded`}}"
- alert: ceph_osd_down_pct_high - alert: ceph_osd_down_pct_high
expr: avg_over_time(ceph_osd_down_percent[5m]) > 80 expr: avg_over_time(ceph_osd_down_percent[5m]) > 80
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: 'ceph OSDs down percent is more than 80 percent' description: "{{`ceph OSDs down percent is more than 80 percent`}}"
summary: 'ceph OSDs down percent is high' summary: "{{`ceph OSDs down percent is high`}}"
- alert: ceph_osd_down - alert: ceph_osd_down
expr: avg_over_time(ceph_osd_up[5m]) == 0 expr: avg_over_time(ceph_osd_up[5m]) == 0
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: 'ceph OSD {{ $labels.ceph_daemon }} is down in instance {{ $labels.instance }}.' description: "{{`ceph OSD {{ $labels.ceph_daemon }} is down in instance {{ $labels.instance }}.`}}"
summary: 'ceph OSD {{ $labels.ceph_daemon }} is down in instance {{ $labels.instance }}.' summary: "{{`ceph OSD {{ $labels.ceph_daemon }} is down in instance {{ $labels.instance }}.`}}"
- alert: ceph_osd_out - alert: ceph_osd_out
expr: avg_over_time(ceph_osd_in[5m]) == 0 expr: avg_over_time(ceph_osd_in[5m]) == 0
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'ceph OSD {{ $labels.ceph_daemon }} is out in instance {{ $labels.instance }}.' description: "{{`ceph OSD {{ $labels.ceph_daemon }} is out in instance {{ $labels.instance }}.`}}"
summary: 'ceph OSD {{ $labels.ceph_daemon }} is out in instance {{ $labels.instance }}.' summary: "{{`ceph OSD {{ $labels.ceph_daemon }} is out in instance {{ $labels.instance }}.`}}"
... ...

36
prometheus/values_overrides/elasticsearch.yaml
View File

@ -20,72 +20,72 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Elasticsearch at {{ $labels.host }} has more than 64000 process open file count.' description: "{{`Elasticsearch at {{ $labels.host }} has more than 64000 process open file count.`}}"
summary: 'Elasticsearch has a very high process open file count.' summary: Elasticsearch has a very high process open file count.
- alert: es_high_process_cpu_percent - alert: es_high_process_cpu_percent
expr: elasticsearch_process_cpu_percent > 95 expr: elasticsearch_process_cpu_percent > 95
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Elasticsearch at {{ $labels.instance }} has high process cpu percent of {{ $value }}.' description: "{{`Elasticsearch at {{ $labels.instance }} has high process cpu percent of {{ $value }}.`}}"
summary: 'Elasticsearch process cpu usage is more than 95 percent.' summary: Elasticsearch process cpu usage is more than 95 percent.
- alert: es_fs_usage_high - alert: es_fs_usage_high
expr: (100 * (elasticsearch_filesystem_data_size_bytes - elasticsearch_filesystem_data_free_bytes) / elasticsearch_filesystem_data_size_bytes) > 80 expr: (100 * (elasticsearch_filesystem_data_size_bytes - elasticsearch_filesystem_data_free_bytes) / elasticsearch_filesystem_data_size_bytes) > 80
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Elasticsearch at {{ $labels.instance }} has filesystem usage of {{ $value }}.' description: "{{`Elasticsearch at {{ $labels.instance }} has filesystem usage of {{ $value }}.`}}"
summary: 'Elasticsearch filesystem usage is high.' summary: Elasticsearch filesystem usage is high.
- alert: es_unassigned_shards - alert: es_unassigned_shards
expr: elasticsearch_cluster_health_unassigned_shards > 0 expr: elasticsearch_cluster_health_unassigned_shards > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Elasticsearch has {{ $value }} unassigned shards.' description: "{{`Elasticsearch has {{ $value }} unassigned shards.`}}"
summary: 'Elasticsearch has unassigned shards and hence a unhealthy cluster state.' summary: Elasticsearch has unassigned shards and hence a unhealthy cluster state.
- alert: es_cluster_health_timed_out - alert: es_cluster_health_timed_out
expr: elasticsearch_cluster_health_timed_out > 0 expr: elasticsearch_cluster_health_timed_out > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Elasticsearch cluster health status call timedout {{ $value }} times.' description: "{{`Elasticsearch cluster health status call timedout {{ $value }} times.`}}"
summary: 'Elasticsearch cluster health status calls are timing out.' summary: Elasticsearch cluster health status calls are timing out.
- alert: es_cluster_health_status_alert - alert: es_cluster_health_status_alert
expr: (sum(elasticsearch_cluster_health_status{color="green"})*2)+sum(elasticsearch_cluster_health_status{color="yellow"}) < 2 expr: (sum(elasticsearch_cluster_health_status{color="green"})*2)+sum(elasticsearch_cluster_health_status{color="yellow"}) < 2
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Elasticsearch cluster health status is {{ $value }}, not 2 (green). One or more shards or replicas are unallocated.' description: "{{`Elasticsearch cluster health status is {{ $value }}, not 2 (green). One or more shards or replicas are unallocated.`}}"
summary: 'Elasticsearch cluster health status is not green.' summary: Elasticsearch cluster health status is not green.
- alert: es_cluster_health_too_few_nodes_running - alert: es_cluster_health_too_few_nodes_running
expr: elasticsearch_cluster_health_number_of_nodes < 3 expr: elasticsearch_cluster_health_number_of_nodes < 3
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'There are only {{$value}} < 3 ElasticSearch nodes running' description: "{{`There are only {{$value}} < 3 ElasticSearch nodes running`}}"
summary: 'ElasticSearch running on less than 3 nodes' summary: ElasticSearch running on less than 3 nodes
- alert: es_cluster_health_too_few_data_nodes_running - alert: es_cluster_health_too_few_data_nodes_running
expr: elasticsearch_cluster_health_number_of_data_nodes < 3 expr: elasticsearch_cluster_health_number_of_data_nodes < 3
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'There are only {{$value}} < 3 ElasticSearch data nodes running' description: "{{`There are only {{$value}} < 3 ElasticSearch data nodes running`}}"
summary: 'ElasticSearch running on less than 3 data nodes' summary: ElasticSearch running on less than 3 data nodes
- alert: es_cluster_health_too_few_data_nodes_running - alert: es_cluster_health_too_few_data_nodes_running
expr: elasticsearch_cluster_health_number_of_data_nodes < 3 expr: elasticsearch_cluster_health_number_of_data_nodes < 3
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'There are only {{$value}} < 3 ElasticSearch data nodes running' description: "{{`There are only {{$value}} < 3 ElasticSearch data nodes running`}}"
summary: 'ElasticSearch running on less than 3 data nodes' summary: ElasticSearch running on less than 3 data nodes
fluentd: fluentd:
groups: groups:
- name: fluentd.alerting_rules - name: fluentd.alerting_rules

126
prometheus/values_overrides/kubernetes.yaml
View File

@ -19,45 +19,45 @@ conf:
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Felix instance {{ $labels.instance }} has seen {{ $value }} dataplane failures within the last hour' description: "{{`Felix instance {{ $labels.instance }} has seen {{ $value }} dataplane failures within the last hour`}}"
summary: 'A high number of dataplane failures within Felix are happening' summary: A high number of dataplane failures within Felix are happening
- alert: calico_datapane_address_msg_batch_size_high_5m - alert: calico_datapane_address_msg_batch_size_high_5m
expr: absent(felix_int_dataplane_addr_msg_batch_size_sum) OR absent(felix_int_dataplane_addr_msg_batch_size_count) OR (felix_int_dataplane_addr_msg_batch_size_sum/felix_int_dataplane_addr_msg_batch_size_count) > 5 expr: absent(felix_int_dataplane_addr_msg_batch_size_sum) OR absent(felix_int_dataplane_addr_msg_batch_size_count) OR (felix_int_dataplane_addr_msg_batch_size_sum/felix_int_dataplane_addr_msg_batch_size_count) > 5
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Felix instance {{ $labels.instance }} has seen a high value of {{ $value }} dataplane address message batch size' description: "{{`Felix instance {{ $labels.instance }} has seen a high value of {{ $value }} dataplane address message batch size`}}"
summary: 'Felix address message batch size is higher' summary: Felix address message batch size is higher
- alert: calico_datapane_iface_msg_batch_size_high_5m - alert: calico_datapane_iface_msg_batch_size_high_5m
expr: absent(felix_int_dataplane_iface_msg_batch_size_sum) OR absent(felix_int_dataplane_iface_msg_batch_size_count) OR (felix_int_dataplane_iface_msg_batch_size_sum/felix_int_dataplane_iface_msg_batch_size_count) > 5 expr: absent(felix_int_dataplane_iface_msg_batch_size_sum) OR absent(felix_int_dataplane_iface_msg_batch_size_count) OR (felix_int_dataplane_iface_msg_batch_size_sum/felix_int_dataplane_iface_msg_batch_size_count) > 5
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Felix instance {{ $labels.instance }} has seen a high value of {{ $value }} dataplane interface message batch size' description: "{{`Felix instance {{ $labels.instance }} has seen a high value of {{ $value }} dataplane interface message batch size`}}"
summary: 'Felix interface message batch size is higher' summary: Felix interface message batch size is higher
- alert: calico_ipset_errors_high_1h - alert: calico_ipset_errors_high_1h
expr: absent(felix_ipset_errors) OR increase(felix_ipset_errors[1h]) > 5 expr: absent(felix_ipset_errors) OR increase(felix_ipset_errors[1h]) > 5
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Felix instance {{ $labels.instance }} has seen {{ $value }} ipset errors within the last hour' description: "{{`Felix instance {{ $labels.instance }} has seen {{ $value }} ipset errors within the last hour`}}"
summary: 'A high number of ipset errors within Felix are happening' summary: A high number of ipset errors within Felix are happening
- alert: calico_iptable_save_errors_high_1h - alert: calico_iptable_save_errors_high_1h
expr: absent(felix_iptables_save_errors) OR increase(felix_iptables_save_errors[1h]) > 5 expr: absent(felix_iptables_save_errors) OR increase(felix_iptables_save_errors[1h]) > 5
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Felix instance {{ $labels.instance }} has seen {{ $value }} iptable save errors within the last hour' description: "{{`Felix instance {{ $labels.instance }} has seen {{ $value }} iptable save errors within the last hour`}}"
summary: 'A high number of iptable save errors within Felix are happening' summary: A high number of iptable save errors within Felix are happening
- alert: calico_iptable_restore_errors_high_1h - alert: calico_iptable_restore_errors_high_1h
expr: absent(felix_iptables_restore_errors) OR increase(felix_iptables_restore_errors[1h]) > 5 expr: absent(felix_iptables_restore_errors) OR increase(felix_iptables_restore_errors[1h]) > 5
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Felix instance {{ $labels.instance }} has seen {{ $value }} iptable restore errors within the last hour' description: "{{`Felix instance {{ $labels.instance }} has seen {{ $value }} iptable restore errors within the last hour`}}"
summary: 'A high number of iptable restore errors within Felix are happening' summary: A high number of iptable restore errors within Felix are happening
- name: etcd3.rules - name: etcd3.rules
rules: rules:
- alert: etcd_InsufficientMembers - alert: etcd_InsufficientMembers
@ -74,14 +74,14 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: etcd member {{ $labels.instance }} has no leader description: "{{`etcd member {{ $labels.instance }} has no leader`}}"
summary: etcd member has no leader summary: etcd member has no leader
- alert: etcd_HighNumberOfLeaderChanges - alert: etcd_HighNumberOfLeaderChanges
expr: increase(etcd_server_leader_changes_seen_total{job="etcd"}[1h]) > 3 expr: increase(etcd_server_leader_changes_seen_total{job="etcd"}[1h]) > 3
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: etcd instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last hour description: "{{`etcd instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last hour`}}"
summary: a high number of leader changes within the etcd cluster are happening summary: a high number of leader changes within the etcd cluster are happening
- alert: etcd_HighNumberOfFailedGRPCRequests - alert: etcd_HighNumberOfFailedGRPCRequests
expr: sum(rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) BY (grpc_method) / sum(rate(etcd_grpc_total{job="etcd"}[5m])) BY (grpc_method) > 0.01 expr: sum(rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) BY (grpc_method) / sum(rate(etcd_grpc_total{job="etcd"}[5m])) BY (grpc_method) > 0.01
@ -89,7 +89,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}' description: "{{`{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}`}}"
summary: a high number of gRPC requests are failing summary: a high number of gRPC requests are failing
- alert: etcd_HighNumberOfFailedGRPCRequests - alert: etcd_HighNumberOfFailedGRPCRequests
expr: sum(rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) BY (grpc_method) / sum(rate(etcd_grpc_total{job="etcd"}[5m])) BY (grpc_method) > 0.05 expr: sum(rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) BY (grpc_method) / sum(rate(etcd_grpc_total{job="etcd"}[5m])) BY (grpc_method) > 0.05
@ -97,7 +97,7 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}' description: "{{`{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}`}}"
summary: a high number of gRPC requests are failing summary: a high number of gRPC requests are failing
- alert: etcd_GRPCRequestsSlow - alert: etcd_GRPCRequestsSlow
expr: histogram_quantile(0.99, rate(etcd_grpc_unary_requests_duration_seconds_bucket[5m])) > 0.15 expr: histogram_quantile(0.99, rate(etcd_grpc_unary_requests_duration_seconds_bucket[5m])) > 0.15
@ -105,7 +105,7 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: on etcd instance {{ $labels.instance }} gRPC requests to {{ $labels.grpc_method }} are slow description: "{{`on etcd instance {{ $labels.instance }} gRPC requests to {{ $labels.grpc_method }} are slow`}}"
summary: slow gRPC requests summary: slow gRPC requests
- alert: etcd_HighNumberOfFailedHTTPRequests - alert: etcd_HighNumberOfFailedHTTPRequests
expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) BY (method) > 0.01 expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) BY (method) > 0.01
@ -113,7 +113,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}' description: "{{`{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}`}}"
summary: a high number of HTTP requests are failing summary: a high number of HTTP requests are failing
- alert: etcd_HighNumberOfFailedHTTPRequests - alert: etcd_HighNumberOfFailedHTTPRequests
expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) BY (method) > 0.05 expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) BY (method) > 0.05
@ -121,7 +121,7 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}' description: "{{`{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}`}}"
summary: a high number of HTTP requests are failing summary: a high number of HTTP requests are failing
- alert: etcd_HTTPRequestsSlow - alert: etcd_HTTPRequestsSlow
expr: histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) > 0.15 expr: histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) > 0.15
@ -129,7 +129,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: on etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow description: "{{`on etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow`}}"
summary: slow HTTP requests summary: slow HTTP requests
- alert: etcd_EtcdMemberCommunicationSlow - alert: etcd_EtcdMemberCommunicationSlow
expr: histogram_quantile(0.99, rate(etcd_network_member_round_trip_time_seconds_bucket[5m])) > 0.15 expr: histogram_quantile(0.99, rate(etcd_network_member_round_trip_time_seconds_bucket[5m])) > 0.15
@ -137,14 +137,14 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: etcd instance {{ $labels.instance }} member communication with {{ $labels.To }} is slow description: "{{`etcd instance {{ $labels.instance }} member communication with {{ $labels.To }} is slow`}}"
summary: etcd member communication is slow summary: etcd member communication is slow
- alert: etcd_HighNumberOfFailedProposals - alert: etcd_HighNumberOfFailedProposals
expr: increase(etcd_server_proposals_failed_total{job="etcd"}[1h]) > 5 expr: increase(etcd_server_proposals_failed_total{job="etcd"}[1h]) > 5
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: etcd instance {{ $labels.instance }} has seen {{ $value }} proposal failures within the last hour description: "{{`etcd instance {{ $labels.instance }} has seen {{ $value }} proposal failures within the last hour`}}"
summary: a high number of proposals within the etcd cluster are failing summary: a high number of proposals within the etcd cluster are failing
- alert: etcd_HighFsyncDurations - alert: etcd_HighFsyncDurations
expr: histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) > 0.5 expr: histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) > 0.5
@ -152,7 +152,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: etcd instance {{ $labels.instance }} fync durations are high description: "{{`etcd instance {{ $labels.instance }} fync durations are high`}}"
summary: high fsync durations summary: high fsync durations
- alert: etcd_HighCommitDurations - alert: etcd_HighCommitDurations
expr: histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) > 0.25 expr: histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) > 0.25
@ -160,7 +160,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: etcd instance {{ $labels.instance }} commit durations are high description: "{{`etcd instance {{ $labels.instance }} commit durations are high`}}"
summary: high commit durations summary: high commit durations
- name: kubelet.rules - name: kubelet.rules
rules: rules:
@ -170,15 +170,15 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: The Kubelet on {{ $labels.node }} has not checked in with the API, or has set itself to NotReady, for more than a minute description: "{{`The Kubelet on {{ $labels.node }} has not checked in with the API, or has set itself to NotReady, for more than a minute`}}"
summary: '{{ $labels.node }} Node status is NotReady and {{ $labels.status }}' summary: "{{`{{ $labels.node }} Node status is NotReady and {{ $labels.status }}`}}"
- alert: K8SManyNodesNotReady - alert: K8SManyNodesNotReady
expr: count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) > 1 and (count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) / count(kube_node_status_condition{condition="Ready", status="unknown"})) > 0.2 expr: count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) > 1 and (count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) / count(kube_node_status_condition{condition="Ready", status="unknown"})) > 0.2
for: 1m for: 1m
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: '{{ $value }} Kubernetes nodes (more than 10% are in the NotReady state).' description: "{{`{{ $value }} Kubernetes nodes (more than 10% are in the NotReady state).`}}"
summary: Many Kubernetes nodes are Not Ready summary: Many Kubernetes nodes are Not Ready
- alert: K8SManyNodesNotReady - alert: K8SManyNodesNotReady
expr: count(kube_node_status_condition{condition="Ready", status="false"} == 1) > 1 and (count(kube_node_status_condition{condition="Ready", status="false"} == 1) / count(kube_node_status_condition{condition="Ready", status="false"})) > 0.2 expr: count(kube_node_status_condition{condition="Ready", status="false"} == 1) > 1 and (count(kube_node_status_condition{condition="Ready", status="false"} == 1) / count(kube_node_status_condition{condition="Ready", status="false"})) > 0.2
@ -186,7 +186,7 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: '{{ $value }} Kubernetes nodes (more than 10% are in the NotReady state).' description: "{{`{{ $value }} Kubernetes nodes (more than 10% are in the NotReady state).`}}"
summary: Many Kubernetes nodes are Not Ready summary: Many Kubernetes nodes are Not Ready
- alert: K8SNodesNotReady - alert: K8SNodesNotReady
expr: count(kube_node_status_condition{condition="Ready", status="false"} == 1) > 0 or count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) > 0 expr: count(kube_node_status_condition{condition="Ready", status="false"} == 1) > 0 or count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) > 0
@ -194,7 +194,7 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: '{{ $value }} nodes are notReady state.' description: "{{`{{ $value }} nodes are notReady state.`}}"
summary: One or more Kubernetes nodes are Not Ready summary: One or more Kubernetes nodes are Not Ready
- alert: K8SKubeletDown - alert: K8SKubeletDown
expr: count(up{job="kubelet"} == 0) / count(up{job="kubelet"}) > 0.03 expr: count(up{job="kubelet"} == 0) / count(up{job="kubelet"}) > 0.03
@ -202,7 +202,7 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: Prometheus failed to scrape {{ $value }}% of kubelets. description: "{{`Prometheus failed to scrape {{ $value }}% of kubelets.`}}"
summary: Many Kubelets cannot be scraped summary: Many Kubelets cannot be scraped
- alert: K8SKubeletDown - alert: K8SKubeletDown
expr: absent(up{job="kubelet"} == 1) or count(up{job="kubelet"} == 0) / count(up{job="kubelet"}) > 0.1 expr: absent(up{job="kubelet"} == 1) or count(up{job="kubelet"} == 0) / count(up{job="kubelet"}) > 0.1
@ -210,14 +210,14 @@ conf:
labels: labels:
severity: critical severity: critical
annotations: annotations:
description: Prometheus failed to scrape {{ $value }}% of kubelets, or all Kubelets have disappeared from service discovery. description: "{{`Prometheus failed to scrape {{ $value }}% of kubelets, or all Kubelets have disappeared from service discovery.`}}"
summary: Many Kubelets cannot be scraped summary: Many Kubelets cannot be scraped
- alert: K8SKubeletTooManyPods - alert: K8SKubeletTooManyPods
expr: kubelet_running_pod_count > 100 expr: kubelet_running_pod_count > 100
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Kubelet {{$labels.instance}} is running {{$value}} pods, close to the limit of 110 description: "{{`Kubelet {{$labels.instance}} is running {{$value}} pods, close to the limit of 110`}}"
summary: Kubelet is close to pod limit summary: Kubelet is close to pod limit
- name: kube-apiserver.rules - name: kube-apiserver.rules
rules: rules:
@ -235,7 +235,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 99th percentile Latency for {{ $labels.verb }} requests to the kube-apiserver is higher than 1s. description: "{{`99th percentile Latency for {{ $labels.verb }} requests to the kube-apiserver is higher than 1s.`}}"
summary: Kubernetes apiserver latency is high summary: Kubernetes apiserver latency is high
- name: kube-controller-manager.rules - name: kube-controller-manager.rules
rules: rules:
@ -264,118 +264,118 @@ conf:
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'statefulset {{$labels.statefulset}} has {{$value}} replicas, which is less than desired' description: "{{`statefulset {{$labels.statefulset}} has {{$value}} replicas, which is less than desired`}}"
summary: '{{$labels.statefulset}}: has inssuficient replicas.' summary: "{{`{{$labels.statefulset}}: has inssuficient replicas.`}}"
- alert: daemonsets_misscheduled - alert: daemonsets_misscheduled
expr: kube_daemonset_status_number_misscheduled > 0 expr: kube_daemonset_status_number_misscheduled > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Daemonset {{$labels.daemonset}} is running where it is not supposed to run' description: "{{`Daemonset {{$labels.daemonset}} is running where it is not supposed to run`}}"
summary: 'Daemonsets not scheduled correctly' summary: Daemonsets not scheduled correctly
- alert: daemonsets_not_scheduled - alert: daemonsets_not_scheduled
expr: kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled > 0 expr: kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: '{{ $value }} of Daemonset {{$labels.daemonset}} scheduled which is less than desired number' description: "{{`{{ $value }} of Daemonset {{$labels.daemonset}} scheduled which is less than desired number`}}"
summary: 'Less than desired number of daemonsets scheduled' summary: Less than desired number of daemonsets scheduled
- alert: daemonset_pods_unavailable - alert: daemonset_pods_unavailable
expr: kube_daemonset_status_number_unavailable > 0 expr: kube_daemonset_status_number_unavailable > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Daemonset {{$labels.daemonset}} currently has pods unavailable' description: "{{`Daemonset {{$labels.daemonset}} currently has pods unavailable`}}"
summary: 'Daemonset pods unavailable, due to one of many reasons' summary: Daemonset pods unavailable, due to one of many reasons
- alert: deployment_replicas_unavailable - alert: deployment_replicas_unavailable
expr: kube_deployment_status_replicas_unavailable > 0 expr: kube_deployment_status_replicas_unavailable > 0
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'deployment {{$labels.deployment}} has {{$value}} replicas unavailable' description: "{{`deployment {{$labels.deployment}} has {{$value}} replicas unavailable`}}"
summary: '{{$labels.deployment}}: has inssuficient replicas.' summary: "{{`{{$labels.deployment}}: has inssuficient replicas.`}}"
- alert: rollingupdate_deployment_replica_less_than_spec_max_unavailable - alert: rollingupdate_deployment_replica_less_than_spec_max_unavailable
expr: kube_deployment_status_replicas_available - kube_deployment_spec_strategy_rollingupdate_max_unavailable < 0 expr: kube_deployment_status_replicas_available - kube_deployment_spec_strategy_rollingupdate_max_unavailable < 0
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'deployment {{$labels.deployment}} has {{$value}} replicas available which is less than specified as max unavailable during a rolling update' description: "{{`deployment {{$labels.deployment}} has {{$value}} replicas available which is less than specified as max unavailable during a rolling update`}}"
summary: '{{$labels.deployment}}: has inssuficient replicas during a rolling update.' summary: "{{`{{$labels.deployment}}: has inssuficient replicas during a rolling update.`}}"
- alert: job_status_failed - alert: job_status_failed
expr: kube_job_status_failed > 0 expr: kube_job_status_failed > 0
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Job {{$labels.exported_job}} is in failed status' description: "{{`Job {{$labels.exported_job}} is in failed status`}}"
summary: '{{$labels.exported_job}} has failed status' summary: "{{`{{$labels.exported_job}} has failed status`}}"
- alert: pod_status_pending - alert: pod_status_pending
expr: kube_pod_status_phase{phase="Pending"} == 1 expr: kube_pod_status_phase{phase="Pending"} == 1
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} has been in pending status for more than 10 minutes' description: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} has been in pending status for more than 10 minutes`}}"
summary: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} in pending status' summary: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} in pending status`}}"
- alert: pod_status_error_image_pull - alert: pod_status_error_image_pull
expr: kube_pod_container_status_waiting_reason {reason="ErrImagePull"} == 1 expr: kube_pod_container_status_waiting_reason {reason="ErrImagePull"} == 1
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} has an Image pull error for more than 10 minutes' description: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} has an Image pull error for more than 10 minutes`}}"
summary: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status' summary: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status`}}"
- alert: pod_status_error_image_pull_backoff - alert: pod_status_error_image_pull_backoff
expr: kube_pod_container_status_waiting_reason {reason="ImagePullBackOff"} == 1 expr: kube_pod_container_status_waiting_reason {reason="ImagePullBackOff"} == 1
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} has an ImagePullBackOff error for more than 10 minutes' description: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} has an ImagePullBackOff error for more than 10 minutes`}}"
summary: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status' summary: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status`}}"
- alert: pod_error_crash_loop_back_off - alert: pod_error_crash_loop_back_off
expr: kube_pod_container_status_waiting_reason {reason="CrashLoopBackOff"} == 1 expr: kube_pod_container_status_waiting_reason {reason="CrashLoopBackOff"} == 1
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} has an CrashLoopBackOff error for more than 10 minutes' description: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} has an CrashLoopBackOff error for more than 10 minutes`}}"
summary: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status' summary: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status`}}"
- alert: pod_error_config_error - alert: pod_error_config_error
expr: kube_pod_container_status_waiting_reason {reason="CreateContainerConfigError"} == 1 expr: kube_pod_container_status_waiting_reason {reason="CreateContainerConfigError"} == 1
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} has a CreateContainerConfigError error for more than 10 minutes' description: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} has a CreateContainerConfigError error for more than 10 minutes`}}"
summary: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status' summary: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status`}}"
- alert: replicaset_missing_replicas - alert: replicaset_missing_replicas
expr: kube_replicaset_spec_replicas - kube_replicaset_status_ready_replicas > 0 expr: kube_replicaset_spec_replicas - kube_replicaset_status_ready_replicas > 0
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Replicaset {{$labels.replicaset}} is missing desired number of replicas for more than 10 minutes' description: "{{`Replicaset {{$labels.replicaset}} is missing desired number of replicas for more than 10 minutes`}}"
summary: 'Replicaset {{$labels.replicaset}} is missing replicas' summary: "{{`Replicaset {{$labels.replicaset}} is missing replicas`}}"
- alert: pod_container_terminated - alert: pod_container_terminated
expr: kube_pod_container_status_terminated_reason{reason=~"OOMKilled|Error|ContainerCannotRun"} > 0 expr: kube_pod_container_status_terminated_reason{reason=~"OOMKilled|Error|ContainerCannotRun"} > 0
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} has a container terminated for more than 10 minutes' description: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} has a container terminated for more than 10 minutes`}}"
summary: 'Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status' summary: "{{`Pod {{$labels.pod}} in namespace {{$labels.namespace}} in error status`}}"
- alert: volume_claim_capacity_high_utilization - alert: volume_claim_capacity_high_utilization
expr: 100 * kubelet_volume_stats_used_bytes / kubelet_volume_stats_capacity_bytes > 80 expr: 100 * kubelet_volume_stats_used_bytes / kubelet_volume_stats_capacity_bytes > 80
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'volume claim {{$labels.persistentvolumeclaim}} usage has exceeded 80% of total capacity' description: "{{`volume claim {{$labels.persistentvolumeclaim}} usage has exceeded 80% of total capacity`}}"
summary: '{{$labels.persistentvolumeclaim}} usage has exceeded 80% of total capacity.' summary: "{{`{{$labels.persistentvolumeclaim}} usage has exceeded 80% of total capacity.`}}"
... ...

105
prometheus/values_overrides/nodes.yaml
View File

@ -28,80 +28,71 @@ conf:
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} device {{$labels.device}} on {{$labels.mountpoint}} description: "{{`{{$labels.alias}} device {{$labels.device}} on {{$labels.mountpoint}} has less than 20% free space left.`}}"
has less than 20% free space left.' summary: "{{`{{$labels.alias}}: Filesystem is running out of space soon.`}}"
summary: '{{$labels.alias}}: Filesystem is running out of space soon.'
- alert: node_filesystem_full_in_4h - alert: node_filesystem_full_in_4h
expr: predict_linear(node_filesystem_free{fstype =~ "xfs|ext[34]"}[1h], 4 * 3600) <= 0 expr: predict_linear(node_filesystem_free{fstype =~ "xfs|ext[34]"}[1h], 4 * 3600) <= 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} device {{$labels.device}} on {{$labels.mountpoint}} description: "{{`{{$labels.alias}} device {{$labels.device}} on {{$labels.mountpoint}} is running out of space of in approx. 4 hours`}}"
is running out of space of in approx. 4 hours' summary: "{{`{{$labels.alias}}: Filesystem is running out of space in 4 hours.`}}"
summary: '{{$labels.alias}}: Filesystem is running out of space in 4 hours.'
- alert: node_filedescriptors_full_in_3h - alert: node_filedescriptors_full_in_3h
expr: predict_linear(node_filefd_allocated[1h], 3 * 3600) >= node_filefd_maximum expr: predict_linear(node_filefd_allocated[1h], 3 * 3600) >= node_filefd_maximum
for: 20m for: 20m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} is running out of available file descriptors description: "{{`{{$labels.alias}} is running out of available file descriptors in approx. 3 hours`}}"
in approx. 3 hours' summary: "{{`{{$labels.alias}} is running out of available file descriptors in 3 hours.`}}"
summary: '{{$labels.alias}} is running out of available file descriptors in
3 hours.'
- alert: node_load1_90percent - alert: node_load1_90percent
expr: node_load1 / ON(alias) count(node_cpu{mode="system"}) BY (alias) >= 0.9 expr: node_load1 / ON(alias) count(node_cpu{mode="system"}) BY (alias) >= 0.9
for: 1h for: 1h
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} is running with > 90% total load for at least description: "{{`{{$labels.alias}} is running with > 90% total load for at least 1h.`}}"
1h.' summary: "{{`{{$labels.alias}}: Running on high load.`}}"
summary: '{{$labels.alias}}: Running on high load.'
- alert: node_cpu_util_90percent - alert: node_cpu_util_90percent
expr: 100 - (avg(irate(node_cpu{mode="idle"}[5m])) BY (alias) * 100) >= 90 expr: 100 - (avg(irate(node_cpu{mode="idle"}[5m])) BY (alias) * 100) >= 90
for: 1h for: 1h
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} has total CPU utilization over 90% for at least description: "{{`{{$labels.alias}} has total CPU utilization over 90% for at least 1h.`}}"
1h.' summary: "{{`{{$labels.alias}}: High CPU utilization.`}}"
summary: '{{$labels.alias}}: High CPU utilization.'
- alert: node_ram_using_90percent - alert: node_ram_using_90percent
expr: avg_over_time(node_ram_usage_percent[2m]) > 90 expr: avg_over_time(node_ram_usage_percent[2m]) > 90
for: 30m for: 30m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} is using at least 90% of its RAM for at least description: "{{`{{$labels.alias}} is using at least 90% of its RAM for at least 30 minutes now.`}}"
30 minutes now.' summary: "{{`{{$labels.alias}}: Using lots of RAM.`}}"
summary: '{{$labels.alias}}: Using lots of RAM.'
- alert: node_swap_using_80percent - alert: node_swap_using_80percent
expr: avg_over_time(node_swap_usage_percent[2m]) > 80 expr: avg_over_time(node_swap_usage_percent[2m]) > 80
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} is using 80% of its swap space for at least description: "{{`{{$labels.alias}} is using 80% of its swap space for at least 10 minutes now.`}}"
10 minutes now.' summary: "{{`{{$labels.alias}}: Running out of swap soon.`}}"
summary: '{{$labels.alias}}: Running out of swap soon.'
- alert: node_high_cpu_load - alert: node_high_cpu_load
expr: node_load15 / on(alias) count(node_cpu{mode="system"}) by (alias) >= 0 expr: node_load15 / on(alias) count(node_cpu{mode="system"}) by (alias) >= 0
for: 1m for: 1m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: '{{$labels.alias}} is running with load15 > 1 for at least 5 minutes: {{$value}}' description: "{{`{{$labels.alias}} is running with load15 > 1 for at least 5 minutes: {{$value}}`}}"
summary: '{{$labels.alias}}: Running on high load: {{$value}}' summary: "{{`{{$labels.alias}}: Running on high load: {{$value}}`}}"
- alert: node_high_memory_load - alert: node_high_memory_load
expr: avg_over_time(node_ram_usage_percent[2m]) > 85 expr: avg_over_time(node_ram_usage_percent[2m]) > 85
for: 1m for: 1m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Host memory usage is {{ humanize $value }}%. Reported by description: "{{`Host memory usage is {{ humanize $value }}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}.`}}"
instance {{ $labels.instance }} of job {{ $labels.job }}.
summary: Server memory is almost full summary: Server memory is almost full
- alert: node_high_storage_load - alert: node_high_storage_load
expr: avg_over_time(node_storage_usage_percent{mountpoint="/"}[2m]) > 85 expr: avg_over_time(node_storage_usage_percent{mountpoint="/"}[2m]) > 85
@ -109,8 +100,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Host storage usage is {{ humanize $value }}%. Reported by description: "{{`Host storage usage is {{ humanize $value }}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}.`}}"
instance {{ $labels.instance }} of job {{ $labels.job }}.
summary: Server storage is almost full summary: Server storage is almost full
- alert: node_high_swap - alert: node_high_swap
expr: (node_memory_SwapTotal - node_memory_SwapFree) < (node_memory_SwapTotal expr: (node_memory_SwapTotal - node_memory_SwapFree) < (node_memory_SwapTotal
@ -119,8 +109,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Host system has a high swap usage of {{ humanize $value }}. Reported description: "{{`Host system has a high swap usage of {{ humanize $value }}. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}.`}}"
by instance {{ $labels.instance }} of job {{ $labels.job }}.
summary: Server has a high swap usage summary: Server has a high swap usage
- alert: node_high_network_drop_rcv - alert: node_high_network_drop_rcv
expr: node_network_receive_drop{device!="lo"} > 3000 expr: node_network_receive_drop{device!="lo"} > 3000
@ -128,9 +117,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Host system has an unusally high drop in network reception ({{ description: "{{`Host system has an unusally high drop in network reception ({{ humanize $value }}). Reported by instance {{ $labels.instance }} of job {{ $labels.job }}`}}"
humanize $value }}). Reported by instance {{ $labels.instance }} of job {{
$labels.job }}
summary: Server has a high receive drop summary: Server has a high receive drop
- alert: node_high_network_drop_send - alert: node_high_network_drop_send
expr: node_network_transmit_drop{device!="lo"} > 3000 expr: node_network_transmit_drop{device!="lo"} > 3000
@ -138,9 +125,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Host system has an unusally high drop in network transmission ({{ description: "{{`Host system has an unusally high drop in network transmission ({{ humanize $value }}). Reported by instance {{ $labels.instance }} of job {{$labels.job }}`}}"
humanize $value }}). Reported by instance {{ $labels.instance }} of job {{
$labels.job }}
summary: Server has a high transmit drop summary: Server has a high transmit drop
- alert: node_high_network_errs_rcv - alert: node_high_network_errs_rcv
expr: node_network_receive_errs{device!="lo"} > 3000 expr: node_network_receive_errs{device!="lo"} > 3000
@ -148,9 +133,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Host system has an unusally high error rate in network reception description: "{{`Host system has an unusally high error rate in network reception ({{ humanize $value }}). Reported by instance {{ $labels.instance }} of job {{ $labels.job }}`}}"
({{ humanize $value }}). Reported by instance {{ $labels.instance }} of job
{{ $labels.job }}
summary: Server has unusual high reception errors summary: Server has unusual high reception errors
- alert: node_high_network_errs_send - alert: node_high_network_errs_send
expr: node_network_transmit_errs{device!="lo"} > 3000 expr: node_network_transmit_errs{device!="lo"} > 3000
@ -158,9 +141,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Host system has an unusally high error rate in network transmission description: "{{`Host system has an unusally high error rate in network transmission ({{ humanize $value }}). Reported by instance {{ $labels.instance }} of job {{ $labels.job }}`}}"
({{ humanize $value }}). Reported by instance {{ $labels.instance }} of job
{{ $labels.job }}
summary: Server has unusual high transmission errors summary: Server has unusual high transmission errors
- alert: node_network_conntrack_usage_80percent - alert: node_network_conntrack_usage_80percent
expr: sort(node_nf_conntrack_entries{job="node-exporter"} > node_nf_conntrack_entries_limit{job="node-exporter"} * 0.8) expr: sort(node_nf_conntrack_entries{job="node-exporter"} > node_nf_conntrack_entries_limit{job="node-exporter"} * 0.8)
@ -168,78 +149,78 @@ conf:
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.instance}} has network conntrack entries of {{ $value }} which is more than 80% of maximum limit' description: "{{`{{$labels.instance}} has network conntrack entries of {{ $value }} which is more than 80% of maximum limit`}}"
summary: '{{$labels.instance}}: available network conntrack entries are low.' summary: "{{`{{$labels.instance}}: available network conntrack entries are low.`}}"
- alert: node_entropy_available_low - alert: node_entropy_available_low
expr: node_entropy_available_bits < 300 expr: node_entropy_available_bits < 300
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.instance}} has available entropy bits of {{ $value }} which is less than required of 300' description: "{{`{{$labels.instance}} has available entropy bits of {{ $value }} which is less than required of 300`}}"
summary: '{{$labels.instance}}: is low on entropy bits.' summary: "{{`{{$labels.instance}}: is low on entropy bits.`}}"
- alert: node_hwmon_high_cpu_temp - alert: node_hwmon_high_cpu_temp
expr: node_hwmon_temp_crit_celsius*0.9 - node_hwmon_temp_celsius < 0 OR node_hwmon_temp_max_celsius*0.95 - node_hwmon_temp_celsius < 0 expr: node_hwmon_temp_crit_celsius*0.9 - node_hwmon_temp_celsius < 0 OR node_hwmon_temp_max_celsius*0.95 - node_hwmon_temp_celsius < 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} reports hwmon sensor {{$labels.sensor}}/{{$labels.chip}} temperature value is nearly critical: {{$value}}' description: "{{`{{$labels.alias}} reports hwmon sensor {{$labels.sensor}}/{{$labels.chip}} temperature value is nearly critical: {{$value}}`}}"
summary: '{{$labels.alias}}: Sensor {{$labels.sensor}}/{{$labels.chip}} temp is high: {{$value}}' summary: "{{`{{$labels.alias}}: Sensor {{$labels.sensor}}/{{$labels.chip}} temp is high: {{$value}}`}}"
- alert: node_vmstat_paging_rate_high - alert: node_vmstat_paging_rate_high
expr: irate(node_vmstat_pgpgin[5m]) > 80 expr: irate(node_vmstat_pgpgin[5m]) > 80
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} has a memory paging rate of change higher than 80%: {{$value}}' description: "{{`{{$labels.alias}} has a memory paging rate of change higher than 80%: {{$value}}`}}"
summary: '{{$labels.alias}}: memory paging rate is high: {{$value}}' summary: "{{`{{$labels.alias}}: memory paging rate is high: {{$value}}`}}"
- alert: node_xfs_block_allocation_high - alert: node_xfs_block_allocation_high
expr: 100*(node_xfs_extent_allocation_blocks_allocated_total{job="node-exporter", instance=~"172.17.0.1.*"} / (node_xfs_extent_allocation_blocks_freed_total{job="node-exporter", instance=~"172.17.0.1.*"} + node_xfs_extent_allocation_blocks_allocated_total{job="node-exporter", instance=~"172.17.0.1.*"})) > 80 expr: 100*(node_xfs_extent_allocation_blocks_allocated_total{job="node-exporter", instance=~"172.17.0.1.*"} / (node_xfs_extent_allocation_blocks_freed_total{job="node-exporter", instance=~"172.17.0.1.*"} + node_xfs_extent_allocation_blocks_allocated_total{job="node-exporter", instance=~"172.17.0.1.*"})) > 80
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} has xfs allocation blocks higher than 80%: {{$value}}' description: "{{`{{$labels.alias}} has xfs allocation blocks higher than 80%: {{$value}}`}}"
summary: '{{$labels.alias}}: xfs block allocation high: {{$value}}' summary: "{{`{{$labels.alias}}: xfs block allocation high: {{$value}}`}}"
- alert: node_network_bond_slaves_down - alert: node_network_bond_slaves_down
expr: node_net_bonding_slaves - node_net_bonding_slaves_active > 0 expr: node_net_bonding_slaves - node_net_bonding_slaves_active > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{ $labels.master }} is missing {{ $value }} slave interface(s).' description: "{{`{{ $labels.master }} is missing {{ $value }} slave interface(s).`}}"
summary: 'Instance {{ $labels.instance }}: {{ $labels.master }} missing {{ $value }} slave interface(s)' summary: "{{`Instance {{ $labels.instance }}: {{ $labels.master }} missing {{ $value }} slave interface(s)`}}"
- alert: node_numa_memory_used - alert: node_numa_memory_used
expr: 100*node_memory_numa_MemUsed / node_memory_numa_MemTotal > 80 expr: 100*node_memory_numa_MemUsed / node_memory_numa_MemTotal > 80
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} has more than 80% NUMA memory usage: {{ $value }}' description: "{{`{{$labels.alias}} has more than 80% NUMA memory usage: {{ $value }}`}}"
summary: '{{$labels.alias}}: has high NUMA memory usage: {{$value}}' summary: "{{`{{$labels.alias}}: has high NUMA memory usage: {{$value}}`}}"
- alert: node_ntp_clock_skew_high - alert: node_ntp_clock_skew_high
expr: abs(node_ntp_drift_seconds) > 2 expr: abs(node_ntp_drift_seconds) > 2
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.alias}} has time difference of more than 2 seconds compared to NTP server: {{ $value }}' description: "{{`{{$labels.alias}} has time difference of more than 2 seconds compared to NTP server: {{ $value }}`}}"
summary: '{{$labels.alias}}: time is skewed by : {{$value}} seconds' summary: "{{`{{$labels.alias}}: time is skewed by : {{$value}} seconds`}}"
- alert: node_disk_read_latency - alert: node_disk_read_latency
expr: (rate(node_disk_read_time_ms[5m]) / rate(node_disk_reads_completed[5m])) > 40 expr: (rate(node_disk_read_time_ms[5m]) / rate(node_disk_reads_completed[5m])) > 40
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.device}} has a high read latency of {{ $value }}' description: "{{`{{$labels.device}} has a high read latency of {{ $value }}`}}"
summary: 'High read latency observed for device {{ $labels.device }}' summary: "{{`High read latency observed for device {{ $labels.device }}`}}"
- alert: node_disk_write_latency - alert: node_disk_write_latency
expr: (rate(node_disk_write_time_ms[5m]) / rate(node_disk_writes_completed[5m])) > 40 expr: (rate(node_disk_write_time_ms[5m]) / rate(node_disk_writes_completed[5m])) > 40
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: '{{$labels.device}} has a high write latency of {{ $value }}' description: "{{`{{$labels.device}} has a high write latency of {{ $value }}`}}"
summary: 'High write latency observed for device {{ $labels.device }}' summary: "{{`High write latency observed for device {{ $labels.device }}`}}"
... ...

148
prometheus/values_overrides/openstack.yaml
View File

@ -12,7 +12,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: MariaDB exporter in {{ $labels.kubernetes_namespace }} is not collecting metrics or is not available for past 10 minutes description: "{{`MariaDB exporter in {{ $labels.kubernetes_namespace }} is not collecting metrics or is not available for past 10 minutes`}}"
title: MariaDB exporter is not collecting metrics or is not available title: MariaDB exporter is not collecting metrics or is not available
- alert: prom_exporter_mariadb_osh_infra_unavailable - alert: prom_exporter_mariadb_osh_infra_unavailable
expr: avg_over_time(up{job="mysql-exporter",kubernetes_namespace="osh-infra"}[5m]) == 0 expr: avg_over_time(up{job="mysql-exporter",kubernetes_namespace="osh-infra"}[5m]) == 0
@ -20,7 +20,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: MariaDB exporter in {{ $labels.kubernetes_namespace }} is not collecting metrics or is not available for past 10 minutes description: "{{`MariaDB exporter in {{ $labels.kubernetes_namespace }} is not collecting metrics or is not available for past 10 minutes`}}"
title: MariaDB exporter is not collecting metrics or is not available title: MariaDB exporter is not collecting metrics or is not available
- alert: mariadb_table_lock_wait_high - alert: mariadb_table_lock_wait_high
expr: 100 * mysql_global_status_table_locks_waited/(mysql_global_status_table_locks_waited + mysql_global_status_table_locks_immediate) > 30 expr: 100 * mysql_global_status_table_locks_waited/(mysql_global_status_table_locks_waited + mysql_global_status_table_locks_immediate) > 30
@ -28,32 +28,32 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'Mariadb has high table lock waits of {{ $value }} percentage' description: "{{`Mariadb has high table lock waits of {{ $value }} percentage`}}"
summary: 'Mariadb table lock waits are high' summary: Mariadb table lock waits are high
- alert: mariadb_node_not_ready - alert: mariadb_node_not_ready
expr: mysql_global_status_wsrep_ready != 1 expr: mysql_global_status_wsrep_ready != 1
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: '{{$labels.job}} on {{$labels.instance}} is not ready.' description: "{{`{{$labels.job}} on {{$labels.instance}} is not ready.`}}"
summary: 'Galera cluster node not ready' summary: Galera cluster node not ready
- alert: mariadb_galera_node_out_of_sync - alert: mariadb_galera_node_out_of_sync
expr: mysql_global_status_wsrep_local_state != 4 AND mysql_global_variables_wsrep_desync == 0 expr: mysql_global_status_wsrep_local_state != 4 AND mysql_global_variables_wsrep_desync == 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: '{{$labels.job}} on {{$labels.instance}} is not in sync ({{$value}} != 4)' description: "{{`{{$labels.job}} on {{$labels.instance}} is not in sync ({{$value}} != 4)`}}"
summary: 'Galera cluster node out of sync' summary: Galera cluster node out of sync
- alert: mariadb_innodb_replication_fallen_behind - alert: mariadb_innodb_replication_fallen_behind
expr: (mysql_global_variables_innodb_replication_delay > 30) AND on (instance) (predict_linear(mysql_global_variables_innodb_replication_delay[5m], 60*2) > 0) expr: (mysql_global_variables_innodb_replication_delay > 30) AND on (instance) (predict_linear(mysql_global_variables_innodb_replication_delay[5m], 60*2) > 0)
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'The mysql innodb replication has fallen behind and is not recovering' description: The mysql innodb replication has fallen behind and is not recovering
summary: 'MySQL innodb replication is lagging' summary: MySQL innodb replication is lagging
- name: openstack.rules - name: openstack.rules
rules: rules:
- alert: prom_exporter_openstack_unavailable - alert: prom_exporter_openstack_unavailable
@ -70,184 +70,184 @@ conf:
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Glance API is not available at {{$labels.url}} for more than 5 minutes' description: "{{`Glance API is not available at {{$labels.url}} for more than 5 minutes`}}"
summary: 'Glance API is not available at {{$labels.url}}' summary: "{{`Glance API is not available at {{$labels.url}}`}}"
- alert: os_nova_api_availability - alert: os_nova_api_availability
expr: openstack_check_nova_api != 1 expr: openstack_check_nova_api != 1
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Nova API is not available at {{$labels.url}} for more than 5 minutes' description: "{{`Nova API is not available at {{$labels.url}} for more than 5 minutes`}}"
summary: 'Nova API is not available at {{$labels.url}}' summary: "{{`Nova API is not available at {{$labels.url}}`}}"
- alert: os_keystone_api_availability - alert: os_keystone_api_availability
expr: openstack_check_keystone_api != 1 expr: openstack_check_keystone_api != 1
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Keystone API is not available at {{$labels.url}} for more than 5 minutes' description: "{{`Keystone API is not available at {{$labels.url}} for more than 5 minutes`}}"
summary: 'Keystone API is not available at {{$labels.url}}' summary: "{{`Keystone API is not available at {{$labels.url}}`}}"
- alert: os_neutron_api_availability - alert: os_neutron_api_availability
expr: openstack_check_neutron_api != 1 expr: openstack_check_neutron_api != 1
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Neutron API is not available at {{$labels.url}} for more than 5 minutes' description: "{{`Neutron API is not available at {{$labels.url}} for more than 5 minutes`}}"
summary: 'Neutron API is not available at {{$labels.url}}' summary: "{{`Neutron API is not available at {{$labels.url}}`}}"
- alert: os_neutron_metadata_agent_availability - alert: os_neutron_metadata_agent_availability
expr: openstack_services_neutron_metadata_agent_down_total > 0 expr: openstack_services_neutron_metadata_agent_down_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'One or more neutron metadata_agents are not available for more than 5 minutes' description: One or more neutron metadata_agents are not available for more than 5 minutes
summary: 'One or more neutron metadata_agents are not available' summary: One or more neutron metadata_agents are not available
- alert: os_neutron_openvswitch_agent_availability - alert: os_neutron_openvswitch_agent_availability
expr: openstack_services_neutron_openvswitch_agent_down_total > 0 expr: openstack_services_neutron_openvswitch_agent_down_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'One or more neutron openvswitch agents are not available for more than 5 minutes' description: One or more neutron openvswitch agents are not available for more than 5 minutes
summary: 'One or more neutron openvswitch agents are not available' summary: One or more neutron openvswitch agents are not available
- alert: os_neutron_dhcp_agent_availability - alert: os_neutron_dhcp_agent_availability
expr: openstack_services_neutron_dhcp_agent_down_total > 0 expr: openstack_services_neutron_dhcp_agent_down_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'One or more neutron dhcp agents are not available for more than 5 minutes' description: One or more neutron dhcp agents are not available for more than 5 minutes
summary: 'One or more neutron dhcp agents are not available' summary: One or more neutron dhcp agents are not available
- alert: os_neutron_l3_agent_availability - alert: os_neutron_l3_agent_availability
expr: openstack_services_neutron_l3_agent_down_total > 0 expr: openstack_services_neutron_l3_agent_down_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'One or more neutron L3 agents are not available for more than 5 minutes' description: One or more neutron L3 agents are not available for more than 5 minutes
summary: 'One or more neutron L3 agents are not available' summary: One or more neutron L3 agents are not available
- alert: os_swift_api_availability - alert: os_swift_api_availability
expr: openstack_check_swift_api != 1 expr: openstack_check_swift_api != 1
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Swift API is not available at {{$labels.url}} for more than 5 minutes' description: "{{`Swift API is not available at {{$labels.url}} for more than 5 minutes`}}"
summary: 'Swift API is not available at {{$labels.url}}' summary: "{{`Swift API is not available at {{$labels.url}}`}}"
- alert: os_cinder_api_availability - alert: os_cinder_api_availability
expr: openstack_check_cinder_api != 1 expr: openstack_check_cinder_api != 1
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Cinder API is not available at {{$labels.url}} for more than 5 minutes' description: "{{`Cinder API is not available at {{$labels.url}} for more than 5 minutes`}}"
summary: 'Cinder API is not available at {{$labels.url}}' summary: "{{`Cinder API is not available at {{$labels.url}}`}}"
- alert: os_cinder_scheduler_availability - alert: os_cinder_scheduler_availability
expr: openstack_services_cinder_cinder_scheduler != 1 expr: openstack_services_cinder_cinder_scheduler != 1
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Cinder scheduler is not available for more than 5 minutes' description: Cinder scheduler is not available for more than 5 minutes
summary: 'Cinder scheduler is not available' summary: Cinder scheduler is not available
- alert: os_heat_api_availability - alert: os_heat_api_availability
expr: openstack_check_heat_api != 1 expr: openstack_check_heat_api != 1
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Heat API is not available at {{$labels.url}} for more than 5 minutes' description: "{{`Heat API is not available at {{$labels.url}} for more than 5 minutes`}}"
summary: 'Heat API is not available at {{$labels.url}}' summary: "{{`Heat API is not available at {{$labels.url}}`}}"
- alert: os_nova_compute_disabled - alert: os_nova_compute_disabled
expr: openstack_services_nova_compute_disabled_total > 0 expr: openstack_services_nova_compute_disabled_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'nova-compute is disabled on certain hosts for more than 5 minutes' description: nova-compute is disabled on certain hosts for more than 5 minutes
summary: 'Openstack compute service nova-compute is disabled on some hosts' summary: Openstack compute service nova-compute is disabled on some hosts
- alert: os_nova_conductor_disabled - alert: os_nova_conductor_disabled
expr: openstack_services_nova_conductor_disabled_total > 0 expr: openstack_services_nova_conductor_disabled_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'nova-conductor is disabled on certain hosts for more than 5 minutes' description: nova-conductor is disabled on certain hosts for more than 5 minutes
summary: 'Openstack compute service nova-conductor is disabled on some hosts' summary: Openstack compute service nova-conductor is disabled on some hosts
- alert: os_nova_consoleauth_disabled - alert: os_nova_consoleauth_disabled
expr: openstack_services_nova_consoleauth_disabled_total > 0 expr: openstack_services_nova_consoleauth_disabled_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'nova-consoleauth is disabled on certain hosts for more than 5 minutes' description: nova-consoleauth is disabled on certain hosts for more than 5 minutes
summary: 'Openstack compute service nova-consoleauth is disabled on some hosts' summary: Openstack compute service nova-consoleauth is disabled on some hosts
- alert: os_nova_scheduler_disabled - alert: os_nova_scheduler_disabled
expr: openstack_services_nova_scheduler_disabled_total > 0 expr: openstack_services_nova_scheduler_disabled_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'nova-scheduler is disabled on certain hosts for more than 5 minutes' description: nova-scheduler is disabled on certain hosts for more than 5 minutes
summary: 'Openstack compute service nova-scheduler is disabled on some hosts' summary: Openstack compute service nova-scheduler is disabled on some hosts
- alert: os_nova_compute_down - alert: os_nova_compute_down
expr: openstack_services_nova_compute_down_total > 0 expr: openstack_services_nova_compute_down_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'nova-compute is down on certain hosts for more than 5 minutes' description: nova-compute is down on certain hosts for more than 5 minutes
summary: 'Openstack compute service nova-compute is down on some hosts' summary: Openstack compute service nova-compute is down on some hosts
- alert: os_nova_conductor_down - alert: os_nova_conductor_down
expr: openstack_services_nova_conductor_down_total > 0 expr: openstack_services_nova_conductor_down_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'nova-conductor is down on certain hosts for more than 5 minutes' description: nova-conductor is down on certain hosts for more than 5 minutes
summary: 'Openstack compute service nova-conductor is down on some hosts' summary: Openstack compute service nova-conductor is down on some hosts
- alert: os_nova_consoleauth_down - alert: os_nova_consoleauth_down
expr: openstack_services_nova_consoleauth_down_total > 0 expr: openstack_services_nova_consoleauth_down_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'nova-consoleauth is down on certain hosts for more than 5 minutes' description: nova-consoleauth is down on certain hosts for more than 5 minutes
summary: 'Openstack compute service nova-consoleauth is down on some hosts' summary: Openstack compute service nova-consoleauth is down on some hosts
- alert: os_nova_scheduler_down - alert: os_nova_scheduler_down
expr: openstack_services_nova_scheduler_down_total > 0 expr: openstack_services_nova_scheduler_down_total > 0
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'nova-scheduler is down on certain hosts for more than 5 minutes' description: nova-scheduler is down on certain hosts for more than 5 minutes
summary: 'Openstack compute service nova-scheduler is down on some hosts' summary: Openstack compute service nova-scheduler is down on some hosts
- alert: os_vm_vcpu_usage_high - alert: os_vm_vcpu_usage_high
expr: openstack_total_used_vcpus * 100/(openstack_total_used_vcpus + openstack_total_free_vcpus) > 80 expr: openstack_total_used_vcpus * 100/(openstack_total_used_vcpus + openstack_total_free_vcpus) > 80
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Openstack VM vcpu usage is hight at {{$value}} percent' description: "{{`Openstack VM vcpu usage is hight at {{$value}} percent`}}"
summary: 'Openstack VM vcpu usage is high' summary: Openstack VM vcpu usage is high
- alert: os_vm_ram_usage_high - alert: os_vm_ram_usage_high
expr: openstack_total_used_ram_MB * 100/(openstack_total_used_ram_MB + openstack_total_free_ram_MB) > 80 expr: openstack_total_used_ram_MB * 100/(openstack_total_used_ram_MB + openstack_total_free_ram_MB) > 80
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Openstack VM RAM usage is hight at {{$value}} percent' description: "{{`Openstack VM RAM usage is hight at {{$value}} percent`}}"
summary: 'Openstack VM RAM usage is high' summary: Openstack VM RAM usage is high
- alert: os_vm_disk_usage_high - alert: os_vm_disk_usage_high
expr: openstack_total_used_disk_GB * 100/ ( openstack_total_used_disk_GB + openstack_total_free_disk_GB ) > 80 expr: openstack_total_used_disk_GB * 100/ ( openstack_total_used_disk_GB + openstack_total_free_disk_GB ) > 80
for: 5m for: 5m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'Openstack VM Disk usage is hight at {{$value}} percent' description: "{{`Openstack VM Disk usage is hight at {{$value}} percent`}}"
summary: 'Openstack VM Disk usage is high' summary: Openstack VM Disk usage is high
- name: rabbitmq.rules - name: rabbitmq.rules
rules: rules:
- alert: rabbitmq_network_pratitions_detected - alert: rabbitmq_network_pratitions_detected
@ -256,70 +256,70 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'RabbitMQ at {{ $labels.instance }} has {{ $value }} partitions' description: "{{`RabbitMQ at {{ $labels.instance }} has {{ $value }} partitions`}}"
summary: 'RabbitMQ Network partitions detected' summary: RabbitMQ Network partitions detected
- alert: rabbitmq_down - alert: rabbitmq_down
expr: min(rabbitmq_up) by(instance) != 1 expr: min(rabbitmq_up) by(instance) != 1
for: 10m for: 10m
labels: labels:
severity: page severity: page
annotations: annotations:
description: 'RabbitMQ Server instance {{ $labels.instance }} is down' description: "{{`RabbitMQ Server instance {{ $labels.instance }} is down`}}"
summary: 'The RabbitMQ Server instance at {{ $labels.instance }} has been down the last 10 mins' summary: "{{`The RabbitMQ Server instance at {{ $labels.instance }} has been down the last 10 mins`}}"
- alert: rabbitmq_file_descriptor_usage_high - alert: rabbitmq_file_descriptor_usage_high
expr: fd_used * 100 /fd_total > 80 expr: fd_used * 100 /fd_total > 80
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'RabbitMQ Server instance {{ $labels.instance }} has high file descriptor usage of {{ $value }} percent.' description: "{{`RabbitMQ Server instance {{ $labels.instance }} has high file descriptor usage of {{ $value }} percent.`}}"
summary: 'RabbitMQ file descriptors usage is high for last 10 mins' summary: RabbitMQ file descriptors usage is high for last 10 mins
- alert: rabbitmq_node_disk_free_alarm - alert: rabbitmq_node_disk_free_alarm
expr: node_disk_free_alarm > 0 expr: node_disk_free_alarm > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'RabbitMQ Server instance {{ $labels.instance }} has low disk free space available.' description: "{{`RabbitMQ Server instance {{ $labels.instance }} has low disk free space available.`}}"
summary: 'RabbitMQ disk space usage is high' summary: RabbitMQ disk space usage is high
- alert: rabbitmq_node_memory_alarm - alert: rabbitmq_node_memory_alarm
expr: node_mem_alarm > 0 expr: node_mem_alarm > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'RabbitMQ Server instance {{ $labels.instance }} has low free memory.' description: "{{`RabbitMQ Server instance {{ $labels.instance }} has low free memory.`}}"
summary: 'RabbitMQ memory usage is high' summary: RabbitMQ memory usage is high
- alert: rabbitmq_less_than_3_nodes - alert: rabbitmq_less_than_3_nodes
expr: running < 3 expr: running < 3
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'RabbitMQ Server has less than 3 nodes running.' description: RabbitMQ Server has less than 3 nodes running.
summary: 'RabbitMQ server is at risk of loosing data' summary: RabbitMQ server is at risk of loosing data
- alert: rabbitmq_queue_messages_returned_high - alert: rabbitmq_queue_messages_returned_high
expr: queue_messages_returned_total/queue_messages_published_total * 100 > 50 expr: queue_messages_returned_total/queue_messages_published_total * 100 > 50
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'RabbitMQ Server is returing more than 50 percent of messages received.' description: RabbitMQ Server is returing more than 50 percent of messages received.
summary: 'RabbitMQ server is returning more than 50 percent of messages received.' summary: RabbitMQ server is returning more than 50 percent of messages received.
- alert: rabbitmq_consumers_low_utilization - alert: rabbitmq_consumers_low_utilization
expr: queue_consumer_utilisation < .4 expr: queue_consumer_utilisation < .4
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'RabbitMQ consumers message consumption speed is low' description: RabbitMQ consumers message consumption speed is low
summary: 'RabbitMQ consumers message consumption speed is low' summary: RabbitMQ consumers message consumption speed is low
- alert: rabbitmq_high_message_load - alert: rabbitmq_high_message_load
expr: queue_messages_total > 17000 or increase(queue_messages_total[5m]) > 4000 expr: queue_messages_total > 17000 or increase(queue_messages_total[5m]) > 4000
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: 'RabbitMQ has high message load. Total Queue depth > 17000 or growth more than 4000 messages.' description: RabbitMQ has high message load. Total Queue depth > 17000 or growth more than 4000 messages.
summary: 'RabbitMQ has high message load' summary: RabbitMQ has high message load
... ...

6
prometheus/values_overrides/postgresql.yaml
View File

@ -20,7 +20,7 @@ conf:
labels: labels:
severity: warning severity: warning
annotations: annotations:
description: Replication lag on server {{$labels.instance}} is currently {{$value | humanizeDuration }} description: "{{`Replication lag on server {{$labels.instance}} is currently {{$value | humanizeDuration }}`}}"
title: Postgres Replication lag is over 2 minutes title: Postgres Replication lag is over 2 minutes
- alert: pg_connections_too_high - alert: pg_connections_too_high
expr: sum(pg_stat_activity_count) BY (environment, fqdn) > ON(fqdn) pg_settings_max_connections * 0.95 expr: sum(pg_stat_activity_count) BY (environment, fqdn) > ON(fqdn) pg_settings_max_connections * 0.95
@ -29,13 +29,13 @@ conf:
severity: warn severity: warn
channel: database channel: database
annotations: annotations:
title: Postgresql has {{$value}} connections on {{$labels.fqdn}} which is close to the maximum description: "{{`Postgresql has {{$value}} connections on {{$labels.fqdn}} which is close to the maximum`}}"
- alert: pg_deadlocks_detected - alert: pg_deadlocks_detected
expr: sum by(datname) (rate(pg_stat_database_deadlocks[1m])) > 0 expr: sum by(datname) (rate(pg_stat_database_deadlocks[1m])) > 0
for: 5m for: 5m
labels: labels:
severity: warn severity: warn
annotations: annotations:
description: postgresql at {{$labels.instance}} is showing {{$value}} rate of deadlocks for database {{$labels.datname}} description: "{{`postgresql at {{$labels.instance}} is showing {{$value}} rate of deadlocks for database {{$labels.datname}}`}}"
title: Postgres server is experiencing deadlocks title: Postgres server is experiencing deadlocks
... ...