diff --git a/stable/rabbitmq-ha/Chart.yaml b/stable/rabbitmq-ha/Chart.yaml index 03e3514c1b..52c3dc27a1 100644 --- a/stable/rabbitmq-ha/Chart.yaml +++ b/stable/rabbitmq-ha/Chart.yaml @@ -1,7 +1,7 @@ name: rabbitmq-ha apiVersion: v1 appVersion: 3.7.8 -version: 1.15.0 +version: 1.16.0 description: Highly available RabbitMQ cluster, the open source message broker software that implements the Advanced Message Queuing Protocol (AMQP). keywords: diff --git a/stable/rabbitmq-ha/templates/alerts.yaml b/stable/rabbitmq-ha/templates/alerts.yaml index 20b4f3bb9c..32c45a4b12 100644 --- a/stable/rabbitmq-ha/templates/alerts.yaml +++ b/stable/rabbitmq-ha/templates/alerts.yaml @@ -1,6 +1,6 @@ {{ if and .Values.prometheus.exporter.enabled .Values.prometheus.operator.enabled .Values.prometheus.operator.alerts.enabled }} -apiVersion: v1 -kind: ConfigMap +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule metadata: name: {{ .Release.Name }}-rabbitmq-alerts namespace: {{ .Values.prometheus.operator.serviceMonitor.namespace }} @@ -15,91 +15,90 @@ metadata: {{- if .Values.prometheus.operator.alerts.selector }} {{ toYaml .Values.prometheus.operator.alerts.selector | indent 4 }} {{- end }} -data: - rabbitmq.rules: |- - groups: - - name: rabbitmq-alerts - rules: - - alert: RabbitMqClusterNodeDown - expr: rabbitmq_up{service="{{ template "rabbitmq-ha.fullname" . }}"} == 0 - for: 5m - labels: - installed_by: {{ .Release.Name }} - severity: critical +spec: + groups: + - name: {{ template "rabbitmq-ha.fullname" . }}.rules + rules: + - alert: RabbitMqClusterNodeDown + expr: rabbitmq_up{service="{{ template "rabbitmq-ha.fullname" . }}"} == 0 + for: 5m + labels: + installed_by: {{ .Release.Name }} + severity: critical {{- if .Values.prometheus.operator.alerts.labels }} {{ toYaml .Values.prometheus.operator.alerts.labels | indent 10 }} {{- end }} - annotations: - description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} is down - summary: RabbitMQ Node Is Down - - alert: RabbitMqClusterNotAllNodesRunning - expr: sum(rabbitmq_up{service="{{ template "rabbitmq-ha.fullname" . }}"}) by (service) < {{ .Values.replicaCount }} - for: 5m - labels: - installed_by: {{ .Release.Name }} - severity: critical - team: devops - annotations: - description: Some RabbitMQ Cluster Nodes Are Down in Service {{`{{ $labels.namespace }}`}}/{{`{{ $labels.service}}`}} - summary: Some RabbitMQ Cluster Nodes Are Down in Service {{`{{ $labels.namespace }}`}}/{{`{{ $labels.service}}`}} - - alert: RabbitMqDiskSpaceAlarm - expr: rabbitmq_node_disk_free_alarm{service="{{ template "rabbitmq-ha.fullname" . }}"} == 1 - for: 1m - labels: - installed_by: {{ .Release.Name }} - severity: critical + annotations: + description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} is down + summary: RabbitMQ Node Is Down + - alert: RabbitMqClusterNotAllNodesRunning + expr: sum(rabbitmq_up{service="{{ template "rabbitmq-ha.fullname" . }}"}) by (service) < {{ .Values.replicaCount }} + for: 5m + labels: + installed_by: {{ .Release.Name }} + severity: critical + team: devops + annotations: + description: Some RabbitMQ Cluster Nodes Are Down in Service {{`{{ $labels.namespace }}`}}/{{`{{ $labels.service}}`}} + summary: Some RabbitMQ Cluster Nodes Are Down in Service {{`{{ $labels.namespace }}`}}/{{`{{ $labels.service}}`}} + - alert: RabbitMqDiskSpaceAlarm + expr: rabbitmq_node_disk_free_alarm{service="{{ template "rabbitmq-ha.fullname" . }}"} == 1 + for: 1m + labels: + installed_by: {{ .Release.Name }} + severity: critical {{- if .Values.prometheus.operator.alerts.labels }} {{ toYaml .Values.prometheus.operator.alerts.labels | indent 10 }} {{- end }} - annotations: - description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} Disk Space Alarm is going off. Which means the node hit highwater mark and has cut off network connectivity, see RabbitMQ WebUI - summary: RabbitMQ is Out of Disk Space - - alert: RabbitMqMemoryAlarm - expr: rabbitmq_node_mem_alarm{service="{{ template "rabbitmq-ha.fullname" . }}"} == 1 - for: 1m - labels: - installed_by: {{ .Release.Name }} - severity: critical + annotations: + description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} Disk Space Alarm is going off. Which means the node hit highwater mark and has cut off network connectivity, see RabbitMQ WebUI + summary: RabbitMQ is Out of Disk Space + - alert: RabbitMqMemoryAlarm + expr: rabbitmq_node_mem_alarm{service="{{ template "rabbitmq-ha.fullname" . }}"} == 1 + for: 1m + labels: + installed_by: {{ .Release.Name }} + severity: critical {{- if .Values.prometheus.operator.alerts.labels }} {{ toYaml .Values.prometheus.operator.alerts.labels | indent 10 }} {{- end }} - annotations: - description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} High Memory Alarm is going off. Which means the node hit highwater mark and has cut off network connectivity, see RabbitMQ WebUI - summary: RabbitMQ is Out of Memory - - alert: RabbitMqMemoryUsageHigh - expr: (rabbitmq_node_mem_used{service="{{ template "rabbitmq-ha.fullname" . }}"} / rabbitmq_node_mem_limit{service="{{ template "rabbitmq-ha.fullname" . }}"}) > .9 - for: 1m - labels: - installed_by: {{ .Release.Name }} - severity: critical + annotations: + description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} High Memory Alarm is going off. Which means the node hit highwater mark and has cut off network connectivity, see RabbitMQ WebUI + summary: RabbitMQ is Out of Memory + - alert: RabbitMqMemoryUsageHigh + expr: (rabbitmq_node_mem_used{service="{{ template "rabbitmq-ha.fullname" . }}"} / rabbitmq_node_mem_limit{service="{{ template "rabbitmq-ha.fullname" . }}"}) > .9 + for: 1m + labels: + installed_by: {{ .Release.Name }} + severity: critical {{- if .Values.prometheus.operator.alerts.labels }} {{ toYaml .Values.prometheus.operator.alerts.labels | indent 10 }} {{- end }} - annotations: - description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} Memory Usage > 90% - summary: RabbitMQ Node > 90% Memory Usage - - alert: RabbitMqFileDescriptorsLow - expr: (rabbitmq_fd_used{service="{{ template "rabbitmq-ha.fullname" . }}"} / rabbitmq_fd_total{service="{{ template "rabbitmq-ha.fullname" . }}"}) > .9 - for: 5m - labels: - installed_by: {{ .Release.Name }} - severity: critical + annotations: + description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} Memory Usage > 90% + summary: RabbitMQ Node > 90% Memory Usage + - alert: RabbitMqFileDescriptorsLow + expr: (rabbitmq_fd_used{service="{{ template "rabbitmq-ha.fullname" . }}"} / rabbitmq_fd_total{service="{{ template "rabbitmq-ha.fullname" . }}"}) > .9 + for: 5m + labels: + installed_by: {{ .Release.Name }} + severity: critical {{- if .Values.prometheus.operator.alerts.labels }} {{ toYaml .Values.prometheus.operator.alerts.labels | indent 10 }} {{- end }} - annotations: - description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} File Descriptor Usage > 90% - summary: RabbitMQ Low File Descriptor Available - - alert: RabbitMqDiskSpaceLow - expr: predict_linear(rabbitmq_node_disk_free{service="{{ template "rabbitmq-ha.fullname" . }}"}[15m], 1 * 60 * 60) < rabbitmq_node_disk_free_limit{service="{{ template "rabbitmq-ha.fullname" . }}"} - for: 5m - labels: - installed_by: {{ .Release.Name }} - severity: critical + annotations: + description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} File Descriptor Usage > 90% + summary: RabbitMQ Low File Descriptor Available + - alert: RabbitMqDiskSpaceLow + expr: predict_linear(rabbitmq_node_disk_free{service="{{ template "rabbitmq-ha.fullname" . }}"}[15m], 1 * 60 * 60) < rabbitmq_node_disk_free_limit{service="{{ template "rabbitmq-ha.fullname" . }}"} + for: 5m + labels: + installed_by: {{ .Release.Name }} + severity: critical {{- if .Values.prometheus.operator.alerts.labels }} {{ toYaml .Values.prometheus.operator.alerts.labels | indent 10 }} {{- end }} - annotations: - description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} will hit disk limit in the next hr based on last 15 mins trend. - summary: RabbitMQ is Low on Disk Space and will Run Out in the next hour + annotations: + description: RabbitMQ {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} will hit disk limit in the next hr based on last 15 mins trend. + summary: RabbitMQ is Low on Disk Space and will Run Out in the next hour {{ end }}