diff --git a/.gitignore b/.gitignore index 2d4d5a5..9823635 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,2 @@ alertmanager -alert-manager-config-2.yml +.env diff --git a/Makefile b/Makefile index 7b04aa9..e7f6ac5 100644 --- a/Makefile +++ b/Makefile @@ -1,5 +1,15 @@ +ifneq (,$(wildcard ./.env)) + include .env + export +endif + ALERTMANAGER_VERSION := $(shell ./alertmanager --version | cut -d" " -f3) +sed: + sed -i 's/WEBHOOK_SECRET/${WEBHOOK_SECRET}/' alert-manager-config.yml + sed -i 's/WEBHOOK_SECRET/${WEBHOOK_SECRET}/' deployment/toy_alert_manager.yml + # sed 's/WEBHOOK_SECRET/${WEBHOOK_SECRET}/' alert-manager-config.yml + clean: rm alertmanager @@ -7,7 +17,11 @@ build: vet go build -tags netgo docker-build: build - docker build -t alertmanager:$(ALERTMANAGER_VERSION) -f Dockerfile . + docker build -t alertmanager:$(ALERTMANAGER_VERSION) -f Dockerfile . + +docker-push: docker-build + docker tag alertmanager:$(ALERTMANAGER_VERSION) sohom83/tam:$(ALERTMANAGER_VERSION) + docker push sohom83/tam:$(ALERTMANAGER_VERSION) test: go test ./... -v diff --git a/alert-manager-config.yml b/alert-manager-config.yml index 8f69b19..e6594be 100644 --- a/alert-manager-config.yml +++ b/alert-manager-config.yml @@ -13,7 +13,7 @@ alert_pipelines: action_args: ARG1,ARG2 - step_name: ACTION_STEP_1 action_name: SendToSlack - action_args: "https://hooks.slack.com/services/SECRET" + action_args: "https://hooks.slack.com/services/WEBHOOK_SECRET" - alert_name: KubePodCrashLooping enrichments: diff --git a/deployment/kube-prometheus-stack.yml b/deployment/kube-prometheus-stack.yml new file mode 100644 index 0000000..464c7b9 --- /dev/null +++ b/deployment/kube-prometheus-stack.yml @@ -0,0 +1,726 @@ +## Create default rules for monitoring the cluster +## +defaultRules: + create: true + rules: + alertmanager: false + etcd: true + configReloaders: false + general: false + k8sContainerCpuUsageSecondsTotal: false + k8sContainerMemoryCache: false + k8sContainerMemoryRss: false + k8sContainerMemorySwap: false + k8sContainerResource: false + k8sContainerMemoryWorkingSetBytes: false + k8sPodOwner: false + kubeApiserverAvailability: false + kubeApiserverBurnrate: false + kubeApiserverHistogram: false + kubeApiserverSlos: false + kubeControllerManager: false + kubelet: false + kubeProxy: false + kubePrometheusGeneral: false + kubePrometheusNodeRecording: false + kubernetesApps: false + kubernetesResources: false + kubernetesStorage: false + kubernetesSystem: false + kubeSchedulerAlerting: false + kubeSchedulerRecording: false + kubeStateMetrics: false + network: false + node: false + nodeExporterAlerting: false + nodeExporterRecording: false + prometheus: false + prometheusOperator: false + windows: false + +## Configuration for alertmanager +## ref: https://prometheus.io/docs/alerting/alertmanager/ +## +alertmanager: + ## Deploy alertmanager + ## + enabled: true + + ## Annotations for Alertmanager + ## + annotations: {} + + ## Api that prometheus will use to communicate with alertmanager. Possible values are v1, v2 + ## + apiVersion: v2 + + ## @param alertmanager.enableFeatures Enable access to Alertmanager disabled features. + ## + enableFeatures: [] + + ## Service account for Alertmanager to use. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/ + ## + serviceAccount: + create: true + name: "" + annotations: {} + automountServiceAccountToken: true + + ## Configure pod disruption budgets for Alertmanager + ## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/#specifying-a-poddisruptionbudget + ## + podDisruptionBudget: + enabled: false + minAvailable: 1 + maxUnavailable: "" + + ## Alertmanager configuration directives + ## ref: https://prometheus.io/docs/alerting/configuration/#configuration-file + ## https://prometheus.io/webtools/alerting/routing-tree-editor/ + ## + config: + global: + resolve_timeout: 5m + inhibit_rules: + - source_matchers: + - "severity = critical" + target_matchers: + - "severity =~ warning|info" + equal: + - "namespace" + - "alertname" + - source_matchers: + - "severity = warning" + target_matchers: + - "severity = info" + equal: + - "namespace" + - "alertname" + - source_matchers: + - "alertname = InfoInhibitor" + target_matchers: + - "severity = info" + equal: + - "namespace" + - target_matchers: + - "alertname = InfoInhibitor" + route: + group_by: ["namespace"] + group_wait: 30s + group_interval: 5m + repeat_interval: 12h + receiver: "null" + routes: + - receiver: "null" + matchers: + - alertname = "Watchdog" + receivers: + - name: "null" + templates: + - "/etc/alertmanager/config/*.tmpl" + + ## Alertmanager configuration directives (as string type, preferred over the config hash map) + ## stringConfig will be used only, if tplConfig is true + ## ref: https://prometheus.io/docs/alerting/configuration/#configuration-file + ## https://prometheus.io/webtools/alerting/routing-tree-editor/ + ## + stringConfig: "" + + ## Pass the Alertmanager configuration directives through Helm's templating + ## engine. If the Alertmanager configuration contains Alertmanager templates, + ## they'll need to be properly escaped so that they are not interpreted by + ## Helm + ## ref: https://helm.sh/docs/developing_charts/#using-the-tpl-function + ## https://prometheus.io/docs/alerting/configuration/#tmpl_string + ## https://prometheus.io/docs/alerting/notifications/ + ## https://prometheus.io/docs/alerting/notification_examples/ + tplConfig: false + + ## Alertmanager template files to format alerts + ## By default, templateFiles are placed in /etc/alertmanager/config/ and if + ## they have a .tmpl file suffix will be loaded. See config.templates above + ## to change, add other suffixes. If adding other suffixes, be sure to update + ## config.templates above to include those suffixes. + ## ref: https://prometheus.io/docs/alerting/notifications/ + ## https://prometheus.io/docs/alerting/notification_examples/ + ## + templateFiles: {} + # + ## An example template: + # template_1.tmpl: |- + # {{ define "cluster" }}{{ .ExternalURL | reReplaceAll ".*alertmanager\\.(.*)" "$1" }}{{ end }} + # + # {{ define "slack.myorg.text" }} + # {{- $root := . -}} + # {{ range .Alerts }} + # *Alert:* {{ .Annotations.summary }} - `{{ .Labels.severity }}` + # *Cluster:* {{ template "cluster" $root }} + # *Description:* {{ .Annotations.description }} + # *Graph:* <{{ .GeneratorURL }}|:chart_with_upwards_trend:> + # *Runbook:* <{{ .Annotations.runbook }}|:spiral_note_pad:> + # *Details:* + # {{ range .Labels.SortedPairs }} - *{{ .Name }}:* `{{ .Value }}` + # {{ end }} + # {{ end }} + # {{ end }} + + ingress: + enabled: false + + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + + annotations: {} + + labels: {} + + ## Override ingress to a different defined port on the service + # servicePort: 8081 + ## Override ingress to a different service then the default, this is useful if you need to + ## point to a specific instance of the alertmanager (eg kube-prometheus-stack-alertmanager-0) + # serviceName: kube-prometheus-stack-alertmanager-0 + + ## Hosts must be provided if Ingress is enabled. + ## + hosts: + [] + # - alertmanager.domain.com + + ## Paths to use for ingress rules - one path should match the alertmanagerSpec.routePrefix + ## + paths: [] + # - / + + ## For Kubernetes >= 1.18 you should specify the pathType (determines how Ingress paths should be matched) + ## See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#better-path-matching-with-path-types + # pathType: ImplementationSpecific + + ## TLS configuration for Alertmanager Ingress + ## Secret must be manually created in the namespace + ## + tls: [] + # - secretName: alertmanager-general-tls + # hosts: + # - alertmanager.example.com + + ## Configuration for Alertmanager secret + ## + secret: + annotations: {} + + ## Configuration for creating an Ingress that will map to each Alertmanager replica service + ## alertmanager.servicePerReplica must be enabled + ## + ingressPerReplica: + enabled: false + + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + + annotations: {} + labels: {} + + ## Final form of the hostname for each per replica ingress is + ## {{ ingressPerReplica.hostPrefix }}-{{ $replicaNumber }}.{{ ingressPerReplica.hostDomain }} + ## + ## Prefix for the per replica ingress that will have `-$replicaNumber` + ## appended to the end + hostPrefix: "" + ## Domain that will be used for the per replica ingress + hostDomain: "" + + ## Paths to use for ingress rules + ## + paths: [] + # - / + + ## For Kubernetes >= 1.18 you should specify the pathType (determines how Ingress paths should be matched) + ## See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#better-path-matching-with-path-types + # pathType: ImplementationSpecific + + ## Secret name containing the TLS certificate for alertmanager per replica ingress + ## Secret must be manually created in the namespace + tlsSecretName: "" + + ## Separated secret for each per replica Ingress. Can be used together with cert-manager + ## + tlsSecretPerReplica: + enabled: false + ## Final form of the secret for each per replica ingress is + ## {{ tlsSecretPerReplica.prefix }}-{{ $replicaNumber }} + ## + prefix: "alertmanager" + + ## Configuration for Alertmanager service + ## + service: + annotations: {} + labels: {} + clusterIP: "" + ipDualStack: + enabled: false + ipFamilies: ["IPv6", "IPv4"] + ipFamilyPolicy: "PreferDualStack" + + ## Port for Alertmanager Service to listen on + ## + port: 9093 + ## To be used with a proxy extraContainer port + ## + targetPort: 9093 + ## Port to expose on each node + ## Only used if service.type is 'NodePort' + ## + nodePort: 30903 + ## List of IP addresses at which the Prometheus server service is available + ## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips + ## + + ## Additional ports to open for Alertmanager service + ## + additionalPorts: [] + # - name: oauth-proxy + # port: 8081 + # targetPort: 8081 + # - name: oauth-metrics + # port: 8082 + # targetPort: 8082 + + externalIPs: [] + loadBalancerIP: "" + loadBalancerSourceRanges: [] + + ## Denotes if this Service desires to route external traffic to node-local or cluster-wide endpoints + ## + externalTrafficPolicy: Cluster + + ## If you want to make sure that connections from a particular client are passed to the same Pod each time + ## Accepts 'ClientIP' or 'None' + ## + sessionAffinity: None + + ## If you want to modify the ClientIP sessionAffinity timeout + ## The value must be >0 && <=86400(for 1 day) if ServiceAffinity == "ClientIP" + ## + sessionAffinityConfig: + clientIP: + timeoutSeconds: 10800 + + ## Service type + ## + type: ClusterIP + + ## Configuration for creating a separate Service for each statefulset Alertmanager replica + ## + servicePerReplica: + enabled: false + annotations: {} + + ## Port for Alertmanager Service per replica to listen on + ## + port: 9093 + + ## To be used with a proxy extraContainer port + targetPort: 9093 + + ## Port to expose on each node + ## Only used if servicePerReplica.type is 'NodePort' + ## + nodePort: 30904 + + ## Loadbalancer source IP ranges + ## Only used if servicePerReplica.type is "LoadBalancer" + loadBalancerSourceRanges: [] + + ## Denotes if this Service desires to route external traffic to node-local or cluster-wide endpoints + ## + externalTrafficPolicy: Cluster + + ## Service type + ## + type: ClusterIP + + ## Configuration for creating a ServiceMonitor for AlertManager + ## + serviceMonitor: + ## If true, a ServiceMonitor will be created for the AlertManager service. + ## + selfMonitor: true + + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + + ## Additional labels + ## + additionalLabels: {} + + ## SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + ## + sampleLimit: 0 + + ## TargetLimit defines a limit on the number of scraped targets that will be accepted. + ## + targetLimit: 0 + + ## Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelLimit: 0 + + ## Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelNameLengthLimit: 0 + + ## Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelValueLengthLimit: 0 + + ## proxyUrl: URL of a proxy that should be used for scraping. + ## + proxyUrl: "" + + ## scheme: HTTP scheme to use for scraping. Can be used with `tlsConfig` for example if using istio mTLS. + scheme: "" + + ## enableHttp2: Whether to enable HTTP2. + ## See https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#endpoint + enableHttp2: true + + ## tlsConfig: TLS configuration to use when scraping the endpoint. For example if using istio mTLS. + ## Of type: https://github.com/coreos/prometheus-operator/blob/main/Documentation/api.md#tlsconfig + tlsConfig: {} + + bearerTokenFile: + + ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion. + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#relabelconfig + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + ## RelabelConfigs to apply to samples before scraping + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#relabelconfig + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + ## Additional Endpoints + ## + additionalEndpoints: [] + # - port: oauth-metrics + # path: /metrics + + ## Settings affecting alertmanagerSpec + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#alertmanagerspec + ## + alertmanagerSpec: + ## Standard object's metadata. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#metadata + ## Metadata Labels and Annotations gets propagated to the Alertmanager pods. + ## + podMetadata: {} + + ## Image of Alertmanager + ## + image: + registry: quay.io + repository: prometheus/alertmanager + tag: v0.27.0 + sha: "" + + ## If true then the user will be responsible to provide a secret with alertmanager configuration + ## So when true the config part will be ignored (including templateFiles) and the one in the secret will be used + ## + useExistingSecret: false + + ## Secrets is a list of Secrets in the same namespace as the Alertmanager object, which shall be mounted into the + ## Alertmanager Pods. The Secrets are mounted into /etc/alertmanager/secrets/. + ## + secrets: [] + + ## If false then the user will opt out of automounting API credentials. + ## + automountServiceAccountToken: true + + ## ConfigMaps is a list of ConfigMaps in the same namespace as the Alertmanager object, which shall be mounted into the Alertmanager Pods. + ## The ConfigMaps are mounted into /etc/alertmanager/configmaps/. + ## + configMaps: [] + + ## ConfigSecret is the name of a Kubernetes Secret in the same namespace as the Alertmanager object, which contains configuration for + ## this Alertmanager instance. Defaults to 'alertmanager-' The secret is mounted into /etc/alertmanager/config. + ## + # configSecret: + + ## WebTLSConfig defines the TLS parameters for HTTPS + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#alertmanagerwebspec + web: {} + + ## AlertmanagerConfigs to be selected to merge and configure Alertmanager with. + ## + alertmanagerConfigSelector: {} + ## Example which selects all alertmanagerConfig resources + ## with label "alertconfig" with values any of "example-config" or "example-config-2" + # alertmanagerConfigSelector: + # matchExpressions: + # - key: alertconfig + # operator: In + # values: + # - example-config + # - example-config-2 + # + ## Example which selects all alertmanagerConfig resources with label "role" set to "example-config" + # alertmanagerConfigSelector: + # matchLabels: + # role: example-config + + ## Namespaces to be selected for AlertmanagerConfig discovery. If nil, only check own namespace. + ## + alertmanagerConfigNamespaceSelector: {} + ## Example which selects all namespaces + ## with label "alertmanagerconfig" with values any of "example-namespace" or "example-namespace-2" + # alertmanagerConfigNamespaceSelector: + # matchExpressions: + # - key: alertmanagerconfig + # operator: In + # values: + # - example-namespace + # - example-namespace-2 + + ## Example which selects all namespaces with label "alertmanagerconfig" set to "enabled" + # alertmanagerConfigNamespaceSelector: + # matchLabels: + # alertmanagerconfig: enabled + + ## AlermanagerConfig to be used as top level configuration + ## + alertmanagerConfiguration: {} + ## Example with select a global alertmanagerconfig + # alertmanagerConfiguration: + # name: global-alertmanager-Configuration + + ## Defines the strategy used by AlertmanagerConfig objects to match alerts. eg: + ## + alertmanagerConfigMatcherStrategy: {} + ## Example with use OnNamespace strategy + # alertmanagerConfigMatcherStrategy: + # type: OnNamespace + + ## Define Log Format + # Use logfmt (default) or json logging + logFormat: logfmt + + ## Log level for Alertmanager to be configured with. + ## + logLevel: info + + ## Size is the expected size of the alertmanager cluster. The controller will eventually make the size of the + ## running cluster equal to the expected size. + replicas: 1 + + ## Time duration Alertmanager shall retain data for. Default is '120h', and must match the regular expression + ## [0-9]+(ms|s|m|h) (milliseconds seconds minutes hours). + ## + retention: 120h + + ## Storage is the definition of how storage will be used by the Alertmanager instances. + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/user-guides/storage.md + ## + storage: {} + # volumeClaimTemplate: + # spec: + # storageClassName: gluster + # accessModes: ["ReadWriteOnce"] + # resources: + # requests: + # storage: 50Gi + # selector: {} + + ## The external URL the Alertmanager instances will be available under. This is necessary to generate correct URLs. This is necessary if Alertmanager is not served from root of a DNS name. string false + ## + externalUrl: + + ## The route prefix Alertmanager registers HTTP handlers for. This is useful, if using ExternalURL and a proxy is rewriting HTTP routes of a request, and the actual ExternalURL is still true, + ## but the server serves requests under a different route prefix. For example for use with kubectl proxy. + ## + routePrefix: / + + ## scheme: HTTP scheme to use. Can be used with `tlsConfig` for example if using istio mTLS. + scheme: "" + + ## tlsConfig: TLS configuration to use when connect to the endpoint. For example if using istio mTLS. + ## Of type: https://github.com/coreos/prometheus-operator/blob/main/Documentation/api.md#tlsconfig + tlsConfig: {} + + ## If set to true all actions on the underlying managed objects are not going to be performed, except for delete actions. + ## + paused: false + + ## Define which Nodes the Pods are scheduled on. + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + + ## Define resources requests and limits for single Pods. + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## + resources: {} + # requests: + # memory: 400Mi + + ## Pod anti-affinity can prevent the scheduler from placing Prometheus replicas on the same node. + ## The default value "soft" means that the scheduler should *prefer* to not schedule two replica pods onto the same node but no guarantee is provided. + ## The value "hard" means that the scheduler is *required* to not schedule two replica pods onto the same node. + ## The value "" will disable pod anti-affinity so that no anti-affinity rules will be configured. + ## + podAntiAffinity: "" + + ## If anti-affinity is enabled sets the topologyKey to use for anti-affinity. + ## This can be changed to, for example, failure-domain.beta.kubernetes.io/zone + ## + podAntiAffinityTopologyKey: kubernetes.io/hostname + + ## Assign custom affinity rules to the alertmanager instance + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/ + ## + affinity: {} + # nodeAffinity: + # requiredDuringSchedulingIgnoredDuringExecution: + # nodeSelectorTerms: + # - matchExpressions: + # - key: kubernetes.io/e2e-az-name + # operator: In + # values: + # - e2e-az1 + # - e2e-az2 + + ## If specified, the pod's tolerations. + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + # - key: "key" + # operator: "Equal" + # value: "value" + # effect: "NoSchedule" + + ## If specified, the pod's topology spread constraints. + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ + ## + topologySpreadConstraints: [] + # - maxSkew: 1 + # topologyKey: topology.kubernetes.io/zone + # whenUnsatisfiable: DoNotSchedule + # labelSelector: + # matchLabels: + # app: alertmanager + + ## SecurityContext holds pod-level security attributes and common container settings. + ## This defaults to non root user with uid 1000 and gid 2000. *v1.PodSecurityContext false + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + ## + securityContext: + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + fsGroup: 2000 + seccompProfile: + type: RuntimeDefault + + ## ListenLocal makes the Alertmanager server listen on loopback, so that it does not bind against the Pod IP. + ## Note this is only for the Alertmanager UI, not the gossip communication. + ## + listenLocal: false + + ## Containers allows injecting additional containers. This is meant to allow adding an authentication proxy to an Alertmanager pod. + ## + containers: [] + # containers: + # - name: oauth-proxy + # image: quay.io/oauth2-proxy/oauth2-proxy:v7.5.1 + # args: + # - --upstream=http://127.0.0.1:9093 + # - --http-address=0.0.0.0:8081 + # - --metrics-address=0.0.0.0:8082 + # - ... + # ports: + # - containerPort: 8081 + # name: oauth-proxy + # protocol: TCP + # - containerPort: 8082 + # name: oauth-metrics + # protocol: TCP + # resources: {} + + # Additional volumes on the output StatefulSet definition. + volumes: [] + + # Additional VolumeMounts on the output StatefulSet definition. + volumeMounts: [] + + ## InitContainers allows injecting additional initContainers. This is meant to allow doing some changes + ## (permissions, dir tree) on mounted volumes before starting prometheus + initContainers: [] + + ## Priority class assigned to the Pods + ## + priorityClassName: "" + + ## AdditionalPeers allows injecting a set of additional Alertmanagers to peer with to form a highly available cluster. + ## + additionalPeers: [] + + ## PortName to use for Alert Manager. + ## + portName: "http-web" + + ## ClusterAdvertiseAddress is the explicit address to advertise in cluster. Needs to be provided for non RFC1918 [1] (public) addresses. [1] RFC1918: https://tools.ietf.org/html/rfc1918 + ## + clusterAdvertiseAddress: false + + ## clusterGossipInterval determines interval between gossip attempts. + ## Needs to be specified as GoDuration, a time duration that can be parsed by Go’s time.ParseDuration() (e.g. 45ms, 30s, 1m, 1h20m15s) + clusterGossipInterval: "" + + ## clusterPeerTimeout determines timeout for cluster peering. + ## Needs to be specified as GoDuration, a time duration that can be parsed by Go’s time.ParseDuration() (e.g. 45ms, 30s, 1m, 1h20m15s) + clusterPeerTimeout: "" + + ## clusterPushpullInterval determines interval between pushpull attempts. + ## Needs to be specified as GoDuration, a time duration that can be parsed by Go’s time.ParseDuration() (e.g. 45ms, 30s, 1m, 1h20m15s) + clusterPushpullInterval: "" + + ## ForceEnableClusterMode ensures Alertmanager does not deactivate the cluster mode when running with a single replica. + ## Use case is e.g. spanning an Alertmanager cluster across Kubernetes clusters with a single replica in each. + forceEnableClusterMode: false + + ## Minimum number of seconds for which a newly created pod should be ready without any of its container crashing for it to + ## be considered available. Defaults to 0 (pod will be considered available as soon as it is ready). + minReadySeconds: 0 + + ## Additional configuration which is not covered by the properties above. (passed through tpl) + additionalConfig: {} + + ## Additional configuration which is not covered by the properties above. + ## Useful, if you need advanced templating inside alertmanagerSpec. + ## Otherwise, use alertmanager.alertmanagerSpec.additionalConfig (passed through tpl) + additionalConfigString: "" + + ## ExtraSecret can be used to store various data in an extra secret + ## (use it for example to store hashed basic auth credentials) + extraSecret: + ## if not set, name will be auto generated + # name: "" + annotations: {} + data: {} + # auth: | + # foo:$apr1$OFG3Xybp$ckL0FHDAkoXYIlH9.cysT0 + # someoneelse:$apr1$DMZX2Z4q$6SbQIfyuLQd.xmo/P0m2c. diff --git a/deployment/toy_alert_manager.yml b/deployment/toy_alert_manager.yml new file mode 100644 index 0000000..de30d6f --- /dev/null +++ b/deployment/toy_alert_manager.yml @@ -0,0 +1,88 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: tam-config + labels: + app: tam +data: + alert-manager-config-2.yml: | + alert_pipelines: + - alert_name: NOOP_ALERT + enrichments: + - step_name: ENRICHMENT_STEP_1 + enrichment_name: UPPER_CASE + enrichment_args: arg1,arg2 + - step_name: ENRICHMENT_STEP_2 + enrichment_name: GetPromQL + enrichment_args: "http://localhost:9090/api/v1/query?query=sum%28rate%28node_cpu_seconds_total%5B1m%5D%29%29&time=1719778255.812" + actions: + - step_name: ACTION_STEP_1 + action_name: NOOP_ACTION + action_args: ARG1,ARG2 + - step_name: ACTION_STEP_1 + action_name: SendToSlack + action_args: "https://hooks.slack.com/services/WEBHOOK_SECRET" + - alert_name: etcdInsufficientMembers + enrichments: + - step_name: ENRICHMENT_STEP_1 + enrichment_name: UPPER_CASE + enrichment_args: arg1,arg2 + actions: + - step_name: ACTION_STEP_1 + action_name: SendToSlack + action_args: "https://hooks.slack.com/services/WEBHOOK_SECRET" + - alert_name: etcdMembersDown + enrichments: + - step_name: ENRICHMENT_STEP_1 + enrichment_name: UPPER_CASE + enrichment_args: arg1,arg2 + actions: + - step_name: ACTION_STEP_1 + action_name: SendToSlack + action_args: "https://hooks.slack.com/services/WEBHOOK_SECRET" +--- +apiVersion: apps/v1 +kind: Deployment +metadata: + name: toy-alert-manager + labels: + app: tam +spec: + replicas: 1 + selector: + matchLabels: + app: tam + template: + metadata: + labels: + app: tam + spec: + containers: + - name: tam + image: sohom83/tam:0.0.1 + args: + - "server" + - "--config.file=/etc/alertmanager/alert-manager-config-2.yml" + - "--log.level=debug" + volumeMounts: + - name: config-volume + mountPath: /etc/alertmanager + subPath: alert-manager-config-2.yml + volumes: + - name: config-volume + configMap: + name: tam-config +--- +apiVersion: v1 +kind: Service +metadata: + name: tam + labels: + app: tam +spec: + ports: + - port: 8080 + targetPort: 8080 + selector: + app: tam + type: ClusterIP diff --git a/scratchpad.md b/scratchpad.md index 4e48654..6ea962a 100644 --- a/scratchpad.md +++ b/scratchpad.md @@ -36,3 +36,13 @@ process this query for now ``` curl 'http://localhost:9090/api/v1/query?query=sum%28rate%28node_cpu_seconds_total%5B1m%5D%29%29&time=1719778255.812' ``` + +## SETUP + +``` +kind setup cluster +helm repo add prometheus-community https://prometheus-community.github.io/helm-charts +helm repo update +helm install prom-stack prometheus-community/kube-prometheus-stack -f values.yml + +```