values.yaml

# -- Cloud service being deployed on (example: `aws`, `azure`, `do`, `gcp`, `other`).
cloud:

# -- Notification email for notifications to be sent to from the PostHog stack
notificationEmail:

# -- Site url specifies the canonical URL root the site can be accessed using.
# This is used to e.g. generate shareable links to Dashboards.
siteUrl:

image:
  # -- PostHog image repository to use.
  repository: posthog/posthog
  # -- PostHog image SHA to use (example: `sha256:20af35fca6756d689d6705911a49dd6f2f6631e001ad43377b605cfc7c133eb4`).
  sha:
  # -- PostHog image tag to use (example: `release-1.43.0`).
  tag:
  # -- PostHog default image. Do not overwrite, use `image.sha` or `image.tag` instead.
  default: ":latest"
  # -- PostHog image pull policy.
  pullPolicy: Always
  ## Optionally specify an array of imagePullSecrets.
  ## Secrets must be manually created in the namespace.
  ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
  ## Example:
  ## pullSecrets:
  ##   - myRegistryKeySecretName
  ##
  pullSecrets: []

# -- Sentry endpoint to send errors to.
sentryDSN:

# -- Django SECRET_KEY to use for hashing e.g. passwords. See
# https://docs.djangoproject.com/en/4.0/ref/settings/#secret-key
posthogSecretKey:
  # -- Specify that the key should be pulled from an existing secret key. By
  # default the chart will generate a secret and create a Kubernetes Secret
  # containing it.
  existingSecret:
  # -- Specify the key within the secret from which SECRET_KEY should be taken.
  existingSecretKey: posthog-secret

# -- Environment variables to inject into every PostHog deployment.
env: []
# env:
#   - name: FOO
#     value: bar

migrate:
  # -- Whether to install the PostHog migrate job or not.
  enabled: true

events:
  # -- Whether to install the PostHog events stack or not.
  enabled: true

  # -- Count of events pods to run. This setting is ignored if `events.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the events stack.
    enabled: false
    # -- CPU threshold percent for the events stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the events stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the events stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  pdb:
    enabled: false

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the events stack, uses `web.env` if empty.
  env: []

  # -- Container security context for the events stack HorizontalPodAutoscaler.
  securityContext:
    enabled: false
  # -- Pod security context for the events stack HorizontalPodAutoscaler.
  podSecurityContext:
    enabled: false

recordings:
  # -- Whether to install the PostHog recordings stack or not.
  enabled: false
  # -- Whether to route /s traffic to the recordings stack instead of the events stack
  ingressEnabled: false

  # -- Count of recordings pods to run. This setting is ignored if `recordings.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the recordings stack.
    enabled: false
    # -- CPU threshold percent for the recordings stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the recordings stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the recordings stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  pdb:
    enabled: false

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the recordings stack, uses `web.env` if empty.
  env: []

  # -- Container security context for the recordings stack HorizontalPodAutoscaler.
  securityContext:
    enabled: false
  # -- Pod security context for the recordings stack HorizontalPodAutoscaler.
  podSecurityContext:
    enabled: false

# The majority of the capture config + chart resides in posthog/charts
capture:
  ingress:
    enabled: false
    service: 
      name: capture
      port: 3000

decide:
  # -- Whether to install the PostHog decide stack or not.
  enabled: false
  ingressEnabled: false

  # -- Count of decide pods to run. This setting is ignored if `decide.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the decide stack.
    enabled: false
    # -- CPU threshold percent for the decide stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the decide stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the decide stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  pdb:
    # -- Whether to create a PodDisruptionBudget for the decide stack.
    enabled: true
    # -- Maximum number of decide pods that can be unavailable at any time
    maxUnavailable: 1

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the decide stack, uses `web.env` if empty.
  env: []

  # -- Container security context for the decide stack HorizontalPodAutoscaler.
  securityContext:
    enabled: false
  # -- Pod security context for the decide stack HorizontalPodAutoscaler.
  podSecurityContext:
    enabled: false

web:
  # -- Whether to install the PostHog web stack or not.
  enabled: true

  podAnnotations:
    # Uncomment these lines if you want Prometheus server to scrape metrics.
    # prometheus.io/scrape: "true"
    # prometheus.io/path: /metrics
    # prometheus.io/port: "8001"

  # -- Count of web pods to run. This setting is ignored if `web.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the web stack.
    enabled: false
    # -- CPU threshold percent for the web stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the web stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the web stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  pdb:
    enabled: false

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Resource limits for web service.
  resources: {}

  # -- Additional env variables to inject into the web stack deployment.
  env:
    # -- Set google oauth 2 key. Requires posthog ee license.
    - name: SOCIAL_AUTH_GOOGLE_OAUTH2_KEY
      value:
    # -- Set google oauth 2 secret. Requires posthog ee license.
    - name: SOCIAL_AUTH_GOOGLE_OAUTH2_SECRET
      value:
    # -- Set google oauth 2 whitelisted domains users can log in from.
    - name: SOCIAL_AUTH_GOOGLE_OAUTH2_WHITELISTED_DOMAINS
      value: "posthog.com"

  internalMetrics:
    # -- Deprecated: Whether to capture information on operation of posthog into posthog, exposed in /instance/status page
    capture: false

  # -- Node labels for web stack deployment.
  nodeSelector: {}
  # -- Toleration labels for web stack deployment.
  tolerations: []
  # -- Affinity settings for web stack deployment.
  affinity: {}
  # :TODO:
  secureCookies: true

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 0
    # -- The liveness probe period seconds
    periodSeconds: 5
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 0
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  startupProbe:
    # -- The startup probe failure threshold
    failureThreshold: 6
    # -- The startup probe initial delay seconds
    initialDelaySeconds: 0
    # -- The startup probe period seconds
    periodSeconds: 10
    # -- The startup probe success threshold
    successThreshold: 1
    # -- The startup probe timeout seconds
    timeoutSeconds: 5

  # -- Container security context for web stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for web stack deployment.
  podSecurityContext:
    enabled: false

worker:
  # -- Whether to install the PostHog worker stack or not.
  enabled: true

  # -- Count of worker pods to run. This setting is ignored if `worker.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the worker stack.
    enabled: false
    # -- CPU threshold percent for the worker stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the worker stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the worker stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the worker stack deployment.
  env: []

  # -- Resource limits for the worker stack deployment.
  resources: {}

  # -- Node labels for the worker stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the worker stack deployment.
  tolerations: []
  # -- Affinity settings for the worker stack deployment.
  affinity: {}

  # -- Container security context for the worker stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the worker stack deployment.
  podSecurityContext:
    enabled: false

plugins:
  # -- Whether to install the PostHog plugin-server stack or not.
  # This service handles data ingestion into ClickHouse, running apps and async
  # jobs. To scale these components separately, instead use the individual
  # component deployments, pluginsIngestion, pluginsAsync, pluginsJobs, and
  # pluginsScheduler.
  enabled: true

  # -- Count of plugin-server pods to run. This setting is ignored if `plugins.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env: []

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: false

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

pluginsAsync:
  # -- Whether to install the PostHog plugin-server async stack or not.
  # If disabled (default), plugins service handles both ingestion and running of async tasks.
  # Allows for separate scaling of this service.
  enabled: false

  # -- Count of plugin-server-async pods to run. This setting is ignored if `pluginsAsync.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env: []

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: false

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

# -- A deconstructed plugin-server that handles the various workloads of the
# pipeline separately. For most workloads this will not be needed, rather you
# can disable the below plugins* and instead just use `plugins.enabled=true`.
# Note that the behaviour of pluginsAsync is unchanged to maintain backwards
# compatibility.

pluginsIngestion:
  # -- Whether to install the PostHog plugin-server ingestion capability as an
  # individual workload.
  enabled: false

  # -- Count of plugin-server pods to run. This setting is ignored if `pluginsIngestion.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env:
    - name: INGESTION_OVERFLOW_ENABLED
      # -- Whether or not to send events to a "slow-lane" to be consumed
      # separately by the pluginsIngestionOverflow deployment. When setting this
      # to true, you must set pluginsIngestionOverflow.enabled to `true``
      # otherwise some events will not be processed in cases of overflow. This
      # behaviour is triggered for instance if there are too many events to be
      # processed in near real time from a single device.
      value: "false"

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: false

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

pluginsAnalyticsIngestion:
  # -- Whether to install the PostHog plugin-server analytics ingestion
  # capability as an individual workload. Note that this is different from the
  # `pluginsIngestion` setting above specifically in that the deployment
  # controlled by these settings does not handle session recordings. This
  # deployment is intended to be a replacement for `pluginsIngestion` and is
  # intended to be used along side the `recordingsIngestion` deployment.
  #
  # The reason these values were added is to be able to scale analytics and
  # session recordings events independently, and to be able to roll this out in
  # a backwards compatible way.
  enabled: false

  # -- Count of plugin-server pods to run. This setting is ignored if
  # `pluginsAnalyticsIngestion.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env:
    - name: INGESTION_OVERFLOW_ENABLED
      # -- Whether or not to send events to a "slow-lane" to be consumed
      # separately by the pluginsIngestionOverflow deployment. When setting this
      # to true, you must set pluginsIngestionOverflow.enabled to `true``
      # otherwise some events will not be processed in cases of overflow. This
      # behaviour is triggered for instance if there are too many events to be
      # processed in near real time from a single device.
      value: "false"

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: false

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

pluginsIngestionOverflow:
  # -- Whether to install the PostHog plugin-server ingestion overflow
  # capability as an individual workload.
  enabled: false

  # -- Count of plugin-server overflow pods to run. This setting is ignored if
  # `pluginsIngestionOverflow.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

recordingsIngestion:
  # -- Whether to install the PostHog session recordings ingestion capability as
  # an individual workload.
  enabled: false

  # -- Count of plugin-server pods to run. This setting is ignored if `recordingsIngestion.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  keda:
    # -- Whether to create a ScaleObject to handle scaling of the consumer group
    # deployment using KEDA. `hpa.enabled` must be false to use this. We will
    # use the same configuration to connect to Kafka as either the ones
    # generated by the chart if using `kafka.enabled=true` or the config from
    # `externalKafka` otherwise.
    enabled: false

    # -- Config added to spec at the top level of the `ScaledObject`.
    config:
      pollingInterval: 30

    # -- KEDA trigger config for type kafka. This will be merged in with other
    # config such as consumer group id and topic which will be set
    # automatically.
    kafkaTrigger:
      enabled: true

      metadata:
        # -- At what lag value should KEDA scaling start.
        lagThreshold: "1000"
        # -- At what lag value should KEDA scale from 0 replicas.
        activationLagThreshold: "0"
        excludePersistentLag: "true" # Don't include stuck partitions in autoscaling decisions.

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env: []

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: false

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

recordingsBlobIngestion:
  # -- Whether to install the PostHog session recordings blob ingestion capability as
  # an individual workload.
  enabled: false

  # -- Count of plugin-server pods to run. This setting is ignored if `recordingsBlobIngestion.hpa.enabled` is set to `true`.
  replicacount: 1

  volumeMounts:
    - mountPath: "/session-buffers"
      name: session-buffers

  volumes:
    - name: session-buffers
      ephemeral:
        volumeClaimTemplate:
          spec:
            accessModes: ["ReadWriteOnce"]
            storageClassName: "gp3"
            resources:
              requests:
                storage: 50Gi

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  keda:
    # -- Whether to create a ScaleObject to handle scaling of the consumer group
    # deployment using KEDA. `hpa.enabled` must be false to use this. We will
    # use the same configuration to connect to Kafka as either the ones
    # generated by the chart if using `kafka.enabled=true` or the config from
    # `externalKafka` otherwise.
    enabled: false

    # -- Config added to spec at the top level of the `ScaledObject`.
    config:
      pollingInterval: 30

    # -- KEDA trigger config for type kafka. This will be merged in with other
    # config such as consumer group id and topic which will be set
    # automatically.
    #
    # TODO: add support for all security protocol config.
    kafkaTrigger:
      enabled: true

      metadata:
        # -- At what lag value should KEDA scaling start.
        lagThreshold: "1000"
        # -- At what lag value should KEDA scale from 0 replicas.
        activationLagThreshold: "0"
        excludePersistentLag: "true" # Don't include stuck partitions in autoscaling decisions.

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env: []

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: true
    fsGroup: 1000

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

pluginsExports:
  # -- Whether to install the PostHog plugin-server exports capability as an
  # individual workload.
  enabled: false

  # -- Count of plugin-server-async pods to run. This setting is ignored if `pluginsExports.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env: []

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: false

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

pluginsJobs:
  # -- Whether to install the PostHog plugin-server jobs capability as an
  # individual workload.
  enabled: false

  # -- Count of plugin-server-async pods to run. This setting is ignored if `pluginsJobs.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env: []

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: false

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

pluginsScheduler:
  # -- Whether to install the PostHog plugin-server scheduler capability as an
  # individual workload.
  enabled: false

  # -- Count of plugin-server-async pods to run. This setting is ignored if `pluginsScheduler.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the plugin stack.
    enabled: false
    # -- CPU threshold percent for the plugin-server stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the plugin-server stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the plugin-server stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the plugin-server stack deployment.
  env: []

  # -- Resource limits for the plugin-server stack deployment.
  resources: {}

  # -- Node labels for the plugin-server stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the plugin-server stack deployment.
  tolerations: []
  # -- Affinity settings for the plugin-server stack deployment.
  affinity: {}

  # -- Container security context for the plugin-server stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the plugin-server stack deployment.
  podSecurityContext:
    enabled: false

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 50
    # -- The readiness probe period seconds
    periodSeconds: 30
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 5

  # -- Sentry endpoint to send errors to. Falls back to global sentryDSN
  sentryDSN:

toolbox:
  # -- Whether to install the PostHog toolbox deployment
  enabled: false
  # -- Additional env variables to inject into the toolbox deployment.
  env: []
  # -- Resource limits for the toolbox deployment.
  resources: {}

temporalPyWorker:
  # -- Whether to install the PostHog Temporal Python worker stack or not.
  enabled: false

  # -- Count of worker pods to run. This setting is ignored if `worker.hpa.enabled` is set to `true`.
  replicacount: 1

  # -- The grace period for the worker pods. This is slightly larger than the
  # default 5 minutes of the worker by default.
  terminationGracePeriodSeconds: 310

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the worker stack.
    enabled: false
    # -- CPU threshold percent for the worker stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the worker stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the worker stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  rollout:
    # The max surge in pods during a rollout
    maxSurge: 25%
    # The max unavailable during a rollout
    maxUnavailable: 25%

  # -- Additional env variables to inject into the worker stack deployment.
  env: []

  # -- Resource limits for the worker stack deployment.
  resources: {}

  # -- Node labels for the worker stack deployment.
  nodeSelector: {}
  # -- Toleration labels for the worker stack deployment.
  tolerations: []
  # -- Affinity settings for the worker stack deployment.
  affinity: {}

  # -- Container security context for the worker stack deployment.
  securityContext:
    enabled: false
  # -- Pod security context for the worker stack deployment.
  podSecurityContext:
    enabled: false

email:
  # -- SMTP service host.
  host:
  # -- SMTP service port.
  port:
  # -- SMTP service user.
  user:
  # -- SMTP service password.
  password:
  # -- Name of an existing Kubernetes secret object containing the SMTP service password.
  existingSecret: ""
  # -- Name of the key pointing to the password in your Kubernetes secret.
  existingSecretKey: ""
  # -- Use TLS to authenticate to the SMTP service.
  use_tls: true
  # -- Use SSL to authenticate to the SMTP service.
  use_ssl:
  # -- Outbound email sender to use.
  from_email:

saml:
  # -- Whether password-based login is disabled and users automatically redirected to SAML login. Requires SAML to be properly configured.
  enforced: false
  # -- Whether SAML should be completely disabled. If set at build time, this will also prevent SAML dependencies from being installed.
  disabled: false
  # -- Entity ID from your SAML IdP.
  # entity_id: "id-from-idp-5f9d4e-47ca-5080"
  entity_id:
  # -- Assertion Consumer Service URL from your SAML IdP.
  # acs_url: "https://mysamlidp.com/saml2"
  acs_url:
  # -- Public X509 certificate from your SAML IdP to validate SAML assertions
  # x509_cert: |
  # MIID3DCCAsSgAwIBAgIUdriHo8qmAU1I0gxsI7cFZHmna38wDQYJKoZIhvcNAQEF
  # BQAwRTEQMA4GA1UECgwHUG9zdEhvZzEVMBMGA1UECwwMT25lTG9naW4gSWRQMRow
  # GAYDVQQDDBFPbmVMb2dpbiBBY2NvdW50IDAeFw0yMTA4MTYyMTUyMzNaFw0yNjA4
  # MTYyMTUyMzNaMEUxEDAOBgNVBAoMB1Bvc3RIb2cxFTATBgNVBAsMDE9uZUxvZ2lu
  # IElkUDEaMBgGA1UEAwwRT25lTG9naW4gQWNjb3VudCAwggEiMA0GCSqGSIb3DQEB
  # AQUAA4IBDwAwggEKAoIBAQDEfUWFIU38ztF2EgijVsIbnlB8OIwkjZU8c34B9VwZ
  # BQQUSxbrkuT9AX/5O27G04TBCHFZsXRId+ABSjVo8daCPu0d38Quo9KS3V3627Nw
  # YcTYsje95lB02E/PgfiEQ6ZGCOV0P4xY9C99d26PoYTcoMT1S73jDDMOFtoD5WXG
  # ZsKqwBks1jbLkv6RYoFBlZX00aGzOXDzUXI59/0c15KR4EzgTad0t6CU7X0HZ2Qf
  # xGUiRb7hDLvgSby0SzpQpYUyYDnN9aSNYzpu1hiyIqrhQ7kZNy7LyGBz0UIuIImF
  # pF6A3bzzrR4wdacFY9U0vmqFXXcepxuT5p2UyAxwbLeDAgMBAAGjgcMwgcAwDAYD
  # VR0TAQH/BAIwADAdBgNVHQ4EFgQURLVVKanZPoXGEfYr1HmlaCEoD54wgYAGA1Ud
  # IwR5MHeAFES1VSmp2T6FxhH2K9R5pWghKA+eoUmkRzBFMRAwDgYDVQQKDAdQb3N0
  # SG9nMRUwEwYDVQQLDAxPbmVMb2dpbiBJZFAxGjAYBgNVBAMMEU9uZUxvZ2luIEFj
  # Y291bnQgghR2uIejyqYBTUjSDGwjtwVkeadrfzAOBgNVHQ8BAf8EBAMCB4AwDQYJ
  # KoZIhvcNAQEFBQADggEBALP5lhlcV8avbnVnqO7PBtlS2mVOJ2B7obm50OaJCbRh
  # t0I/dcNssWhT31/zmtNfKtrFicNImlKhdirApxpIp1WLEFY01a40GLmO6FG/WVvB
  # EzwXonWP+cP8jYQnqZ15JkuHjP3DYJuOak2GqAJAfaGO67q6IkRZzRq6UwEUgNJD
  # TlcsJAFaJDrcw07TY3mRFragdzGC7Xt/CM6r/0seY3+VBwMUMiJlvawcyQxap7om
  # EdgmQkJA8Dk6f+geI+U7jV3orkPiofBJi9K6cp5Fd9usut8jwi3GYg2wExNGbhF4
  # wlMD1LOhymQGBnTXPk+000nkBnYdqEnqXzVpDiCG1Pc=
  x509_cert:
  # -- Name of attribute that contains the permanent ID of the user in SAML assertions.
  # attr_permanent_id: "nameID"
  attr_permanent_id:
  # -- Name of attribute that contains the first name of the user in SAML assertions.
  # attr_first_name: "firstName"
  attr_first_name:
  # -- Name of attribute that contains the last name of the user in SAML assertions.
  # attr_last_name: "lastName"
  attr_last_name:
  # -- Name of attribute that contains the email of the user in SAML assertions.
  # attr_email: "email"
  attr_email:

service:
  # -- PostHog service name.
  name: posthog
  # -- PostHog service type.
  type: NodePort
  externalPort: 8000
  internalPort: 8000

  # -- PostHog service annotations.
  annotations: {}

###
###
### ---- CERT-MANAGER ----
###
###
cert-manager:
  # -- Whether to install `cert-manager` resources.
  enabled: false
  # -- Whether to install `cert-manager` CRDs.
  installCRDs: true
  # -- Who to email if the certificate is about to expire
  # -- Defaults to `notificationEmail` if it is available
  # -- Base default is noreply@<your-ingress-hostname>
  email: null

  #
  # [Workaround] - do not use the local DNS for the 'cert-manager' pods since it would return local IPs
  # and break self checks.
  #
  # For more info see:
  #   - https://github.com/jetstack/cert-manager/issues/1292
  #   - https://github.com/jetstack/cert-manager/issues/3238
  #   - https://github.com/jetstack/cert-manager/issues/4286
  #   - https://github.com/compumike/hairpin-proxy
  #
  # This has some side effects, like 'cert-manager' pods not being able to resolve cluster-local names,
  # but so far this has not caused issues (and we don't expect it to do so).
  #
  podDnsPolicy: None
  podDnsConfig:
    nameservers:
      - 8.8.8.8
      - 1.1.1.1
      - 208.67.222.222

###
###
### ---- INGRESS ----
###
###
ingress:
  # -- Enable ingress controller resource
  enabled: true
  # -- Ingress handler type. Defaults to `nginx` if nginx is enabled and to `clb` on gcp.
  type:
  # -- URL to address your PostHog installation. You will need to set up DNS after installation
  hostname:
  gcp:
    # -- Specifies the name of the global IP address resource to be associated with the google clb
    ip_name: "posthog"
    # -- If true, will force a https redirect when accessed over http
    forceHttps: true
    # -- Specifies the name of the tls secret to be used by the ingress. If not specified a managed certificate will be generated.
    secretName: ""
  # -- Whether to enable letsencrypt. Defaults to true if hostname is defined and nginx and cert-manager are enabled otherwise false.
  letsencrypt:
  nginx:
    # -- Whether nginx is enabled
    enabled: false
    # -- Whether to redirect to TLS with nginx ingress.
    redirectToTLS: true
  # -- Extra annotations
  annotations: {}
  # -- TLS secret to be used by the ingress.
  secretName:

ingress-nginx:
  controller:
    config:
      # -- Whether to forward "X-Forwarded-*" headers to upstream services.
      # -- This is needed to ensure the PostHog application knows e.g. if the
      # -- downstream proxy is using a secure connection. See the official
      # -- [ingress-nginx documentation](https://kubernetes.github.io/ingress-nginx/user-guide/nginx-configuration/configmap/#use-forwarded-headers)
      use-forwarded-headers: "true"

      # Use JSON format for logs, such that we can easily parse them in e.g. Promtail
      #
      # We also add in:
      #
      #  1. the X-Forwarded-For header so we can correlate if requests are from
      #     the same ip.
      #  2. a correlation_id that for the purposes of having functional defaults
      #     is the NGINX generated $request_id. If you are using e.g. an AWS ALB
      #     in front of ingress then consider instead changing this to
      #     `$http_x_amzn_trace_id`.
      #
      log-format-escape-json: "true"
      log-format-upstream: '{
        "time": "$time_iso8601",
        "remote_addr": "$proxy_protocol_addr",
        "request_id": "$request_id",
        "correlation_id": "$request_id",
        "remote_user": "$remote_user",
        "bytes_sent": $bytes_sent,
        "request_time": $request_time,
        "status": $status,
        "host": "$host",
        "request_proto": "$server_protocol",
        "uri": "$uri",
        "request_query": "$args",
        "request_length": $request_length,
        "duration": $request_time,
        "method": "$request_method",
        "http_referrer": "$http_referer",
        "http_user_agent": "$http_user_agent",
        "http_x_forwarded_for": "$http_x_forwarded_for"
        }'

    # Pass NGINX generated $request_id as X-Correlation-ID such that downstreams can use it
    # for logging. See
    # https://django-structlog.readthedocs.io/en/latest/events.html#request-bound-metadata
    # for how django_structlog uses it.
    #
    # If using behind an AWS ALB you can set this to $http_x_amzn_trace_id such
    # that you can correlate with ALB level requests as well.
    proxySetHeaders:
      X-Correlation-ID: $request_id

    # Uncomment those lines if you want Prometheus server to scrape NGINX Ingress controller pods metrics.
    # metrics:
    #   enabled: true
    #   service:
    #     annotations:
    #       prometheus.io/port: "10254"
    #       prometheus.io/scrape: "true"

###
###
### ---- POSTGRESQL ----
###
###
postgresql:
  # -- Whether to deploy a PostgreSQL server to satisfy the applications requirements. To use an external PostgreSQL instance set this to `false` and configure the `externalPostgresql` parameters.
  enabled: true
  # -- Name override for PostgreSQL app.
  nameOverride: posthog-postgresql
  # -- PostgreSQL database name.
  postgresqlDatabase: posthog
  # -- PostgreSQL database password.
  postgresqlPassword: postgres
  persistence:
    # -- Enable persistence using PVC.
    enabled: true
    # -- PVC Storage Request for PostgreSQL volume.
    size: 10Gi

externalPostgresql:
  # -- External PostgreSQL service host.
  postgresqlHost:
  # -- External PostgreSQL service port.
  postgresqlPort: 5432
  # -- External PostgreSQL service database name.
  postgresqlDatabase:
  # -- External PostgreSQL service user.
  postgresqlUsername:
  # -- External PostgreSQL service password. Either this or `externalPostgresql.existingSecret` must be set.
  postgresqlPassword:
  # -- Name of an existing Kubernetes secret object containing the PostgreSQL password
  existingSecret:
  # -- Name of the key pointing to the password in your Kubernetes secret
  existingSecretPasswordKey: postgresql-password

###
###
### ---- PGBOUNCER ----
###
###

_pgbouncer: &_pgbouncer 
# -- Whether to deploy a PgBouncer service to satisfy the applications requirements.
  enabled: true

  exporter:
    # -- Whether to install a Prometheus export as a sidecar
    enabled: false
    port: 9127
    image:
      repository: prometheuscommunity/pgbouncer-exporter
      tag: v0.4.1
      pullPolicy: IfNotPresent
      ## Optionally specify an array of imagePullSecrets.
      ## Secrets must be manually created in the namespace.
      ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
      ## Example:
      ## pullSecrets:
      ##   - myRegistryKeySecretName
      ##
      pullSecrets: []

    # -- Resource limits for pgbouncer-exporter.
    resources: {}

    # -- Container security context for pgbouncer-exporter.
    securityContext:
      enabled: false

  # -- Count of pgbouncer pods to run. This setting is ignored if `pgbouncer.hpa.enabled` is set to `true`.
  replicacount: 1

  hpa:
    # -- Whether to create a HorizontalPodAutoscaler for the pgbouncer stack.
    enabled: false
    # -- CPU threshold percent for the pgbouncer stack HorizontalPodAutoscaler.
    cputhreshold: 60
    # -- Min pods for the pgbouncer stack HorizontalPodAutoscaler.
    minpods: 1
    # -- Max pods for the pgbouncer stack HorizontalPodAutoscaler.
    maxpods: 10
    # -- Set the HPA behavior. See
    # https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/
    # for configuration options
    behavior:

  # -- Additional env variables to inject into the pgbouncer stack deployment.
  env:
    - name: PGBOUNCER_PORT
      value: "6543"
    - name: PGBOUNCER_MAX_CLIENT_CONN
      value: "1000"
    - name: PGBOUNCER_POOL_MODE
      value: transaction
    - name: PGBOUNCER_IGNORE_STARTUP_PARAMETERS
      value: extra_float_digits

  # -- Resource limits for the pgbouncer stack deployment.
  resources: {}

  # -- Node labels for the pgbouncer stack deployment.
  nodeSelector: {}

  # -- Toleration labels for the pgbouncer stack deployment.
  tolerations: []

  # -- Affinity settings for the pgbouncer stack deployment.
  affinity: {}

  # -- Container security context for the pgbouncer stack deployment.
  securityContext:
    enabled: false

  # -- Pod security context for the pgbouncer stack deployment.
  podSecurityContext:
    enabled: false

  readinessProbe:
    # -- The readiness probe failure threshold
    failureThreshold: 3
    # -- The readiness probe initial delay seconds
    initialDelaySeconds: 10
    # -- The readiness probe period seconds
    periodSeconds: 5
    # -- The readiness probe success threshold
    successThreshold: 1
    # -- The readiness probe timeout seconds
    timeoutSeconds: 2

  livenessProbe:
    # -- The liveness probe failure threshold
    failureThreshold: 3
    # -- The liveness probe initial delay seconds
    initialDelaySeconds: 60
    # -- The liveness probe period seconds
    periodSeconds: 10
    # -- The liveness probe success threshold
    successThreshold: 1
    # -- The liveness probe timeout seconds
    timeoutSeconds: 2

  image:
    repository: bitnami/pgbouncer
    tag: 1.18.0
    pullPolicy: IfNotPresent
    ## Optionally specify an array of imagePullSecrets.
    ## Secrets must be manually created in the namespace.
    ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
    ## Example:
    ## pullSecrets:
    ##   - myRegistryKeySecretName
    ##
    pullSecrets: []

  service:
    type: ClusterIP
    annotations: {}

  ## -- PgBouncer pod(s) annotation.
  podAnnotations: {}

pgbouncer:
  <<: *_pgbouncer

  fqdn: ""

pgbouncerRead:
  <<: *_pgbouncer

  # Specify the host to use for a read-replica. This would usually be some sort of load balancer,
  # and otherwise all credentials would be the same
  host: ""
  fqdn: ""

  enabled: false

###
###
### ---- REDIS ----
###
###
redis:
  # -- Whether to deploy a Redis server to satisfy the applications requirements. To use an external redis instance set this to `false` and configure the `externalRedis` parameters.
  enabled: true

  nameOverride: "posthog-redis"

  fullnameOverride: ""

  architecture: standalone

  auth:
    # -- Enable Redis password authentication.
    enabled: false

    # -- Redis password.
    #    Defaults to a random 10-character alphanumeric string if not set.
    #    NOTE: ignored unless `redis.auth.enabled` is `true` or if `redis.auth.existingSecret` is set.
    #
    password: ""

    # -- The name of an existing secret containing the Redis credential to use.
    #    NOTE: ignored unless `redis.auth.enabled` is `true`.
    #          When it is set, the previous `redis.auth.password` parameter is ignored.
    #
    existingSecret: ""

    # -- Password key to be retrieved from existing secret.
    #    NOTE: ignored unless `redis.auth.existingSecret` parameter is set.
    #
    existingSecretPasswordKey: ""

  master:
    persistence:
      # -- Enable data persistence using PVC.
      enabled: true

      # -- Persistent Volume size.
      size: 5Gi
    # -- Array with additional command line flags for Redis master.
    extraFlags:
      ## The maxmemory configuration directive is used in order to configure Redis to use a specified
      ## amount of memory for the data set. Setting maxmemory to zero results into no memory limits
      ## see https://redis.io/topics/lru-cache for more details
      - "--maxmemory 400mb"
      ## The exact behavior Redis follows when the maxmemory limit is reached is configured using the
      ## maxmemory-policy configuration directive
      ## allkeys-lru: evict keys by trying to remove the less recently used (LRU) keys first, in order
      ## to make space for the new data added
      - "--maxmemory-policy allkeys-lru"

externalRedis:
  # -- External Redis host to use.
  host: ""
  # -- External Redis port to use.
  port: 6379
  # -- Password for the external Redis. Ignored if `externalRedis.existingSecret` is set.
  password: ""
  # -- Name of an existing Kubernetes secret object containing the Redis password.
  existingSecret: ""
  # -- Name of the key pointing to the password in your Kubernetes secret.
  existingSecretPasswordKey: ""

externalSessionRecordingRedis: {}
  # -- External Redis host to use.
  # host: ""
  # -- External Redis port to use.
  # port: 6379


###
###
### ---- KAFKA ----
###
###
kafka:
  # -- Whether to deploy Kafka as part of this release. To use an external Kafka instance set this to `false` and configure the `externalKafka` values.
  enabled: true

  nameOverride: posthog-kafka

  fullnameOverride: ""

  # -- A size-based retention policy for logs.
  logRetentionBytes: _15_000_000_000

  # -- The minimum age of a log file to be eligible for deletion due to age.
  logRetentionHours: 24

  # -- The default number of log partitions per topic.
  numPartitions: 1

  persistence:
    # - Enable data persistence using PVC.
    enabled: true
    # -- PVC Storage Request for Kafka data volume.
    size: 20Gi

  zookeeper:
    # -- Switch to enable or disable the ZooKeeper helm chart. !!! Please DO NOT override this (this chart installs Zookeeper separately) !!!
    enabled: false

  externalZookeeper:
    # -- List of external zookeeper servers to use.
    servers:
      - posthog-posthog-zookeeper:2181

externalKafka:
  # - External Kafka brokers. Ignored if `kafka.enabled` is set to `true`. Multiple brokers can be provided as array/list.
  brokers: []
  # - Use TLS to connect to the external kafka cluster
  tls: false

externalSessionRecordingKafka:
  # - External Kafka brokers for session recordings. Ignored if `kafka.enabled` is set to `true`. Multiple brokers can be provided as array/list.
  brokers: []
  # - Use TLS to connect to the external kafka cluster
  tls: false

###
###
### ---- TEMPORAL SCHEDULER ----
### TODO: add support for a self-hosted scheduler in another PR.
###
externalTemporal:
  # - External Temporal scheduler's hostname
  host: ""
  # - External Temporal scheduler's port
  port: 7233
  # - Namespace to register into
  namespace: ""

###
###
### ---- ZOOKEEPER ----
###
###
zookeeper:
  # -- Whether to deploy Zookeeper as part of this release.
  enabled: true

  nameOverride: posthog-zookeeper

  # -- Number of ZooKeeper nodes
  replicaCount: 1

  autopurge:
    # -- The time interval (in hours) for which the purge task has to be triggered
    purgeInterval: 1

  metrics:
    # -- Enable Prometheus to access ZooKeeper metrics endpoint.
    enabled: false
    service:
      annotations:
        "prometheus.io/scrape":
          "false" # let's make Prometheus skip the scraping of the
          # service as we already scrape the pods (see below
          # and https://github.com/bitnami/charts/issues/10101)

  ## -- Zookeeper pod(s) annotation.
  podAnnotations:
    # Uncomment those lines if you want Prometheus server to scrape Zookeeper pods metrics.
    # prometheus.io/scrape: "true"
    # prometheus.io/path: /metrics
    # prometheus.io/port: "9141"

###
###
### ---- CLICKHOUSE ----
###
###
clickhouse:
  # -- Whether to install clickhouse. If false, `clickhouse.host` must be set
  enabled: true
  # -- Which namespace to install clickhouse and the `clickhouse-operator` to (defaults to namespace chart is installed to)
  namespace:
  # -- Clickhouse cluster
  cluster: posthog
  # -- Clickhouse database
  database: posthog
  # -- Clickhouse user
  user: admin
  # -- Clickhouse password
  password: a1f31e03-c88e-4ca6-a2df-ad49183d15d9
  # -- Clickhouse existing secret name that needs to be in the namespace where
  # posthog is deployed into. Will not use the above password value if set
  existingSecret: ""
  # -- Key in the existingSecret containing the password value
  existingSecretPasswordKey: ""
  # -- Whether to use TLS connection connecting to ClickHouse
  secure: false
  # -- Whether to verify TLS certificate on connection to ClickHouse
  verify: false
  # -- List of external Zookeeper servers to use.
  # externalZookeeper:
  #   servers:
  #     - host: host1
  #       port: 2181
  #     - host: host2
  #       port: 2181
  #     - host: host3
  #       port: 2181

  image:
    # -- ClickHouse image repository.
    repository: clickhouse/clickhouse-server
    # -- ClickHouse image tag. Note: PostHog does not support all versions of ClickHouse. Please override the default only if you know what you are doing.
    tag: "23.9.2.56"
    # -- Image pull policy
    pullPolicy: IfNotPresent
    ## Optionally specify an array of imagePullSecrets.
    ## Secrets must be manually created in the namespace.
    ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
    ## Example:
    ## pullSecrets:
    ##   - myRegistryKeySecretName
    ##
    pullSecrets: []

  # -- Toleration labels for clickhouse pod assignment
  tolerations: []
  # -- Affinity settings for clickhouse pod
  affinity: {}
  # -- Clickhouse resource requests/limits. See more at http://kubernetes.io/docs/user-guide/compute-resources/
  resources: {}
  #   limits:
  #     cpu: 1000m
  #     memory: 16Gi
  #   requests:
  #     cpu: 4000m
  #     memory: 16Gi
  securityContext:
    enabled: true
    runAsUser: 101
    runAsGroup: 101
    fsGroup: 101

  # -- Kubernetes Service type.
  serviceType: ClusterIP

  # -- An allowlist of IP addresses or network masks the ClickHouse user is
  # allowed to access from. By default anything within a private network will be
  # allowed. This should suffice for most use case although to expose to other
  # networks you will need to update this setting.
  #
  # For more details on usage, see https://posthog.com/docs/self-host/deploy/configuration#securing-clickhouse
  allowedNetworkIps:
    - "10.0.0.0/8"
    - "172.16.0.0/12"
    - "192.168.0.0/16"

  persistence:
    # -- Enable data persistence using PVC.
    enabled: true

    # -- Use a manually managed Persistent Volume and Claim.
    #    If defined, PVC must be created manually before volume will be bound.
    #
    existingClaim: ""

    # -- Persistent Volume Storage Class to use.
    #    If defined, `storageClassName: <storageClass>`.
    #    If set to `storageClassName: ""`, disables dynamic provisioning.
    #    If undefined (the default) or set to `null`, no storageClassName spec is
    #    set, choosing the default provisioner.
    #
    storageClass: null

    # -- Persistent Volume size
    size: 20Gi

  ## -- Clickhouse user profile configuration.
  ## You can use this to override profile settings, for example `default/max_memory_usage: 40000000000`
  ## For the full list of settings, see:
  ## - https://clickhouse.com/docs/en/operations/settings/settings-profiles/
  ## - https://clickhouse.com/docs/en/operations/settings/settings/
  profiles: {}

  ## -- Default user profile configuration for Clickhouse. !!! Please DO NOT override this !!!
  defaultProfiles:
    default/allow_experimental_window_functions: "1"
    default/allow_nondeterministic_mutations: "1"

  ## -- Clickhouse cluster layout. (Experimental, use at own risk)
  ## For a full list of options, see https://github.com/Altinity/clickhouse-operator/blob/master/docs/custom_resource_explained.md
  ## section on clusters and layouts.
  layout:
    shardsCount: 1
    replicasCount: 1

  ## -- ClickHouse settings configuration.
  ## You can use this to override settings, for example `prometheus/port: 9363`
  ## For the full list of settings, see:
  ## - https://clickhouse.com/docs/en/operations/settings/settings/
  settings:
    {}
    # Uncomment those lines if you want to enable the built-in Prometheus HTTP endpoint in ClickHouse.
    # prometheus/endpoint: /metrics
    # prometheus/port: 9363
    # prometheus/metrics: true
    # prometheus/events: true
    # prometheus/asynchronous_metrics: true

  ## -- Default settings configuration for ClickHouse. !!! Please DO NOT override this !!!
  defaultSettings:
    default_database: "posthog"
    format_schema_path: /etc/clickhouse-server/config.d/

  ## -- specify additional user configs for ClickHouse. This will be added to
  ## the users.xml configuration. See
  ## https://github.com/Altinity/clickhouse-operator for details.
  additionalUsersConfig:

  ## -- ClickHouse pod(s) annotation.
  podAnnotations:
    # Uncomment those lines if you want Prometheus server to scrape ClickHouse pods metrics.
    # prometheus.io/scrape: "true"
    # prometheus.io/path: /metrics
    # prometheus.io/port: "9363"

  ## -- Clickhouse pod distribution.
  podDistribution:
    # Uncomment to have replicas of each shard reside in different availability zones.
    # - scope: Shard
    #   type: ShardAntiAffinity
    #   topologyKey: "topology.kubernetes.io/zone"

  client:
    image:
      # -- ClickHouse image repository.
      repository: clickhouse/clickhouse-server
      # -- ClickHouse image tag. Note: PostHog does not support all versions of ClickHouse. Please override the default only if you know what you are doing.
      tag: "23.9.2.56"
      # -- Image pull policy
      pullPolicy: IfNotPresent
      ## Optionally specify an array of imagePullSecrets.
      ## Secrets must be manually created in the namespace.
      ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
      ## Example:
      ## pullSecrets:
      ##   - myRegistryKeySecretName
      ##
      pullSecrets: []

  backup:
    # https://posthog.com/docs/self-host/runbook/clickhouse/backup
    # https://github.com/AlexAkulov/clickhouse-backup
    enabled: false
    image:
      # -- Clickhouse backup image repository.
      repository: altinity/clickhouse-backup
      # -- ClickHouse backup image tag.
      tag: "1.5.0"
      # -- Image pull policy
      pullPolicy: IfNotPresent
      ## Optionally specify an array of imagePullSecrets.
      ## Secrets must be manually created in the namespace.
      ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
      ## Example:
      ## pullSecrets:
      ##   - myRegistryKeySecretName
      ##
      pullSecrets: []

    backup_user: backup
    # password in plain text because it's using in cronjob
    backup_password: backup_password
    # -- Use an existing secret name in the deployed namespace for the backup
    # password
    existingSecret: ""
    # -- Key in the existingSecret containing the password value
    existingSecretPasswordKey: ""
    backup_schedule: "0 0 * * *" # backup every day at 0:00
    clickhouse_services: "chi-posthog-posthog-0-0" # use first replica in each shard, use `kubectl get svc | grep chi-posthog-posthog`

    # All options: https://github.com/AlexAkulov/clickhouse-backup#default-config
    env:
      - name: LOG_LEVEL
        value: "debug"
      - name: ALLOW_EMPTY_BACKUPS
        value: "true"
      - name: API_LISTEN
        value: "0.0.0.0:7171"
      # INSERT INTO system.backup_actions to execute backup
      - name: API_CREATE_INTEGRATION_TABLES
        value: "true"
      - name: BACKUPS_TO_KEEP_REMOTE
        value: "0"
      # Add settings for remote backup storage.

## External clickhouse configuration
##
externalClickhouse:
  # -- Host of the external cluster. This is required when clickhouse.enabled is false
  host:
  # -- Name of the external cluster to run DDL queries on. This is required when clickhouse.enabled is false
  cluster:
  # -- Database name for the external cluster
  database: posthog
  # -- User name for the external cluster to connect to the external cluster as
  user:
  # -- Password for the cluster. Ignored if existingClickhouse.existingSecret is set
  password:
  # -- Name of an existing Kubernetes secret object containing the password
  existingSecret:
  # -- Name of the key pointing to the password in your Kubernetes secret
  existingSecretPasswordKey:
  # -- Whether to use TLS connection connecting to ClickHouse
  secure: false
  # -- Whether to verify TLS connection connecting to ClickHouse
  verify: false

cloudwatch:
  # -- Enable cloudwatch container insights to get logs and metrics on AWS
  enabled: false
  # -- AWS region
  region:
  # -- AWS EKS cluster name
  clusterName:
  # -- fluentBit configuration
  fluentBit:
    server: "On"
    port: 2020
    readHead: "On"
    readTail: "Off"

# Provide affinity for hooks if needed
hooks:
  # -- Node labels for hooks.
  nodeSelector: {}
  # -- Toleration labels for hooks.
  tolerations: []
  # -- Affinity settings for hooks.
  affinity: {}
  migrate:
    # -- Env variables for migate hooks
    env: []
    # -- Hook job resource limits/requests
    resources: {}

serviceAccount:
  # -- Configures if a ServiceAccount with this name should be created
  create: true
  # The name of the service account to use.
  # If not set and create is true, a name is generated using the fullname template
  # -- name of the ServiceAccount to be used by access-controlled resources.
  # @default autogenerated
  name:
  # -- Configures annotation for the ServiceAccount
  annotations: {}

###
###
### ---- MINIO (Object Storage system) ----
###
###
minio:
  # -- Whether to install MinIO (object storage system) or not. You can keep it disabled or rely on `externalObjectStorage` if you want to use a managed object storage service (AWS S3, Google Cloud Storage, ...).
  enabled: false
  auth:
    # -- MinIO root username
    rootUser: root-user
    # -- MinIO root password
    rootPassword: root-password-change-me-please
    # -- Use existing secret for credentials details (`auth.rootUser` and `auth.rootPassword` will be ignored and picked up from this secret). The secret has to contain the keys `root-user` and `root-password`)
    existingSecret:
  persistence:
    # -- Enable MinIO data persistence using PVC.
    enabled: true
  # -- Comma, semi-colon or space separated list of buckets to create at initialization (only in standalone mode)
  defaultBuckets: "posthog"
  # -- Disable MinIO Web UI
  disableWebUI: true

  # We are overriding the default service ports as they collide with ClickHouse
  service:
    ports:
      # -- MinIO API service port
      api: "19000"
      # -- MinIO Console service port
      console: "19001"

  ## -- MinIO pod(s) annotation.
  podAnnotations:
    # Uncomment those lines if you want Prometheus server to scrape MinIO pods metrics.
    # prometheus.io/scrape: "true"
    # prometheus.io/path: "/minio/v2/metrics/cluster"
    # prometheus.io/port: "9000"

## External Object Storage configuration
##
externalObjectStorage:
  # -- Endpoint of the external object storage. e.g. https://s3.us-east-1.amazonaws.com
  endpoint:
  # -- Host of the external object storage. Deprecated: use endpoint instead
  host:
  # -- Port of the external object storage. Deprecated: use endpoint instead
  port:
  # -- Bucket name to use.
  bucket:
  # -- Region of the bucket (for AWS).
  region:
  # -- Name of an existing Kubernetes secret object containing the `access_key_id` and `secret_access_key`. The secret has to contain the keys `root-user` and `root-password`).
  existingSecret:

###
###
### ---- Grafana ----
###
###
grafana:
  # -- Whether to install Grafana or not.
  enabled: false

  # -- Sidecar configuration to automagically pull the dashboards from the `charts/posthog/grafana-dashboard` folder. See [official docs](https://github.com/grafana/helm-charts/blob/main/charts/grafana/README.md) for more info.
  sidecar:
    dashboards:
      enabled: true
      label: grafana_dashboard
      folderAnnotation: grafana_folder
      provider:
        foldersFromFilesStructure: true

  # -- Configure Grafana datasources. See [docs](http://docs.grafana.org/administration/provisioning/#datasources) for more info.
  datasources:
    datasources.yaml:
      apiVersion: 1
      datasources:
        # Comment the snippet below if you are running with `prometheus.enabled: false`
        - name: Prometheus
          type: prometheus
          url: http://posthog-prometheus-server
          access: proxy
          isDefault: true
          jsonData:
            timeInterval:
              60s # pass this explicitly so it can be used by '$__rate_interval'
              # https://grafana.com/blog/2020/09/28/new-in-grafana-7.2-__rate_interval-for-prometheus-rate-queries-that-just-work/

        # Comment the snippet below if you are running with `loki.enabled: false`
        - name: Loki
          type: loki
          url: http://posthog-loki-read:3100
          access: proxy
          isDefault: false

        # Comment the snippet below if you are running with `prometheus.alertmanager.enabled: false`
        - name: Alertmanager
          type: alertmanager
          url: http://posthog-prometheus-alertmanager
          access: proxy
          isDefault: false
          jsonData:
            implementation: prometheus

###
###
### ---- Loki ----
###
###
loki:
  # -- Whether to install Loki or not. With the default configuration you will
  # get no replication, so as to easily support small deploys that e.g. do not
  # have multiple nodes in the cluster. For production setups that are
  # distributed across e.g. multiple AWS AZs it's recommended that you increase
  # the replica counts for `read:` and `write:`. These stateful sets by default
  # have an anti-affinity so you'll need at least as many nodes as replicas in a
  # set.
  enabled: false

  loki:
    auth_enabled: false
    commonConfig:
      replication_factor: 1

    ## -- Pod annotations.
    podAnnotations:
      {}
      # Uncomment those lines if you want Prometheus server to scrape metrics.
      # prometheus.io/scrape: "true"
      # prometheus.io/path: /metrics
      # prometheus.io/port: "3100"

  read:
    replicas: 1

  write:
    replicas: 1

  gateway:
    enabled: false

  minio:
    # -- Whether to enable minio as backing storage for Loki. To use S3 or GCS
    # instead, set this to false and specify the appropriate `loki.storage`
    # configuration.
    #
    # Note if you do use minio in production, the default setup is minimal and
    # will only run with 1 replica. In production setups it's recommended change
    # minio settings to your needs.
    enabled: true
    replicas: 1
    drivesPerNode: 2

  # We add this override as otherwise the resource naming doesn't include
  # "posthog-" prepended. The upgrade from Loki Chart 2.x to 3.x resulted in the
  # naming of e.g. services to change. By adding we maintain backwards compat.
  # for anything that may be referencing e.g. services.
  fullnameOverride: posthog-loki
  nameOverride: posthog-loki

  # Whether to enabled monitoring of Loki. We avoid enabling this by default as
  # it requires installing additional CRDs (e.g. the grafana-operator)
  monitoring:
    alerts:
      enabled: false
    dashboards:
      enabled: false
    rules:
      enabled: false
    selfMonitoring:
      enabled: false
      grafanaAgent:
        installOperator: false
      lokiCanary:
        enabled: false
    serviceMonitor:
      enabled: false

  test:
    enabled: false

###
###
### ---- EventRouter: https://github.com/vmware-archive/eventrouter
###
###
eventrouter:
  # -- Whether to install eventrouter.
  enabled: false
  image:
    repository: gcr.io/heptio-images/eventrouter
    tag: v0.3
    pullPolicy: IfNotPresent
    ## Optionally specify an array of imagePullSecrets.
    ## Secrets must be manually created in the namespace.
    ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
    ## Example:
    ## pullSecrets:
    ##   - myRegistryKeySecretName
    ##
    pullSecrets: []

  # -- Resource limits for eventrouter.
  resources: {}

###
###
### ---- Promtail ----
###
###
promtail:
  # -- Whether to install Promtail or not.
  enabled: false

  config:
    clients:
      - url: http://posthog-loki-write:3100/loki/api/v1/push

    snippets:
      pipelineStages:
        - cri: {}
        - match:
            selector: '{app="ingress-nginx"}'
            stages:
              - json:
                  expressions:
                    timestamp: time
                    host: host
                    method: method
                    uri: uri
                    status: status
                    user_agent: http_user_agent
                    correlation_id: correlation_id
                    forwarded_for: http_x_forwarded_for
              - labels:
                  method:
                  status:
              - timestamp:
                  source: timestamp
                  format: RFC3339
        - match:
            selector: '{app="posthog", container=~"posthog-web|posthog-worker|posthog-events"}'
            stages:
              - json:
                  expressions:
                    timestamp:
                    level:
              - labels:
                  level:
              - timestamp:
                  source: timestamp
                  format: RFC3339Nano

  ## -- Pod annotations.
  podAnnotations:
    {}
    # Uncomment those lines if you want Prometheus server to scrape metrics.
    # prometheus.io/scrape: "true"
    # prometheus.io/path: /metrics
    # prometheus.io/port: "3101"

###
###
### ---- Prometheus ----
###
###
prometheus:
  # -- Whether to install Prometheus or not.
  enabled: false

  alertmanager:
    # -- Whether to install Prometheus AlertManager or not.
    enabled: false
    podAnnotations:
      {}
      # Uncomment those lines if you want Prometheus server to scrape metrics.
      # prometheus.io/scrape: "true"
      # prometheus.io/path: /metrics
      # prometheus.io/port: "9093"

  pushgateway:
    # -- Whether to install Prometheus Pushgateway or not.
    enabled: false

  serverFiles:
    # -- Alerts configuration. For more information see: https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/
    #
    # -- NOTE: alerting is an important part of any production system. With this Helm chart we aim to provide a good
    # -- collection of default rules that can be used to successfully alert an operator if a PostHog installation is not
    # -- working as expected. As those rules will likely evolve over time and as we don't want to cut a new major release
    # -- every time it happens, please consider the `prometheus.serverFiles.alerting_rules.yml` defaults as UNSTABLE.
    # -- Please consider to explicitly override this input in your `values.yaml` if you need to keep it stable.
    #
    alerting_rules.yml:
      #
      # The majority of alerts are inspired by the great collection of rules available at:
      # https://github.com/samber/awesome-prometheus-alerts
      #
      groups:
        - name: PostHog
          rules:
            - alert: IngestionOverflowProduction
              expr: |
                sum(
                  delta(
                    kafka_topic_partition_current_offset{
                      topic="events_plugin_ingestion_overflow"
                    }[1m]
                  )
                ) > 0
              for: 10m
              labels:
                rotation: common
                severity: warning
              annotations:
                summary: |
                  Ingestion has pushed events to the overflow topic for
                  10 minutes.
                description: Due to some scenario such as many events from a
                  single distinct_id, we have pushed some events to the
                  ingestion overflow topic so we can keed up with events from
                  other users. Check partition stats for how many events we've
                  received for each distinct_id or team_id, or look in
                  ClickHouse for any recent trends for distinct_ids.

            - alert: IngestionOverflowConsumerLag
              expr: |
                sum(
                  delta(
                    kafka_consumergroup_lag{
                      topic='events_plugin_ingestion_overflow', consumergroup="clickhouse-ingestion-overflow"
                    }[2m]
                  )
                ) > 0
              for: 10m
              labels:
                rotation: common
                severity: warning
              annotations:
                summary: |
                  Ingestion lag on the Overflow topic has been increasing over the past 10 minutes.
                description: |
                  Lag on the ingestion topic is increasing. Check that the
                  consumer for the topic is running. Also check the production
                  rate to the topic to see if there is an unusually high volume
                  going to it.

            - alert: DjangoErrorRate
              expr: |
                sum by (role) (increase(django_http_responses_total_by_status_view_method_total{status=~"^5.*"}[5m])) /
                sum by (role) (increase(django_http_responses_total_by_status_view_method_total[5m])) > 0.02
              for: 5m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: Django error rate exceeds 2% on role {{ $labels.role }}
                description: |
                  Django reports a high error rate (5xx status codes) on role {{ $labels.role }}.
                  Check the "Exceptions" widget in the "HTTP by application endpoint" dashboard and the pod logs to
                  identify the issue. Either a dependency is unhealthy, or a recent code change triggered a bug and
                  needs to be rolled-back.

            - alert: End2EndIngestionLag
              expr: (max by(scenario) (posthog_celery_observed_ingestion_lag_seconds{scenario=~"ingestion_api|ingestion"})) > 1200
              for: 5m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: End-to-end analytics event ingestion lag exceeds 20 minutes for more than 5 minutes.
                description: |
                  Our end-to-end probe measured an ingestion lag higher than 20 minutes for scenario {{ $labels.scenario }}.
                  Check the "Kafka (cluster overview)" dashboard to identify what topics and partitions are lagging and
                  follow the https://posthog.com/docs/runbook/services/plugin-server/ingestion-lag runbook for recovery
                  steps.

            - alert: ExportsConsumerDelayed
              expr: (time() * 1000 - (max(latest_processed_timestamp_ms{groupId="async_handlers",topic="clickhouse_events_json"}))) > 300000
              for: 5m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: Exports and WebHooks have delayed by more than 5 minutes for more than 5 minutes.
                description: "Latest timestamp registered as processed on topic 'clickhouse_events_json', consumer group 'async_handlers' more then 5 minutes old"

            - alert: ScheduledTasksConsumerDelayed
              expr: (time() * 1000 - (max(latest_processed_timestamp_ms{groupId="scheduled-tasks-runner",topic="scheduled_tasks"}))) > 300000
              for: 10m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: RunEveryX tasks have been delayed by more than 5 minutes for more than 5 minutes.
                description: "Latest timestamp registered as processed on topic 'scheduled_tasks', consumer group 'scheduled-tasks-runner' more then 5 minutes old"

            - alert: JobsConsumerDelayed
              expr: (time() * 1000 - (max(latest_processed_timestamp_ms{groupId="jobs-inserter",topic="jobs"}))) > 300000
              for: 10m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: Jobs scheduled via Apps jobs have been delayed by more than 5 minutes for more than 5 minutes.
                runbook_url: https://github.com/PostHog/product-internal/blob/main/infrastructure/runbooks/pipeline/graphile.md
                description: |
                  Latest timestamp registered as processed on topic 'jobs', consumer group 'jobs-inserter' more then 5 minutes old.
                  Check https://github.com/PostHog/product-internal/blob/main/infrastructure/runbooks/pipeline/graphile.md
                  for more context and steps to recovery.

            - alert: IngestionConsumerDelayed
              expr: (time() * 1000 - (max(latest_processed_timestamp_ms{groupId="ingestion",topic="events_plugin_ingestion"}))) > 300000
              for: 5m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: Ingestion for analytics events has been delayed by more than 5 minutes for more than 5 minutes.
                description: "Latest timestamp registered as processed on topic 'events_plugin_ingestion', consumer group 'ingestion' more then 5 minutes old"

            - alert: RecordingsConsumerDelayed
              # TODO: fix these consumer delay alerts. The issue with the
              # current alerts is that they are not the _oldest_ message not
              # processed but the _newest_ of the oldest _per partition_. This
              # applies to all the alerts for consumer lag above. Adjusting the
              # query to the below could work, but also simply using absolute
              # lag may be the least work
              #
              # ```
              # (time() * 1000 - (
              #   min(
              #     max(
              #       latest_processed_timestamp_ms{groupId="session-recordings",topic="session_recording_events"}
              #     ) by (topic)
              #   )
              # ))
              # ```
              #
              # The issue with the above is when there is no volume on a
              # partition, then we end up not reporting a timestamp for this
              # partition and the alert will sound incorrectly.
              expr: (time() * 1000 - (max(latest_processed_timestamp_ms{groupId="session-recordings",topic="session_recording_events"}))) > 300000
              for: 5m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: Ingestion for session recording and web performance events has been delayed by more than 5 minutes for more than 5 minutes.
                description: "Latest timestamp registered as processed on topic 'session_recording_events', consumer group 'session-recordings' more then 5 minutes old"

            - alert: RecordingsConsumerDLQ
              expr: sum(delta(kafka_topic_partition_current_offset{topic="session_recording_events_dlq"}[5m])) > 0
              for: 1m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: Failed to process some session recording events and have been sent to the dead letter queue for review.
                description: "The `session_recording_events_dlq` topic offset has increased over the past 5 minutes."

            - alert: GraphileJobExecutionLag
              expr: (max by(task_identifier) (posthog_celery_graphile_lag_seconds{task_identifier!="bufferJob"})) > 900
              for: 5m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: Graphile jobs execution lag exceeds 15 minutes for more than 5 minutes.
                runbook_url: https://github.com/PostHog/product-internal/blob/main/infrastructure/runbooks/pipeline/graphile.md
                description: |
                  Jobs of type {{ $labels.task_identifier }} have been sitting in the Graphile execution queue for more
                  than 5 minutes, possibly delaying apps and/or exports.
                  Check https://github.com/PostHog/product-internal/blob/main/infrastructure/runbooks/pipeline/graphile.md
                  for more context and steps to recovery.

            - alert: CeleryQueueDepth
              expr: (max (posthog_celery_queue_depth)) > 1000
              for: 10m
              labels:
                rotation: common
                severity: critical
              annotations:
                summary: Celery job execution delayed for more than 10 minutes.
                description: |
                  The Celery jobs queue (stored in Redis) is filling up faster than it is consumed. This impacts our
                  monitoring, as some paging monitors depend on metrics exported by Celery jobs.
                    - make sure posthog-worker pods are healthy and check their logs
                    - look for recent code changes to posthog/celery.py and rollback if needed
                    - check the health of Postgres and Clickhouse, many jobs query them and could hang if these
                      stores get slow

            - alert: KafkaDiskCritical
              expr: min by (instance) (aws_msk_node_filesystem_free_bytes{mountpoint="/kafka/datalogs"}) < 536870912000
              for: 2m
              labels:
                severity: critical
                rotation: common
              annotations:
                summary: Less than 500GB free on Kafka broker(s)
                description: |
                  Kafka disks are getting full and should be upscaled before we lose new events.
                  We should upscale the disks, or (as a last-ditch option) lower the data retention
                  to free up disk space.

            - alert: KafkaDiskCapacityPlanning
              expr: min by (instance) (aws_msk_node_filesystem_free_bytes{mountpoint="/kafka/datalogs"}) < 1036870912000
              for: 2m
              labels:
                severity: warning
                rotation: infra
              annotations:
                summary: Less than 1TB free on Kafka broker(s)
                description: |
                  Kafka disks are getting full and should be upscaled before we lose new events.
                  If not handled, the KafkaDiskCritical will page the common rotation at 500GB.

        - name: Kubernetes # via kube-state-metrics
          rules:
            - alert: KubernetesNodeReady
              expr: kube_node_status_condition{condition="Ready",status="true"} == 0
              for: 10m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes Node ready (instance {{ $labels.instance }})
                description: "Node {{ $labels.node }} has been unready for a long time"

            - alert: KubernetesMemoryPressure
              expr: kube_node_status_condition{condition="MemoryPressure",status="true"} == 1
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes memory pressure (instance {{ $labels.instance }})
                description: "{{ $labels.node }} has MemoryPressure condition"

            - alert: KubernetesDiskPressure
              expr: kube_node_status_condition{condition="DiskPressure",status="true"} == 1
              for: 10m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes disk pressure (instance {{ $labels.instance }})
                description: "{{ $labels.node }} has DiskPressure condition"

            - alert: KubernetesOutOfDisk
              expr: kube_node_status_condition{condition="OutOfDisk",status="true"} == 1
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes out of disk (instance {{ $labels.instance }})
                description: "{{ $labels.node }} has OutOfDisk condition"

            - alert: KubernetesOutOfCapacity
              expr: sum by (node) ((kube_pod_status_phase{phase="Running"} == 1) + on(uid) group_left(node) (0 * kube_pod_info{pod_template_hash=""})) / sum by (node) (kube_node_status_allocatable{resource="pods"}) * 100 > 90
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes out of capacity (instance {{ $labels.instance }})
                description: "{{ $labels.node }} is out of capacity"

            - alert: KubernetesContainerOomKiller
              expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes container oom killer (instance {{ $labels.instance }})
                description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes."

            - alert: KubernetesJobFailed
              expr: kube_job_status_failed > 0
              for: 0m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes Job failed (instance {{ $labels.instance }})
                description: "Job {{$labels.namespace}}/{{$labels.exported_job}} failed to complete"

            - alert: KubernetesCronjobSuspended
              expr: kube_cronjob_spec_suspend != 0
              for: 0m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes CronJob suspended (instance {{ $labels.instance }})
                description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended"

            - alert: KubernetesPersistentvolumeclaimPending
              expr: kube_persistentvolumeclaim_status_phase{phase="Pending"} == 1
              for: 2m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes PersistentVolumeClaim pending (instance {{ $labels.instance }})
                description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending"

            - alert: KubernetesVolumeOutOfDiskSpace
              expr: kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes Volume out of disk space (instance {{ $labels.instance }})
                description: "Volume is almost full (< 10% left)"

            - alert: KubernetesVolumeFullInFourDays
              expr: predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes Volume full in four days (instance {{ $labels.instance }})
                description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available."

            - alert: KubernetesPersistentvolumeError
              expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending", job="kube-state-metrics"} > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes PersistentVolume error (instance {{ $labels.instance }})
                description: "Persistent volume is in bad state"

            - alert: KubernetesStatefulsetDown
              expr: (kube_statefulset_status_replicas_ready / kube_statefulset_status_replicas_current) != 1
              for: 1m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes StatefulSet down (instance {{ $labels.instance }})
                description: "A StatefulSet went down"

            - alert: KubernetesHpaScalingAbility
              expr: kube_horizontalpodautoscaler_status_condition{status="false", condition="AbleToScale"} == 1
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes HPA scaling ability (instance {{ $labels.instance }})
                description: "Pod is unable to scale"

            - alert: KubernetesHpaMetricAvailability
              expr: kube_horizontalpodautoscaler_status_condition{status="false", condition="ScalingActive"} == 1
              for: 5m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes HPA metric availability (instance {{ $labels.instance }})
                description: "HPA is not able to collect metrics"

            - alert: KubernetesHpaScaleCapability
              expr: kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes HPA scale capability (instance {{ $labels.instance }})
                description: "The maximum number of desired Pods has been hit"

            - alert: KubernetesPodNotHealthy
              expr: sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}) > 0
              for: 15m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})
                description: "Pod has been in a non-ready state for longer than 15 minutes."

            - alert: KubernetesPodCrashLooping
              expr: increase(kube_pod_container_status_restarts_total[1m]) > 3
              for: 2m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes pod crash looping (instance {{ $labels.instance }})
                description: "Pod {{ $labels.pod }} is crash looping"

            - alert: KubernetesReplicassetMismatch
              expr: kube_replicaset_spec_replicas != kube_replicaset_status_ready_replicas
              for: 10m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes ReplicasSet mismatch (instance {{ $labels.instance }})
                description: >
                  The number of ready pods in the Deployment's replicaset does
                  not match the desired number.

            - alert: KubernetesDeploymentReplicasMismatch
              expr: kube_deployment_spec_replicas != kube_deployment_status_replicas_available
              for: 10m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes Deployment replicas mismatch (instance {{ $labels.instance }})
                description: >
                  The number of ready pods in the Deployment does not match the
                  desired number.

            - alert: KubernetesStatefulsetReplicasMismatch
              expr: kube_statefulset_status_replicas_ready != kube_statefulset_status_replicas
              for: 10m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes StatefulSet replicas mismatch (instance {{ $labels.instance }})
                description: >
                  The number of ready pods in the StatefulSet does not match the
                  desired number.

            - alert: KubernetesDeploymentGenerationMismatch
              expr: kube_deployment_status_observed_generation != kube_deployment_metadata_generation
              for: 10m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes Deployment generation mismatch (instance {{ $labels.instance }})
                description: "A Deployment has failed but has not been rolled back."

            - alert: KubernetesStatefulsetGenerationMismatch
              expr: kube_statefulset_status_observed_generation != kube_statefulset_metadata_generation
              for: 10m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes StatefulSet generation mismatch (instance {{ $labels.instance }})
                description: "A StatefulSet has failed but has not been rolled back."

            - alert: KubernetesStatefulsetUpdateNotRolledOut
              expr: max without (revision) (kube_statefulset_status_current_revision unless kube_statefulset_status_update_revision) * (kube_statefulset_replicas != kube_statefulset_status_replicas_updated)
              for: 10m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes StatefulSet update not rolled out (instance {{ $labels.instance }})
                description: "StatefulSet update has not been rolled out."

            - alert: KubernetesDaemonsetRolloutStuck
              expr: kube_daemonset_status_number_ready / kube_daemonset_status_desired_number_scheduled * 100 < 100 or kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled > 0
              for: 10m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes DaemonSet rollout stuck (instance {{ $labels.instance }})
                description: "Some Pods of DaemonSet are not scheduled or not ready"

            - alert: KubernetesDaemonsetMisscheduled
              expr: kube_daemonset_status_number_misscheduled > 0
              for: 5m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes DaemonSet misscheduled (instance {{ $labels.instance }})
                description: "Some DaemonSet Pods are running where they are not supposed to run"

            - alert: KubernetesCronjobTooLong
              expr: time() - kube_cronjob_next_schedule_time > 3600
              for: 0m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes CronJob too long (instance {{ $labels.instance }})
                description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete."

            - alert: KubernetesJobSlowCompletion
              expr: kube_job_spec_completions - kube_job_status_succeeded > 0
              for: 12h
              labels:
                severity: critical
              annotations:
                summary: Kubernetes job slow completion (instance {{ $labels.instance }})
                description: "Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time."

            - alert: KubernetesApiServerErrors
              expr: sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[1m])) / sum(rate(apiserver_request_total{job="apiserver"}[1m])) * 100 > 3
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes API server errors (instance {{ $labels.instance }})
                description: "Kubernetes API server is experiencing high error rate"

            - alert: KubernetesApiClientErrors
              expr: (sum(rate(rest_client_requests_total{code=~"(4|5).."}[1m])) by (instance, job) / sum(rate(rest_client_requests_total[1m])) by (instance, job)) * 100 > 1
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes API client errors (instance {{ $labels.instance }})
                description: "Kubernetes API client is experiencing high error rate"

            - alert: KubernetesClientCertificateExpiresNextWeek
              expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 7*24*60*60
              for: 0m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes client certificate expires next week (instance {{ $labels.instance }})
                description: "A client certificate used to authenticate to the apiserver is expiring next week."

            - alert: KubernetesClientCertificateExpiresSoon
              expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 24*60*60
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Kubernetes client certificate expires soon (instance {{ $labels.instance }})
                description: "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours."

            - alert: KubernetesApiServerLatency
              expr: histogram_quantile(0.99, sum(rate(apiserver_request_latencies_bucket{subresource!="log",verb!~"^(?:CONNECT|WATCHLIST|WATCH|PROXY)$"} [10m])) WITHOUT (instance, resource)) / 1e+06 > 1
              for: 2m
              labels:
                severity: warning
              annotations:
                summary: Kubernetes API server latency (instance {{ $labels.instance }})
                description: "Kubernetes API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}."

        - name: Loki # via embedded exporter
          rules:
            - alert: LokiProcessTooManyRestarts
              expr: changes(process_start_time_seconds{app="loki"}[15m]) > 2
              for: 0m
              labels:
                severity: warning
              annotations:
                summary: Loki process too many restarts (instance {{ $labels.instance }})
                description: "A loki process had too many restarts (target {{ $labels.instance }})"

            - alert: LokiRequestErrors
              expr: 100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[1m])) by (namespace, job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route) > 10
              for: 15m
              labels:
                severity: warning
              annotations:
                summary: Loki request errors (instance {{ $labels.instance }})
                description: "The {{ $labels.job }} and {{ $labels.route }} are experiencing errors"

            - alert: LokiRequestPanic
              expr: sum(increase(loki_panic_total[10m])) by (namespace, job) > 0
              for: 5m
              labels:
                severity: warning
              annotations:
                summary: Loki request panic (instance {{ $labels.instance }})
                description: 'The {{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics'

            - alert: LokiRequestLatency
              expr: (histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{route!~"(?i).*tail.*"}[5m])) by (le))) > 3
              for: 10m
              labels:
                severity: warning
              annotations:
                summary: Loki request latency (instance {{ $labels.instance }})
                description: 'The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency'

        - name: Promtail # via embedded exporter
          rules:
            - alert: PromtailRequestErrors
              expr: 100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[1m])) by (namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[1m])) by (namespace, job, route, instance) > 10
              for: 5m
              labels:
                severity: critical
              annotations:
                summary: Promtail request errors (instance {{ $labels.instance }})
                description: 'The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors.'

            - alert: PromtailRequestLatency
              expr: histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[5m])) by (le)) > 1
              for: 5m
              labels:
                severity: critical
              annotations:
                summary: Promtail request latency (instance {{ $labels.instance }})
                description: 'The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency.'

        - name: Prometheus # via embedded exporter
          rules:
            - alert: PrometheusJobMissing
              expr: absent(up{job="prometheus"})
              for: 0m
              labels:
                severity: warning
              annotations:
                summary: Prometheus job missing (instance {{ $labels.instance }})
                description: "A Prometheus job has disappeared"

            - alert: PrometheusTargetMissing
              expr: up == 0
              for: 5m
              labels:
                severity: critical
              annotations:
                summary: Prometheus target missing (instance {{ $labels.instance }})
                description: "A Prometheus target has disappeared. An exporter might be crashed."

            - alert: PrometheusAllTargetsMissing
              expr: sum by (job) (up) == 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus all targets missing (instance {{ $labels.instance }})
                description: "A Prometheus job does not have living target anymore."

            - alert: PrometheusConfigurationReloadFailure
              expr: prometheus_config_last_reload_successful != 1
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus configuration reload failure (instance {{ $labels.instance }})
                description: "Prometheus configuration reload error"

            - alert: PrometheusTooManyRestarts
              expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus too many restarts (instance {{ $labels.instance }})
                description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping."

            - alert: PrometheusAlertmanagerJobMissing
              expr: absent(up{job="kubernetes-pods", app="prometheus", component="alertmanager"})
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus AlertManager job missing (instance {{ $labels.instance }})
                description: "A Prometheus AlertManager job has disappeared"

            - alert: PrometheusAlertmanagerConfigurationReloadFailure
              expr: alertmanager_config_last_reload_successful != 1
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})
                description: "AlertManager configuration reload error"

            - alert: PrometheusAlertmanagerConfigNotSynced
              expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus AlertManager config not synced (instance {{ $labels.instance }})
                description: "Configurations of AlertManager cluster instances are out of sync"

            - alert: PrometheusAlertmanagerE2eDeadManSwitch
              expr: vector(1)
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus AlertManager E2E dead man switch (instance {{ $labels.instance }})
                description: "Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager."

            - alert: PrometheusNotConnectedToAlertmanager
              expr: prometheus_notifications_alertmanagers_discovered < 1
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus not connected to alertmanager (instance {{ $labels.instance }})
                description: "Prometheus cannot connect the alertmanager"

            - alert: PrometheusRuleEvaluationFailures
              expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus rule evaluation failures (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts."

            - alert: PrometheusTemplateTextExpansionFailures
              expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus template text expansion failures (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} template text expansion failures"

            - alert: PrometheusRuleEvaluationSlow
              expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
              for: 5m
              labels:
                severity: warning
              annotations:
                summary: Prometheus rule evaluation slow (instance {{ $labels.instance }})
                description: "Prometheus rule evaluation took more time than the scheduled interval. It indicates a slower storage backend access or too complex query."

            - alert: PrometheusNotificationsBacklog
              expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
              for: 0m
              labels:
                severity: warning
              annotations:
                summary: Prometheus notifications backlog (instance {{ $labels.instance }})
                description: "The Prometheus notification queue has not been empty for 10 minutes"

            - alert: PrometheusAlertmanagerNotificationFailing
              expr: rate(alertmanager_notifications_failed_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus AlertManager notification failing (instance {{ $labels.instance }})
                description: "Alertmanager is failing sending notifications"

            - alert: PrometheusTargetEmpty
              expr: prometheus_sd_discovered_targets == 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus target empty (instance {{ $labels.instance }})
                description: "Prometheus has no target in service discovery"

            - alert: PrometheusTargetScrapingSlow
              expr: prometheus_target_interval_length_seconds{quantile="0.9"} / on (interval, instance, job) prometheus_target_interval_length_seconds{quantile="0.5"} > 1.05
              for: 5m
              labels:
                severity: warning
              annotations:
                summary: Prometheus target scraping slow (instance {{ $labels.instance }})
                description: "Prometheus is scraping exporters slowly since it exceeded the requested interval time. Your Prometheus server is under-provisioned."

            - alert: PrometheusLargeScrape
              expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10
              for: 5m
              labels:
                severity: warning
              annotations:
                summary: Prometheus large scrape (instance {{ $labels.instance }})
                description: "Prometheus has many scrapes that exceed the sample limit"

            - alert: PrometheusTargetScrapeDuplicate
              expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 0
              for: 0m
              labels:
                severity: warning
              annotations:
                summary: Prometheus target scrape duplicate (instance {{ $labels.instance }})
                description: "Prometheus has many samples rejected due to duplicate timestamps but different values"

            - alert: PrometheusTsdbCheckpointCreationFailures
              expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} checkpoint creation failures"

            - alert: PrometheusTsdbCheckpointDeletionFailures
              expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} checkpoint deletion failures"

            - alert: PrometheusTsdbCompactionsFailed
              expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus TSDB compactions failed (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} TSDB compactions failures"

            - alert: PrometheusTsdbHeadTruncationsFailed
              expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus TSDB head truncations failed (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} TSDB head truncation failures"

            - alert: PrometheusTsdbReloadFailures
              expr: increase(prometheus_tsdb_reloads_failures_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus TSDB reload failures (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} TSDB reload failures"

            - alert: PrometheusTsdbWalCorruptions
              expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} TSDB WAL corruptions"

            - alert: PrometheusTsdbWalTruncationsFailed
              expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})
                description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures"

        - name: Redis # via prometheus-redis-exporter
          rules:
            - alert: RedisDown
              expr: redis_up == 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Redis down (instance {{ $labels.instance }})
                description: "Redis instance is down"

            - alert: RedisMissingMaster
              expr: (count(redis_instance_info{role="master"}) or vector(0)) < 1
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Redis missing master (instance {{ $labels.instance }})
                description: "Redis cluster has no node marked as master."

            - alert: RedisTooManyMasters
              expr: count(redis_instance_info{role="master"}) > 1
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Redis too many masters (instance {{ $labels.instance }})
                description: "Redis cluster has too many nodes marked as master."

            - alert: RedisDisconnectedSlaves
              expr: count without (instance, job) (redis_connected_slaves) - sum without (instance, job) (redis_connected_slaves) - 1 > 1
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Redis disconnected slaves (instance {{ $labels.instance }})
                description: "Redis not replicating for all slaves. Consider reviewing the redis replication status."

            - alert: RedisReplicationBroken
              expr: delta(redis_connected_slaves[1m]) < 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Redis replication broken (instance {{ $labels.instance }})
                description: "Redis instance lost a slave"

            - alert: RedisClusterFlapping
              expr: changes(redis_connected_slaves[1m]) > 1
              for: 2m
              labels:
                severity: critical
              annotations:
                summary: Redis cluster flapping (instance {{ $labels.instance }})
                description: "Changes have been detected in Redis replica connection. This can occur when replica nodes lose connection to the master and reconnect (a.k.a flapping)."

            - alert: RedisMissingBackup
              expr: time() - redis_rdb_last_save_timestamp_seconds > 60 * 60 * 24
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Redis missing backup (instance {{ $labels.instance }})
                description: "Redis has not been backuped for 24 hours"

            # The exporter must be started with --include-system-metrics flag or REDIS_EXPORTER_INCL_SYSTEM_METRICS=true environment variable.
            - alert: RedisOutOfSystemMemory
              expr: redis_memory_used_bytes / redis_total_system_memory_bytes * 100 > 90
              for: 2m
              labels:
                severity: warning
              annotations:
                summary: Redis out of system memory (instance {{ $labels.instance }})
                description: "Redis is running out of system memory (> 90%)"

            - alert: RedisOutOfConfiguredMaxmemory
              expr: redis_memory_used_bytes / redis_memory_max_bytes * 100 > 90
              for: 2m
              labels:
                severity: warning
              annotations:
                summary: Redis out of configured maxmemory (instance {{ $labels.instance }})
                description: "Redis is running out of configured maxmemory (> 90%)"

            - alert: RedisTooManyConnections
              expr: redis_connected_clients > 100
              for: 2m
              labels:
                severity: warning
              annotations:
                summary: Redis too many connections (instance {{ $labels.instance }})
                description: "Redis instance has too many connections"

            - alert: RedisNotEnoughConnections
              expr: redis_connected_clients < 5
              for: 2m
              labels:
                severity: warning
              annotations:
                summary: Redis not enough connections (instance {{ $labels.instance }})
                description: "Redis instance should have more connections (> 5)"

            - alert: RedisRejectedConnections
              expr: increase(redis_rejected_connections_total[1m]) > 0
              for: 0m
              labels:
                severity: critical
              annotations:
                summary: Redis rejected connections (instance {{ $labels.instance }})
                description: "Some connections to Redis has been rejected"

###
###
### ---- prometheus-pushgateway ----
###
###
prometheus-pushgateway:
  # -- Whether to install the `prometheus-pushgateway` or not.
  enabled: false
  # -- Map of annotations to add to the pods.
  podAnnotations:
    prometheus.io/scrape: "true"
    prometheus.io/path: /metrics
    prometheus.io/port: "9091"

###
###
### ---- external-prometheus-pushgateway ----
###
###
external-prometheus-pushgateway:
  # -- Whether to enable the external `prometheus-pushgateway` or not.
  enabled: false
  # -- Address to the external `prometheus-pushgateway`
  address: prometheus-pushgateway:9091

###
###
### ---- prometheus-statsd-exporter ----
###
###
prometheus-statsd-exporter:
  # -- Whether to install the `prometheus-statsd-exporter` or not.
  enabled: false
  # -- Map of annotations to add to the pods.
  podAnnotations:
    prometheus.io/scrape: "true"
    prometheus.io/path: /metrics
    prometheus.io/port: "9102"

externalStatsd:
  # -- External Statsd host to use.
  host:
  # -- External Statsd port to use.
  port:

###
###
### ---- prometheus-kafka-exporter ----
###
###
prometheus-kafka-exporter:
  # -- Whether to install the `prometheus-kafka-exporter` or not.
  enabled: false

  # -- Map of annotations to add to the pods.
  annotations:
    prometheus.io/scrape: "true"
    prometheus.io/path: /metrics
    prometheus.io/port: "9308"

  # -- Specify the target Kafka brokers to monitor.
  kafkaServer:
    - posthog-posthog-kafka:9092

###
###
### ---- prometheus-postgres-exporter ----
###
###
prometheus-postgres-exporter:
  # -- Whether to install the `prometheus-postgres-exporter` or not.
  enabled: false

  # -- Map of annotations to add to the pods.
  annotations:
    prometheus.io/scrape: "true"
    prometheus.io/path: /metrics
    prometheus.io/port: "9187"

  # -- Configuration options.
  config:
    datasource:
      host: posthog-posthog-postgresql
      user: postgres
      passwordSecret:
        name: posthog-posthog-postgresql
        key: postgresql-password

###
###
### ---- prometheus-redis-exporter ----
###
###
prometheus-redis-exporter:
  # -- Whether to install the `prometheus-redis-exporter` or not.
  enabled: false

  # -- Map of annotations to add to the pods.
  annotations:
    prometheus.io/scrape: "true"
    prometheus.io/path: /metrics
    prometheus.io/port: "9121"

  # -- Specify the target Redis instance to monitor.
  redisAddress: redis://posthog-posthog-redis-master:6379

###
###
### ---- MISC ----
###
###
installCustomStorageClass: false

busybox:
  # -- Specify the image to use for e.g. init containers
  image: busybox:1.34
  # -- Image pull policy
  pullPolicy: IfNotPresent
  ## Optionally specify an array of imagePullSecrets.
  ## Secrets must be manually created in the namespace.
  ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
  ## Example:
  ## pullSecrets:
  ##   - myRegistryKeySecretName
  ##
  pullSecrets: []

# -- Kubernetes cluster domain name
clusterDomain: cluster.local