diff --git a/CHANGELOG.md b/CHANGELOG.md index 403e37d253..69b9352f5d 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -30,6 +30,7 @@ * [9184](https://github.com/grafana/loki/pull/9184) **periklis**: Bump dskit to introduce IPv6 support for memberlist * [9357](https://github.com/grafana/loki/pull/9357) **Indransh**: Add HTTP API to change the log level at runtime * [9431](https://github.com/grafana/loki/pull/9431) **dannykopping**: Add more buckets to `loki_memcache_request_duration_seconds` metric; latencies can increase if using memcached with NVMe +* [8684](https://github.com/grafana/loki/pull/8684) **oleksii-boiko-ua**: Helm: Add hpa templates for read, write and backend components. ##### Fixes diff --git a/docs/sources/installation/helm/reference.md b/docs/sources/installation/helm/reference.md index b32ba88aff..7de274aa52 100644 --- a/docs/sources/installation/helm/reference.md +++ b/docs/sources/installation/helm/reference.md @@ -38,6 +38,60 @@ This is the generated reference for the Loki Helm Chart values. 
 Hard node and soft zone anti-affinity
+ + + + backend.autoscaling.behavior + object + Behavior policies while scaling. + 
+{}
+
+ + + + backend.autoscaling.enabled + bool + Enable autoscaling for the backend. + 
+false
+
+ + + + backend.autoscaling.maxReplicas + int + Maximum autoscaling replicas for the backend. + 
+3
+
+ + + + backend.autoscaling.minReplicas + int + Minimum autoscaling replicas for the backend. + 
+1
+
+ + + + backend.autoscaling.targetCPUUtilizationPercentage + int + Target CPU utilization percentage for the backend. + 
+60
+
+ + + + backend.autoscaling.targetMemoryUtilizationPercentage + string + Target memory utilization percentage for the backend. + 
+null
+
@@ -764,6 +818,15 @@ null 
 Hard node and soft zone anti-affinity
+ + + + gateway.autoscaling.behavior + object + Behavior policies while scaling. + 
+{}
+
@@ -874,13 +937,11 @@ null - gateway.deploymentStrategy - object - ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy + gateway.deploymentStrategy.type + string + 
-{
-  "type": "RollingUpdate"
-}
+"RollingUpdate"
@@ -2780,6 +2841,15 @@ false 
 Hard node and soft zone anti-affinity
+ + + + read.autoscaling.behavior + object + Behavior policies while scaling. + 
+{}
+
@@ -3699,6 +3769,97 @@ null 
 Hard node and soft zone anti-affinity
+ + + + write.autoscaling.behavior + object + Behavior policies while scaling. + 
+{
+  "scaleDown": {
+    "policies": [
+      {
+        "periodSeconds": 1800,
+        "type": "Pods",
+        "value": 1
+      }
+    ]
+  },
+  "scaleUp": {
+    "policies": [
+      {
+        "periodSeconds": 900,
+        "type": "Pods",
+        "value": 1
+      }
+    ]
+  },
+  "stabilizationWindowSeconds": 3600
+}
+
+ + + + write.autoscaling.behavior.scaleUp + object + see https://github.com/grafana/loki/blob/main/docs/sources/operations/storage/wal.md#how-to-scale-updown for scaledown details + 
+{
+  "policies": [
+    {
+      "periodSeconds": 900,
+      "type": "Pods",
+      "value": 1
+    }
+  ]
+}
+
+ + + + write.autoscaling.enabled + bool + Enable autoscaling for the write. + 
+false
+
+ + + + write.autoscaling.maxReplicas + int + Maximum autoscaling replicas for the write. + 
+3
+
+ + + + write.autoscaling.minReplicas + int + Minimum autoscaling replicas for the write. + 
+1
+
+ + + + write.autoscaling.targetCPUUtilizationPercentage + int + Target CPU utilisation percentage for the write. + 
+60
+
+ + + + write.autoscaling.targetMemoryUtilizationPercentage + string + Target memory utilization percentage for the write. + 
+null
+
diff --git a/docs/sources/operations/storage/wal.md b/docs/sources/operations/storage/wal.md index bc31bc4aa3..85eaa3d83d 100644 --- a/docs/sources/operations/storage/wal.md +++ b/docs/sources/operations/storage/wal.md @@ -95,6 +95,18 @@ Statefulsets are significantly more cumbersome to work with/upgrade/etc. Much of In this case, try `kubectl -n delete sts ingester --cascade=false`. This will leave the pods alive but delete the statefulset. Then you may recreate the (updated) statefulset and one-by-one start deleting the `ingester-0` through `ingester-n` pods _in that order_, allowing the statefulset to spin up new pods to replace them. +#### Scaling Down Using `/flush_shutdown` Endpoint and Lifecycle Hook + +1. **StatefulSets for Ordered Scaling Down**: Loki's ingesters should be scaled down one by one, which is efficiently handled by Kubernetes StatefulSets. This ensures an ordered and reliable scaling process, as described in the [Deployment and Scaling Guarantees](https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#deployment-and-scaling-guarantees) documentation. + +2. **Using PreStop Lifecycle Hook**: During the pod scaling down process, the PreStop [lifecycle hook](https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/) triggers the `/flush_shutdown` endpoint on the ingester. This action flushes the chunks and removes the ingester from the ring, allowing it to register as unready and become eligible for deletion. + +3. **Using terminationGracePeriodSeconds**: Provides time for the ingester to flush its data before being deleted, if flushing data takes more than 30 minutes, you may need to increase it. + +4. **Cleaning Persistent Volumes**: Persistent volumes are automatically cleaned up by leveraging the [enableStatefulSetAutoDeletePVC](https://kubernetes.io/blog/2021/12/16/kubernetes-1-23-statefulset-pvc-auto-deletion/) feature in Kubernetes. + +By following the above steps, you can ensure a smooth scaling down process for Loki's ingesters while maintaining data integrity and minimizing potential disruptions. + ### Non-Kubernetes or baremetal deployments * When the ingester restarts for any reason (upgrade, crash, etc), it should be able to attach to the same volume in order to recover back the WAL and tokens. diff --git a/production/helm/loki/CHANGELOG.md b/production/helm/loki/CHANGELOG.md index b159fd163c..5dde3e2687 100644 --- a/production/helm/loki/CHANGELOG.md +++ b/production/helm/loki/CHANGELOG.md @@ -13,6 +13,10 @@ Entries should include a reference to the pull request that introduced the chang [//]: # ( : do not remove this line. This locator is used by the CI pipeline to automatically create a changelog entry for each new Loki release. Add other chart versions and respective changelog entries bellow this line.) +## 5.5.6 + +- [FEATURE] Add hpa templates for read, write and backend. + ## 5.5.5 - [BUGFIX] Quote tenantId value in logsInstance diff --git a/production/helm/loki/Chart.yaml b/production/helm/loki/Chart.yaml index 53eb136dea..9976bb270a 100644 --- a/production/helm/loki/Chart.yaml +++ b/production/helm/loki/Chart.yaml @@ -3,7 +3,7 @@ name: loki description: Helm chart for Grafana Loki in simple, scalable mode type: application appVersion: 2.8.2 -version: 5.5.5 +version: 5.5.6 home: https://grafana.github.io/helm-charts sources: - https://github.com/grafana/loki diff --git a/production/helm/loki/README.md b/production/helm/loki/README.md index b2b0a61603..85239d198c 100644 --- a/production/helm/loki/README.md +++ b/production/helm/loki/README.md @@ -1,6 +1,6 @@ # loki -![Version: 5.5.5](https://img.shields.io/badge/Version-5.5.5-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.8.2](https://img.shields.io/badge/AppVersion-2.8.2-informational?style=flat-square) +![Version: 5.5.6](https://img.shields.io/badge/Version-5.5.6-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.8.2](https://img.shields.io/badge/AppVersion-2.8.2-informational?style=flat-square) Helm chart for Grafana Loki in simple, scalable mode diff --git a/production/helm/loki/templates/backend/hpa.yaml b/production/helm/loki/templates/backend/hpa.yaml new file mode 100644 index 0000000000..83487e9aaa --- /dev/null +++ b/production/helm/loki/templates/backend/hpa.yaml @@ -0,0 +1,49 @@ +{{- $isSimpleScalable := eq (include "loki.deployment.isScalable" .) "true" -}} +{{- $autoscalingv2 := .Capabilities.APIVersions.Has "autoscaling/v2" -}} +{{- if and $isSimpleScalable (not .Values.read.legacyReadTarget ) ( .Values.backend.autoscaling.enabled ) }} +{{- if $autoscalingv2 }} +apiVersion: autoscaling/v2 +{{- else }} +apiVersion: autoscaling/v2beta1 +{{- end }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "loki.backendFullname" . }} + labels: + {{- include "loki.backendLabels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: StatefulSet + name: {{ include "loki.backendFullname" . }} + minReplicas: {{ .Values.backend.autoscaling.minReplicas }} + maxReplicas: {{ .Values.backend.autoscaling.maxReplicas }} + {{- with .Values.backend.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.backend.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if $autoscalingv2 }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.backend.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if $autoscalingv2 }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/production/helm/loki/templates/backend/statefulset-backend.yaml b/production/helm/loki/templates/backend/statefulset-backend.yaml index d74bd9c957..59816a4749 100644 --- a/production/helm/loki/templates/backend/statefulset-backend.yaml +++ b/production/helm/loki/templates/backend/statefulset-backend.yaml @@ -10,7 +10,9 @@ metadata: {{- include "loki.backendLabels" . | nindent 4 }} app.kubernetes.io/part-of: memberlist spec: +{{- if not .Values.backend.autoscaling.enabled }} replicas: {{ .Values.backend.replicas }} +{{- end }} podManagementPolicy: Parallel updateStrategy: rollingUpdate: diff --git a/production/helm/loki/templates/gateway/hpa.yaml b/production/helm/loki/templates/gateway/hpa.yaml index c71b4f2284..3541ec6965 100644 --- a/production/helm/loki/templates/gateway/hpa.yaml +++ b/production/helm/loki/templates/gateway/hpa.yaml @@ -18,6 +18,10 @@ spec: name: {{ include "loki.gatewayFullname" . }} minReplicas: {{ .Values.gateway.autoscaling.minReplicas }} maxReplicas: {{ .Values.gateway.autoscaling.maxReplicas }} + {{- with .Values.gateway.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} metrics: {{- with .Values.gateway.autoscaling.targetMemoryUtilizationPercentage }} - type: Resource diff --git a/production/helm/loki/templates/read/hpa.yaml b/production/helm/loki/templates/read/hpa.yaml new file mode 100644 index 0000000000..5515ecb0b4 --- /dev/null +++ b/production/helm/loki/templates/read/hpa.yaml @@ -0,0 +1,55 @@ +{{- $isSimpleScalable := eq (include "loki.deployment.isScalable" .) "true" -}} +{{- $autoscalingv2 := .Capabilities.APIVersions.Has "autoscaling/v2" -}} +{{- if and $isSimpleScalable ( .Values.read.autoscaling.enabled ) }} +{{- if $autoscalingv2 }} +apiVersion: autoscaling/v2 +{{- else }} +apiVersion: autoscaling/v2beta1 +{{- end }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "loki.readFullname" . }} + labels: + {{- include "loki.readLabels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 +{{- if and $isSimpleScalable (not .Values.read.legacyReadTarget ) }} + kind: Deployment + name: {{ include "loki.readFullname" . }} +{{- else }} + kind: StatefulSet + name: {{ include "loki.readFullname" . }} +{{- end }} + minReplicas: {{ .Values.read.autoscaling.minReplicas }} + maxReplicas: {{ .Values.read.autoscaling.maxReplicas }} + {{- with .Values.read.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} + metrics: + {{- with .Values.read.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if $autoscalingv2 }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.read.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if $autoscalingv2 }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/production/helm/loki/templates/read/statefulset-read.yaml b/production/helm/loki/templates/read/statefulset-read.yaml index 93e9c0e85e..b4eb9ba369 100644 --- a/production/helm/loki/templates/read/statefulset-read.yaml +++ b/production/helm/loki/templates/read/statefulset-read.yaml @@ -10,7 +10,9 @@ metadata: app.kubernetes.io/part-of: memberlist {{- include "loki.readLabels" . | nindent 4 }} spec: +{{- if not .Values.read.autoscaling.enabled }} replicas: {{ .Values.read.replicas }} +{{- end }} podManagementPolicy: Parallel updateStrategy: rollingUpdate: diff --git a/production/helm/loki/templates/write/hpa.yaml b/production/helm/loki/templates/write/hpa.yaml new file mode 100644 index 0000000000..18d59dbd07 --- /dev/null +++ b/production/helm/loki/templates/write/hpa.yaml @@ -0,0 +1,50 @@ +{{- $isSimpleScalable := eq (include "loki.deployment.isScalable" .) "true" -}} +{{- $autoscalingv2 := .Capabilities.APIVersions.Has "autoscaling/v2" -}} +{{- if and $isSimpleScalable ( .Values.write.autoscaling.enabled ) }} +{{- if $autoscalingv2 }} +apiVersion: autoscaling/v2 +{{- else }} +apiVersion: autoscaling/v2beta1 +{{- end }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "loki.writeFullname" . }} + labels: + {{- include "loki.writeLabels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: StatefulSet + name: {{ include "loki.writeFullname" . }} + minReplicas: {{ .Values.write.autoscaling.minReplicas }} + maxReplicas: {{ .Values.write.autoscaling.maxReplicas }} + {{- with .Values.write.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} + metrics: + {{- with .Values.write.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if $autoscalingv2 }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.write.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if $autoscalingv2 }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/production/helm/loki/templates/write/statefulset-write.yaml b/production/helm/loki/templates/write/statefulset-write.yaml index 3a55247251..b1756e4321 100644 --- a/production/helm/loki/templates/write/statefulset-write.yaml +++ b/production/helm/loki/templates/write/statefulset-write.yaml @@ -9,9 +9,10 @@ metadata: {{- include "loki.writeLabels" . | nindent 4 }} app.kubernetes.io/part-of: memberlist spec: +{{- if not .Values.write.autoscaling.enabled }} replicas: {{ .Values.write.replicas }} - - podManagementPolicy: Parallel +{{- end }} + podManagementPolicy: OrderedReady updateStrategy: rollingUpdate: partition: 0 @@ -101,9 +102,15 @@ spec: {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} readinessProbe: {{- toYaml .Values.loki.readinessProbe | nindent 12 }} - {{- with .Values.write.lifecycle }} + {{- if .Values.write.lifecycle }} lifecycle: - {{- toYaml . | nindent 12 }} + {{- toYaml .Values.write.lifecycle | nindent 12 }} + {{- else if .Values.write.autoscaling.enabled }} + lifecycle: + preStop: + httpGet: + path: "/ingester/flush_shutdown" + port: http-metrics {{- end }} volumeMounts: - name: config diff --git a/production/helm/loki/values.yaml b/production/helm/loki/values.yaml index ad799bb770..3b1aafad51 100644 --- a/production/helm/loki/values.yaml +++ b/production/helm/loki/values.yaml @@ -645,6 +645,31 @@ monitoring: write: # -- Number of replicas for the write replicas: 3 + autoscaling: + # -- Enable autoscaling for the write. + enabled: false + # -- Minimum autoscaling replicas for the write. + minReplicas: 1 + # -- Maximum autoscaling replicas for the write. + maxReplicas: 3 + # -- Target CPU utilisation percentage for the write. + targetCPUUtilizationPercentage: 60 + # -- Target memory utilization percentage for the write. + targetMemoryUtilizationPercentage: + # -- Behavior policies while scaling. + behavior: + # -- see https://github.com/grafana/loki/blob/main/docs/sources/operations/storage/wal.md#how-to-scale-updown for scaledown details + scaleUp: + policies: + - type: Pods + value: 1 + periodSeconds: 900 + scaleDown: + policies: + - type: Pods + value: 1 + periodSeconds: 1800 + stabilizationWindowSeconds: 3600 image: # -- The Docker registry for the write image. Overrides `loki.image.registry` registry: null @@ -672,6 +697,11 @@ write: extraEnvFrom: [] # -- Lifecycle for the write container lifecycle: {} + # -- The default /flush_shutdown preStop hook is recommended as part of the ingester + # scaledown process so it's added to the template by default when autoscaling is enabled, + # but it's disabled to optimize rolling restarts in instances that will never be scaled + # down or when using chunks storage with WAL disabled. + # https://github.com/grafana/loki/blob/main/docs/sources/operations/storage/wal.md#how-to-scale-updown # -- Init containers to add to the write pods initContainers: [] # -- Volume mounts to add to the write pods @@ -784,6 +814,20 @@ read: targetCPUUtilizationPercentage: 60 # -- Target memory utilisation percentage for the read targetMemoryUtilizationPercentage: + # -- Behavior policies while scaling. + behavior: {} + # scaleUp: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 1 + # periodSeconds: 60 + # scaleDown: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 1 + # periodSeconds: 180 image: # -- The Docker registry for the read image. Overrides `loki.image.registry` registry: null @@ -853,6 +897,31 @@ read: backend: # -- Number of replicas for the backend replicas: 3 + autoscaling: + # -- Enable autoscaling for the backend. + enabled: false + # -- Minimum autoscaling replicas for the backend. + minReplicas: 1 + # -- Maximum autoscaling replicas for the backend. + maxReplicas: 3 + # -- Target CPU utilization percentage for the backend. + targetCPUUtilizationPercentage: 60 + # -- Target memory utilization percentage for the backend. + targetMemoryUtilizationPercentage: + # -- Behavior policies while scaling. + behavior: {} + # scaleUp: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 1 + # periodSeconds: 60 + # scaleDown: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 1 + # periodSeconds: 180 image: # -- The Docker registry for the backend image. Overrides `loki.image.registry` registry: null @@ -1060,6 +1129,20 @@ gateway: targetMemoryUtilizationPercentage: # -- See `kubectl explain deployment.spec.strategy` for more # -- ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy + # -- Behavior policies while scaling. + behavior: {} + # scaleUp: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 1 + # periodSeconds: 60 + # scaleDown: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 1 + # periodSeconds: 180 deploymentStrategy: type: RollingUpdate image: