feat(helm): update chart kube-prometheus-stack to 39.13.3

[chii-bot]

This PR contains the following updates:

Package	Update	Change
kube-prometheus-stack (source)	minor	39.4.0 -> 39.13.3

---

⚠ Dependency Lookup Warnings ⚠

Warnings were logged while processing this repo. Please check the Dependency Dashboard for more information.

---

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about these updates again.

---

• If you want to rebase/retry this PR, click this checkbox.

---

This PR has been generated by Renovate Bot.

[chii-bot]

Path: cluster/apps/monitoring/kube-prometheus-stack/helm-release.yaml
Version: 39.4.0 -> 39.13.3

@@ -5689,7 +5689,7 @@
 "steppedLine": false,
 "targets": [
 {
- "expr": "sum(rate(grpc_server_started_total{job=\"$cluster\",grpc_type=\"unary\"}[5m]))",
+ "expr": "sum(rate(grpc_server_started_total{job=\"$cluster\",grpc_type=\"unary\"}[$__rate_interval]))",
 "format": "time_series",
 "intervalFactor": 2,
 "legendFormat": "RPC Rate",
@@ -5698,7 +5698,7 @@
 "step": 2
 },
 {
- "expr": "sum(rate(grpc_server_handled_total{job=\"$cluster\",grpc_type=\"unary\",grpc_code!=\"OK\"}[5m]))",
+ "expr": "sum(rate(grpc_server_handled_total{job=\"$cluster\",grpc_type=\"unary\",grpc_code=~\"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded\"}[$__rate_interval]))",
 "format": "time_series",
 "intervalFactor": 2,
 "legendFormat": "RPC Failed Rate",
@@ -5945,7 +5945,7 @@
 "steppedLine": true,
 "targets": [
 {
- "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))",
+ "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=\"$cluster\"}[$__rate_interval])) by (instance, le))",
 "hide": false,
 "intervalFactor": 2,
 "legendFormat": "{{instance}} WAL fsync",
@@ -5954,7 +5954,7 @@
 "step": 4
 },
 {
- "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))",
+ "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=\"$cluster\"}[$__rate_interval])) by (instance, le))",
 "intervalFactor": 2,
 "legendFormat": "{{instance}} DB fsync",
 "metric": "etcd_disk_backend_commit_duration_seconds_bucket",
@@ -6112,7 +6112,7 @@
 "steppedLine": false,
 "targets": [
 {
- "expr": "rate(etcd_network_client_grpc_received_bytes_total{job=\"$cluster\"}[5m])",
+ "expr": "rate(etcd_network_client_grpc_received_bytes_total{job=\"$cluster\"}[$__rate_interval])",
 "intervalFactor": 2,
 "legendFormat": "{{instance}} Client Traffic In",
 "metric": "etcd_network_client_grpc_received_bytes_total",
@@ -6188,7 +6188,7 @@
 "steppedLine": false,
 "targets": [
 {
- "expr": "rate(etcd_network_client_grpc_sent_bytes_total{job=\"$cluster\"}[5m])",
+ "expr": "rate(etcd_network_client_grpc_sent_bytes_total{job=\"$cluster\"}[$__rate_interval])",
 "intervalFactor": 2,
 "legendFormat": "{{instance}} Client Traffic Out",
 "metric": "etcd_network_client_grpc_sent_bytes_total",
@@ -6264,7 +6264,7 @@
 "steppedLine": false,
 "targets": [
 {
- "expr": "sum(rate(etcd_network_peer_received_bytes_total{job=\"$cluster\"}[5m])) by (instance)",
+ "expr": "sum(rate(etcd_network_peer_received_bytes_total{job=\"$cluster\"}[$__rate_interval])) by (instance)",
 "intervalFactor": 2,
 "legendFormat": "{{instance}} Peer Traffic In",
 "metric": "etcd_network_peer_received_bytes_total",
@@ -6341,7 +6341,7 @@
 "steppedLine": false,
 "targets": [
 {
- "expr": "sum(rate(etcd_network_peer_sent_bytes_total{job=\"$cluster\"}[5m])) by (instance)",
+ "expr": "sum(rate(etcd_network_peer_sent_bytes_total{job=\"$cluster\"}[$__rate_interval])) by (instance)",
 "hide": false,
 "interval": "",
 "intervalFactor": 2,
@@ -6425,7 +6425,7 @@
 "steppedLine": false,
 "targets": [
 {
- "expr": "sum(rate(etcd_server_proposals_failed_total{job=\"$cluster\"}[5m]))",
+ "expr": "sum(rate(etcd_server_proposals_failed_total{job=\"$cluster\"}[$__rate_interval]))",
 "intervalFactor": 2,
 "legendFormat": "Proposal Failure Rate",
 "metric": "etcd_server_proposals_failed_total",
@@ -6441,7 +6441,7 @@
 "step": 2
 },
 {
- "expr": "sum(rate(etcd_server_proposals_committed_total{job=\"$cluster\"}[5m]))",
+ "expr": "sum(rate(etcd_server_proposals_committed_total{job=\"$cluster\"}[$__rate_interval]))",
 "intervalFactor": 2,
 "legendFormat": "Proposal Commit Rate",
 "metric": "etcd_server_proposals_committed_total",
@@ -6449,7 +6449,7 @@
 "step": 2
 },
 {
- "expr": "sum(rate(etcd_server_proposals_applied_total{job=\"$cluster\"}[5m]))",
+ "expr": "sum(rate(etcd_server_proposals_applied_total{job=\"$cluster\"}[$__rate_interval]))",
 "intervalFactor": 2,
 "legendFormat": "Proposal Apply Rate",
 "refId": "D",
@@ -6570,6 +6570,115 @@
 "show": true
 }
 ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "decimals": 0,
+ "editable": true,
+ "error": false,
+ "fieldConfig": {
+ "defaults": {
+ "custom": {}
+ },
+ "overrides": []
+ },
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 28
+ },
+ "hiddenSeries": false,
+ "id": 42,
+ "isNew": true,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "connected",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "7.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile(0.99, sum by (instance, le) (rate(etcd_network_peer_round_trip_time_seconds_bucket{job=\"$cluster\"}[$__rate_interval])))",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} Peer round trip time",
+ "metric": "etcd_network_peer_round_trip_time_seconds_bucket",
+ "refId": "A",
+ "step": 2
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Peer round trip time",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:925",
+ "decimals": null,
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:926",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
 }
 ],
 "title": "New row"
@@ -6578,7 +6687,9 @@
 "schemaVersion": 13,
 "sharedCrosshair": false,
 "style": "dark",
- "tags": [],
+ "tags": [
+ "etcd-mixin"
+ ],
 "templating": {
 "list": [
 {
@@ -6587,7 +6698,7 @@
 "value": "Prometheus"
 },
 "hide": 0,
- "label": null,
+ "label": "Data Source",
 "name": "datasource",
 "options": [],
 "query": "prometheus",
@@ -6609,7 +6720,7 @@
 "name": "cluster",
 "options": [],
 "query": "label_values(etcd_server_has_leader, job)",
- "refresh": 1,
+ "refresh": 2,
 "regex": "",
 "sort": 2,
 "tagValuesQuery": "",
@@ -38691,6 +38802,7 @@
 namespace: default
 name: kube-prometheus-stack-operator
 path: /admission-prometheusrules/mutate
+ timeoutSeconds: 10
 admissionReviewVersions: ["v1", "v1beta1"]
 sideEffects: None
 ---
@@ -38958,61 +39070,84 @@
 groups:
 - name: etcd
 rules:
+ - alert: etcdMembersDown
+ annotations:
+ description: 'etcd cluster "{{ $labels.job }}": members are down ({{ $value }}).'
+ summary: etcd cluster members are down.
+ expr: |-
+ max without (endpoint) (
+ sum without (instance) (up{job=~".*etcd.*"} == bool 0)
+ or
+ count without (To) (
+ sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01
+ )
+ )
+ > 0
+ for: 10m
+ labels:
+ severity: critical
 - alert: etcdInsufficientMembers
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value }}).'
- expr: sum(up{job=~".*etcd.*"} == bool 1) by (job) < ((count(up{job=~".*etcd.*"}) by (job) + 1) / 2)
+ description: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value }}).'
+ summary: etcd cluster has insufficient number of members.
+ expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2)
 for: 3m
 labels:
 severity: critical
 - alert: etcdNoLeader
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has no leader.'
+ description: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has no leader.'
+ summary: etcd cluster has no leader.
 expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
 for: 1m
 labels:
 severity: critical
 - alert: etcdHighNumberOfLeaderChanges
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last hour.'
- expr: rate(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}[15m]) > 3
- for: 15m
+ description: 'etcd cluster "{{ $labels.job }}": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.'
+ summary: etcd cluster has high number of leader changes.
+ expr: increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 4
+ for: 5m
 labels:
 severity: warning
 - alert: etcdHighNumberOfFailedGRPCRequests
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
+ description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
+ summary: etcd cluster has high number of failed grpc requests.
 expr: |-
- 100 LICENSE README.md Taskfile.yml cluster default docs hack mkdocs.yml scripts talos sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
+ 100 LICENSE README.md Taskfile.yml cluster default docs hack mkdocs.yml scripts talos sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code)
 /
- sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
+ sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code)
 > 1
 for: 10m
 labels:
 severity: warning
 - alert: etcdHighNumberOfFailedGRPCRequests
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
+ description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
+ summary: etcd cluster has high number of failed grpc requests.
 expr: |-
- 100 LICENSE README.md Taskfile.yml cluster default docs hack mkdocs.yml scripts talos sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
+ 100 LICENSE README.md Taskfile.yml cluster default docs hack mkdocs.yml scripts talos sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code)
 /
- sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
+ sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code)
 > 5
 for: 5m
 labels:
 severity: critical
 - alert: etcdGRPCRequestsSlow
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": gRPC requests to {{ $labels.grpc_method }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}.'
+ description: 'etcd cluster "{{ $labels.job }}": 99th percentile of gRPC requests is {{ $value }}s on etcd instance {{ $labels.instance }} for {{ $labels.grpc_method }} method.'
+ summary: etcd grpc requests are slow
 expr: |-
- histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_type="unary"}[5m])) by (job, instance, grpc_service, grpc_method, le))
+ histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type))
 > 0.15
 for: 10m
 labels:
 severity: critical
 - alert: etcdMemberCommunicationSlow
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.'
+ description: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.'
+ summary: etcd cluster member communication is slow.
 expr: |-
 histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m]))
 > 0.15
@@ -39021,53 +39156,64 @@
 severity: warning
 - alert: etcdHighNumberOfFailedProposals
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within the last hour on etcd instance {{ $labels.instance }}.'
+ description: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}.'
+ summary: etcd cluster has high number of proposal failures.
 expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
 for: 15m
 labels:
 severity: warning
 - alert: etcdHighFsyncDurations
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": 99th percentile fync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.'
+ description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.'
+ summary: etcd cluster 99th percentile fsync durations are too high.
 expr: |-
 histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
 > 0.5
 for: 10m
 labels:
 severity: warning
+ - alert: etcdHighFsyncDurations
+ annotations:
+ description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.'
+ summary: etcd cluster 99th percentile fsync durations are too high.
+ expr: |-
+ histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
+ > 1
+ for: 10m
+ labels:
+ severity: critical
 - alert: etcdHighCommitDurations
 annotations:
- message: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.'
+ description: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.'
+ summary: etcd cluster 99th percentile commit durations are too high.
 expr: |-
 histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
 > 0.25
 for: 10m
 labels:
 severity: warning
- - alert: etcdHighNumberOfFailedHTTPRequests
+ - alert: etcdDatabaseQuotaLowSpace
 annotations:
- message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}'
- expr: |-
- sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
- BY (method) > 0.01
+ description: 'etcd cluster "{{ $labels.job }}": database size exceeds the defined quota on etcd instance {{ $labels.instance }}, please defrag or increase the quota as the writes to etcd will be disabled when it is full.'
+ summary: etcd cluster database is running full.
+ expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes[5m]) / last_over_time(etcd_server_quota_backend_bytes[5m]))*100 > 95
 for: 10m
 labels:
- severity: warning
- - alert: etcdHighNumberOfFailedHTTPRequests
+ severity: critical
+ - alert: etcdExcessiveDatabaseGrowth
 annotations:
- message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}.'
- expr: |-
- sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
- BY (method) > 0.05
+ description: 'etcd cluster "{{ $labels.job }}": Predicting running out of disk space in the next four hours, based on write observations within the past four hours on etcd instance {{ $labels.instance }}, please check as it might be disruptive.'
+ summary: etcd cluster database growing very fast.
+ expr: predict_linear(etcd_mvcc_db_total_size_in_bytes[4h], 4*60*60) > etcd_server_quota_backend_bytes
 for: 10m
 labels:
- severity: critical
- - alert: etcdHTTPRequestsSlow
+ severity: warning
+ - alert: etcdDatabaseHighFragmentationRatio
 annotations:
- message: etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow.
- expr: |-
- histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))
- > 0.15
+ description: 'etcd cluster "{{ $labels.job }}": database size in use on instance {{ $labels.instance }} is {{ $value | humanizePercentage }} of the actual allocated disk space, please run defragmentation (e.g. etcdctl defrag) to retrieve the unused fragmented disk space.'
+ runbook_url: https://etcd.io/docs/v3.5/op-guide/maintenance/#defragmentation
+ summary: etcd database size in use is less than 50% of the actual allocated storage.
+ expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes[5m])) < 0.5
 for: 10m
 labels:
 severity: warning
@@ -42154,6 +42300,7 @@
 - --host=kube-prometheus-stack-operator,kube-prometheus-stack-operator.default.svc
 - --namespace=default
 - --secret-name=kube-prometheus-stack-admission
+ securityContext: {}
 resources: {}
 restartPolicy: OnFailure
 serviceAccountName: kube-prometheus-stack-admission
@@ -42200,6 +42347,7 @@
 - --namespace=default
 - --secret-name=kube-prometheus-stack-admission
 - --patch-failure-policy=Fail
+ securityContext: {}
 resources: {}
 restartPolicy: OnFailure
 serviceAccountName: kube-prometheus-stack-admission

[chii-bot]

MegaLinter status: ❌ ERROR

Descriptor	Linter	Files	Fixed	Errors	Elapsed time
❌ COPYPASTE	jscpd	yes		2	1.97s
✅ REPOSITORY	git_diff	yes		no	0.02s
✅ REPOSITORY	secretlint	yes		no	2.3s
✅ YAML	prettier	2		0	0.9s
✅ YAML	yamllint	2		0	0.23s

See errors details in artifact MegaLinter reports on CI Job page
Set VALIDATE_ALL_CODEBASE: true in mega-linter.yml to validate all sources, not only the diff