201 lines
7.5 KiB
Cheetah
201 lines
7.5 KiB
Cheetah
- name: loki
|
|
namespace: observability
|
|
create_namespace: true
|
|
chart_ref: {{ .Modules.Observability.Logging.Loki.ChartRef }}
|
|
chart_version: {{ .Modules.Observability.Logging.Loki.ChartVersion }}
|
|
{{- if and .Modules.Observability.Enabled .Modules.Observability.Logging.Enabled }}
|
|
release_state: "present"
|
|
{{- else }}
|
|
release_state: "absent"
|
|
{{- end }}
|
|
values:
|
|
loki:
|
|
image:
|
|
registry: {{ .Modules.Observability.Logging.Loki.Registry }}
|
|
repository: {{ .Modules.Observability.Logging.Loki.Image }}
|
|
tag: {{ .Modules.Observability.Logging.Loki.Tag }}
|
|
podAnnotations:
|
|
app.kubernetes.io/component: "loki"
|
|
auth_enabled: false
|
|
commonConfig:
|
|
replication_factor: 1
|
|
storage:
|
|
type: 'filesystem'
|
|
|
|
frontend:
|
|
max_outstanding_per_tenant: 10000
|
|
|
|
limits_config:
|
|
reject_old_samples: false
|
|
split_queries_by_interval: 15m
|
|
max_query_parallelism: 32
|
|
max_query_series: 10000
|
|
retention_period: {{ .Modules.Observability.Logging.Loki.Persistence.Retention }}
|
|
|
|
compactor:
|
|
compaction_interval: 10m
|
|
retention_enabled: true
|
|
retention_delete_delay: 2h
|
|
|
|
querier:
|
|
max_concurrent: 2048
|
|
|
|
query_scheduler:
|
|
max_outstanding_requests_per_tenant: 10000
|
|
|
|
rulerConfig:
|
|
storage:
|
|
type: local
|
|
local:
|
|
directory: /var/loki/rules
|
|
rule_path: /tmp/rules
|
|
|
|
alertmanager_url: {{ .Modules.Observability.Logging.Loki.AlertManagerUrl }}
|
|
|
|
|
|
singleBinary:
|
|
replicas: 1
|
|
|
|
extraVolumes:
|
|
- name: loki-default-rules
|
|
configMap:
|
|
name: loki-default-alerting-rules
|
|
|
|
extraVolumeMounts:
|
|
- name: loki-default-rules
|
|
mountPath: /var/loki/rules
|
|
|
|
|
|
write:
|
|
persistence:
|
|
volumeClaimsEnabled: true
|
|
storageClass: "{{ .Modules.Observability.Logging.Loki.Persistence.StorageClass }}"
|
|
size: {{ .Modules.Observability.Logging.Loki.Persistence.StorageSize }}
|
|
|
|
test:
|
|
enabled: false
|
|
|
|
gateway:
|
|
enabled: false
|
|
|
|
monitoring:
|
|
selfMonitoring:
|
|
enabled: false
|
|
grafanaAgent:
|
|
installOperator: false
|
|
lokiCanary:
|
|
enabled: false
|
|
rules:
|
|
enabled: true
|
|
alerting: true
|
|
additionalGroups: {}
|
|
|
|
extraObjects:
|
|
- apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: loki-default-alerting-rules
|
|
labels:
|
|
loki_rule: ""
|
|
|
|
data:
|
|
loki-default-alerting-rules.yaml: |-
|
|
groups:
|
|
{{- .Modules.Observability.Logging.Loki.AdditionalRulesGroups | toString | nindent 14 -}}
|
|
- name: kube-events-alerts
|
|
rules:
|
|
- alert: FailedEventsOccured
|
|
expr: |
|
|
count(rate({logs_type="kube-events"} | json reason="reason", event_type="event_type" | event_type = `Warning` | reason = `Failed` [1h])) > 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
alertname: FailedEventsOccured
|
|
instance: kube-cluster
|
|
jobName: kube_events
|
|
summary: Failed events occured in cluster
|
|
addDefaultUrl: "true"
|
|
|
|
- alert: OOMKilledEventsOccured
|
|
expr: |
|
|
count(rate({logs_type="kube-events"} | json reason="reason", event_type="event_type" | event_type = `Warning` | reason = `OOMKilled` [1h])) > 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
alertname: OOMKilledEventsOccured
|
|
instance: kube-cluster
|
|
jobName: kube_events
|
|
summary: OOMKilled events occured in cluster
|
|
addDefaultUrl: "true"
|
|
|
|
- alert: EvictedEventsOccured
|
|
expr: |
|
|
count(rate({logs_type="kube-events"} | json reason="reason", event_type="event_type" | event_type = `Warning` | reason = `Evicted` [1h])) > 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
alertname: EvictedEventsOccured
|
|
instance: kube-cluster
|
|
jobName: kube_events
|
|
summary: Evicted events occured in cluster
|
|
addDefaultUrl: "true"
|
|
|
|
- alert: ImagePullBackOffEventsOccured
|
|
expr: |
|
|
count(rate({logs_type="kube-events"} | json reason="reason", event_type="event_type" | event_type = `Warning` | reason = `ImagePullBackOff` [1h])) > 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
alertname: ImagePullBackOffEventsOccured
|
|
instance: kube-cluster
|
|
jobName: kube_events
|
|
summary: ImagePullBackOff events occured in cluster
|
|
addDefaultUrl: "true"
|
|
|
|
- alert: BackOffEventsOccured
|
|
expr: |
|
|
count(rate({logs_type="kube-events"} | json reason="reason", event_type="event_type" | event_type = `Warning` | reason = `BackOff` [1h])) > 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
alertname: BackOffEventsOccured
|
|
instance: kube-cluster
|
|
jobName: kube_events
|
|
summary: BackOff events occured in cluster
|
|
addDefaultUrl: "true"
|
|
sidecar:
|
|
rules:
|
|
enabled: true
|
|
# -- Label that the configmaps/secrets with rules will be marked with.
|
|
label: loki_rule
|
|
# -- Label value that the configmaps/secrets with rules will be set to.
|
|
labelValue: ""
|
|
# -- Folder into which the rules will be placed.
|
|
folder: /var/loki/rules
|
|
# -- Comma separated list of namespaces. If specified, the sidecar will search for config-maps/secrets inside these namespaces.
|
|
# Otherwise the namespace in which the sidecar is running will be used.
|
|
# It's also possible to specify 'ALL' to search in all namespaces.
|
|
searchNamespace: 'ALL'
|
|
# -- Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH request, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds.
|
|
watchMethod: WATCH
|
|
# -- Search in configmap, secret, or both.
|
|
resource: both
|
|
# -- Absolute path to the shell script to execute after a configmap or secret has been reloaded.
|
|
script: null
|
|
# -- WatchServerTimeout: request to the server, asking it to cleanly close the connection after that.
|
|
# defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S.
|
|
watchServerTimeout: 60
|
|
#
|
|
# -- WatchClientTimeout: is a client-side timeout, configuring your local socket.
|
|
# If you have a network outage dropping all packets with no RST/FIN,
|
|
# this is how long your client waits before realizing & dropping the connection.
|
|
# Defaults to 66sec.
|
|
watchClientTimeout: 60
|
|
# -- Log level of the sidecar container.
|
|
logLevel: INFO
|