k8s部署loki3.6.10监控pod日志
部署loki(如果grafana跟loki在一个集群,将service改成ClusterIP)
# 1. Namespace
apiVersion: v1
kind: Namespace
metadata:
name: loki
labels:
app.kubernetes.io/name: loki
---
# 2. Loki ConfigMap
apiVersion: v1
kind: ConfigMap
metadata:
name: loki-config
namespace: loki
labels:
app.kubernetes.io/name: loki
data:
loki.yaml: |
auth_enabled: false
server:
http_listen_port: 3100
grpc_listen_port: 9096
log_level: info
common:
instance_addr: 0.0.0.0
path_prefix: /loki
storage:
filesystem:
chunks_directory: /loki/chunks
rules_directory: /loki/rules
replication_factor: 1
ring:
kvstore:
store: inmemory
query_range:
results_cache:
cache:
embedded_cache:
enabled: true
max_size_mb: 100
limits_config:
# 每个租户的日志摄入速率限制
ingestion_rate_mb: 10
ingestion_burst_size_mb: 20
# 每个查询返回的最大条目数
max_entries_limit_per_query: 5000
# 日志保留期
retention_period: 168h
schema_config:
configs:
- from: "2024-01-01"
store: tsdb
object_store: filesystem
schema: v13
index:
prefix: index_
period: 24h
storage_config:
tsdb_shipper:
active_index_directory: /loki/tsdb-index
cache_location: /loki/tsdb-cache
compactor:
working_directory: /loki/compactor
compaction_interval: 10m
retention_enabled: true
retention_delete_delay: 2h
delete_request_store: filesystem
analytics:
reporting_enabled: false
---
# 3. PersistentVolumeClaim (持久化存储)
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: loki-data
namespace: loki
labels:
app.kubernetes.io/name: loki
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 5000Gi
# 如需指定 StorageClass，取消下面注释
storageClassName: nfs
---
# 4. Loki StatefulSet
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: loki
namespace: loki
labels:
app.kubernetes.io/name: loki
app.kubernetes.io/version: "3.6.10"
spec:
replicas: 1
serviceName: loki-headless
selector:
matchLabels:
app.kubernetes.io/name: loki
template:
metadata:
labels:
app.kubernetes.io/name: loki
annotations:
checksum/config: "loki-config-v1"
spec:
securityContext:
fsGroup: 10001
runAsGroup: 10001
runAsUser: 10001
runAsNonRoot: true
containers:
- name: loki
image: grafana/loki:3.6.10
args:
- -config.file=/etc/loki/loki.yaml
- -target=all
ports:
- name: http
containerPort: 3100
protocol: TCP
- name: grpc
containerPort: 9096
protocol: TCP
readinessProbe:
httpGet:
path: /ready
port: http
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 5
livenessProbe:
httpGet:
path: /ready
port: http
initialDelaySeconds: 60
periodSeconds: 30
timeoutSeconds: 5
resources:
requests:
cpu: 250m
memory: 512Mi
limits:
cpu: "2"
memory: 2Gi
volumeMounts:
- name: config
mountPath: /etc/loki
- name: data
mountPath: /loki
volumes:
- name: config
configMap:
name: loki-config
- name: data
persistentVolumeClaim:
claimName: loki-data
---
# 5. Loki Headless Service (for StatefulSet)
apiVersion: v1
kind: Service
metadata:
name: loki-headless
namespace: loki
labels:
app.kubernetes.io/name: loki
spec:
type: ClusterIP
clusterIP: None
ports:
- name: http
port: 3100
targetPort: http
protocol: TCP
selector:
app.kubernetes.io/name: loki
---
# 6. Loki Service (供 Grafana 和 Promtail 连接)
apiVersion: v1
kind: Service
metadata:
name: loki
namespace: loki
labels:
app.kubernetes.io/name: loki
spec:
type: NodePort
ports:
- name: http
port: 3100
targetPort: http
protocol: TCP
nodePort: 30100
- name: grpc
port: 9096
targetPort: grpc
protocol: TCP
selector:
app.kubernetes.io/name: loki部署promtail
apiVersion: v1
kind: ServiceAccount
metadata:
name: promtail
namespace: loki
labels:
app.kubernetes.io/name: promtail
---
# 2. ClusterRole (读取 Pod 日志和元数据)
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: promtail
labels:
app.kubernetes.io/name: promtail
rules:
- apiGroups: [""]
resources:
- nodes
- nodes/proxy
- services
- endpoints
- pods
verbs: ["get", "watch", "list"]
---
# 3. ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: promtail
labels:
app.kubernetes.io/name: promtail
subjects:
- kind: ServiceAccount
name: promtail
namespace: loki
roleRef:
kind: ClusterRole
name: promtail
apiGroup: rbac.authorization.k8s.io
---
apiVersion: v1
kind: ConfigMap
metadata:
name: promtail-config
namespace: loki
labels:
app.kubernetes.io/name: promtail
data:
promtail.yaml: |
server:
http_listen_port: 9080
grpc_listen_port: 0
log_level: info
positions:
filename: /run/promtail/positions.yaml
clients:
- url: http://loki.loki.svc.cluster.local:3100/loki/api/v1/push
batchwait: 1s
batchsize: 1048576
scrape_configs:
# Job 1: 采集本节点所有 Pod 日志（排除系统组件）
- job_name: kubernetes-pods-all
kubernetes_sd_configs:
- role: pod
pipeline_stages:
- cri: {}
- drop:
older_than: 168h
drop_counter_reason: too_old
relabel_configs:
- source_labels: [__meta_kubernetes_pod_node_name]
action: keep
regex: ${HOSTNAME}
- source_labels: [__meta_kubernetes_namespace]
action: drop
regex: (kube-system|loki)
- source_labels: [__meta_kubernetes_pod_name]
target_label: pod
- source_labels: [__meta_kubernetes_namespace]
target_label: namespace
- source_labels: [__meta_kubernetes_pod_container_name]
target_label: container
- source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_name]
target_label: app
- source_labels: [__meta_kubernetes_pod_node_name]
target_label: node
- replacement: /var/log/pods/*$1/*.log
separator: /
source_labels:
- __meta_kubernetes_pod_uid
- __meta_kubernetes_pod_container_name
target_label: __path__
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: promtail
namespace: loki
labels:
app.kubernetes.io/name: promtail
spec:
selector:
matchLabels:
app.kubernetes.io/name: promtail
updateStrategy:
type: RollingUpdate
rollingUpdate:
maxUnavailable: 1
template:
metadata:
labels:
app.kubernetes.io/name: promtail
spec:
serviceAccountName: promtail
tolerations:
- effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
- effect: NoSchedule
key: node-role.kubernetes.io/control-plane
operator: Exists
containers:
- name: promtail
image: grafana/promtail:3.6.10
args:
- -config.file=/etc/promtail/promtail.yaml
- -config.expand-env=true
ports:
- name: http
containerPort: 9080
protocol: TCP
readinessProbe:
httpGet:
path: /ready
port: http
initialDelaySeconds: 30
periodSeconds: 10
failureThreshold: 6
resources:
requests:
cpu: 100m
memory: 128Mi
limits:
cpu: 500m
memory: 512Mi
volumeMounts:
- name: config
mountPath: /etc/promtail
- name: run
mountPath: /run/promtail
- name: pods-logs
mountPath: /var/log/pods
readOnly: true
env:
- name: HOSTNAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
volumes:
- name: config
configMap:
name: promtail-config
- name: run
hostPath:
path: /run/promtail
type: DirectoryOrCreate
- name: pods-logs
hostPath:
path: /var/log/pods
type: Directory