使用 Loki 实现 Kubernetes 容器日志监控的方法
时间：2022-11-10 09:23:18 | 栏目： | 点击：次
一、基本介绍
Loki 是由 Grafana Labs 团队开发的，基于 Go 语言实现，是一个水平可扩展，高可用性，多租户的日志聚合系统。它的设计非常经济高效且易于操作，因为它不会为日志内容编制索引，而是为每个日志流配置一组标签。Loki 项目受 Prometheus 启发。
官方的介绍就是：Like Prometheus, but for logs，类似于 Prometheus 的日志系统。
1.Loki 架构
Loki：主服务，用于存储日志和处理查询。Promtail：代理服务，用于采集日志，并转发给 Loki。Grafana：通过 Web 界面来提供数据展示、查询、告警等功能。
2.Loki 工作原理
首先由 Promtail 进行日志采集，并发送给 Distributor 组件，Distributor 组件会对接收到的日志流进行正确性校验，并将验证后的日志分批并行发送给 Ingester 组件。Ingester 组件会将接收过来的日志流构建成数据块，并进行压缩后存放到所连接的后端存储中。
Querier 组件，用于接收 HTTP 查询请求，并将查询请求转发给 Ingester 组件，来返回存在 Ingester 内存中的数据。要是在 Ingester 的内存中没有找到符合条件的数据时，那么 Querier 组件便会直接在后端存储中进行查询（内置去重功能）。
二、使用 Loki 实现容器日志监控
1.安装 Loki
1）创建 RBAC 授权
[root@k8s-master01 ~]# cat <<END > loki-rbac.yaml apiVersion: v1 kind: Namespace metadata: name: logging --- apiVersion: v1 kind: ServiceAccount metadata: name: loki namespace: logging --- apiVersion: rbac.authorization.k8s.io/v1 kind: Role metadata: name: loki namespace: logging rules: - apiGroups: ["extensions"] resources: ["podsecuritypolicies"] verbs: ["use"] resourceNames: [loki] --- apiVersion: rbac.authorization.k8s.io/v1 kind: RoleBinding metadata: name: loki namespace: logging roleRef: apiGroup: rbac.authorization.k8s.io kind: Role name: loki subjects: - kind: ServiceAccount name: loki END [root@k8s-master01 ~]# kubectl create -f loki-rbac.yaml
2）创建 ConfigMap 文件
[root@k8s-master01 ~]# cat <<END > loki-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: loki
namespace: logging
labels:
app: loki
data:
loki.yaml: |
auth_enabled: false
ingester:
chunk_idle_period: 3m
chunk_block_size: 262144
chunk_retain_period: 1m
max_transfer_retries: 0
lifecycler:
ring:
kvstore:
store: inmemory
replication_factor: 1
limits_config:
enforce_metric_name: false
reject_old_samples: true
reject_old_samples_max_age: 168h
schema_config:
configs:
- from: "2022-05-15"
store: boltdb-shipper
object_store: filesystem
schema: v11
index:
prefix: index_
period: 24h
server:
http_listen_port: 3100
storage_config:
boltdb_shipper:
active_index_directory: /data/loki/boltdb-shipper-active
cache_location: /data/loki/boltdb-shipper-cache
cache_ttl: 24h
shared_store: filesystem
filesystem:
directory: /data/loki/chunks
chunk_store_config:
max_look_back_period: 0s
table_manager:
retention_deletes_enabled: true
retention_period: 48h
compactor:
working_directory: /data/loki/boltdb-shipper-compactor
shared_store: filesystem
END
[root@k8s-master01 ~]# kubectl create -f loki-configmap.yaml
3）创建 StatefulSet
[root@k8s-master01 ~]# cat <<END > loki-statefulset.yaml
apiVersion: v1
kind: Service
metadata:
name: loki
namespace: logging
labels:
app: loki
spec:
type: NodePort
ports:
- port: 3100
protocol: TCP
name: http-metrics
targetPort: http-metrics
nodePort: 30100
selector:
app: loki
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: loki
namespace: logging
labels:
app: loki
spec:
podManagementPolicy: OrderedReady
replicas: 1
selector:
matchLabels:
app: loki
serviceName: loki
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
app: loki
spec:
serviceAccountName: loki
initContainers:
- name: chmod-data
image: busybox:1.28.4
imagePullPolicy: IfNotPresent
command: ["chmod","-R","777","/loki/data"]
volumeMounts:
- name: storage
mountPath: /loki/data
containers:
- name: loki
image: grafana/loki:2.3.0
imagePullPolicy: IfNotPresent
args:
- -config.file=/etc/loki/loki.yaml
volumeMounts:
- name: config
mountPath: /etc/loki
- name: storage
mountPath: /data
ports:
- name: http-metrics
containerPort: 3100
protocol: TCP
livenessProbe:
httpGet:
path: /ready
port: http-metrics
scheme: HTTP
initialDelaySeconds: 45
readinessProbe:
httpGet:
path: /ready
port: http-metrics
scheme: HTTP
initialDelaySeconds: 45
securityContext:
readOnlyRootFilesystem: true
terminationGracePeriodSeconds: 4800
volumes:
- name: config
configMap:
name: loki
- name: storage
hostPath:
path: /app/loki
END
[root@k8s-master01 ~]# kubectl create -f loki-statefulset.yaml
2.安装 Promtail
1）创建 RBAC 授权文件
[root@k8s-master01 ~]# cat <<END > promtail-rbac.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: loki-promtail
labels:
app: promtail
namespace: logging
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
labels:
app: promtail
name: promtail-clusterrole
namespace: logging
rules:
- apiGroups: [""]
resources: ["nodes","nodes/proxy","services","endpoints","pods"]
verbs: ["get", "watch", "list"]
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: promtail-clusterrolebinding
labels:
app: promtail
namespace: logging
subjects:
- kind: ServiceAccount
name: loki-promtail
namespace: logging
roleRef:
kind: ClusterRole
name: promtail-clusterrole
apiGroup: rbac.authorization.k8s.io
END
[root@k8s-master01 ~]# kubectl create -f promtail-rbac.yaml
2）创建 ConfigMap 文件
Promtail 配置文件：官方介绍
[root@k8s-master01 ~]# cat <<"END" > promtail-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: loki-promtail
namespace: logging
labels:
app: promtail
data:
promtail.yaml: |
client:
backoff_config:
max_period: 5m
max_retries: 10
min_period: 500ms
batchsize: 1048576
batchwait: 1s
external_labels: {}
timeout: 10s
positions:
filename: /run/promtail/positions.yaml
server:
http_listen_port: 3101
target_config:
sync_period: 10s
scrape_configs:
- job_name: kubernetes-pods-name
pipeline_stages:
- docker: {}
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels:
- __meta_kubernetes_pod_label_name
target_label: __service__
- source_labels:
- __meta_kubernetes_pod_node_name
target_label: __host__
- action: drop
regex: ''
source_labels:
- __service__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
replacement: $1
separator: /
source_labels:
- __meta_kubernetes_namespace
- __service__
target_label: job
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: pod
- action: replace
source_labels:
- __meta_kubernetes_pod_container_name
target_label: container
- replacement: /var/log/pods/*$1/*.log
separator: /
source_labels:
- __meta_kubernetes_pod_uid
- __meta_kubernetes_pod_container_name
target_label: __path__
- job_name: kubernetes-pods-app
pipeline_stages:
- docker: {}
kubernetes_sd_configs:
- role: pod
relabel_configs:
- action: drop
regex: .+
source_labels:
- __meta_kubernetes_pod_label_name
- source_labels:
- __meta_kubernetes_pod_label_app
target_label: __service__
- source_labels:
- __meta_kubernetes_pod_node_name
target_label: __host__
- action: drop
regex: ''
source_labels:
- __service__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
replacement: $1
separator: /
source_labels:
- __meta_kubernetes_namespace
- __service__
target_label: job
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: pod
- action: replace
source_labels:
- __meta_kubernetes_pod_container_name
target_label: container
- replacement: /var/log/pods/*$1/*.log
separator: /
source_labels:
- __meta_kubernetes_pod_uid
- __meta_kubernetes_pod_container_name
target_label: __path__
- job_name: kubernetes-pods-direct-controllers
pipeline_stages:
- docker: {}
kubernetes_sd_configs:
- role: pod
relabel_configs:
- action: drop
regex: .+
separator: ''
source_labels:
- __meta_kubernetes_pod_label_name
- __meta_kubernetes_pod_label_app
- action: drop
regex: '[0-9a-z-.]+-[0-9a-f]{8,10}'
source_labels:
- __meta_kubernetes_pod_controller_name
- source_labels:
- __meta_kubernetes_pod_controller_name
target_label: __service__
- source_labels:
- __meta_kubernetes_pod_node_name
target_label: __host__
- action: drop
regex: ''
source_labels:
- __service__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
replacement: $1
separator: /
source_labels:
- __meta_kubernetes_namespace
- __service__
target_label: job
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: pod
- action: replace
source_labels:
- __meta_kubernetes_pod_container_name
target_label: container
- replacement: /var/log/pods/*$1/*.log
separator: /
source_labels:
- __meta_kubernetes_pod_uid
- __meta_kubernetes_pod_container_name
target_label: __path__
- job_name: kubernetes-pods-indirect-controller
pipeline_stages:
- docker: {}
kubernetes_sd_configs:
- role: pod
relabel_configs:
- action: drop
regex: .+
separator: ''
source_labels:
- __meta_kubernetes_pod_label_name
- __meta_kubernetes_pod_label_app
- action: keep
regex: '[0-9a-z-.]+-[0-9a-f]{8,10}'
source_labels:
- __meta_kubernetes_pod_controller_name
- action: replace
regex: '([0-9a-z-.]+)-[0-9a-f]{8,10}'
source_labels:
- __meta_kubernetes_pod_controller_name
target_label: __service__
- source_labels:
- __meta_kubernetes_pod_node_name
target_label: __host__
- action: drop
regex: ''
source_labels:
- __service__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
replacement: $1
separator: /
source_labels:
- __meta_kubernetes_namespace
- __service__
target_label: job
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: pod
- action: replace
source_labels:
- __meta_kubernetes_pod_container_name
target_label: container
- replacement: /var/log/pods/*$1/*.log
separator: /
source_labels:
- __meta_kubernetes_pod_uid
- __meta_kubernetes_pod_container_name
target_label: __path__
- job_name: kubernetes-pods-static
pipeline_stages:
- docker: {}
kubernetes_sd_configs:
- role: pod
relabel_configs:
- action: drop
regex: ''
source_labels:
- __meta_kubernetes_pod_annotation_kubernetes_io_config_mirror
- action: replace
source_labels:
- __meta_kubernetes_pod_label_component
target_label: __service__
- source_labels:
- __meta_kubernetes_pod_node_name
target_label: __host__
- action: drop
regex: ''
source_labels:
- __service__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
replacement: $1
separator: /
source_labels:
- __meta_kubernetes_namespace
- __service__
target_label: job
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: pod
- action: replace
source_labels:
- __meta_kubernetes_pod_container_name
target_label: container
- replacement: /var/log/pods/*$1/*.log
separator: /
source_labels:
- __meta_kubernetes_pod_annotation_kubernetes_io_config_mirror
- __meta_kubernetes_pod_container_name
target_label: __path__
END
[root@k8s-master01 ~]# kubectl create -f promtail-configmap.yaml
3）创建 DaemonSet 文件
[root@k8s-master01 ~]# cat <<END > promtail-daemonset.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: loki-promtail
namespace: logging
labels:
app: promtail
spec:
selector:
matchLabels:
app: promtail
updateStrategy:
rollingUpdate:
maxUnavailable: 1
type: RollingUpdate
template:
metadata:
labels:
app: promtail
spec:
serviceAccountName: loki-promtail
containers:
- name: promtail
image: grafana/promtail:2.3.0
imagePullPolicy: IfNotPresent
args:
- -config.file=/etc/promtail/promtail.yaml
- -client.url=http://192.168.1.1:30100/loki/api/v1/push
env:
- name: HOSTNAME
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: spec.nodeName
volumeMounts:
- mountPath: /etc/promtail
name: config
- mountPath: /run/promtail
name: run
- mountPath: /data/k8s/docker/data/containers
name: docker
readOnly: true
- mountPath: /var/log/pods
name: pods
readOnly: true
ports:
- containerPort: 3101
name: http-metrics
protocol: TCP
securityContext:
readOnlyRootFilesystem: true
runAsGroup: 0
runAsUser: 0
readinessProbe:
failureThreshold: 5
httpGet:
path: /ready
port: http-metrics
scheme: HTTP
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 1
tolerations:
- effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
volumes:
- name: config
configMap:
name: loki-promtail
- name: run
hostPath:
path: /run/promtail
type: ""
- name: docker
hostPath:
path: /data/k8s/docker/data/containers
- name: pods
hostPath:
path: /var/log/pods
END
[root@k8s-master01 ~]# kubectl create -f promtail-daemonset.yaml
4）Promtail 关键配置
volumeMounts:
- mountPath: /data/k8s/docker/data/containers
name: docker
readOnly: true
- mountPath: /var/log/pods
name: pods
readOnly: true
volumes:
- name: docker
hostPath:
path: /data/k8s/docker/data/containers
- name: pods
hostPath:
path: /var/log/pods
这里需要注意，hostPath 和 mountPath 配置的路径要相同（这里说的相同指的是，要和宿主机的容器目录相同），因为 Promtail 在读取容器内的日志时，会通过 K8s 的 API 接口来返回容器信息（通过源路径取的）。如果配置的不同，将会导致 httpGet 检查失败。
输出：Not ready: Unable to find any logs to tail. Please verify permissions, volumes, scrape_config, etc. 信息，原因可能就是因为挂载路径没有匹配上，导致 Promtail tail 不到日志文件。可以先手动将就绪检查关闭，来查看 Promtail 容器的日志。
3.安装 Grafana
[root@k8s-master01 ~]# cat <<END > grafana-deploy.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: grafana
labels:
app: grafana
namespace: logging
spec:
replicas: 1
selector:
matchLabels:
app: grafana
template:
metadata:
labels:
app: grafana
spec:
containers:
- name: grafana
image: grafana/grafana:8.4.7
imagePullPolicy: IfNotPresent
env:
- name: GF_AUTH_BASIC_ENABLED
value: "true"
- name: GF_AUTH_ANONYMOUS_ENABLED
value: "false"
resources:
requests:
cpu: 100m
memory: 200Mi
limits:
cpu: '1'
memory: 2Gi
readinessProbe:
httpGet:
path: /login
port: 3000
volumeMounts:
- name: storage
mountPath: /var/lib/grafana
volumes:
- name: storage
hostPath:
path: /app/grafana
---
apiVersion: v1
kind: Service
metadata:
name: grafana
labels:
app: grafana
namespace: logging
spec:
type: NodePort
ports:
- port: 3000
targetPort: 3000
nodePort: 30030
selector:
app: grafana
END
[root@k8s-master01 ~]# mkdir -p /app/grafana
[root@k8s-master01 ~]# chmod -R 777 /app/grafana
[root@k8s-master01 ~]# kubectl create -f grafana-deploy.yaml
4.验证
访问 Grafana 控制台：http://192.168.1.1:30030（账号密码：admin/admin）
1）配置数据源
2）选择 Loki 数据源
3）配置 Loki 的 URL 地址
4）验证
