企业级日志平台新秀Grafana Loki，比ELK轻量多了~
共 64951字，需浏览 130分钟
·
2021-08-30 02:31
来源博客：https://blog.csdn.net/Linkthaha
我们的监控使用的是基于Prometheus体系进行改造的，Prometheus中比较重要的是Metric和Alert，Metric是来说明当前或者历史达到了某个值，Alert设置Metric达到某个特定的基数触发了告警，但是这些信息明显是不够的。我们都知道，Kubernetes的基本单位是Pod，Pod把日志输出到stdout和stderr，平时有什么问题我们通常在界面或者通过命令查看相关的日志，举个例子：当我们的某个Pod的内存变得很大，触发了我们的Alert，这个时候管理员，去页面查询确认是哪个Pod有问题，然后要确认Pod内存变大的原因，我们还需要去查询Pod的日志，如果没有日志系统，那么我们就需要到页面或者使用命令进行查询了：
oc new-project loki
oc adm policy add-scc-to-user anyuid -z default -n loki
oc adm policy add-cluster-role-to-user cluster-admin system:serviceaccount:loki:default
oc create -f statefulset.json -n loki
{
"apiVersion": "apps/v1",
"kind": "StatefulSet",
"metadata": {
"name": "loki"
},
"spec": {
"podManagementPolicy": "OrderedReady",
"replicas": 1,
"revisionHistoryLimit": 10,
"selector": {
"matchLabels": {
"app": "loki"
}
},
"serviceName": "womping-stoat-loki-headless",
"template": {
"metadata": {
"annotations": {
"checksum/config": "da297d66ee53e0ce68b58e12be7ec5df4a91538c0b476cfe0ed79666343df72b",
"prometheus.io/port": "http-metrics",
"prometheus.io/scrape": "true"
},
"creationTimestamp": null,
"labels": {
"app": "loki",
"name": "loki"
}
},
"spec": {
"affinity": {},
"containers": [
{
"args": [
"-config.file=/etc/loki/local-config.yaml"
],
"image": "grafana/loki:latest",
"imagePullPolicy": "IfNotPresent",
"livenessProbe": {
"failureThreshold": 3,
"httpGet": {
"path": "/ready",
"port": "http-metrics",
"scheme": "HTTP"
},
"initialDelaySeconds": 45,
"periodSeconds": 10,
"successThreshold": 1,
"timeoutSeconds": 1
},
"name": "loki",
"ports": [
{
"containerPort": 3100,
"name": "http-metrics",
"protocol": "TCP"
}
],
"readinessProbe": {
"failureThreshold": 3,
"httpGet": {
"path": "/ready",
"port": "http-metrics",
"scheme": "HTTP"
},
"initialDelaySeconds": 45,
"periodSeconds": 10,
"successThreshold": 1,
"timeoutSeconds": 1
},
"resources": {},
"terminationMessagePath": "/dev/termination-log",
"terminationMessagePolicy": "File",
"volumeMounts": [
{
"mountPath": "/tmp/loki",
"name": "storage"
}
]
}
],
"dnsPolicy": "ClusterFirst",
"restartPolicy": "Always",
"schedulerName": "default-scheduler",
"terminationGracePeriodSeconds": 30,
"volumes": [
{
"emptyDir": {},
"name": "storage"
}
]
}
},
"updateStrategy": {
"type": "RollingUpdate"
}
}
}
oc create -f configmap.json -n loki
{
"apiVersion": "v1",
"data": {
"promtail.yaml": "client:\n backoff_config:\n maxbackoff: 5s\n maxretries: 5\n minbackoff: 100ms\n batchsize: 102400\n batchwait: 1s\n external_labels: {}\n timeout: 10s\npositions:\n filename: /run/promtail/positions.yaml\nserver:\n http_listen_port: 3101\ntarget_config:\n sync_period: 10s\n\nscrape_configs:\n- job_name: kubernetes-pods-name\n pipeline_stages:\n - docker: {}\n \n kubernetes_sd_configs:\n - role: pod\n relabel_configs:\n - source_labels:\n - __meta_kubernetes_pod_label_name\n target_label: __service__\n - source_labels:\n - __meta_kubernetes_pod_node_name\n target_label: __host__\n - action: drop\n regex: ^$\n source_labels:\n - __service__\n - action: labelmap\n regex: __meta_kubernetes_pod_label_(.+)\n - action: replace\n replacement: $1\n separator: /\n source_labels:\n - __meta_kubernetes_namespace\n - __service__\n target_label: job\n - action: replace\n source_labels:\n - __meta_kubernetes_namespace\n target_label: namespace\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_name\n target_label: instance\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_container_name\n target_label: container_name\n - replacement: /var/log/pods/*$1/*.log\n separator: /\n source_labels:\n - __meta_kubernetes_pod_uid\n - __meta_kubernetes_pod_container_name\n target_label: __path__\n- job_name: kubernetes-pods-app\n pipeline_stages:\n - docker: {}\n \n kubernetes_sd_configs:\n - role: pod\n relabel_configs:\n - action: drop\n regex: .+\n source_labels:\n - __meta_kubernetes_pod_label_name\n - source_labels:\n - __meta_kubernetes_pod_label_app\n target_label: __service__\n - source_labels:\n - __meta_kubernetes_pod_node_name\n target_label: __host__\n - action: drop\n regex: ^$\n source_labels:\n - __service__\n - action: labelmap\n regex: __meta_kubernetes_pod_label_(.+)\n - action: replace\n replacement: $1\n separator: /\n source_labels:\n - __meta_kubernetes_namespace\n - __service__\n target_label: job\n - action: replace\n source_labels:\n - __meta_kubernetes_namespace\n target_label: namespace\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_name\n target_label: instance\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_container_name\n target_label: container_name\n - replacement: /var/log/pods/*$1/*.log\n separator: /\n source_labels:\n - __meta_kubernetes_pod_uid\n - __meta_kubernetes_pod_container_name\n target_label: __path__\n- job_name: kubernetes-pods-direct-controllers\n pipeline_stages:\n - docker: {}\n \n kubernetes_sd_configs:\n - role: pod\n relabel_configs:\n - action: drop\n regex: .+\n separator: ''\n source_labels:\n - __meta_kubernetes_pod_label_name\n - __meta_kubernetes_pod_label_app\n - action: drop\n regex: ^([0-9a-z-.]+)(-[0-9a-f]{8,10})$\n source_labels:\n - __meta_kubernetes_pod_controller_name\n - source_labels:\n - __meta_kubernetes_pod_controller_name\n target_label: __service__\n - source_labels:\n - __meta_kubernetes_pod_node_name\n target_label: __host__\n - action: drop\n regex: ^$\n source_labels:\n - __service__\n - action: labelmap\n regex: __meta_kubernetes_pod_label_(.+)\n - action: replace\n replacement: $1\n separator: /\n source_labels:\n - __meta_kubernetes_namespace\n - __service__\n target_label: job\n - action: replace\n source_labels:\n - __meta_kubernetes_namespace\n target_label: namespace\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_name\n target_label: instance\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_container_name\n target_label: container_name\n - replacement: /var/log/pods/*$1/*.log\n separator: /\n source_labels:\n - __meta_kubernetes_pod_uid\n - __meta_kubernetes_pod_container_name\n target_label: __path__\n- job_name: kubernetes-pods-indirect-controller\n pipeline_stages:\n - docker: {}\n \n kubernetes_sd_configs:\n - role: pod\n relabel_configs:\n - action: drop\n regex: .+\n separator: ''\n source_labels:\n - __meta_kubernetes_pod_label_name\n - __meta_kubernetes_pod_label_app\n - action: keep\n regex: ^([0-9a-z-.]+)(-[0-9a-f]{8,10})$\n source_labels:\n - __meta_kubernetes_pod_controller_name\n - action: replace\n regex: ^([0-9a-z-.]+)(-[0-9a-f]{8,10})$\n source_labels:\n - __meta_kubernetes_pod_controller_name\n target_label: __service__\n - source_labels:\n - __meta_kubernetes_pod_node_name\n target_label: __host__\n - action: drop\n regex: ^$\n source_labels:\n - __service__\n - action: labelmap\n regex: __meta_kubernetes_pod_label_(.+)\n - action: replace\n replacement: $1\n separator: /\n source_labels:\n - __meta_kubernetes_namespace\n - __service__\n target_label: job\n - action: replace\n source_labels:\n - __meta_kubernetes_namespace\n target_label: namespace\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_name\n target_label: instance\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_container_name\n target_label: container_name\n - replacement: /var/log/pods/*$1/*.log\n separator: /\n source_labels:\n - __meta_kubernetes_pod_uid\n - __meta_kubernetes_pod_container_name\n target_label: __path__\n- job_name: kubernetes-pods-static\n pipeline_stages:\n - docker: {}\n \n kubernetes_sd_configs:\n - role: pod\n relabel_configs:\n - action: drop\n regex: ^$\n source_labels:\n - __meta_kubernetes_pod_annotation_kubernetes_io_config_mirror\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_label_component\n target_label: __service__\n - source_labels:\n - __meta_kubernetes_pod_node_name\n target_label: __host__\n - action: drop\n regex: ^$\n source_labels:\n - __service__\n - action: labelmap\n regex: __meta_kubernetes_pod_label_(.+)\n - action: replace\n replacement: $1\n separator: /\n source_labels:\n - __meta_kubernetes_namespace\n - __service__\n target_label: job\n - action: replace\n source_labels:\n - __meta_kubernetes_namespace\n target_label: namespace\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_name\n target_label: instance\n - action: replace\n source_labels:\n - __meta_kubernetes_pod_container_name\n target_label: container_name\n - replacement: /var/log/pods/*$1/*.log\n separator: /\n source_labels:\n - __meta_kubernetes_pod_annotation_kubernetes_io_config_mirror\n - __meta_kubernetes_pod_container_name\n target_label: __path__\n"
},
"kind": "ConfigMap",
"metadata": {
"creationTimestamp": "2019-09-05T01:05:03Z",
"labels": {
"app": "promtail",
"chart": "promtail-0.12.0",
"heritage": "Tiller",
"release": "lame-zorse"
},
"name": "lame-zorse-promtail",
"namespace": "loki",
"resourceVersion": "17921611",
"selfLink": "/api/v1/namespaces/loki/configmaps/lame-zorse-promtail",
"uid": "30fcb896-cf79-11e9-b58e-e4a8b6cc47d2"
}
}
oc create -f daemonset.json -n loki
{
"apiVersion": "apps/v1",
"kind": "DaemonSet",
"metadata": {
"annotations": {
"deployment.kubernetes.io/revision": "2"
},
"creationTimestamp": "2019-09-05T01:16:37Z",
"generation": 2,
"labels": {
"app": "promtail",
"chart": "promtail-0.12.0",
"heritage": "Tiller",
"release": "lame-zorse"
},
"name": "lame-zorse-promtail",
"namespace": "loki"
},
"spec": {
"progressDeadlineSeconds": 600,
"replicas": 1,
"revisionHistoryLimit": 10,
"selector": {
"matchLabels": {
"app": "promtail",
"release": "lame-zorse"
}
},
"strategy": {
"rollingUpdate": {
"maxSurge": 1,
"maxUnavailable": 1
},
"type": "RollingUpdate"
},
"template": {
"metadata": {
"annotations": {
"checksum/config": "75a25ee4f2869f54d394bf879549a9c89c343981a648f8d878f69bad65dba809",
"prometheus.io/port": "http-metrics",
"prometheus.io/scrape": "true"
},
"creationTimestamp": null,
"labels": {
"app": "promtail",
"release": "lame-zorse"
}
},
"spec": {
"affinity": {},
"containers": [
{
"args": [
"-config.file=/etc/promtail/promtail.yaml",
"-client.url=http://loki.loki.svc:3100/api/prom/push"
],
"env": [
{
"name": "HOSTNAME",
"valueFrom": {
"fieldRef": {
"apiVersion": "v1",
"fieldPath": "spec.nodeName"
}
}
}
],
"image": "grafana/promtail:v0.3.0",
"imagePullPolicy": "IfNotPresent",
"name": "promtail",
"ports": [
{
"containerPort": 3101,
"name": "http-metrics",
"protocol": "TCP"
}
],
"readinessProbe": {
"failureThreshold": 5,
"httpGet": {
"path": "/ready",
"port": "http-metrics",
"scheme": "HTTP"
},
"initialDelaySeconds": 10,
"periodSeconds": 10,
"successThreshold": 1,
"timeoutSeconds": 1
},
"resources": {},
"securityContext": {
"readOnlyRootFilesystem": true,
"runAsUser": 0
},
"terminationMessagePath": "/dev/termination-log",
"terminationMessagePolicy": "File",
"volumeMounts": [
{
"mountPath": "/etc/promtail",
"name": "config"
},
{
"mountPath": "/run/promtail",
"name": "run"
},
{
"mountPath": "/var/lib/docker/containers",
"name": "docker",
"readOnly": true
},
{
"mountPath": "/var/log/pods",
"name": "pods",
"readOnly": true
}
]
}
],
"dnsPolicy": "ClusterFirst",
"restartPolicy": "Always",
"schedulerName": "default-scheduler",
"securityContext": {},
"terminationGracePeriodSeconds": 30,
"volumes": [
{
"configMap": {
"defaultMode": 420,
"name": "lame-zorse-promtail"
},
"name": "config"
},
{
"hostPath": {
"path": "/run/promtail",
"type": ""
},
"name": "run"
},
{
"hostPath": {
"path": "/var/lib/docker/containers",
"type": ""
},
"name": "docker"
},
{
"hostPath": {
"path": "/var/log/pods",
"type": ""
},
"name": "pods"
}
]
}
}
}
}
oc create -f service.json -n loki
{
"apiVersion": "v1",
"kind": "Service",
"metadata": {
"creationTimestamp": "2019-09-04T09:37:49Z",
"name": "loki",
"namespace": "loki",
"resourceVersion": "17800188",
"selfLink": "/api/v1/namespaces/loki/services/loki",
"uid": "a87fe237-cef7-11e9-b58e-e4a8b6cc47d2"
},
"spec": {
"externalTrafficPolicy": "Cluster",
"ports": [
{
"name": "lokiport",
"port": 3100,
"protocol": "TCP",
"targetPort": 3100
}
],
"selector": {
"app": "loki"
},
"sessionAffinity": "None",
"type": "NodePort"
},
"status": {
"loadBalancer": {}
}
curl http://192.168.25.30:30972/api/prom/label
{
"values": ["alertmanager", "app", "component", "container_name", "controller_revision_hash", "deployment", "deploymentconfig", "docker_registry", "draft", "filename", "instance", "job", "logging_infra", "metrics_infra", "name", "namespace", "openshift_io_component", "pod_template_generation", "pod_template_hash", "project", "projectname", "prometheus", "provider", "release", "router", "servicename", "statefulset_kubernetes_io_pod_name", "stream", "tekton_dev_pipeline", "tekton_dev_pipelineRun", "tekton_dev_pipelineTask", "tekton_dev_task", "tekton_dev_taskRun", "type", "webconsole"]
}
curl http://192.168.25.30:30972/api/prom/label/namespace/values
{"values":["cicd","default","gitlab","grafanaserver","jenkins","jx-staging","kube-system","loki","mysql-exporter","new2","openshift-console","openshift-infra","openshift-logging","openshift-monitoring","openshift-node","openshift-sdn","openshift-web-console","tekton-pipelines","test111"]}
http://192.168.25.30:30972/api/prom/query?direction=BACKWARD&limit=1000®exp=&query={namespace="cicd"}&start=1567644457221000000&end=1567730857221000000&refId=A
query：一种查询语法详细见下面章节，{name=~“mysql.+”} or {namespace=“cicd”} |= "error"表示查询，namespace为CI/CD的日志中，有error字样的信息。
limit：返回日志的数量
start：开始时间，Unix时间表示方法 默认为，一小时前时间
end：结束时间，默认为当前时间
direction：forward或者backward，指定limit时候有用，默认为 backward
regexp：对结果进行regex过滤
{app="mysql",name="mysql-backup"}
=：完全相同。
!=：不平等。
=~：正则表达式匹配。
!~：不要正则表达式匹配。
{job=“mysql”} |= “error”
{name=“kafka”} |~ “tsdb-ops.*io:2003”
{instance=~“kafka-[23]”,name=“kafka”} != kafka.server:type=ReplicaManager
{job=“mysql”} |= “error” != “timeout”
|= line包含字符串。
!= line不包含字符串。
|~ line匹配正则表达式。
!~ line与正则表达式不匹配。
- END -
推荐阅读 Kubernetes 企业容器云平台运维实战 Kubernetes 的这些核心资源原理，你一定要了解 终于搞懂了服务器为啥产生大量的TIME_WAIT！ Kubernetes 网络方案之炫酷的 Cilium Prometheus+InfluxDB+Grafana 打造高逼格监控平台 民生银行 IT运维故障管理 可视化案例 Kubernetes YAML 学习，提升编写能力 这些 K8S 日常故障处理集锦，运维请收藏~ 猪八戒网 CI/CD 最佳实践之路 从零开始搭建创业公司DevOps技术栈 12年资深运维老司机的成长感悟 搭建一套完整的企业级 K8s 集群（v1.20，二进制方式）
点亮，服务器三年不宕机
