2.1 创建配置文件
2.1.1 创建命名空间的配置
apiVersion: v1
kind: Namespace
metadata:
name: kube-logging
2.1.2 创建es的配置
---
apiVersion: v1
kind: Service
metadata:
name: elasticsearch-logging
namespace: kube-logging
labels:
k8s-app: elasticsearch-logging
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
kubernetes.io/name: "Elasticsearch"
spec:
ports:
- port: 9200
protocol: TCP
targetPort: db
selector:
k8s-app: elasticsearch-logging
---
# RBAC authn and authz
apiVersion: v1
kind: ServiceAccount
metadata:
name: elasticsearch-logging
namespace: kube-logging
labels:
k8s-app: elasticsearch-logging
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: elasticsearch-logging
labels:
k8s-app: elasticsearch-logging
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
rules:
- apiGroups:
- ""
resources:
- "services"
- "namespaces"
- "endpoints"
verbs:
- "get"
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
namespace: kube-logging
name: elasticsearch-logging
labels:
k8s-app: elasticsearch-logging
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
subjects:
- kind: ServiceAccount
name: elasticsearch-logging
namespace: kube-logging
apiGroup: ""
roleRef:
kind: ClusterRole
name: elasticsearch-logging
apiGroup: ""
---
# Elasticsearch deployment itself
apiVersion: apps/v1
kind: StatefulSet #使用statefulset创建Pod
metadata:
name: elasticsearch-logging #pod名称,使用statefulSet创建的Pod是有序号有顺序的
namespace: kube-logging #命名空间
labels:
k8s-app: elasticsearch-logging
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
srv: srv-elasticsearch
spec:
serviceName: elasticsearch-logging #与svc相关联，这可以确保使用以下DNS地址访问Statefulset中的每个pod (es-cluster-[0,1,2].elasticsearch.elk.svc.cluster.local)
replicas: 1 #副本数量,单节点
selector:
matchLabels:
k8s-app: elasticsearch-logging #和pod template配置的labels相匹配
template:
metadata:
labels:
k8s-app: elasticsearch-logging
kubernetes.io/cluster-service: "true"
spec:
serviceAccountName: elasticsearch-logging
containers:
- image: docker.io/library/elasticsearch:7.9.3
name: elasticsearch-logging
resources:
# need more cpu upon initialization, therefore burstable class
limits:
cpu: 1000m
memory: 2Gi
requests:
cpu: 100m
memory: 500Mi
ports:
- containerPort: 9200
name: db
protocol: TCP
- containerPort: 9300
name: transport
protocol: TCP
volumeMounts:
- name: elasticsearch-logging
mountPath: /usr/share/elasticsearch/data/ #挂载点
env:
- name: "NAMESPACE"
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: "discovery.type" #定义单节点类型
value: "single-node"
- name: ES_JAVA_OPTS #设置Java的内存参数，可以适当进行加大调整
value: "-Xms512m -Xmx2g"
volumes:
- name: elasticsearch-logging
hostPath:
path: /data/es/
nodeSelector: #如果需要匹配落盘节点可以添加 nodeSelect
es: data
tolerations:
- effect: NoSchedule
operator: Exists
# Elasticsearch requires vm.max_map_count to be at least 262144.
# If your OS already sets up this number to a higher value, feel free
# to remove this init container.
initContainers: #容器初始化前的操作
- name: elasticsearch-logging-init
image: alpine:3.6
command: ["/sbin/sysctl", "-w", "vm.max_map_count=262144"] #添加mmap计数限制，太低可能造成内存不足的错误
securityContext: #仅应用到指定的容器上，并且不会影响Volume
privileged: true #运行特权容器
- name: increase-fd-ulimit
image: busybox
imagePullPolicy: IfNotPresent
command: ["sh", "-c", "ulimit -n 65536"] #修改文件描述符最大数量
securityContext:
privileged: true
- name: elasticsearch-volume-init #es数据落盘初始化，加上777权限
image: alpine:3.6
command:
- chmod
- -R
- "777"
- /usr/share/elasticsearch/data/
volumeMounts:
- name: elasticsearch-logging
mountPath: /usr/share/elasticsearch/data/
2.1.3 创建logstash的配置
---
apiVersion: v1
kind: Service
metadata:
name: logstash
namespace: kube-logging
spec:
ports:
- port: 5044
targetPort: beats
selector:
type: logstash
clusterIP: None
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: logstash
namespace: kube-logging
spec:
selector:
matchLabels:
type: logstash
template:
metadata:
labels:
type: logstash
srv: srv-logstash
spec:
containers:
- image: docker.io/kubeimages/logstash:7.9.3 #该镜像支持arm64和amd64两种架构
name: logstash
ports:
- containerPort: 5044
name: beats
command:
- logstash
- '-f'
- '/etc/logstash_c/logstash.conf'
env:
- name: "XPACK_MONITORING_ELASTICSEARCH_HOSTS"
value: "http://elasticsearch-logging:9200"
volumeMounts:
- name: config-volume
mountPath: /etc/logstash_c/
- name: config-yml-volume
mountPath: /usr/share/logstash/config/
- name: timezone
mountPath: /etc/localtime
resources: #logstash一定要加上资源限制，避免对其他业务造成资源抢占影响
limits:
cpu: 1000m
memory: 2048Mi
requests:
cpu: 512m
memory: 512Mi
volumes:
- name: config-volume
configMap:
name: logstash-conf
items:
- key: logstash.conf
path: logstash.conf
- name: timezone
hostPath:
path: /etc/localtime
- name: config-yml-volume
configMap:
name: logstash-yml
items:
- key: logstash.yml
path: logstash.yml
---
apiVersion: v1
kind: ConfigMap
metadata:
name: logstash-conf
namespace: kube-logging
labels:
type: logstash
data:
logstash.conf: |-
input {
beats {
port => 5044
}
}
filter {
# 处理 ingress 日志
if [kubernetes][container][name] == "nginx-ingress-controller" {
json {
source => "message"
target => "ingress_log"
}
if [ingress_log][requesttime] {
mutate {
convert => ["[ingress_log][requesttime]", "float"]
}
}
if [ingress_log][upstremtime] {
mutate {
convert => ["[ingress_log][upstremtime]", "float"]
}
}
if [ingress_log][status] {
mutate {
convert => ["[ingress_log][status]", "float"]
}
}
if [ingress_log][httphost] and [ingress_log][uri] {
mutate {
add_field => {"[ingress_log][entry]" => "%{[ingress_log][httphost]}%{[ingress_log][uri]}"}
}
mutate {
split => ["[ingress_log][entry]","/"]
}
if [ingress_log][entry][1] {
mutate {
add_field => {"[ingress_log][entrypoint]" => "%{[ingress_log][entry][0]}/%{[ingress_log][entry][1]}"}
remove_field => "[ingress_log][entry]"
}
} else {
mutate {
add_field => {"[ingress_log][entrypoint]" => "%{[ingress_log][entry][0]}/"}
remove_field => "[ingress_log][entry]"
}
}
}
}
# 处理以srv进行开头的业务服务日志
if [kubernetes][container][name] =~ /^srv*/ {
json {
source => "message"
target => "tmp"
}
if [kubernetes][namespace] == "kube-logging" {
drop{}
}
if [tmp][level] {
mutate{
add_field => {"[applog][level]" => "%{[tmp][level]}"}
}
if [applog][level] == "debug"{
drop{}
}
}
if [tmp][msg] {
mutate {
add_field => {"[applog][msg]" => "%{[tmp][msg]}"}
}
}
if [tmp][func] {
mutate {
add_field => {"[applog][func]" => "%{[tmp][func]}"}
}
}
if [tmp][cost]{
if "ms" in [tmp][cost] {
mutate {
split => ["[tmp][cost]","m"]
add_field => {"[applog][cost]" => "%{[tmp][cost][0]}"}
convert => ["[applog][cost]", "float"]
}
} else {
mutate {
add_field => {"[applog][cost]" => "%{[tmp][cost]}"}
}
}
}
if [tmp][method] {
mutate {
add_field => {"[applog][method]" => "%{[tmp][method]}"}
}
}
if [tmp][request_url] {
mutate {
add_field => {"[applog][request_url]" => "%{[tmp][request_url]}"}
}
}
if [tmp][meta._id] {
mutate {
add_field => {"[applog][traceId]" => "%{[tmp][meta._id]}"}
}
}
if [tmp][project] {
mutate {
add_field => {"[applog][project]" => "%{[tmp][project]}"}
}
}
if [tmp][time] {
mutate {
add_field => {"[applog][time]" => "%{[tmp][time]}"}
}
}
if [tmp][status] {
mutate {
add_field => {"[applog][status]" => "%{[tmp][status]}"}
convert => ["[applog][status]", "float"]
}
}
}
mutate {
rename => ["kubernetes", "k8s"]
remove_field => "beat"
remove_field => "tmp"
remove_field => "[k8s][labels][app]"
}
}
output {
elasticsearch {
hosts => ["http://elasticsearch-logging:9200"]
codec => json
index => "logstash-%{+YYYY.MM.dd}" #索引名称以logstash+日志进行每日新建
}
}
---
apiVersion: v1
kind: ConfigMap
metadata:
name: logstash-yml
namespace: kube-logging
labels:
type: logstash
data:
logstash.yml: |-
http.host: "0.0.0.0"
xpack.monitoring.elasticsearch.hosts: http://elasticsearch-logging:9200
2.1.4 创建filebeat的配置
---
apiVersion: v1
kind: ConfigMap
metadata:
name: filebeat-config
namespace: kube-logging
labels:
k8s-app: filebeat
data:
filebeat.yml: |-
filebeat.inputs:
- type: container
enable: true
paths:
- /var/log/containers/*.log #这里是filebeat采集挂载到pod中的日志目录
processors:
- add_kubernetes_metadata: #添加k8s的字段用于后续的数据清洗
host: ${NODE_NAME}
matchers:
- logs_path:
logs_path: "/var/log/containers/"
#output.kafka: #如果日志量较大，es中的日志有延迟，可以选择在filebeat和logstash中间加入kafka
# hosts: ["kafka-log-01:9092", "kafka-log-02:9092", "kafka-log-03:9092"]
# topic: 'topic-test-log'
# version: 2.0.0
output.logstash: #因为还需要部署logstash进行数据的清洗，因此filebeat是把数据推到logstash中
hosts: ["logstash:5044"]
enabled: true
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: filebeat
namespace: kube-logging
labels:
k8s-app: filebeat
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: filebeat
labels:
k8s-app: filebeat
rules:
- apiGroups: [""] # "" indicates the core API group
resources:
- namespaces
- pods
verbs: ["get", "watch", "list"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: filebeat
subjects:
- kind: ServiceAccount
name: filebeat
namespace: kube-logging
roleRef:
kind: ClusterRole
name: filebeat
apiGroup: rbac.authorization.k8s.io
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: filebeat
namespace: kube-logging
labels:
k8s-app: filebeat
spec:
selector:
matchLabels:
k8s-app: filebeat
template:
metadata:
labels:
k8s-app: filebeat
spec:
serviceAccountName: filebeat
terminationGracePeriodSeconds: 30
containers:
- name: filebeat
image: docker.io/kubeimages/filebeat:7.9.3 #该镜像支持arm64和amd64两种架构
args: [
"-c", "/etc/filebeat.yml",
"-e","-httpprof","0.0.0.0:6060"
]
#ports:
# - containerPort: 6060
# hostPort: 6068
env:
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
- name: ELASTICSEARCH_HOST
value: elasticsearch-logging
- name: ELASTICSEARCH_PORT
value: "9200"
securityContext:
runAsUser: 0
# If using Red Hat OpenShift uncomment this:
#privileged: true
resources:
limits:
memory: 1000Mi
cpu: 1000m
requests:
memory: 100Mi
cpu: 100m
volumeMounts:
- name: config #挂载的是filebeat的配置文件
mountPath: /etc/filebeat.yml
readOnly: true
subPath: filebeat.yml
- name: data #持久化filebeat数据到宿主机上
mountPath: /usr/share/filebeat/data
- name: varlibdockercontainers #这里主要是把宿主机上的源日志目录挂载到filebeat容器中,如果没有修改docker或者containerd的runtime进行了标准的日志落盘路径，可以把mountPath改为/var/lib
mountPath: /var/lib
readOnly: true
- name: varlog #这里主要是把宿主机上/var/log/pods和/var/log/containers的软链接挂载到filebeat容器中
mountPath: /var/log/
readOnly: true
- name: timezone
mountPath: /etc/localtime
volumes:
- name: config
configMap:
defaultMode: 0600
name: filebeat-config
- name: varlibdockercontainers
hostPath: #如果没有修改docker或者containerd的runtime进行了标准的日志落盘路径，可以把path改为/var/lib
path: /var/lib
- name: varlog
hostPath:
path: /var/log/
# data folder stores a registry of read status for all files, so we don't send everything again on a Filebeat pod restart
- name: inputs
configMap:
defaultMode: 0600
name: filebeat-inputs
- name: data
hostPath:
path: /data/filebeat-data
type: DirectoryOrCreate
- name: timezone
hostPath:
path: /etc/localtime
tolerations: #加入容忍能够调度到每一个节点
- effect: NoExecute
key: dedicated
operator: Equal
value: gpu
- effect: NoSchedule
operator: Exists
2.1.5 创建kibana的配置
---
apiVersion: v1
kind: ConfigMap
metadata:
namespace: kube-logging
name: kibana-config
labels:
k8s-app: kibana
data:
kibana.yml: |-
server.name: kibana
server.host: "0.0.0.0"
i18n.locale: zh-CN #设置默认语言为中文
elasticsearch:
hosts: ${ELASTICSEARCH_HOSTS} #es集群连接地址，由于我这都都是k8s部署且在一个ns下，可以直接使用service name连接
---
apiVersion: v1
kind: Service
metadata:
name: kibana
namespace: kube-logging
labels:
k8s-app: kibana
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
kubernetes.io/name: "Kibana"
srv: srv-kibana
spec:
type: NodePort
ports:
- port: 5601
protocol: TCP
targetPort: ui
selector:
k8s-app: kibana
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: kibana
namespace: kube-logging
labels:
k8s-app: kibana
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
srv: srv-kibana
spec:
replicas: 1
selector:
matchLabels:
k8s-app: kibana
template:
metadata:
labels:
k8s-app: kibana
spec:
containers:
- name: kibana
image: docker.io/kubeimages/kibana:7.9.3 #该镜像支持arm64和amd64两种架构
resources:
# need more cpu upon initialization, therefore burstable class
limits:
cpu: 1000m
requests:
cpu: 100m
env:
- name: ELASTICSEARCH_HOSTS
value: http://elasticsearch-logging:9200
ports:
- containerPort: 5601
name: ui
protocol: TCP
volumeMounts:
- name: config
mountPath: /usr/share/kibana/config/kibana.yml
readOnly: true
subPath: kibana.yml
volumes:
- name: config
configMap:
name: kibana-config
---
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: kibana
namespace: kube-logging
spec:
ingressClassName: nginx
rules:
- host: kibana.lan-he.com.cn
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: kibana
port:
number: 5601
2.2 部署elk服务
2.2.1 部署elk服务以及查看状态
[root@k8s-master elk]# kubectl apply -f namespace.yaml
namespace/kube-logging created
[root@k8s-master elk]# kubectl apply -f es.yaml
service/elasticsearch-logging created
serviceaccount/elasticsearch-logging created
clusterrole.rbac.authorization.k8s.io/elasticsearch-logging created
clusterrolebinding.rbac.authorization.k8s.io/elasticsearch-logging created
statefulset.apps/elasticsearch-logging created
[root@k8s-master elk]# kubectl apply -f logstash.yaml
service/logstash created
deployment.apps/logstash created
configmap/logstash-conf created
configmap/logstash-yml created
[root@k8s-master elk]# kubectl apply -f kibana.yaml
configmap/kibana-config created
service/kibana created
deployment.apps/kibana created
ingress.networking.k8s.io/kibana created
[root@k8s-master elk]# kubectl apply -f filebeat.yaml
configmap/filebeat-config created
serviceaccount/filebeat created
clusterrole.rbac.authorization.k8s.io/filebeat created
clusterrolebinding.rbac.authorization.k8s.io/filebeat created
daemonset.apps/filebeat created
[root@k8s-master elk]# kubectl get all -n kube-logging
NAME READY STATUS RESTARTS AGE
pod/elasticsearch-logging-0 0/1 Pending 0 27s
pod/filebeat-2fz26 1/1 Running 0 2m17s
pod/filebeat-j4qf2 1/1 Running 0 2m17s
pod/filebeat-r97lm 1/1 Running 0 2m17s
pod/kibana-86ddf46d47-9q79f 0/1 ContainerCreating 0 8s
pod/logstash-5f774b55bb-992qj 0/1 Pending 0 20s
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/elasticsearch-logging ClusterIP 10.1.16.54 <none> 9200/TCP 28s
service/kibana NodePort 10.1.181.71 <none> 5601:32274/TCP 8s
service/logstash ClusterIP None <none> 5044/TCP 21s
NAME DESIRED CURRENT READY UP-TO-DATE AVAILABLE NODE SELECTOR AGE
daemonset.apps/filebeat 3 3 2 3 2 <none> 3m26s
NAME READY UP-TO-DATE AVAILABLE AGE
deployment.apps/kibana 0/1 1 0 8s
deployment.apps/logstash 0/1 1 0 21s
NAME DESIRED CURRENT READY AGE
replicaset.apps/kibana-86ddf46d47 1 1 0 8s
replicaset.apps/logstash-5f774b55bb 1 1 0 20s
NAME READY AGE
statefulset.apps/elasticsearch-logging 0/1 27s
2.2.2 Q1：es的pod状态是Pending
2.2.2.1 查看pod的描述信息
-
信息一： node(s) had untolerated taint {node-role.kubernetes.io/control-plane: },
- 这表示有一个节点（控制平面节点）被标记（tainted）为 node-role.kubernetes.io/control-plane，并且没有 Pod 能够容忍（tolerate）这个标记。通常，控制平面节点（即 Kubernetes 集群中的 master 节点）是不应该运行工作负载的。
-
信息二： 1 node(s) had untolerated taint {node.kubernetes.io/unreachable: }：
- 这表明还有一个节点被认为是不可达的，因此 Pod 无法被调度到该节点上。
-
信息三： 2 Insufficient memory. preemption:
- 这表示有两个节点上的可用内存不足以满足 Pod 的资源请求。
-
信息四： 0/3 nodes are available
- 这表示即使考虑 Pod 抢占，也没有可用的节点可以供 Pod 使用。
-
信息五： 1 No preemption victims found for incoming pod, 2 Preemption is not helpful for scheduling.
- 这两条信息表明，对于即将到来的 Pod，没有找到可以被抢占（即终止并重新调度）的低优先级 Pod，或者即使进行了抢占，也不会对调度有帮助。
[root@k8s-master elk]# kubectl describe -n kube-logging po elasticsearch-logging-0
Name: elasticsearch-logging-0
Namespace: kube-logging
Priority: 0
Service Account: elasticsearch-logging
Node: <none>
Labels: controller-revision-hash=elasticsearch-logging-bcd67584
k8s-app=elasticsearch-logging
kubernetes.io/cluster-service=true
statefulset.kubernetes.io/pod-name=elasticsearch-logging-0
Annotations: <none>
Status: Pending
IP:
IPs: <none>
Controlled By: StatefulSet/elasticsearch-logging
Init Containers:
elasticsearch-logging-init:
Image: alpine:3.6
Port: <none>
Host Port: <none>
Command:
/sbin/sysctl
-w
vm.max_map_count=262144
Environment: <none>
Mounts:
/var/run/secrets/kubernetes.io/serviceaccount from kube-api-access-fwbvr (ro)
increase-fd-ulimit:
Image: busybox
Port: <none>
Host Port: <none>
Command:
sh
-c
ulimit -n 65536
Environment: <none>
Mounts:
/var/run/secrets/kubernetes.io/serviceaccount from kube-api-access-fwbvr (ro)
elasticsearch-volume-init:
Image: alpine:3.6
Port: <none>
Host Port: <none>
Command:
chmod
-R
777
/usr/share/elasticsearch/data/
Environment: <none>
Mounts:
/usr/share/elasticsearch/data/ from elasticsearch-logging (rw)
/var/run/secrets/kubernetes.io/serviceaccount from kube-api-access-fwbvr (ro)
Containers:
elasticsearch-logging:
Image: docker.io/elastic/elasticsearch:8.12.0
Ports: 9200/TCP, 9300/TCP
Host Ports: 0/TCP, 0/TCP
Limits:
cpu: 1
memory: 2Gi
Requests:
cpu: 100m
memory: 500Mi
Environment:
NAMESPACE: kube-logging (v1:metadata.namespace)
discovery.type: single-node
ES_JAVA_OPTS: -Xms512m -Xmx2g
Mounts:
/usr/share/elasticsearch/data/ from elasticsearch-logging (rw)
/var/run/secrets/kubernetes.io/serviceaccount from kube-api-access-fwbvr (ro)
Conditions:
Type Status
PodScheduled False
Volumes:
elasticsearch-logging:
Type: HostPath (bare host directory volume)
Path: /data/es/
HostPathType:
kube-api-access-fwbvr:
Type: Projected (a volume that contains injected data from multiple sources)
TokenExpirationSeconds: 3607
ConfigMapName: kube-root-ca.crt
ConfigMapOptional: <nil>
DownwardAPI: true
QoS Class: Burstable
Node-Selectors: es=data
Tolerations: :NoSchedule op=Exists
node.kubernetes.io/not-ready:NoExecute op=Exists for 300s
node.kubernetes.io/unreachable:NoExecute op=Exists for 300s
Events:
Type Reason Age From Message
---- ------ ---- ---- -------
Warning FailedScheduling 2m37s default-scheduler 0/3 nodes are available: 2 Insufficient memory, 3 node(s) didn't match Pod's node affinity/selector. preemption: 0/3 nodes are available: 3 Preemption is not helpful for scheduling.
2.2.2.2 给master打一个标签
- 查看es的yaml文件中得到pod需要往哪个node上调用，标签如下图
[root@k8s-master elk]# kubectl label nodes k8s-master es='data'
node/k8s-master labeled
[root@k8s-master elk]# kubectl get all -n kube-logging
NAME READY STATUS RESTARTS AGE
pod/elasticsearch-logging-0 0/1 Init:0/3 0 16m
pod/filebeat-2fz26 1/1 Running 0 2m17s
pod/filebeat-j4qf2 1/1 Running 0 2m17s
pod/filebeat-r97lm 1/1 Running 0 2m17s
pod/kibana-86ddf46d47-6vmrb 0/1 ContainerCreating 0 59s
pod/kibana-86ddf46d47-9q79f 1/1 Terminating 0 16m
pod/logstash-5f774b55bb-992qj 0/1 Pending 0 16m
NAME DESIRED CURRENT READY UP-TO-DATE AVAILABLE NODE SELECTOR AGE
daemonset.apps/filebeat 3 3 2 3 2 <none> 3m26s
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/elasticsearch-logging ClusterIP 10.1.16.54 <none> 9200/TCP 16m
service/kibana NodePort 10.1.181.71 <none> 5601:32274/TCP 16m
service/logstash ClusterIP None <none> 5044/TCP 16m
NAME DESIRED CURRENT READY UP-TO-DATE AVAILABLE NODE SELECTOR AGE
daemonset.apps/filebeat 3 3 2 3 2 <none> 3m26s
NAME READY UP-TO-DATE AVAILABLE AGE
deployment.apps/kibana 0/1 1 0 16m
deployment.apps/logstash 0/1 1 0 16m
NAME DESIRED CURRENT READY AGE
replicaset.apps/kibana-86ddf46d47 1 1 0 16m
replicaset.apps/logstash-5f774b55bb 1 1 0 16m
NAME READY AGE
statefulset.apps/elasticsearch-logging 0/1 16m
2.2.3 Q2：logstash的状态也是Pending
2.2.3.1 查看pod的描述信息
- 问题和刚才es启动的时候问题差不多一致
[root@k8s-master elk]# kubectl describe -n kube-logging po logstash-5f774b55bb-992qj
Name: logstash-5f774b55bb-992qj
Namespace: kube-logging
Priority: 0
Service Account: default
Node: <none>
Labels: pod-template-hash=5f774b55bb
srv=srv-logstash
type=logstash
Annotations: <none>
Status: Pending
IP:
IPs: <none>
Controlled By: ReplicaSet/logstash-5f774b55bb
Containers:
logstash:
Image: docker.io/elastic/logstash:8.12.0
Port: 5044/TCP
Host Port: 0/TCP
Command:
logstash
-f
/etc/logstash_c/logstash.conf
Limits:
cpu: 1
memory: 2Gi
Requests:
cpu: 512m
memory: 512Mi
Environment:
XPACK_MONITORING_ELASTICSEARCH_HOSTS: http://elasticsearch-logging:9200
Mounts:
/etc/localtime from timezone (rw)
/etc/logstash_c/ from config-volume (rw)
/usr/share/logstash/config/ from config-yml-volume (rw)
/var/run/secrets/kubernetes.io/serviceaccount from kube-api-access-2x2t5 (ro)
Conditions:
Type Status
PodScheduled False
Volumes:
config-volume:
Type: ConfigMap (a volume populated by a ConfigMap)
Name: logstash-conf
Optional: false
timezone:
Type: HostPath (bare host directory volume)
Path: /etc/localtime
HostPathType:
config-yml-volume:
Type: ConfigMap (a volume populated by a ConfigMap)
Name: logstash-yml
Optional: false
kube-api-access-2x2t5:
Type: Projected (a volume that contains injected data from multiple sources)
TokenExpirationSeconds: 3607
ConfigMapName: kube-root-ca.crt
ConfigMapOptional: <nil>
DownwardAPI: true
QoS Class: Burstable
Node-Selectors: <none>
Tolerations: node.kubernetes.io/not-ready:NoExecute op=Exists for 300s
node.kubernetes.io/unreachable:NoExecute op=Exists for 300s
Events:
Type Reason Age From Message
---- ------ ---- ---- -------
Warning FailedScheduling 5m59s (x2 over 10m) default-scheduler 0/3 nodes are available: 1 node(s) had untolerated taint {node-role.kubernetes.io/control-plane: }, 1 node(s) had untolerated taint {node.kubernetes.io/unreachable: }, 2 Insufficient memory. preemption: 0/3 nodes are available: 1 No preemption victims found for incoming pod, 2 Preemption is not helpful for scheduling.
Warning FailedScheduling 3m23s (x5 over 21m) default-scheduler 0/3 nodes are available: 1 node(s) had untolerated taint {node-role.kubernetes.io/control-plane: }, 2 Insufficient memory. preemption: 0/3 nodes are available: 1 Preemption is not helpful for scheduling, 2 No preemption victims found for incoming pod.
2.2.3.2 释放资源和添加标签
[root@k8s-master ~]# kubectl label nodes k8s-node-01 type="logstash"
node/k8s-node-01 labeled
# 删除之前创建的prometheus资源
[root@k8s-master ~]# kubectl delete -f kube-prometheus-0.12.0/manifests/
2.2.4 Q3：kibana状态是：CrashLoopBackOff
[root@k8s-master ~]# kubectl get po -n kube-logging -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
elasticsearch-logging-0 1/1 Running 3 (4m54s ago) 71m 10.2.0.4 k8s-master <none> <none>
filebeat-2fz26 1/1 Running 0 6m7s 10.2.0.5 k8s-master <none> <none>
filebeat-j4qf2 1/1 Running 0 6m7s 10.2.1.20 k8s-node-01 <none> <none>
filebeat-r97lm 1/1 Running 0 6m7s 10.2.2.17 k8s-node-02 <none> <none>
kibana-86ddf46d47-6vmrb 0/1 CrashLoopBackOff 20 (43s ago) 93m 10.2.2.12 k8s-node-02 <none> <none>
logstash-5f774b55bb-992qj 1/1 Running 0 108m 10.2.1.19 k8s-node-01 <none> <none>
2.2.4.1、查看pod的描述信息
[root@k8s-master ~]# kubectl describe -n kube-logging po kibana-86ddf46d47-d97cj
Name: kibana-86ddf46d47-d97cj
Namespace: kube-logging
Priority: 0
Service Account: default
Node: k8s-node-02/192.168.0.191
Start Time: Sat, 02 Mar 2024 15:23:10 +0800
Labels: k8s-app=kibana
pod-template-hash=86ddf46d47
Annotations: <none>
Status: Running
IP: 10.2.2.15
IPs:
IP: 10.2.2.15
Controlled By: ReplicaSet/kibana-86ddf46d47
Containers:
kibana:
Container ID: docker://c5a6e6ee69e7766dd38374be22bad6d44c51deae528f36f00624e075e4ffe1d2
Image: docker.io/elastic/kibana:8.12.0
Image ID: docker-pullable://elastic/kibana@sha256:596700740fdb449c5726e6b6a6dd910c2140c8a37e68a301a5186e86b0834c9f
Port: 5601/TCP
Host Port: 0/TCP
State: Waiting
Reason: CrashLoopBackOff
Last State: Terminated
Reason: Error
Exit Code: 1
Started: Sat, 02 Mar 2024 15:24:50 +0800
Finished: Sat, 02 Mar 2024 15:24:54 +0800
Ready: False
Restart Count: 4
Limits:
cpu: 1
Requests:
cpu: 100m
Environment:
ELASTICSEARCH_HOSTS: http://elasticsearch-logging:9200
Mounts:
/usr/share/kibana/config/kibana.yml from config (ro,path="kibana.yml")
/var/run/secrets/kubernetes.io/serviceaccount from kube-api-access-fpcqx (ro)
Conditions:
Type Status
Initialized True
Ready False
ContainersReady False
PodScheduled True
Volumes:
config:
Type: ConfigMap (a volume populated by a ConfigMap)
Name: kibana-config
Optional: false
kube-api-access-fpcqx:
Type: Projected (a volume that contains injected data from multiple sources)
TokenExpirationSeconds: 3607
ConfigMapName: kube-root-ca.crt
ConfigMapOptional: <nil>
DownwardAPI: true
QoS Class: Burstable
Node-Selectors: <none>
Tolerations: node.kubernetes.io/not-ready:NoExecute op=Exists for 300s
node.kubernetes.io/unreachable:NoExecute op=Exists for 300s
Events:
Type Reason Age From Message
---- ------ ---- ---- -------
Normal Scheduled 2m12s default-scheduler Successfully assigned kube-logging/kibana-86ddf46d47-d97cj to k8s-node-02
Normal Pulled 32s (x5 over 2m10s) kubelet Container image "docker.io/elastic/kibana:8.12.0" already present on machine
Normal Created 32s (x5 over 2m10s) kubelet Created container kibana
Normal Started 32s (x5 over 2m10s) kubelet Started container kibana
Warning BackOff 1s (x9 over 2m) kubelet Back-off restarting failed container
2.2.4.2、查看容器的日志信息
# 1、查看pod的描述信息
[root@k8s-master ~]# kubectl logs -n kube-logging kibana-86ddf46d47-d97cj
Kibana is currently running with legacy OpenSSL providers enabled! For details and instructions on how to disable see https://www.elastic.co/guide/en/kibana/8.12/production.html#openssl-legacy-provider
{"log.level":"info","@timestamp":"2024-03-02T07:24:52.627Z","log.logger":"elastic-apm-node","ecs.version":"8.10.0","agentVersion":"4.2.0","env":{"pid":7,"proctitle":"/usr/share/kibana/bin/../node/bin/node","os":"linux 3.10.0-1160.105.1.el7.x86_64","arch":"x64","host":"kibana-86ddf46d47-d97cj","timezone":"UTC+00","runtime":"Node.js v18.18.2"},"config":{"active":{"source":"start","value":true},"breakdownMetrics":{"source":"start","value":false},"captureBody":{"source":"start","value":"off","commonName":"capture_body"},"captureHeaders":{"source":"start","value":false},"centralConfig":{"source":"start","value":false},"contextPropagationOnly":{"source":"start","value":true},"environment":{"source":"start","value":"production"},"globalLabels":{"source":"start","value":[["git_rev","e9092c0a17923f4ed984456b8a5db619b0a794b3"]],"sourceValue":{"git_rev":"e9092c0a17923f4ed984456b8a5db619b0a794b3"}},"logLevel":{"source":"default","value":"info","commonName":"log_level"},"metricsInterval":{"source":"start","value":120,"sourceValue":"120s"},"serverUrl":{"source":"start","value":"https://kibana-cloud-apm.apm.us-east-1.aws.found.io/","commonName":"server_url"},"transactionSampleRate":{"source":"start","value":0.1,"commonName":"transaction_sample_rate"},"captureSpanStackTraces":{"source":"start","sourceValue":false},"secretToken":{"source":"start","value":"[REDACTED]","commonName":"secret_token"},"serviceName":{"source":"start","value":"kibana","commonName":"service_name"},"serviceVersion":{"source":"start","value":"8.12.0","commonName":"service_version"}},"activationMethod":"require","message":"Elastic APM Node.js Agent v4.2.0"}
[2024-03-02T07:24:54.467+00:00][INFO ][root] Kibana is starting
[2024-03-02T07:24:54.550+00:00][INFO ][root] Kibana is shutting down
[2024-03-02T07:24:54.554+00:00][FATAL][root] Reason: [config validation of [server].host]: value must be a valid hostname (see RFC 1123).
Error: [config validation of [server].host]: value must be a valid hostname (see RFC 1123).
at ObjectType.validate (/usr/share/kibana/node_modules/@kbn/config-schema/src/types/type.js:94:13)
at ConfigService.validateAtPath (/usr/share/kibana/node_modules/@kbn/config/src/config_service.js:253:19)
at /usr/share/kibana/node_modules/@kbn/config/src/config_service.js:263:204
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/map.js:10:37
at OperatorSubscriber._this._next (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/OperatorSubscriber.js:33:21)
at OperatorSubscriber.Subscriber.next (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Subscriber.js:51:18)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/distinctUntilChanged.js:18:28
at OperatorSubscriber._this._next (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/OperatorSubscriber.js:33:21)
at OperatorSubscriber.Subscriber.next (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Subscriber.js:51:18)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/map.js:10:24
at OperatorSubscriber._this._next (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/OperatorSubscriber.js:33:21)
at OperatorSubscriber.Subscriber.next (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Subscriber.js:51:18)
at ReplaySubject._subscribe (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/ReplaySubject.js:54:24)
at ReplaySubject.Observable._trySubscribe (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:41:25)
at ReplaySubject.Subject._trySubscribe (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Subject.js:123:47)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:35:31
at Object.errorContext (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/errorContext.js:22:9)
at ReplaySubject.Observable.subscribe (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:26:24)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/share.js:66:18
at OperatorSubscriber.<anonymous> (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/lift.js:14:28)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:30:30
at Object.errorContext (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/errorContext.js:22:9)
at Observable.subscribe (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:26:24)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/map.js:9:16
at OperatorSubscriber.<anonymous> (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/lift.js:14:28)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:30:30
at Object.errorContext (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/errorContext.js:22:9)
at Observable.subscribe (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:26:24)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/distinctUntilChanged.js:13:16
at OperatorSubscriber.<anonymous> (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/lift.js:14:28)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:30:30
at Object.errorContext (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/errorContext.js:22:9)
at Observable.subscribe (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:26:24)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/operators/map.js:9:16
at SafeSubscriber.<anonymous> (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/lift.js:14:28)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:30:30
at Object.errorContext (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/util/errorContext.js:22:9)
at Observable.subscribe (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/Observable.js:26:24)
at /usr/share/kibana/node_modules/rxjs/dist/cjs/internal/firstValueFrom.js:24:16
at new Promise (<anonymous>)
at firstValueFrom (/usr/share/kibana/node_modules/rxjs/dist/cjs/internal/firstValueFrom.js:8:12)
at EnvironmentService.preboot (/usr/share/kibana/node_modules/@kbn/core-environment-server-internal/src/environment_service.js:50:169)
at Server.preboot (/usr/share/kibana/node_modules/@kbn/core-root-server-internal/src/server.js:146:55)
at Root.preboot (/usr/share/kibana/node_modules/@kbn/core-root-server-internal/src/root/index.js:47:32)
at processTicksAndRejections (node:internal/process/task_queues:95:5)
at bootstrap (/usr/share/kibana/node_modules/@kbn/core-root-server-internal/src/bootstrap.js:97:9)
at Command.<anonymous> (/usr/share/kibana/src/cli/serve/serve.js:241:5)
FATAL Error: [config validation of [server].host]: value must be a valid hostname (see RFC 1123).
2.2.4.3 kibana的配置文件中有个hosts信息填写错误
# 1、更新配置文件
[root@k8s-master ~]# kubectl replace -f elk/kibana.yaml
configmap/kibana-config replaced
service/kibana replaced
deployment.apps/kibana replaced
ingress.networking.k8s.io/kibana replaced
# 2、删除旧的pod
[root@k8s-master ~]# kubectl delete po kibana-86ddf46d47-d97cj -n kube-logging
pod "kibana-86ddf46d47-d97cj" deleted
# 3、全部服务都跑起来了
[root@k8s-master ~]# kubectl get all -n kube-logging
NAME READY STATUS RESTARTS AGE
pod/elasticsearch-logging-0 1/1 Running 3 (14m ago) 80m
pod/filebeat-2fz26 1/1 Running 0 4m20s
pod/filebeat-j4qf2 1/1 Running 0 4m20s
pod/filebeat-r97lm 1/1 Running 0 4m20s
pod/kibana-86ddf46d47-d2ddz 1/1 Running 0 3s
pod/logstash-5f774b55bb-992qj 1/1 Running 0 117m
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/elasticsearch-logging ClusterIP 10.1.16.54 <none> 9200/TCP 117m
service/kibana NodePort 10.1.181.71 <none> 5601:32274/TCP 117m
service/logstash ClusterIP None <none> 5044/TCP 117m
NAME DESIRED CURRENT READY UP-TO-DATE AVAILABLE NODE SELECTOR AGE
daemonset.apps/filebeat 3 3 2 3 2 <none> 3m26s
NAME READY UP-TO-DATE AVAILABLE AGE
deployment.apps/kibana 1/1 1 1 117m
deployment.apps/logstash 1/1 1 1 117m
NAME DESIRED CURRENT READY AGE
replicaset.apps/kibana-86ddf46d47 1 1 1 117m
replicaset.apps/logstash-5f774b55bb 1 1 1 117m
NAME READY AGE
statefulset.apps/elasticsearch-logging 1/1 117m
2.2.5 查看elk可视化界面，显示 Kibana 服务器尚未准备就绪。
# 1、查看ingress控制器的信息
[root@k8s-master ~]# kubectl get ingressclasses.networking.k8s.io
NAME CONTROLLER PARAMETERS AGE
nginx k8s.io/ingress-nginx <none> 12h
# 2、查看ingress 信息
[root@k8s-master ~]# kubectl get ingress -n kube-logging
NAME CLASS HOSTS ADDRESS PORTS AGE
kibana nginx kibana.lan-he.com.cn 10.1.86.240 80 131m
# 3、查看ingress的pod 所在那个node节点
[root@k8s-master ~]# kubectl get po -n monitoring -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
ingress-nginx-controller-6gz5k 1/1 Running 2 (110m ago) 11h 10.10.10.177 k8s-node-01 <none> <none>
# 4、查看kibana的日志，如下图
[root@k8s-master elk]# kubectl logs -f kibana-86ddf46d47-d2ddz -n kube-logging
注意：本文未添加安装ingress-nginx控制器的教程，所以在使用elk的时候需要提前把ingress-ngin控制器安装好。另外就是需要注意es的pod共享数据卷的问题，如果没有权限也会导致安装失败，如下图kibana无法访问到es的服务。
[root@k8s-master elk]# kubectl apply -f kibana.yaml
Warning: resource configmaps/kibana-config is missing the kubectl.kubernetes.io/last-applied-configuration annotation which is required by kubectl apply. kubectl apply should only be used on resources created declaratively by either kubectl create --save-config or kubectl apply. The missing annotation will be patched automatically.
configmap/kibana-config configured
Warning: resource services/kibana is missing the kubectl.kubernetes.io/last-applied-configuration annotation which is required by kubectl apply. kubectl apply should only be used on resources created declaratively by either kubectl create --save-config or kubectl apply. The missing annotation will be patched automatically.
service/kibana configured
Warning: resource deployments/kibana is missing the kubectl.kubernetes.io/last-applied-configuration annotation which is required by kubectl apply. kubectl apply should only be used on resources created declaratively by either kubectl create --save-config or kubectl apply. The missing annotation will be patched automatically.
deployment.apps/kibana configured
Warning: resource ingresses/kibana is missing the kubectl.kubernetes.io/last-applied-configuration annotation which is required by kubectl apply. kubectl apply should only be used on resources created declaratively by either kubectl create --save-config or kubectl apply. The missing annotation will be patched automatically.
ingress.networking.k8s.io/kibana configured
