一、以下部署版本为 efk-7.10.2
基于elasticsearch+fluentd+kibana部署
1、创建namespaces
[root@master efk-7.10.2]# cat create-logging-namespace.yaml
# https://github.com/kubernetes/kubernetes/tree/master/cluster/addons
kind: Namespace
apiVersion: v1
metadata:
name: logging
labels:
k8s-app: logging
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
2、创建es服务
[root@master efk-7.10.2]# cat es-statefulset.yaml
# RBAC authn and authz
apiVersion: v1
kind: ServiceAccount
metadata:
name: elasticsearch-logging
namespace: logging
labels:
k8s-app: elasticsearch-logging
addonmanager.kubernetes.io/mode: Reconcile
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: elasticsearch-logging
labels:
k8s-app: elasticsearch-logging
addonmanager.kubernetes.io/mode: Reconcile
rules:
- apiGroups:
- ""
resources:
- "services"
- "namespaces"
- "endpoints"
verbs:
- "get"
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: elasticsearch-logging
labels:
k8s-app: elasticsearch-logging
addonmanager.kubernetes.io/mode: Reconcile
subjects:
- kind: ServiceAccount
name: elasticsearch-logging
namespace: logging
apiGroup: ""
roleRef:
kind: ClusterRole
name: elasticsearch-logging
apiGroup: ""
---
# Elasticsearch deployment itself
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: elasticsearch-logging
namespace: logging
labels:
k8s-app: elasticsearch-logging
version: v7.10.2
addonmanager.kubernetes.io/mode: Reconcile
spec:
serviceName: elasticsearch-logging
replicas: 1
selector:
matchLabels:
k8s-app: elasticsearch-logging
version: v7.10.2
template:
metadata:
labels:
k8s-app: elasticsearch-logging
version: v7.10.2
spec:
serviceAccountName: elasticsearch-logging
containers:
- image: registry.cn-beijing.aliyuncs.com/dotbalo/elasticsearch:v7.10.2
name: elasticsearch-logging
imagePullPolicy: IfNotPresent
resources:
# need more cpu upon initialization, therefore burstable class
limits:
cpu: 1000m
memory: 3Gi
requests:
cpu: 100m
memory: 3Gi
ports:
- containerPort: 9200
name: db
protocol: TCP
- containerPort: 9300
name: transport
protocol: TCP
livenessProbe:
tcpSocket:
port: transport
initialDelaySeconds: 30
timeoutSeconds: 10
readinessProbe:
tcpSocket:
port: transport
initialDelaySeconds: 30
timeoutSeconds: 10
volumeMounts:
- name: elasticsearch-logging
mountPath: /data
env:
- name: "NAMESPACE"
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: "MINIMUM_MASTER_NODES"
value: "1"
volumes:
- name: elasticsearch-logging
emptyDir: {}
# 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:
- image: registry.cn-beijing.aliyuncs.com/dotbalo/alpine:3.6
command: ["/sbin/sysctl", "-w", "vm.max_map_count=262144"]
name: elasticsearch-logging-init
securityContext:
privileged: true
说明: 本案例没有做数据持久化,如果是生产环境请做数据持久化
3、创建es-service服务发现
[root@master efk-7.10.2]# cat es-service.yaml
apiVersion: v1
kind: Service
metadata:
name: elasticsearch-logging
namespace: logging
labels:
k8s-app: elasticsearch-logging
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
kubernetes.io/name: "Elasticsearch"
spec:
clusterIP: None
ports:
- name: db
port: 9200
protocol: TCP
targetPort: 9200
- name: transport
port: 9300
protocol: TCP
targetPort: 9300
publishNotReadyAddresses: true
selector:
k8s-app: elasticsearch-logging
sessionAffinity: None
type: ClusterIP
3.1、查看es服务是否部署成功
[root@master efk-7.10.2]# kubectl get pod,svc -n logging
NAME READY STATUS RESTARTS AGE
pod/elasticsearch-logging-0 1/1 Running 0 4h19m
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/elasticsearch-logging ClusterIP None <none> 9200/TCP,9300/TCP 4h19m
4、创建fluentd-cm配置文件
[root@master efk-7.10.2]# cat fluentd-es-configmap.yaml
kind: ConfigMap
apiVersion: v1
metadata:
name: fluentd-es-config-v0.2.1
namespace: logging
labels:
addonmanager.kubernetes.io/mode: Reconcile
data:
system.conf: |-
<system>
root_dir /tmp/fluentd-buffers/
</system>
containers.input.conf: |-
<source>
@id fluentd-containers.log
@type tail
path /var/log/containers/*.log
pos_file /var/log/es-containers.log.pos
tag raw.kubernetes.*
read_from_head true
<parse>
@type multi_format
<pattern>
format json
time_key time
time_format %Y-%m-%dT%H:%M:%S.%NZ
</pattern>
<pattern>
format /^(?<time>.+) (?<stream>stdout|stderr) [^ ]* (?<log>.*)$/
time_format %Y-%m-%dT%H:%M:%S.%N%:z
</pattern>
</parse>
</source>
# Detect exceptions in the log output and forward them as one log entry.
<match raw.kubernetes.**>
@id raw.kubernetes
@type detect_exceptions
remove_tag_prefix raw
message log
stream stream
multiline_flush_interval 5
max_bytes 500000
max_lines 1000
</match>
# Concatenate multi-line logs
<filter **>
@id filter_concat
@type concat
key message
multiline_end_regexp /\n$/
separator ""
</filter>
# Enriches records with Kubernetes metadata
<filter kubernetes.**>
@id filter_kubernetes_metadata
@type kubernetes_metadata
</filter>
# Fixes json fields in Elasticsearch
<filter kubernetes.**>
@id filter_parser
@type parser
key_name log
reserve_data true
remove_key_name_field true
<parse>
@type multi_format
<pattern>
format json
</pattern>
<pattern>
format none
</pattern>
</parse>
</filter>
system.input.conf: |-
# Example:
# 2015-12-21 23:17:22,066 [salt.state ][INFO ] Completed state [net.ipv4.ip_forward] at time 23:17:22.066081
<source>
@id minion
@type tail
format /^(?<time>[^ ]* [^ ,]*)[^\[]*\[[^\]]*\]\[(?<severity>[^ \]]*) *\] (?<message>.*)$/
time_format %Y-%m-%d %H:%M:%S
path /var/log/salt/minion
pos_file /var/log/salt.pos
tag salt
</source>
# Example:
# Dec 21 23:17:22 gke-foo-1-1-4b5cbd14-node-4eoj startupscript: Finished running startup script /var/run/google.startup.script
<source>
@id startupscript.log
@type tail
format syslog
path /var/log/startupscript.log
pos_file /var/log/es-startupscript.log.pos
tag startupscript
</source>
# Examples:
# time="2016-02-04T06:51:03.053580605Z" level=info msg="GET /containers/json"
# time="2016-02-04T07:53:57.505612354Z" level=error msg="HTTP Error" err="No such image: -f" statusCode=404
# TODO(random-liu): Remove this after cri container runtime rolls out.
<source>
@id docker.log
@type tail
format /^time="(?<time>[^"]*)" level=(?<severity>[^ ]*) msg="(?<message>[^"]*)"( err="(?<error>[^"]*)")?( statusCode=($<status_code>\d+))?/
path /var/log/docker.log
pos_file /var/log/es-docker.log.pos
tag docker
</source>
# Example:
# 2016/02/04 06:52:38 filePurge: successfully removed file /var/etcd/data/member/wal/00000000000006d0-00000000010a23d1.wal
<source>
@id etcd.log
@type tail
# Not parsing this, because it doesn't have anything particularly useful to
# parse out of it (like severities).
format none
path /var/log/etcd.log
pos_file /var/log/es-etcd.log.pos
tag etcd
</source>
# Multi-line parsing is required for all the kube logs because very large log
# statements, such as those that include entire object bodies, get split into
# multiple lines by glog.
# Example:
# I0204 07:32:30.020537 3368 server.go:1048] POST /stats/container/: (13.972191ms) 200 [[Go-http-client/1.1] 10.244.1.3:40537]
<source>
@id kubelet.log
@type tail
format multiline
multiline_flush_interval 5s
format_firstline /^\w\d{4}/
format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
time_format %m%d %H:%M:%S.%N
path /var/log/kubelet.log
pos_file /var/log/es-kubelet.log.pos
tag kubelet
</source>
# Example:
# I1118 21:26:53.975789 6 proxier.go:1096] Port "nodePort for kube-system/default-http-backend:http" (:31429/tcp) was open before and is still needed
<source>
@id kube-proxy.log
@type tail
format multiline
multiline_flush_interval 5s
format_firstline /^\w\d{4}/
format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
time_format %m%d %H:%M:%S.%N
path /var/log/kube-proxy.log
pos_file /var/log/es-kube-proxy.log.pos
tag kube-proxy
</source>
# Example:
# I0204 07:00:19.604280 5 handlers.go:131] GET /api/v1/nodes: (1.624207ms) 200 [[kube-controller-manager/v1.1.3 (linux/amd64) kubernetes/6a81b50] 127.0.0.1:38266]
<source>
@id kube-apiserver.log
@type tail
format multiline
multiline_flush_interval 5s
format_firstline /^\w\d{4}/
format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
time_format %m%d %H:%M:%S.%N
path /var/log/kube-apiserver.log
pos_file /var/log/es-kube-apiserver.log.pos
tag kube-apiserver
</source>
# Example:
# I0204 06:55:31.872680 5 servicecontroller.go:277] LB already exists and doesn't need update for service kube-system/kube-ui
<source>
@id kube-controller-manager.log
@type tail
format multiline
multiline_flush_interval 5s
format_firstline /^\w\d{4}/
format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
time_format %m%d %H:%M:%S.%N
path /var/log/kube-controller-manager.log
pos_file /var/log/es-kube-controller-manager.log.pos
tag kube-controller-manager
</source>
# Example:
# W0204 06:49:18.239674 7 reflector.go:245] pkg/scheduler/factory/factory.go:193: watch of *api.Service ended with: 401: The event in requested index is outdated and cleared (the requested history has been cleared [2578313/2577886]) [2579312]
<source>
@id kube-scheduler.log
@type tail
format multiline
multiline_flush_interval 5s
format_firstline /^\w\d{4}/
format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
time_format %m%d %H:%M:%S.%N
path /var/log/kube-scheduler.log
pos_file /var/log/es-kube-scheduler.log.pos
tag kube-scheduler
</source>
# Example:
# I0603 15:31:05.793605 6 cluster_manager.go:230] Reading config from path /etc/gce.conf
<source>
@id glbc.log
@type tail
format multiline
multiline_flush_interval 5s
format_firstline /^\w\d{4}/
format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
time_format %m%d %H:%M:%S.%N
path /var/log/glbc.log
pos_file /var/log/es-glbc.log.pos
tag glbc
</source>
# Example:
# I0603 15:31:05.793605 6 cluster_manager.go:230] Reading config from path /etc/gce.conf
<source>
@id cluster-autoscaler.log
@type tail
format multiline
multiline_flush_interval 5s
format_firstline /^\w\d{4}/
format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
time_format %m%d %H:%M:%S.%N
path /var/log/cluster-autoscaler.log
pos_file /var/log/es-cluster-autoscaler.log.pos
tag cluster-autoscaler
</source>
# Logs from systemd-journal for interesting services.
# TODO(random-liu): Remove this after cri container runtime rolls out.
<source>
@id journald-docker
@type systemd
matches [{ "_SYSTEMD_UNIT": "docker.service" }]
<storage>
@type local
persistent true
path /var/log/journald-docker.pos
</storage>
read_from_head true
tag docker
</source>
<source>
@id journald-container-runtime
@type systemd
matches [{ "_SYSTEMD_UNIT": "{{ fluentd_container_runtime_service }}.service" }]
<storage>
@type local
persistent true
path /var/log/journald-container-runtime.pos
</storage>
read_from_head true
tag container-runtime
</source>
<source>
@id journald-kubelet
@type systemd
matches [{ "_SYSTEMD_UNIT": "kubelet.service" }]
<storage>
@type local
persistent true
path /var/log/journald-kubelet.pos
</storage>
read_from_head true
tag kubelet
</source>
<source>
@id journald-node-problem-detector
@type systemd
matches [{ "_SYSTEMD_UNIT": "node-problem-detector.service" }]
<storage>
@type local
persistent true
path /var/log/journald-node-problem-detector.pos
</storage>
read_from_head true
tag node-problem-detector
</source>
<source>
@id kernel
@type systemd
matches [{ "_TRANSPORT": "kernel" }]
<storage>
@type local
persistent true
path /var/log/kernel.pos
</storage>
<entry>
fields_strip_underscores true
fields_lowercase true
</entry>
read_from_head true
tag kernel
</source>
forward.input.conf: |-
# Takes the messages sent over TCP
<source>
@id forward
@type forward
</source>
monitoring.conf: |-
# Prometheus Exporter Plugin
# input plugin that exports metrics
<source>
@id prometheus
@type prometheus
</source>
<source>
@id monitor_agent
@type monitor_agent
</source>
# input plugin that collects metrics from MonitorAgent
<source>
@id prometheus_monitor
@type prometheus_monitor
<labels>
host ${hostname}
</labels>
</source>
# input plugin that collects metrics for output plugin
<source>
@id prometheus_output_monitor
@type prometheus_output_monitor
<labels>
host ${hostname}
</labels>
</source>
# input plugin that collects metrics for in_tail plugin
<source>
@id prometheus_tail_monitor
@type prometheus_tail_monitor
<labels>
host ${hostname}
</labels>
</source>
output.conf: |-
<match **>
@id elasticsearch
@type elasticsearch
@log_level info
type_name _doc
include_tag_key true
host elasticsearch-logging
port 9200
logstash_format true
<buffer>
@type file
path /var/log/fluentd-buffers/kubernetes.system.buffer
flush_mode interval
retry_type exponential_backoff
flush_thread_count 2
flush_interval 5s
retry_forever
retry_max_interval 30
chunk_limit_size 2M
total_limit_size 500M
overflow_action block
</buffer>
</match>
5、创建fluentd服务
[root@master efk-7.10.2]# cat fluentd-es-ds.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: fluentd-es
namespace: logging
labels:
k8s-app: fluentd-es
addonmanager.kubernetes.io/mode: Reconcile
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: fluentd-es
labels:
k8s-app: fluentd-es
addonmanager.kubernetes.io/mode: Reconcile
rules:
- apiGroups:
- ""
resources:
- "namespaces"
- "pods"
verbs:
- "get"
- "watch"
- "list"
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: fluentd-es
labels:
k8s-app: fluentd-es
addonmanager.kubernetes.io/mode: Reconcile
subjects:
- kind: ServiceAccount
name: fluentd-es
namespace: logging
apiGroup: ""
roleRef:
kind: ClusterRole
name: fluentd-es
apiGroup: ""
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: fluentd-es-v3.1.1
namespace: logging
labels:
k8s-app: fluentd-es
version: v3.1.1
addonmanager.kubernetes.io/mode: Reconcile
spec:
selector:
matchLabels:
k8s-app: fluentd-es
version: v3.1.1
template:
metadata:
labels:
k8s-app: fluentd-es
version: v3.1.1
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
priorityClassName: system-node-critical
serviceAccountName: fluentd-es
containers:
- name: fluentd-es
image: registry.cn-beijing.aliyuncs.com/dotbalo/fluentd:v3.1.0
env:
- name: FLUENTD_ARGS
value: --no-supervisor -q
resources:
limits:
memory: 500Mi
requests:
cpu: 100m
memory: 200Mi
volumeMounts:
- name: varlog
mountPath: /var/log
- name: varlibdockercontainers
mountPath: /var/lib/docker/containers
readOnly: true
- name: config-volume
mountPath: /etc/fluent/config.d
ports:
- containerPort: 24231
name: prometheus
protocol: TCP
livenessProbe:
tcpSocket:
port: prometheus
initialDelaySeconds: 5
timeoutSeconds: 10
readinessProbe:
tcpSocket:
port: prometheus
initialDelaySeconds: 5
timeoutSeconds: 10
terminationGracePeriodSeconds: 30
volumes:
- name: varlog
hostPath:
path: /var/log
- name: varlibdockercontainers
hostPath:
path: /var/lib/docker/containers
- name: config-volume
configMap:
name: fluentd-es-config-v0.2.1
5.1、查看fluentd是否创建成功
[root@master efk-7.10.2]# kubectl get pod -n logging
NAME READY STATUS RESTARTS AGE
fluentd-es-v3.1.1-wgv88 1/1 Running 0 4h25m
fluentd-es-v3.1.1-xxck5 1/1 Running 0 4h25m
说明:由于使用的是DaemonSet资源类型,所以会在每个节点都部署一个fluentd服务
6、创建kibana服务
[root@master efk-7.10.2]# cat kibana-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: kibana-logging
namespace: logging
labels:
k8s-app: kibana-logging
addonmanager.kubernetes.io/mode: Reconcile
spec:
replicas: 1
selector:
matchLabels:
k8s-app: kibana-logging
template:
metadata:
labels:
k8s-app: kibana-logging
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- name: kibana-logging
image: registry.cn-beijing.aliyuncs.com/dotbalo/kibana-oss:7.10.2
resources:
# need more cpu upon initialization, therefore burstable class
limits:
cpu: 1000m
requests:
cpu: 100m
env:
- name: ELASTICSEARCH_HOSTS
value: http://elasticsearch-logging:9200
- name: SERVER_NAME
value: kibana-logging
- name: SERVER_BASEPATH
value: "/kibana"
- name: SERVER_REWRITEBASEPATH
value: "true"
ports:
- containerPort: 5601
name: ui
protocol: TCP
livenessProbe:
httpGet:
path: /kibana/api/status
port: ui
initialDelaySeconds: 5
timeoutSeconds: 10
readinessProbe:
httpGet:
path: /kibana/api/status
port: ui
initialDelaySeconds: 5
timeoutSeconds: 10
7、创建kibana-service
[root@master efk-7.10.2]# cat kibana-service.yaml
apiVersion: v1
kind: Service
metadata:
name: kibana-logging
namespace: logging
labels:
k8s-app: kibana-logging
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
kubernetes.io/name: "Kibana"
spec:
ports:
- port: 5601
protocol: TCP
targetPort: ui
selector:
k8s-app: kibana-logging
type: NodePort
7.1、查看kibana是否创建成功
[root@master efk-7.10.2]# kubectl get pod,svc -n logging
NAME READY STATUS RESTARTS AGE
pod/kibana-logging-7bf48fb7b4-k98zs 1/1 Running 0 4h19m
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/kibana-logging NodePort 10.98.179.159 <none> 5601:30716/TCP 4h19m
说明:kibana使用k8s节点的主机地址+30716即可访问