准备工作
- Elasticsearch镜像，我以Elasticsearch官方镜像的5.6.10版本为基础创建的。
Dockerfile
FROM docker.elastic.co/elasticsearch/elasticsearch:5.6.10
MAINTAINER leo.lee(lis85@163.com)
WORKDIR /usr/share/elasticsearch
USER root
# copying custom-entrypoint.sh and configuration (elasticsearch.yml, log4j2.properties)
# to their respective directories in /usr/share/elasticsearch (already the WORKDIR)
COPY custom-entrypoint.sh bin/
COPY elasticsearch.yml config/
COPY log4j2.properties config/
# assuring "elasticsearch" user have appropriate access to configuration and custom-entrypoint.sh
# make sure custom-entrypoint.sh is executable
RUN chown elasticsearch:elasticsearch config/elasticsearch.yml config/log4j2.properties bin/custom-entrypoint.sh && \
chmod +x bin/custom-entrypoint.sh
# start by running the custom entrypoint (as root)
CMD ["/bin/bash", "bin/custom-entrypoint.sh"]
custom-entrypoint.sh
#!/bin/bash
# This is expected to run as root for setting the ulimits
set -e
##################################################################################
# ensure increased ulimits - for nofile - for the Elasticsearch containers
# the limit on the number of files that a single process can have open at a time (default is 1024)
ulimit -n 65536
# ensure increased ulimits - for nproc - for the Elasticsearch containers
# the limit on the number of processes that elasticsearch can create
# 2048 is min to pass the linux checks (default is 50)
# https://www.elastic.co/guide/en/elasticsearch/reference/current/max-number-threads-check.html
ulimit -u 2048
# swapping needs to be disabled for performance and node stability
# in ElasticSearch config we are using: [bootstrap.memory_lock=true]
# this additionally requires the "memlock: true" ulimit; specifically set for each container
# -l: max locked memory
ulimit -l unlimited
# running command to start elasticsearch
# passing all inputs of this entry point script to the es-docker startup script
# NOTE: this entry point script is run as root; but executes the es-docker
# startup script as the elasticsearch user, passing all the root environment-variables
# to the elasticsearch user
su elasticsearch bin/es-docker "$@"
elasticsearch.yml
# attaching the namespace to the cluster.name to differentiate different clusters
# ex. elasticsearh-acceptance, elasticsearh-production, elasticsearh-monitoring
cluster.name: "elasticsearch-${NAMESPACE}"
# we provide a node.name that is the POD_NAME-NAMESPACE
# ex. elasticsearh-0-acceptance, elasticsearh-1-acceptance, elasticsearh-2-acceptance
node.name: "${POD_NAME}-${NAMESPACE}"
network.host: ${POD_IP}
# A hostname that resolves to multiple IP addresses will try all resolved addresses
# we provide the name for the headless service
# which resolves to the ip addresses of all the live attached pods
# alternatively we can directly reference the hostnames of the pods
discovery.zen.ping.unicast.hosts: es-discovery-svc
# minimum_master_nodes need to be explicitly set when bound on a public IP
# set to 1 to allow single node clusters
# more info: https://github.com/elastic/elasticsearch/pull/17288
discovery.zen.minimum_master_nodes: 2
bootstrap.memory_lock: true
#-------------------------------------------------------------------------------------
# RECOVERY: https://www.elastic.co/guide/en/elasticsearch/guide/current/important-configuration-changes.html
# SETTINGS TO avoid the excessive shard swapping that can occur on cluster restarts
#-------------------------------------------------------------------------------------
# how many nodes shall be present to consider the cluster functional;
# prevents Elasticsearch from starting recovery until these nodes are available
gateway.recover_after_nodes: 2
# how many nodes are expected in the cluster
gateway.expected_nodes: 3
# how long we want to wait after [gateway.recover_after_nodes] is reached in order to start recovery process (if applicable).
gateway.recover_after_time: 5m
#-------------------------------------------------------------------------------------
# The following settings control the fault detection process using the discovery.zen.fd prefix:
# How often a node gets pinged. Defaults to 1s.
discovery.zen.fd.ping_interval: 1s
# How long to wait for a ping response, defaults to 30s.
discovery.zen.fd.ping_timeout: 10s
# How many ping failures / timeouts cause a node to be considered failed. Defaults to 3.
discovery.zen.fd.ping_retries: 2
log4j2.properties
status = error
appender.console.type = Console
appender.console.name = console
appender.console.layout.type = PatternLayout
appender.console.layout.pattern = [%d{ISO8601}][%-5p][%-25c{1.}] %marker%m%n
rootLogger.level = info
rootLogger.appenderRef.console.ref = console
将这4个文件放入同一级目录下，然后在该目录下使用命令创建镜像
docker build -t [image name]:[version] .
创建完成后将镜像上传到私有镜像仓库中。
- ES需要用到存储，需要提前创建持久卷（PV）
persistent-volume-es.yaml
kind: PersistentVolume
apiVersion: v1
metadata:
name: k8s-pv-es1
labels:
type: local
spec:
storageClassName: gce-standard-sc
capacity:
storage: 20Gi
accessModes:
- ReadWriteOnce
hostPath:
path: "/usr/share/elasticsearch/data"
persistentVolumeReclaimPolicy: Recycle
---
kind: PersistentVolume
apiVersion: v1
metadata:
name: k8s-pv-es2
labels:
type: local
spec:
storageClassName: gce-standard-sc
capacity:
storage: 20Gi
accessModes:
- ReadWriteOnce
hostPath:
path: "/usr/share/elasticsearch/data"
persistentVolumeReclaimPolicy: Recycle
---
kind: PersistentVolume
apiVersion: v1
metadata:
name: k8s-pv-es3
labels:
type: local
spec:
storageClassName: gce-standard-sc
capacity:
storage: 20Gi
accessModes:
- ReadWriteOnce
hostPath:
path: "/usr/share/elasticsearch/data"
persistentVolumeReclaimPolicy: Recycle
使用如下命令创建
kubectl create -f persistent-volume-es.yaml
create pv
部署Elasticsearch集群
elasticsearch.yaml
#create the statefulset headless service
apiVersion: v1
kind: Service
metadata:
name: es-discovery-svc
labels:
app: es-discovery-svc
spec:
# the set of Pods targeted by this Service are determined by the Label Selector
selector:
app: elasticsearch
# exposing elasticsearch transport port (only)
# this service will be used by es-nodes for discovery;
# communication between es-nodes happens through
# the transport port (9300)
ports:
- protocol: TCP
# port exposed by the service (service reacheable at)
port: 9300
# port exposed by the Pod(s) the service abstracts (pod reacheable at)
# can be a string representing the name of the port @the pod (ex. transport)
targetPort: 9300
name: transport
# specifying this is a headless service by providing ClusterIp "None"
clusterIP: None
---
#create the cluster-ip service
apiVersion: v1
kind: Service
metadata:
name: es-ia-svc
labels:
app: es-ia-svc
spec:
selector:
app: elasticsearch
ports:
- name: http
port: 9200
protocol: TCP
- name: transport
port: 9300
protocol: TCP
---
#create the stateful set
apiVersion: apps/v1beta1
kind: StatefulSet
metadata:
name: elasticsearch
labels:
app: elasticsearch
spec:
# the headless-service that governs this StatefulSet
# responsible for the network identity of the set.
serviceName: es-discovery-svc
replicas: 3
# Template is the object that describes the pod that will be created
template:
metadata:
labels:
app: elasticsearch
spec:
securityContext:
# allows read/write access for mounted volumes
# by users that belong to a group with gid: 1000
fsGroup: 1000
initContainers:
# init-container for setting the mmap count limit
- name: sysctl
image: busybox
imagePullPolicy: IfNotPresent
command: ["sysctl", "-w", "vm.max_map_count=262144"]
securityContext:
privileged: true
containers:
- name: elasticsearch
securityContext:
# applying fix in: https://github.com/kubernetes/kubernetes/issues/3595#issuecomment-287692878
# https://docs.docker.com/engine/reference/run/#operator-exclusive-options
capabilities:
add:
# Lock memory (mlock(2), mlockall(2), mmap(2), shmctl(2))
- IPC_LOCK
# Override resource Limits
- SYS_RESOURCE
image: registry.docker.uih/library/leo-elsticsearch:5.6.10
imagePullPolicy: IfNotPresent
ports:
- containerPort: 9300
name: transport
protocol: TCP
- containerPort: 9200
name: http
protocol: TCP
env:
# environment variables to be directly refrenced from the configuration
- name: NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
# elasticsearch heapsize (to be adjusted based on need)
- name: "ES_JAVA_OPTS"
value: "-Xms2g -Xmx2g"
# mounting storage persistent volume completely on the data dir
volumeMounts:
- name: es-data-vc
mountPath: /usr/share/elasticsearch/data
# The StatefulSet guarantees that a given [POD] network identity will
# always map to the same storage identity
volumeClaimTemplates:
- metadata:
name: es-data-vc
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
# elasticsearch mounted data directory size (to be adjusted based on need)
storage: 20Gi
storageClassName: gce-standard-sc
# no LabelSelector defined
# claims can specify a label selector to further filter the set of volumes
# currently, a PVC with a non-empty selector can not have a PV dynamically provisioned for it
# no volumeName is provided
使用如下命令进行部署
kubectl create -f elasticsearch.yaml
部署完后发现还没运行起来，通过日志查出是用户对文件夹【/usr/share/elasticsearch】没有权限引起的，文件夹的权限是root用户，这里可以在外面通过root用户手动修改文件夹权限，将文件夹权限赋给普通用户即可。
