本文详细介绍了如何在 CentOS 7.6 系统上安装 Elasticsearch 7.9.3，包括下载、创建新用户、设置权限、解决启动异常问题，如文件描述符、线程数和虚拟内存限制。此外，还讲解了配置网络主机为0.0.0.0以允许外部访问，以及启动和停止ES的步骤。文章中还提到了配置文件`elasticsearch.yml`的重要参数，并展示了分词器的测试结果，指出默认分词器与预期不符。
文章目录
Elasticsearch 安装
linux：centos7.6
es版本：elasticsearch-7.9.3
jdk：openJDK
1 ES下载
官网下载：https://www.elastic.co/cn/downloads/elasticsearch
中文社区下载：https://elasticsearch.cn/download/
百度网盘下载：https://pan.baidu.com/s/1Qv5PZW0hny_Ahp7DRMXd3w 提取码：o3vf
2 安装配置
博主将包上传到 /home/es 目录下
2.1 解压
# 解压到当前目录下
[root@localhost es]# tar -zxvf elasticsearch-7.9.3-linux-x86_64.tar.gz
# 解压成功目录
[root@localhost es]# ls
elasticsearch-7.9.3 elasticsearch-7.9.3-linux-x86_64.tar.gz
2.1.1 es目录结构介绍
注意：es不能在root用户下启动，必须创建新的用户，用来启动es
2.2 创建新用户
# 1. 创建新用户
useradd es
# 2. 修改密码
passwd es
# 3. 切换用户
su - es # 密码登录
su es # 无需密码登录
2.2 为用户设置权限，否则启动会报错
chown -R es:es 当前es的安装目录(博主目录/home/es/elasticsearch-7.9.3)
2.2 es授权
为使浏览器允许访问，需要做如下配置：
配置文件为es解压目录下:/config/elasticsearch.yml
# ---------------------------------- Network -----------------------------------
#
# Set the bind address to a specific IP (IPv4 or IPv6):
#
network.host: 0.0.0.0
2.2 启动过程可能引起的异常
- max file descriptors [4096] for elasticsearch process is too low, increase to at least [65536]
- max number of threads [3818] for user [es] is too low, increase to at least [4096]
- max virtual memory areas vm.max_map_count [65530] is too low, increase to at least [262144]
原因：系统配置参数与es启动配置参数不符，需要配置
- 修改/etc/security/limits.conf文件,在底部新增，属于*也要新增
* soft nofile 65536
* hard nofile 65536
* soft nproc 4096
* hard nproc 4096
服务器重启生效，查看
[root@localhost config]# ulimit -Hn
65536
[root@localhost config]# ulimit -Sn
65536
[root@localhost config]# ulimit -Hu
4096
[root@localhost config]# ulimit -Su
4096
- 最大线程个数太低。修改配置文件/etc/security/limits.conf，增加配置
# /etc/security/limits.conf增加
vm.max_map_count=262144
#执行命令sysctl -p生效
[root@localhost config]# sysctl -p
vm.max_map_count = 262144
3 启动停止
3.1 启动
# 守护进程启动,es解压目录下/bin
./elasticsearch -d
3.2 关闭
es只能强制关闭：kill -9 pid
[root@localhost bin]# ps -ef|grep elasticsearch
es 8946 1 0 11:21 pts/0 00:00:56 /usr/lib/jvm/java-1.8.0/bin/java -Xshare:auto -Des.networkaddress.cache.ttl=60 -Des.networkaddress.cache.negative.ttl=10 -XX:+AlwaysPreTouch -Xss1m -Djava.awt.headless=true -Dfile.encoding=UTF-8 -Djna.nosys=true -XX:-OmitStackTraceInFastThrow -Dio.netty.noUnsafe=true -Dio.netty.noKeySetOptimization=true -Dio.netty.recycler.maxCapacityPerThread=0 -Dio.netty.allocator.numDirectArenas=0 -Dlog4j.shutdownHookEnabled=false -Dlog4j2.disable.jmx=true -Djava.locale.providers=SPI,JRE -Xms1g -Xmx1g -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=75 -XX:+UseCMSInitiatingOccupancyOnly -Djava.io.tmpdir=/tmp/elasticsearch-4938857371574732973 -XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=data -XX:ErrorFile=logs/hs_err_pid%p.log -XX:+PrintGCDetails -XX:+PrintGCDateStamps -XX:+PrintTenuringDistribution -XX:+PrintGCApplicationStoppedTime -Xloggc:logs/gc.log -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=32 -XX:GCLogFileSize=64m -XX:MaxDirectMemorySize=536870912 -Des.path.home=/home/es/elasticsearch-7.9.3 -Des.path.conf=/home/es/elasticsearch-7.9.3/config -Des.distribution.flavor=default -Des.distribution.type=tar -Des.bundled_jdk=true -cp /home/es/elasticsearch-7.9.3/lib/* org.elasticsearch.bootstrap.Elasticsearch -d
es 8960 8946 0 11:21 pts/0 00:00:00 /home/es/elasticsearch-7.9.3/modules/x-pack-ml/platform/linux-x86_64/bin/controller
root 9143 7086 0 13:35 pts/0 00:00:00 grep --color=auto elasticsearch
[root@localhost bin]# kill -9 8946
3.3 启动验证
浏览器访问：xxx.xxx.xxx.xxx:9200
{
"name" : "localhost.localdomain",
"cluster_name" : "elasticsearch",
"cluster_uuid" : "qO9-FxOAQkarL_ieSn_R7A",
"version" : {
"number" : "7.9.3",
"build_flavor" : "default",
"build_type" : "tar",
"build_hash" : "c4138e51121ef06a6404866cddc601906fe5c868",
"build_date" : "2020-10-16T10:36:16.141335Z",
"build_snapshot" : false,
"lucene_version" : "8.6.2",
"minimum_wire_compatibility_version" : "6.8.0",
"minimum_index_compatibility_version" : "6.0.0-beta1"
},
"tagline" : "You Know, for Search"
}
4 elasticsearch.yml 配置文件相关介绍
# ======================== Elasticsearch Configuration =========================
#
# NOTE: Elasticsearch comes with reasonable defaults for most settings.
# Before you set out to tweak and tune the configuration, make sure you
# understand what are you trying to accomplish and the consequences.
#
# The primary way of configuring a node is via this file. This template lists
# the most important settings you may want to configure for a production cluster.
#
# Please see the documentation for further information on configuration options:
# <http://www.elastic.co/guide/en/elasticsearch/reference/current/setup-configuration.html>
#
# ---------------------------------- Cluster -----------------------------------
#
# Use a descriptive name for your cluster:
# 集群名称，默认是elasticsearch
# cluster.name: my-application
#
# ------------------------------------ Node ------------------------------------
#
# Use a descriptive name for the node:
# 节点名称，默认从elasticsearch-2.4.3/lib/elasticsearch-2.4.3.jar!config/names.txt中随机选择一个名称
# node.name: node-1
#
# Add custom attributes to the node:
#
# node.rack: r1
#
# ----------------------------------- Paths ------------------------------------
#
# Path to directory where to store the data (separate multiple locations by comma):
# 可以指定es的数据存储目录，默认存储在es_home/data目录下
# path.data: /path/to/data
#
# Path to log files:
# 可以指定es的日志存储目录，默认存储在es_home/logs目录下
# path.logs: /path/to/logs
#
# ----------------------------------- Memory -----------------------------------
#
# Lock the memory on startup:
# 锁定物理内存地址，防止elasticsearch内存被交换出去,也就是避免es使用swap交换分区
# bootstrap.memory_lock: true
#
#
#
# 确保ES_HEAP_SIZE参数设置为系统可用内存的一半左右
# Make sure that the `ES_HEAP_SIZE` environment variable is set to about half the memory
# available on the system and that the owner of the process is allowed to use this limit.
#
# 当系统进行内存交换的时候，es的性能很差
# Elasticsearch performs poorly when the system is swapping the memory.
#
# ---------------------------------- Network -----------------------------------
#
#
# 为es设置ip绑定，默认是127.0.0.1，也就是默认只能通过127.0.0.1 或者localhost才能访问
# es1.x版本默认绑定的是0.0.0.0 所以不需要配置，但是es2.x版本默认绑定的是127.0.0.1，需要配置
# Set the bind address to a specific IP (IPv4 or IPv6):
#
# network.host: 192.168.0.1
#
#
# 为es设置自定义端口，默认是9200
# 注意：在同一个服务器中启动多个es节点的话，默认监听的端口号会自动加1：例如：9200，9201，9202...
# Set a custom port for HTTP:
#
# http.port: 9200
#
# For more information, see the documentation at:
# <http://www.elastic.co/guide/en/elasticsearch/reference/current/modules-network.html>
#
# --------------------------------- Discovery ----------------------------------
#
# 当启动新节点时，通过这个ip列表进行节点发现，组建集群
# 默认节点列表：
# 127.0.0.1，表示ipv4的回环地址。
# [::1]，表示ipv6的回环地址
#
# 在es1.x中默认使用的是组播(multicast)协议，默认会自动发现同一网段的es节点组建集群，
# 在es2.x中默认使用的是单播(unicast)协议，想要组建集群的话就需要在这指定要发现的节点信息了。
# 注意：如果是发现其他服务器中的es服务，可以不指定端口[默认9300]，如果是发现同一个服务器中的es服务，就需要指定端口了。
# Pass an initial list of hosts to perform discovery when new node is started:
#
# The default list of hosts is ["127.0.0.1", "[::1]"]
#
# discovery.zen.ping.unicast.hosts: ["host1", "host2"]
#
#
#
#
# 通过配置这个参数来防止集群脑裂现象 (集群总节点数量/2)+1
# Prevent the "split brain" by configuring the majority of nodes (total number of nodes / 2 + 1):
#
# discovery.zen.minimum_master_nodes: 3
#
# For more information, see the documentation at:
# <http://www.elastic.co/guide/en/elasticsearch/reference/current/modules-discovery.html>
#
# ---------------------------------- Gateway -----------------------------------
#
# Block initial recovery after a full cluster restart until N nodes are started:
# 一个集群中的N个节点启动后,才允许进行数据恢复处理，默认是1
# gateway.recover_after_nodes: 3
#
# For more information, see the documentation at:
# <http://www.elastic.co/guide/en/elasticsearch/reference/current/modules-gateway.html>
#
# ---------------------------------- Various -----------------------------------
# 在一台服务器上禁止启动多个es服务
# Disable starting multiple nodes on a single system:
#
# node.max_local_storage_nodes: 1
#
# 设置是否可以通过正则或者_all删除或者关闭索引库，默认true表示必须需要显式指定索引库名称
# 生产环境建议设置为true，删除索引库的时候必须显式指定，否则可能会误删索引库中的索引库。
# Require explicit names when deleting indices:
#
# action.destructive_requires_name: true
5 其他异常
5.1 启动异常
- 异常信息
ERROR: [1] bootstrap checks failed
[1]: the default discovery settings are unsuitable for production use; at least one of [discovery.seed_hosts, discovery.seed_providers, cluster.initial_master_nodes] must be configured
- 修改elasticsearch.yml配置文件
# --------------------------------- Discovery ----------------------------------
#
# Pass an initial list of hosts to perform discovery when this node is started:
# The default list of hosts is ["127.0.0.1", "[::1]"]
#
#discovery.seed_hosts: ["host1", "host2"]
cluster.initial_master_nodes: ["node-1"]
6 分析器
6.1 默认分词器测试
请求工具：postman
请求uri：192.168.163.104:9200/_analyze
body：{“analyzer”: “chinese”,“text”:“tom今天天气真好”}
分词结果：中文分词与实际预期分词不符，差异太大
{
"tokens": [
{
"token": "tom",
"start_offset": 0,
"end_offset": 3,
"type": "<ALPHANUM>",
"position": 0
},
{
"token": "今",
"start_offset": 3,
"end_offset": 4,
"type": "<IDEOGRAPHIC>",
"position": 1
},
{
"token": "天",
"start_offset": 4,
"end_offset": 5,
"type": "<IDEOGRAPHIC>",
"position": 2
},
{
"token": "天",
"start_offset": 5,
"end_offset": 6,
"type": "<IDEOGRAPHIC>",
"position": 3
},
{
"token": "气",
"start_offset": 6,
"end_offset": 7,
"type": "<IDEOGRAPHIC>",
"position": 4
},
{
"token": "真",
"start_offset": 7,
"end_offset": 8,
"type": "<IDEOGRAPHIC>",
"position": 5
},
{
"token": "好",
"start_offset": 8,
"end_offset": 9,
"type": "<IDEOGRAPHIC>",
"position": 6
}
]
}
6.2 IK分词器介绍
https://www.sojson.com/blog/82.html
扫一扫
879
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
