新运维-新运维社区，新运维，新方向！

Redis4.0集群

NoSQL • ShenghuiChen 发表了文章 • 0 个评论 • 624 次浏览 • 2019-01-04 14:54 • 来自相关话题

节点信息规划：准备部署7001-7004 4个实例，但是redis集群提示最少需要3个主节点，6个节点才能完成启动，所以后面2个是后来加的。注意：这里因为是测试环境，所以将所有实例都放在了一台机器上，生产建议主备节点不要放在一台机器 ...查看全部

节点信息规划：
准备部署7001-7004 4个实例，但是redis集群提示最少需要3个主节点，6个节点才能完成启动，所以后面2个是后来加的。
注意：这里因为是测试环境，所以将所有实例都放在了一台机器上，生产建议主备节点不要放在一台机器上

1、环境安装

~]# cd /opt/

opt]# wget http://download.redis.io/releases/redis-4.0.11.tar.gz

opt]# tar zxf redis-4.0.11.tar.gz

opt]# cd redis-4.0.11

opt]# make test

#yum 安装tcl

opt]# yum install tcl -y

opt]# make test

#将redis的执行脚本拷贝到PATH变量所在目录或加入全局环境变量

opt]# cp -a src/redis-server src/redis-cli src/redis-sentinel src/redis-trib.rb src/redis-check-aof src/redis-check-rdb src/redis-benchmark /usr/local/bin/

2、配置redis集群文件

opt]# mkdir -p redis-cluster

opt]# mkdir -p /opt/redis-cluster/nodes-{7001,7002,7003,7004}

opt]# ln -s redis-4.0.11 redis

按需修改配置文件(以nodes-7001实例为例)

[root@shenghui-ansible opt]# egrep -v "^#|^$" redis-cluster/nodes-7001/redis.conf 

bind 192.168.56.67

protected-mode yes

port 7001

tcp-backlog 511

timeout 0

tcp-keepalive 300

daemonize yes

supervised no

pidfile redis_7001.pid

loglevel notice

logfile "/opt/redis-cluster/nodes-7001/redis_7001.log"

databases 16

always-show-logo yes

save 900 1

save 300 10

save 60 10000

stop-writes-on-bgsave-error yes

rdbcompression yes

rdbchecksum yes

dbfilename dump.rdb

dir /opt/redis-cluster/nodes-7001/

slave-serve-stale-data yes

slave-read-only yes

repl-diskless-sync no

repl-diskless-sync-delay 5

repl-disable-tcp-nodelay no

slave-priority 100

lazyfree-lazy-eviction no

lazyfree-lazy-expire no

lazyfree-lazy-server-del no

slave-lazy-flush no

appendonly yes

appendfilename "appendonly.aof"

appendfsync everysec

no-appendfsync-on-rewrite no

auto-aof-rewrite-percentage 100

auto-aof-rewrite-min-size 64mb

aof-load-truncated yes

aof-use-rdb-preamble no

lua-time-limit 5000

cluster-enabled yes

cluster-config-file nodes-7001.conf

cluster-node-timeout 5000

cluster-slave-validity-factor 10

slowlog-log-slower-than 10000

slowlog-max-len 128

latency-monitor-threshold 0

notify-keyspace-events ""

hash-max-ziplist-entries 512

hash-max-ziplist-value 64

list-max-ziplist-size -2

list-compress-depth 0

set-max-intset-entries 512

zset-max-ziplist-entries 128

zset-max-ziplist-value 64

hll-sparse-max-bytes 3000

activerehashing yes

client-output-buffer-limit normal 0 0 0

client-output-buffer-limit slave 256mb 64mb 60

client-output-buffer-limit pubsub 32mb 8mb 60

hz 10

aof-rewrite-incremental-fsync yes

3、启动redis及创建集群
依次启动各个redis实例

]# redis-server /opt/redis-cluster/nodes-7001/redis.conf

]# redis-server /opt/redis-cluster/nodes-7002/redis.conf

]# redis-server /opt/redis-cluster/nodes-7003/redis.conf

]# redis-server /opt/redis-cluster/nodes-7004/redis.conf

4、创建redis集群
创建redis集群使用redis-trib.rb命令，该命令是基于ruby的脚本，需要安装ruby，ruby-gem以及gem-redis
#如果有老版本，卸载ruby2.0.0，安装ruby2.2.2以上版本

[root@elk01 ~]# ruby -v  #centos7 忽略

ruby 2.0.0p648 (2015-12-16) [x86_64-linux]

[root@elk01 ~]# yum erase ruby

~]# wget https://cache.ruby-lang.org/pub/ruby/2.5/ruby-2.5.3.tar.gz

~]# tar zxf ruby-2.5.3.tar.gz

~]# cd ruby-2.5.3/

ruby-2.5.3]# ./configure

ruby-2.5.3]# make

安装ruby-redis.gem
推荐：如果默认国外的gem源连不上或者很慢，可以试试国内源
添加国内源命令：gem source -a https://gems.ruby-china.com
删除国外源并添加国内源：gem sources --add https://gems.ruby-china.com/ --remove https://rubygems.com/
#检测gem源，注意RubyGems源尽量用新版本，官方建议2.6.X，但是我用2.5.2也没什么问题

[root@shenghui-ansible ~]# gem source -l

*** CURRENT SOURCES ***



https://gems.ruby-china.com

redis-cluster]# gem install redis -v 3.3.5    #注：不要使用4.x版本，不然后期增加实例，迁移哈希槽会失败

创建集群报错：

root@elk01 redis-cluster]# redis-trib.rb create --replicas 1 192.168.56.67:7001 192.168.56.67:7002 192.168.56.67:7003 192.168.56.67:7004

>>> Creating cluster

*** ERROR: Invalid configuration for cluster creation. #错误表示redis集群至少要3个主，6个节点

*** Redis Cluster requires at least 3 master nodes.

*** This is not possible with 4 nodes and 1 replicas per node.

*** At least 6 nodes are required.

#新增两个节点

redis-cluster]# mkdir -p nodes-{7005,7006}

#拷贝并修改下redis配置ip

redis-cluster]# cp nodes-7001/redis.conf nodes-7005/

redis-cluster]# cp nodes-7001/redis.conf nodes-7006/

启动redis

redis-server /opt/redis-cluster/nodes-7005/redis.conf

redis-server /opt/redis-cluster/nodes-7006/redis.conf

[root@shenghui-ansible ~]# ps -ef|grep redis

root      26651      1  0 Nov13 ?        00:01:10 redis-server 127.0.0.1:7002 [cluster]

root      26656      1  0 Nov13 ?        00:01:10 redis-server 127.0.0.1:7003 [cluster]

root      26661      1  0 Nov13 ?        00:01:09 redis-server 127.0.0.1:7004 [cluster]

root      26666      1  0 Nov13 ?        00:01:10 redis-server 127.0.0.1:7005 [cluster]

root      26671      1  0 Nov13 ?        00:01:09 redis-server 127.0.0.1:7006 [cluster]

root      26725      1  0 Nov13 ?        00:01:11 redis-server 127.0.0.1:7001 [cluster]

#创建集群成功

redis-cluster]# redis-trib.rb create --replicas 1 192.168.56.67:7001 192.168.56.67:7002 192.168.56.67:7003 192.168.56.67:7004 192.168.56.67:7005 192.168.56.67:7006

>>> Creating cluster

>>> Performing hash slots allocation on 6 nodes...

Using 3 masters:

192.168.56.67:7001

192.168.56.67:7002

192.168.56.67:7003

Adding replica 192.168.56.67:7004 to 192.168.56.67:7001

Adding replica 192.168.56.67:7005 to 192.168.56.67:7002

Adding replica 1192.168.56.67:7006 to 192.168.56.67:7003

M: 23df12c2bafde34f5bdd53d3463ad20b8ab507d2 192.168.56.67:7001

集群测试：

[root@shenghui-ansible ~]# redis-cli -c -p 7001 #登陆操作集群，-c参数是必须的

127.0.0.1:7001> cluster info

cluster_state:ok

cluster_slots_assigned:16384

cluster_slots_ok:16384

cluster_slots_pfail:0

cluster_slots_fail:0

cluster_known_nodes:6

cluster_size:3

cluster_current_epoch:7

cluster_my_epoch:7

cluster_stats_messages_ping_sent:84881

...

127.0.0.1:7001> cluster nodes

21da5db87c968a926ac98db20c6b3e5db98e86b4 192.168.56.67:7001@17001 myself,slave 64f7850f021d1150b41fc654f247e075f8573813 0 1542181496000 1 connected

bbba5557051520f7d825819415a806b8716f811c 127.0.0.1:7002@17002 master - 0 1542181497150 2 connected 5461-10922

f707863e9846cf9e7c68fd7cdae5b72aa4f6839b 127.0.0.1:7004@17004 slave 66ebc6a414a533a9a2ed27fbcdbea88b9d8ed4db 0 1542181498161 4 connected

ecdf34327e274a8294f7225ddbb5d3f4cd0b7bde 127.0.0.1:7006@17006 slave bbba5557051520f7d825819415a806b8716f811c 0 1542181497000 6 connected

64f7850f021d1150b41fc654f247e075f8573813 127.0.0.1:7005@17005 master - 0 1542181495000 7 connected 0-5460

66ebc6a414a533a9a2ed27fbcdbea88b9d8ed4db 127.0.0.1:7003@17003 master - 0 1542181495132 3 connected 10923-16383

127.0.0.1:7001> set liubai 'papa'

-> Redirected to slot [11252] located at 127.0.0.1:7003

OK

127.0.0.1:7003> get liubai

"papa"

nodes-7001宕机查看数据(redis集群去中心化，连接哪一台都可以)：

~]# kill -9 26725  #生长不建议使用kill，登陆redis-cli 使用shutdown关闭redis

 [root@shenghui-ansible ~]# redis-cli -c -p 7002

127.0.0.1:7002> get liubai

-> Redirected to slot [11252] located at 127.0.0.1:7003  #数据在nodes3，从自动切换选举为主

"papa"

127.0.0.1:7003> cluster nodes

bbba5557051520f7d825819415a806b8716f811c 127.0.0.1:7002@17002 master - 0 1542181782880 2 connected 5461-10922

21da5db87c968a926ac98db20c6b3e5db98e86b4 127.0.0.1:7001@17001 slave,fail 64f7850f021d1150b41fc654f247e075f8573813 1542181666613 1542181664000 7 disconnected

64f7850f021d1150b41fc654f247e075f8573813 127.0.0.1:7005@17005 master - 0 1542181780860 7 connected 0-5460

66ebc6a414a533a9a2ed27fbcdbea88b9d8ed4db 127.0.0.1:7003@17003 myself,master - 0 1542181781000 3 connected 10923-16383

f707863e9846cf9e7c68fd7cdae5b72aa4f6839b 127.0.0.1:7004@17004 slave 66ebc6a414a533a9a2ed27fbcdbea88b9d8ed4db 0 1542181781869 4 connected

ecdf34327e274a8294f7225ddbb5d3f4cd0b7bde 127.0.0.1:7006@17006 slave bbba5557051520f7d825819415a806b8716f811c 0 1542181780000 6 connected

127.0.0.1:7003> get liubai

"papa"

Zabbix监控插件-Nginx、TCP、Redis、Memcached

自动化运维 • 赵班长发表了文章 • 0 个评论 • 850 次浏览 • 2018-12-23 13:55 • 来自相关话题

2014年写的Zabbix监控插件，主要监控TCP的11种状态、Nginx状态、Redis和Memcached状态。监控模板请查看附件。直接导入到Zabbix中即可。 Nginx监控状态 ...查看全部

2014年写的Zabbix监控插件，主要监控TCP的11种状态、Nginx状态、Redis和Memcached状态。

监控模板请查看附件。直接导入到Zabbix中即可。

Nginx监控状态配置默认使用127.0.0.1获取。

Nginx监控配置：

1.为Nginx增加状态配置文件。

[root@linux-node2 ~]# yum install -y nginx

[root@linux-node2 ~]# vim /etc/nginx/conf.d/nginx-status.conf

server {

       server_name 127.0.0.1;

       location /nginx_status {

                stub_status on;

                access_log off;

                allow 127.0.0.1;

                deny all;

                }

}

2.测试Nginx配置并启动

[root@linux-node2 ~]# nginx -t

nginx: the configuration file /etc/nginx/nginx.conf syntax is ok

nginx: configuration file /etc/nginx/nginx.conf test is successful

[root@linux-node2 ~]# systemctl start nginx

3.测试Nginx状态接口

[root@linux-node2 ~]# curl http://127.0.0.1/nginx_status

Active connections: 1 

server accepts handled requests

 7 7 7 

Reading: 0 Writing: 1 Waiting: 0

#!/bin/bash

############################################################

# $Name:         zabbix_linux_plugins.sh

# $Version:      v1.0

# $Function:     zabbix plugins

# $Author:       Jason Zhao

# $organization: www.unixhot.com

# $Create Date:  2014-08-10

# $Description:  Monitor Linux Service Status

############################################################

tcp_status_fun(){

	TCP_STAT=$1

	#netstat -n | awk '/^tcp/ {  state[$NF]} END {for(key in state) print key,state[key]}' > /tmp/netstat.tmp

	ss -ant | awk 'NR>1 {  s[$1]} END {for(k in s) print k,s[k]}' > /tmp/netstat.tmp

	TCP_STAT_VALUE=$(grep "$TCP_STAT" /tmp/netstat.tmp | cut -d ' ' -f2)

	if [ -z $TCP_STAT_VALUE ];then

		TCP_STAT_VALUE=0

	fi

	echo $TCP_STAT_VALUE

}



nginx_status_fun(){

	NGINX_PORT=$1

	NGINX_COMMAND=$2

	nginx_active(){

        /usr/bin/curl "http://127.0.0.1:"$NGINX_PORT"/nginx_status/" 2>/dev/null| grep 'Active' | awk '{print $NF}'

        }

	nginx_reading(){

        /usr/bin/curl "http://127.0.0.1:"$NGINX_PORT"/nginx_status/" 2>/dev/null| grep 'Reading' | awk '{print $2}'

       }

	nginx_writing(){

        /usr/bin/curl "http://127.0.0.1:"$NGINX_PORT"/nginx_status/" 2>/dev/null| grep 'Writing' | awk '{print $4}'

       }

	nginx_waiting(){

        /usr/bin/curl "http://127.0.0.1:"$NGINX_PORT"/nginx_status/" 2>/dev/null| grep 'Waiting' | awk '{print $6}'

       }

	nginx_accepts(){

        /usr/bin/curl "http://127.0.0.1:"$NGINX_PORT"/nginx_status/" 2>/dev/null| awk NR==3 | awk '{print $1}'

       }

	nginx_handled(){

        /usr/bin/curl "http://127.0.0.1:"$NGINX_PORT"/nginx_status/" 2>/dev/null| awk NR==3 | awk '{print $2}'

       }

	nginx_requests(){

        /usr/bin/curl "http://127.0.0.1:"$NGINX_PORT"/nginx_status/" 2>/dev/null| awk NR==3 | awk '{print $3}'

       }

  	case $NGINX_COMMAND in

		active)

			nginx_active;

			;;

		reading)

			nginx_reading;

			;;

		writing)

			nginx_writing;

			;;

		waiting)

			nginx_waiting;

			;;

		accepts)

			nginx_accepts;

			;;

		handled)

			nginx_handled;

			;;

		requests)

			nginx_requests;

		esac 

}



memcached_status_fun(){

	M_PORT=$1

	M_COMMAND=$2

	echo -e "stats\nquit" | nc 127.0.0.1 "$M_PORT" | grep "STAT $M_COMMAND " | awk '{print $3}'

}



redis_status_fun(){

	R_PORT=$1

	R_COMMAND=$2

	(echo -en "INFO \r\n";sleep 1;) | nc 127.0.0.1 "$R_PORT" > /tmp/redis_"$R_PORT".tmp

	REDIS_STAT_VALUE=$(grep ""$R_COMMAND":" /tmp/redis_"$R_PORT".tmp | cut -d ':' -f2)

 	echo $REDIS_STAT_VALUE	

}



main(){

	case $1 in

		tcp_status)

			tcp_status_fun $2;

			;;

		nginx_status)

			nginx_status_fun $2 $3;

			;;

		memcached_status)

			memcached_status_fun $2 $3;

			;;

		redis_status)

			redis_status_fun $2 $3;

			;;

		*)

			echo $"Usage: $0 {tcp_status key|memcached_status key|redis_status key|nginx_status key}"

	esac

}



main $1 $2 $3

使用方法：

[root@linux-node2 ~]# ./zabbix_linux_plugin.sh 

Usage: ./zabbix_linux_plugin.sh {tcp_status key|memcached_status key|redis_status key|nginx_status key}

获取TCP监控状态

[root@linux-node2 ~]# ./zabbix_linux_plugin.sh tcp_status LISTEN

14

Tomcat 开启JMX监控

运维监控 • 赵班长发表了文章 • 0 个评论 • 623 次浏览 • 2018-12-20 15:05 • 来自相关话题

如果需要使用Zabbix Java Gateway监控JMX，需要先打开JMX监控接口。 1.Tomcat部署可以在http://tomcat.apache.org/官网上下载对应的版本。这里在linux-node2这个实验节点上 ...查看全部

如果需要使用Zabbix Java Gateway监控JMX，需要先打开JMX监控接口。

1.Tomcat部署可以在http://tomcat.apache.org/官网上下载对应的版本。这里在linux-node2这个实验节点上，使用Tomcat8做实验。

安装JDK1.8和Tomcat-8.5.20

[root@linux-node2 ~]# yum install -y java-1.8.0

[root@linux-node2 ~]# cd /usr/local/src

# wget http://mirrors.hust.edu.cn/apache/tomcat/tomcat-8/v8.5.20/bin/apache-tomcat-8.5.20.tar.gz

[root@linux-node2 src]# tar zxf apache-tomcat-8.5.20.tar.gz 

[root@linux-node2 src]# mv apache-tomcat-8.5.20 /usr/local/

[root@linux-node2 src]# ln -s /usr/local/apache-tomcat-8.5.20/ /usr/local/tomcat

2.Tomcat开启JMX监控
JMX监控设置有三种类型：

无验证的JMX监控
用户名密码认证
SSL加密

[root@linux-node2 ~]# vim /usr/local/tomcat/bin/catalina.sh

CATALINA_OPTS="$CATALINA_OPTS -Dcom.sun.management.jmxremote -Dcom.sun.management.jmxremote.port=8888 -Dcom.sun.management.jmxremote.ssl=false -Dcom.sun.management.jmxremote.authenticate=false -Djava.rmi.server.hostname=192.168.56.12"

参数行中的com.sun.management.jmxremote.port参数是tomcat JMX监听的端口，可以随意配置，但是不可已经被占用；java.rmi.server.hostname参数的IP地址为远程Linux服务器的IP地址。

3.启动Tomcat

[root@linux-node2 ~]# /usr/local/tomcat/bin/startup.sh 

Using CATALINA_BASE:   /usr/local/tomcat

Using CATALINA_HOME:   /usr/local/tomcat

Using CATALINA_TMPDIR: /usr/local/tomcat/temp

Using JRE_HOME:        /usr

Using CLASSPATH:       /usr/local/tomcat/bin/bootstrap.jar:/usr/local/tomcat/bin/tomcat-juli.jar

Tomcat started.

[root@linux-node2 ~]# netstat -ntlp | grep 8888

tcp6       0      0 :::8888                 :::*                    LISTEN      6154/java

2018年12月15日运维技术沙龙【北京站】

DevOps • 赵班长发表了文章 • 0 个评论 • 403 次浏览 • 2018-12-11 11:27 • 来自相关话题

寻找运维的下一站-腾讯蓝鲸技术沙龙改变中国运维行业 BLUEKING 活动时间：2018.12.15 13:30~18:00 主办单位：蓝鲸智云承办单位：DevOps学院协办单位： ...查看全部

寻找运维的下一站-腾讯蓝鲸技术沙龙改变中国运维行业 BLUEKING

活动时间：2018.12.15 13:30~18:00
主办单位：蓝鲸智云
承办单位：DevOps学院
协办单位：元鼎科技
地点：北京市海淀区知春路49号希格玛大厦B1小礼堂

报名地址：https://www.bagevent.com/event/1292447