orchestrator数据库高可用组件搭建

一、前言

      说一下为什么使用orchestrator作为数据库的高可用组件而不是MHA，因为mha组件存在组件单点问题，而orchestrator组件可以组建集群，不会出现单点问题

二、搭建

搭建mysql gtid主从

参考：mysql主从搭建(gtid)-CSDN博客

上面的主从配置是为了 orchestrator数据库高可用组件的使用，其中有几个配置不能出错

主从配置中的CHANGE MASTER TO MASTER_HOST='rabbitmq02',必须使用主机名，不能使用ip地址，不然在使用orchestrator组件做mysql故障切换时会出问题

还有就是对于主从同步用户的权限配置也是加多了几项，而不是单纯的配置REPLICATION SLAVE权限

搭建orchestrator集群

在github上下载orchestrator的安装包

地址：Releases · openark/orchestrator · GitHub

 这里使用三台主机构建orchestrator集群，使用raft协议使用高可用，允许一台主机宕机

ip	port
10.1.60.118	3306、3001
10.1.60.120	3306、3001
10.1.60.125	3306、3001

需要先为每台主机安装mysql服务

参考：yum安装mysql 5.7_yum安装mysql5.7_Apex Predator的博客-CSDN博客

创建 orchestrator数据库与用户

mysql -u root -p

create database orchestrator;

create user 'orchestrator'@'%' identified by '11111111';

grant all on orchestrator.* to 'orchestrator'@'%';

flush privileges;

将安装包分别放到三台主机上并解压

mkdir /opt/orchestrator && cd /opt/orchestrator

tar -zxvf orchestrator-3.2.5-linux-amd64.tar.gz && ls

拷贝配置文件(三台主机都需要操作)

cd usr/local/orchestrator/

cp orchestrator-sample.conf.json orchestrator.conf.json

编辑配置文件(三台主机都需要操作)

vi orchestrator.conf.json

{
  "Debug": true,
  "EnableSyslog": true,
  "ListenAddress": ":3001",            #默认是使用3000端口，但是我这边有服务被使用了所以改成3001端口
  "MySQLTopologyUser": "orchestrator",    #配置被监控的主从数据库的用户
  "MySQLTopologyPassword": "11111111",     #配置被监控的主从数据库的用户密码
  "MySQLTopologyCredentialsConfigFile": "",
  "MySQLTopologySSLPrivateKeyFile": "",
  "MySQLTopologySSLCertFile": "",
  "MySQLTopologySSLCAFile": "",
  "MySQLTopologySSLSkipVerify": true,
  "MySQLTopologyUseMutualTLS": false,
  "MySQLOrchestratorHost": "10.1.60.125",     #配置orchestrator组件服务本机地址
  "MySQLOrchestratorPort": 3306,              #配置orchestrator组件服务数据库端口
  "MySQLOrchestratorDatabase": "orchestrator",   #配置orchestrator组件数据库
  "MySQLOrchestratorUser": "orchestrator",       #配置orchestrator数据库用户
  "MySQLOrchestratorPassword": "11111111",        ##配置orchestrator数据库用户密码
  "MySQLOrchestratorCredentialsConfigFile": "",
  "MySQLOrchestratorSSLPrivateKeyFile": "",
  "MySQLOrchestratorSSLCertFile": "",
  "MySQLOrchestratorSSLCAFile": "",
  "MySQLOrchestratorSSLSkipVerify": true,
  "MySQLOrchestratorUseMutualTLS": false,
  "MySQLConnectTimeoutSeconds": 1,
  "RaftEnabled": true,                         #启用raft配置，以下配置默认是没有的，需要手动加上
  "RaftDataDir": "/opt/orchestrator",           #配置orchestrator安装包地址
  "RaftBind": "10.1.60.125",                      #配置orchestrator组件服务本机地址
  "DefaultRaftPort": 10008,                 #配置raft服务端口
  "RaftNodes": [                       #配置orchestrator组件集群地址
    "10.1.60.118",
    "10.1.60.120",
    "10.1.60.125"
  ], 
  "DefaultInstancePort": 3306,
  "DiscoverByShowSlaveHosts": true,
  "InstancePollSeconds": 5,
  "DiscoveryIgnoreReplicaHostnameFilters": [
    "a_host_i_want_to_ignore[.]example[.]com",
    ".*[.]ignore_all_hosts_from_this_domain[.]example[.]com",
    "a_host_with_extra_port_i_want_to_ignore[.]example[.]com:3307"
  ],
  "UnseenInstanceForgetHours": 240,
  "SnapshotTopologiesIntervalHours": 0,
  "InstanceBulkOperationsWaitTimeoutSeconds": 10,
  "HostnameResolveMethod": "None",     #此处需要更改为None，默认是default，使用默认的后面通过主机名添加mysql主从的时候会查找不到
  "MySQLHostnameResolveMethod": "SELECT concat(@@report_host,':',@@port)",  #此处也需要更改为report_host模式
  "SkipBinlogServerUnresolveCheck": true,
  "ExpiryHostnameResolvesMinutes": 60,
  "RejectHostnameResolvePattern": "",
  "ReasonableReplicationLagSeconds": 10,
  "ProblemIgnoreHostnameFilters": [],
  "VerifyReplicationFilters": false,
  "ReasonableMaintenanceReplicationLagSeconds": 20,
  "CandidateInstanceExpireMinutes": 60,
  "AuditLogFile": "",
  "AuditToSyslog": false,
  "RemoveTextFromHostnameDisplay": ":3306",
  "ReadOnly": false,
  "AuthenticationMethod": "",
  "HTTPAuthUser": "",
  "HTTPAuthPassword": "",
  "AuthUserHeader": "",
  "PowerAuthUsers": [
    "*"
  ],
  "ClusterNameToAlias": {
    "127.0.0.1": "test suite"
  },
  "ReplicationLagQuery": "",
  "DetectClusterAliasQuery": "SELECT SUBSTRING_INDEX(@@hostname, '.', 1)",
  "DetectClusterDomainQuery": "",
  "DetectInstanceAliasQuery": "",
  "DetectPromotionRuleQuery": "",
  "DataCenterPattern": "[.]([^.]+)[.][^.]+[.]mydomain[.]com",
  "PhysicalEnvironmentPattern": "[.]([^.]+[.][^.]+)[.]mydomain[.]com",
  "PromotionIgnoreHostnameFilters": [],
  "DetectSemiSyncEnforcedQuery": "",
  "ServeAgentsHttp": false,
  "AgentsServerPort": ":3001",      #此处也需要更改orchestrator组件默认的端口号
  "AgentsUseSSL": false,
  "AgentsUseMutualTLS": false,
  "AgentSSLSkipVerify": false,
  "AgentSSLPrivateKeyFile": "",
  "AgentSSLCertFile": "",
  "AgentSSLCAFile": "",
  "AgentSSLValidOUs": [],
  "UseSSL": false,
  "UseMutualTLS": false,
  "SSLSkipVerify": false,
  "SSLPrivateKeyFile": "",
  "SSLCertFile": "",
  "SSLCAFile": "",
  "SSLValidOUs": [],
  "URLPrefix": "",
  "StatusEndpoint": "/api/status",
  "StatusSimpleHealth": true,
  "StatusOUVerify": false,
  "AgentPollMinutes": 60,
  "UnseenAgentForgetHours": 6,
  "StaleSeedFailMinutes": 60,
  "SeedAcceptableBytesDiff": 8192,
  "PseudoGTIDPattern": "",
  "PseudoGTIDPatternIsFixedSubstring": false,
  "PseudoGTIDMonotonicHint": "asc:",
  "DetectPseudoGTIDQuery": "",
  "BinlogEventsChunkSize": 10000,
  "SkipBinlogEventsContaining": [],
  "ReduceReplicationAnalysisCount": true,
  "FailureDetectionPeriodBlockMinutes": 60,
  "FailMasterPromotionOnLagMinutes": 0,
  "RecoveryPeriodBlockSeconds": 3600,
  "RecoveryIgnoreHostnameFilters": [],
  "RecoverMasterClusterFilters": ["*"],           #需要更改默认配置，改为*，不然主从故障自动切换不会生效
  "RecoverIntermediateMasterClusterFilters": ["*"],    #需要更改默认配置，改为*，不然主从故障自动切换不会生效
  "OnFailureDetectionProcesses": [
    "echo 'Detected {failureType} on {failureCluster}. Affected replicas: {countSlaves}' >> /tmp/recovery.log"
  ],
  "PreGracefulTakeoverProcesses": [
    "echo 'Planned takeover about to take place on {failureCluster}. Master will switch to read_only' >> /tmp/recovery.log"
  ],
  "PreFailoverProcesses": [
    "echo 'Will recover from {failureType} on {failureCluster}' >> /tmp/recovery.log"
  ],
  "PostFailoverProcesses": [
    "echo '(for all types) Recovered from {failureType} on {failureCluster}. Failed: {failedHost}:{failedPort}; Successor: {successorHost}:{successorPort}' >> /tmp/recovery.log"
  ],
  "PostUnsuccessfulFailoverProcesses": [],
  "PostMasterFailoverProcesses": [
    "echo 'Recovered from {failureType} on {failureCluster}. Failed: {failedHost}:{failedPort}; Promoted: {successorHost}:{successorPort}' >> /tmp/recovery.log"
  ],
  "PostIntermediateMasterFailoverProcesses": [
    "echo 'Recovered from {failureType} on {failureCluster}. Failed: {failedHost}:{failedPort}; Successor: {successorHost}:{successorPort}' >> /tmp/recovery.log"
  ],
  "PostGracefulTakeoverProcesses": [
    "echo 'Planned takeover complete' >> /tmp/recovery.log"
  ],
  "CoMasterRecoveryMustPromoteOtherCoMaster": true,
  "DetachLostSlavesAfterMasterFailover": true,
  "ApplyMySQLPromotionAfterMasterFailover": true,
  "PreventCrossDataCenterMasterFailover": false,
  "PreventCrossRegionMasterFailover": false,
  "MasterFailoverDetachReplicaMasterHost": false,
  "MasterFailoverLostInstancesDowntimeMinutes": 0,
  "PostponeReplicaRecoveryOnLagMinutes": 0,
  "OSCIgnoreHostnameFilters": [],
  "GraphiteAddr": "",
  "GraphitePath": "",
  "GraphiteConvertHostnameDotsToUnderscores": true,
  "ConsulAddress": "",
  "ConsulAclToken": "",
  "ConsulKVStoreProvider": "consul"
}

启动orchestrator组件服务

nohup ./orchestrator http &>./orchestrator.log&

查看orchestrator组件服务是否正常

netstat -tlpn |grep 3001

访问 orchestrator组件web

接下来添加mysql主从，只需添加主从中的任意一台就会自动识别整个主从架构

 

 关于主从故障的测试就不再演示了，可以自行操作，但是原来挂掉的主数据库重新启动后需要手动配置slave服务才能重新在加入主从架构中