mongodb复制集故障转移测试

测试一

从节点宕机 集群依然可以正常使用，可以读写操作。

docker ps 

三个容器均工作正常 （mongo01为主库，mongo02，mongo01为复制库）
此时手动停止mongo02容器

docker stop mongo02

进入容器，测试读写是否正常
主库插入

rs0:PRIMARY> use test
switched to db test
rs0:PRIMARY> db.user.insert({"id":1002,"name":"lisi"})
WriteResult({ "nInserted" : 1 })

复制库读取

rs0:SECONDARY> use test
switched to db test
rs0:SECONDARY> db.user.find()
{ "_id" : ObjectId("5f90f9c2d5a6806dd78d4879"), "id" : 1001, "name" : "zhangsan" }
{ "_id" : ObjectId("5f90fce6eaa4dcf95a6efb6f"), "id" : 1002, "name" : "lisi" }

测试二

主节点宕机 选举出新的主节点继续提供服务
我们开启mongo02

docker start mongo02

关闭主库

docker stop mongo01

进入容器，查看复制集状态

docker exec -it mongo02 /bin/bash
mongo

rs.status()

响应如下，可以看到节点一已经下线了，节点二被选举为主节点

{
	"set" : "rs0",
	"date" : ISODate("2020-10-22T03:36:10.917Z"),
	"myState" : 1,
	"term" : NumberLong(2),
	"syncSourceHost" : "",
	"syncSourceId" : -1,
	"heartbeatIntervalMillis" : NumberLong(2000),
	"majorityVoteCount" : 2,
	"writeMajorityCount" : 2,
	"votingMembersCount" : 3,
	"writableVotingMembersCount" : 3,
	"optimes" : {
		"lastCommittedOpTime" : {
			"ts" : Timestamp(1603337761, 1),
			"t" : NumberLong(2)
		},
		"lastCommittedWallTime" : ISODate("2020-10-22T03:36:01.825Z"),
		"readConcernMajorityOpTime" : {
			"ts" : Timestamp(1603337761, 1),
			"t" : NumberLong(2)
		},
		"readConcernMajorityWallTime" : ISODate("2020-10-22T03:36:01.825Z"),
		"appliedOpTime" : {
			"ts" : Timestamp(1603337761, 1),
			"t" : NumberLong(2)
		},
		"durableOpTime" : {
			"ts" : Timestamp(1603337761, 1),
			"t" : NumberLong(2)
		},
		"lastAppliedWallTime" : ISODate("2020-10-22T03:36:01.825Z"),
		"lastDurableWallTime" : ISODate("2020-10-22T03:36:01.825Z")
	},
	"lastStableRecoveryTimestamp" : Timestamp(1603337705, 1),
	"electionCandidateMetrics" : {
		"lastElectionReason" : "stepUpRequestSkipDryRun",
		"lastElectionDate" : ISODate("2020-10-22T03:34:00.775Z"),
		"electionTerm" : NumberLong(2),
		"lastCommittedOpTimeAtElection" : {
			"ts" : Timestamp(1603337639, 1),
			"t" : NumberLong(1)
		},
		"lastSeenOpTimeAtElection" : {
			"ts" : Timestamp(1603337639, 1),
			"t" : NumberLong(1)
		},
		"numVotesNeeded" : 2,
		"priorityAtElection" : 1,
		"electionTimeoutMillis" : NumberLong(10000),
		"priorPrimaryMemberId" : 0,
		"numCatchUpOps" : NumberLong(0),
		"newTermStartDate" : ISODate("2020-10-22T03:34:01.808Z"),
		"wMajorityWriteAvailabilityDate" : ISODate("2020-10-22T03:34:02.794Z")
	},
	"members" : [
		{
			"_id" : 0,
			"name" : "192.168.130.128:27017",
			"health" : 0,
			"state" : 8,
			"stateStr" : "(not reachable/healthy)",
			"uptime" : 0,
			"optime" : {
				"ts" : Timestamp(0, 0),
				"t" : NumberLong(-1)
			},
			"optimeDurable" : {
				"ts" : Timestamp(0, 0),
				"t" : NumberLong(-1)
			},
			"optimeDate" : ISODate("1970-01-01T00:00:00Z"),
			"optimeDurableDate" : ISODate("1970-01-01T00:00:00Z"),
			"lastHeartbeat" : ISODate("2020-10-22T03:36:10.024Z"),
			"lastHeartbeatRecv" : ISODate("2020-10-22T03:34:00.276Z"),
			"pingMs" : NumberLong(0),
			"lastHeartbeatMessage" : "Error connecting to 192.168.130.128:27017 :: caused by :: Connection refused",
			"syncSourceHost" : "",
			"syncSourceId" : -1,
			"infoMessage" : "",
			"configVersion" : 1,
			"configTerm" : 1
		},
		{
			"_id" : 1,
			"name" : "192.168.130.128:27018",
			"health" : 1,
			"state" : 1,
			"stateStr" : "PRIMARY",
			"uptime" : 176,
			"optime" : {
				"ts" : Timestamp(1603337761, 1),
				"t" : NumberLong(2)
			},
			"optimeDate" : ISODate("2020-10-22T03:36:01Z"),
			"syncSourceHost" : "",
			"syncSourceId" : -1,
			"infoMessage" : "",
			"electionTime" : Timestamp(1603337640, 1),
			"electionDate" : ISODate("2020-10-22T03:34:00Z"),
			"configVersion" : 1,
			"configTerm" : 2,
			"self" : true,
			"lastHeartbeatMessage" : ""
		},
		{
			"_id" : 2,
			"name" : "192.168.130.128:27019",
			"health" : 1,
			"state" : 2,
			"stateStr" : "SECONDARY",
			"uptime" : 174,
			"optime" : {
				"ts" : Timestamp(1603337761, 1),
				"t" : NumberLong(2)
			},
			"optimeDurable" : {
				"ts" : Timestamp(1603337761, 1),
				"t" : NumberLong(2)
			},
			"optimeDate" : ISODate("2020-10-22T03:36:01Z"),
			"optimeDurableDate" : ISODate("2020-10-22T03:36:01Z"),
			"lastHeartbeat" : ISODate("2020-10-22T03:36:09.922Z"),
			"lastHeartbeatRecv" : ISODate("2020-10-22T03:36:10.907Z"),
			"pingMs" : NumberLong(0),
			"lastHeartbeatMessage" : "",
			"syncSourceHost" : "192.168.130.128:27018",
			"syncSourceId" : 1,
			"infoMessage" : "",
			"configVersion" : 1,
			"configTerm" : 2
		}
	],
	"ok" : 1,
	"$clusterTime" : {
		"clusterTime" : Timestamp(1603337761, 1),
		"signature" : {
			"hash" : BinData(0,"AAAAAAAAAAAAAAAAAAAAAAAAAAA="),
			"keyId" : NumberLong(0)
		}
	},
	"operationTime" : Timestamp(1603337761, 1)
}

测试三

停止集群中的2个节点 当前集群无法选举出Priamry，无法提供写操作，只能进行读操作
此时已经只有两个节点（一主一从）
我们停止主节点

docker stop mongo02

进入mongo03容器

docker exec -it mongo03 /bin/bash
mongo

可以看到节点三仍然是从节点。

测试四

增加arbiter节点
当集群中的节点数为偶数时，如一主一从情况下，任意一节点宕机都无法选举出Priamry，无法提供写操作，加入 arbiter节点后即可解决该问题。
我们开启mongo02，mongo01容器

docker start mongo02

此时为一主两从
创建一个新的容器作为arbiter节点

docker create --name mongo04  -p 27020:27017 -v mongo-data-04:/data/db mongo -replSet "rs0" --bind_ip_all
docker start mongo04

在主节点移除一个节点

rs.remove("192.168.130.128:27017")

响应

{
	"ok" : 1,
	"$clusterTime" : {
		"clusterTime" : Timestamp(1603338733, 1),
		"signature" : {
			"hash" : BinData(0,"AAAAAAAAAAAAAAAAAAAAAAAAAAA="),
			"keyId" : NumberLong(0)
		}
	},
	"operationTime" : Timestamp(1603338733, 1)
}

ps:添加节点

 rs.add("192.168.130.128:27017");

此时为一主一从（mongo03为主节点）
加入arbiter节点

rs.addArb("192.168.130.128:27020")

响应

{
	"ok" : 1,
	"$clusterTime" : {
		"clusterTime" : Timestamp(1603338259, 1),
		"signature" : {
			"hash" : BinData(0,"AAAAAAAAAAAAAAAAAAAAAAAAAAA="),
			"keyId" : NumberLong(0)
		}
	},
	"operationTime" : Timestamp(1603338259, 1)
}

此时停止主节点(mongo03)

docker stop mongo03

进入mongo02

docker exec -it mongo02 /bin/bash
mongo

已成为主节点