mongodb啓用認證後出現RECOVERING 與 not reachable/healthy

問題描述

在部署副本集模式的mongodb的時候，當啓用認證後，執行rs.status()後，變成了如下狀態：

{
	"set" : "mytest",
	"date" : ISODate("2019-12-24T02:24:30.510Z"),
	"myState" : 3,
	"term" : NumberLong(6),
	"syncingTo" : "",
	"syncSourceHost" : "",
	"syncSourceId" : -1,
	"heartbeatIntervalMillis" : NumberLong(2000),
	"majorityVoteCount" : 2,
	"writeMajorityCount" : 2,
	"optimes" : {
		"lastCommittedOpTime" : {
			"ts" : Timestamp(0, 0),
			"t" : NumberLong(-1)
		},
		"lastCommittedWallTime" : ISODate("1970-01-01T00:00:00Z"),
		"appliedOpTime" : {
			"ts" : Timestamp(1577154202, 1),
			"t" : NumberLong(6)
		},
		"durableOpTime" : {
			"ts" : Timestamp(1577154202, 1),
			"t" : NumberLong(6)
		},
		"lastAppliedWallTime" : ISODate("2019-12-24T02:23:22.046Z"),
		"lastDurableWallTime" : ISODate("2019-12-24T02:23:22.046Z")
	},
	"lastStableRecoveryTimestamp" : Timestamp(1577154202, 1),
	"lastStableCheckpointTimestamp" : Timestamp(1577154202, 1),
	"members" : [
		{
			"_id" : 0,
			"name" : "10.38.160.174:27017",
			"ip" : "10.38.160.174",
			"health" : 1,
			"state" : 3,
			"stateStr" : "RECOVERING",
			"uptime" : 54,
			"optime" : {
				"ts" : Timestamp(1577154202, 1),
				"t" : NumberLong(6)
			},
			"optimeDate" : ISODate("2019-12-24T02:23:22Z"),
			"syncingTo" : "",
			"syncSourceHost" : "",
			"syncSourceId" : -1,
			"infoMessage" : "could not find member to sync from",
			"configVersion" : 1,
			"self" : true,
			"lastHeartbeatMessage" : ""
		},
		{
			"_id" : 1,
			"name" : "10.38.160.174:27027",
			"ip" : "10.38.160.174",
			"health" : 0,
			"state" : 6,
			"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("2019-12-24T02:24:30.466Z"),
			"lastHeartbeatRecv" : ISODate("1970-01-01T00:00:00Z"),
			"pingMs" : NumberLong(0),
			"lastHeartbeatMessage" : "",
			"authenticated" : false,
			"syncingTo" : "",
			"syncSourceHost" : "",
			"syncSourceId" : -1,
			"infoMessage" : "",
			"configVersion" : -1
		},
		{
			"_id" : 2,
			"name" : "10.38.160.174:27037",
			"ip" : "10.38.160.174",
			"health" : 0,
			"state" : 6,
			"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("2019-12-24T02:24:30.466Z"),
			"lastHeartbeatRecv" : ISODate("1970-01-01T00:00:00Z"),
			"pingMs" : NumberLong(0),
			"lastHeartbeatMessage" : "",
			"authenticated" : false,
			"syncingTo" : "",
			"syncSourceHost" : "",
			"syncSourceId" : -1,
			"infoMessage" : "",
			"configVersion" : -1
		}
	],
	"ok" : 1
}

具體的表現就是，當前登錄的節點變成了RECOVERING的狀態，其他節點變成了 (not reachable/healthy)的狀態。

問題原因

原因就是當啓用認證後，不僅客戶端連接需要認證，服務內部不同節點之間，也是需要相互認證的，如果僅僅是啓用認證方式，不設定服務內部之間的認證參數，則服務內部各節點之間是無法成功通信的，就造成了當前登錄節點一直是恢復中的狀態，而其他節點應該是 not reachable的狀態，所以會顯示爲 not reachable/healthy。

問題解決

只需要在啓用認證的時候，加上節點內容認證參數即可，mongodb提供了兩種方式：一種是 keyfile的方式，一種是證書方式，詳細內容參見：Internal/Membership Authentication
我採用的是簡單的keyfile的方式，只需要在啓動的時候，加上 --keyFile=key/file/path 即可