我的应用程序定期运行采样查询，它运行良好，大约 30 小时没有任何问题。然后突然出现以下错误。
Java 客户端无法访问数据库并获得以下异常。
Caused by: com.toshiba.mwcloud.gs.common.GSConnectionException: [145028:JC_BAD_CONNECTION] Failed to update by notification (address=/239.0.0.1:31999, reason=Receive timed out)
at com.toshiba.mwcloud.gs.subnet.NodeResolver.updateMasterInfo(NodeResolver.java:815)
at com.toshiba.mwcloud.gs.subnet.NodeResolver.prepareConnectionAndClusterInfo(NodeResolver.java:522)
at com.toshiba.mwcloud.gs.subnet.NodeResolver.getPartitionCount(NodeResolver.java:205)
at com.toshiba.mwcloud.gs.subnet.GridStoreChannel$5.execute(GridStoreChannel.java:2106)
at com.toshiba.mwcloud.gs.subnet.GridStoreChannel.executeStatement(GridStoreChannel.java:1675)
... 38 more
Caused by: java.net.SocketTimeoutException: Receive timed out
为什么会这样？是什么原因。
这是 gs_stat -u admin/admin 的输出
{
"checkpoint": {
"archiveLog": 0,
"backupOperation": 0,
"duplicateLog": 0,
"endTime": 1580053987745,
"mode": "NORMAL_CHECKPOINT",
"normalCheckpointOperation": 1470,
"pendingPartition": 0,
"periodicCheckpoint": "ACTIVE",
"requestedCheckpointOperation": 0,
"startTime": 1580053987741
},
"cluster": {
"activeCount": 0,
"autoGoal": "ACTIVE",
"clusterName": "defaultCluster",
"clusterRevisionId": "4e9be62e-7911-48a4-8d93-19af09be7a15",
"clusterRevisionNo": 17651,
"clusterStatus": "SUB_CLUSTER",
"designatedCount": 1,
"loadBalancer": "ACTIVE",
"nodeList": [
{
"address": "10.128.0.2",
"port": 10040
}
],
"nodeStatus": "ABNORMAL",
"notificationMode": "MULTICAST",
"partitionStatus": "INITIAL",
"startupTime": "2020-01-25T15:20:31.377Z",
"syncCount": 0
},
"currentTime": "2020-01-26T17:20:39Z",
"performance": {
"backupCount": 0,
"batchFree": 0,
"bufferHashCollisionCount": 0,
"checkpointFileAllocateSize": 5443584,
"checkpointFileFlushCount": 0,
"checkpointFileFlushTime": 0,
"checkpointFileSize": 5439488,
"checkpointFileUsageRate": 0.927710843373494,
"checkpointMemory": 196608,
"checkpointMemoryLimit": 1073741824,
"checkpointWriteSize": 270139392,
"checkpointWriteTime": 214,
"currentCheckpointWriteBufferSize": 0,
"currentTime": 1580059239771,
"expirationDetail": {
"autoExpire": false,
"erasableExpiredTime": "1970-01-01T00:00:00.000Z",
"latestExpirationCheckTime": "1970-01-01T00:00:00.000Z"
},
"logFileFlushCount": 8832,
"logFileFlushTime": 38224,
"numBackground": 0,
"numConnection": 2,
"numNoExpireTxn": 0,
"numSession": 0,
"numTxn": 0,
"ownerCount": 128,
"peakProcessMemory": 86626304,
"processMemory": 86626304,
"recoveryReadSize": 262144,
"recoveryReadTime": 0,
"recoveryReadUncompressTime": 0,
"storeCompressionMode": "NO_BLOCK_COMPRESSION",
"storeDetail": {
"batchFreeMapData": {
"storeMemory": 0,
"storeUse": 0,
"swapRead": 0,
"swapWrite": 0
},
"batchFreeRowData": {
"storeMemory": 0,
"storeUse": 0,
"swapRead": 0,
"swapWrite": 0
},
"mapData": {
"storeMemory": 131072,
"storeUse": 131072,
"swapRead": 0,
"swapWrite": 0
},
"metaData": {
"storeMemory": 131072,
"storeUse": 131072,
"swapRead": 0,
"swapWrite": 0
},
"rowData": {
"storeMemory": 4784128,
"storeUse": 4784128,
"swapRead": 0,
"swapWrite": 0
}
},
"storeMemory": 5046272,
"storeMemoryLimit": 1073741824,
"storeTotalUse": 5046272,
"swapRead": 0,
"swapReadSize": 0,
"swapReadTime": 0,
"swapReadUncompressTime": 0,
"swapWrite": 0,
"swapWriteCompressTime": 0,
"swapWriteSize": 0,
"swapWriteTime": 0,
"syncReadSize": 0,
"syncReadTime": 0,
"syncReadUncompressTime": 0,
"totalBackupLsn": 0,
"totalLockConflictCount": 0,
"totalOtherLsn": 0,
"totalOwnerLsn": 110220,
"totalReadOperation": 4733,
"totalRowRead": 2325894,
"totalRowWrite": 55108,
"totalWriteOperation": 55108,
"txnDetail": {
"totalBackgroundOperation": 0
}
},
"recovery": {
"progressRate": 1
},
"version": "4.3.0-36424 CE"
}