AWS DMS keeps on restarting the table import - sql-server

Question

I am pulling in a large database with some large tables (over 80 million rows) that are on Microsoft SQL Server.
I am experiencing weird behaviour where the table loads start reloading after around 60 minutes (or a few minutes over that). I am doing a full load + cdc and this problem occurs on the full load part.
This is how my setting looks like:
{
"TargetMetadata": {
"TargetSchema": "",
"SupportLobs": true,
"FullLobMode": false,
"LobChunkSize": 0,
"LimitedSizeLobMode": true,
"LobMaxSize": 102400,
"InlineLobMaxSize": 0,
"LoadMaxFileSize": 0,
"ParallelLoadThreads": 0,
"ParallelLoadBufferSize": 0,
"BatchApplyEnabled": false,
"TaskRecoveryTableEnabled": false
},
"FullLoadSettings": {
"TargetTablePrepMode": "DROP_AND_CREATE",
"CreatePkAfterFullLoad": true,
"StopTaskCachedChangesApplied": false,
"StopTaskCachedChangesNotApplied": false,
"MaxFullLoadSubTasks": 16,
"TransactionConsistencyTimeout": 600,
"CommitRate": 50000
},
"Logging": {
"EnableLogging": true,
"LogComponents": [
{
"Id": "SOURCE_UNLOAD",
"Severity": "LOGGER_SEVERITY_DEFAULT"
},
{
"Id": "TARGET_LOAD",
"Severity": "LOGGER_SEVERITY_DEFAULT"
},
{
"Id": "SOURCE_CAPTURE",
"Severity": "LOGGER_SEVERITY_DEFAULT"
},
{
"Id": "TARGET_APPLY",
"Severity": "LOGGER_SEVERITY_DEFAULT"
},
{
"Id": "TASK_MANAGER",
"Severity": "LOGGER_SEVERITY_DEFAULT"
}
]
},
"ControlTablesSettings": {
"historyTimeslotInMinutes": 5,
"ControlSchema": "",
"HistoryTimeslotInMinutes": 5,
"HistoryTableEnabled": false,
"SuspendedTablesTableEnabled": false,
"StatusTableEnabled": false
},
"StreamBufferSettings": {
"StreamBufferCount": 3,
"StreamBufferSizeInMB": 8,
"CtrlStreamBufferSizeInMB": 5
},
"ChangeProcessingDdlHandlingPolicy": {
"HandleSourceTableDropped": true,
"HandleSourceTableTruncated": true,
"HandleSourceTableAltered": true
},
"ErrorBehavior": {
"DataErrorPolicy": "LOG_ERROR",
"DataTruncationErrorPolicy": "LOG_ERROR",
"DataErrorEscalationPolicy": "SUSPEND_TABLE",
"DataErrorEscalationCount": 0,
"TableErrorPolicy": "SUSPEND_TABLE",
"TableErrorEscalationPolicy": "SUSPEND_TABLE",
"TableErrorEscalationCount": 0,
"RecoverableErrorCount": -1,
"RecoverableErrorInterval": 5,
"RecoverableErrorThrottling": true,
"RecoverableErrorThrottlingMax": 1800,
"ApplyErrorDeletePolicy": "IGNORE_RECORD",
"ApplyErrorInsertPolicy": "LOG_ERROR",
"ApplyErrorUpdatePolicy": "LOG_ERROR",
"ApplyErrorEscalationPolicy": "LOG_ERROR",
"ApplyErrorEscalationCount": 0,
"ApplyErrorFailOnTruncationDdl": false,
"FullLoadIgnoreConflicts": true,
"FailOnTransactionConsistencyBreached": false,
"FailOnNoTablesCaptured": false
},
"ChangeProcessingTuning": {
"BatchApplyPreserveTransaction": true,
"BatchApplyTimeoutMin": 1,
"BatchApplyTimeoutMax": 30,
"BatchApplyMemoryLimit": 500,
"BatchSplitSize": 0,
"MinTransactionSize": 1000,
"CommitTimeout": 1,
"MemoryLimitTotal": 1024,
"MemoryKeepTime": 60,
"StatementCacheSize": 50
},
"PostProcessingRules": null,
"CharacterSetSettings": null,
"LoopbackPreventionSettings": null
}
I do not see anything useful in the logs on the Cloudwatch, except that the endpoint is disconnected. More logs below:
2022-08-21T13:34:59 [SOURCE_UNLOAD ]E: Endpoint is disconnected [1020414] (endpointshell.c:3807)
2022-08-21T13:34:59 [SOURCE_UNLOAD ]E: Error executing source loop [1020414] (streamcomponent.c:1872)
2022-08-21T13:34:59 [TASK_MANAGER ]E: Stream component failed at subtask 5, component st_5_STAX7TAMIRB2R3PAIOSXO6TO7KT6PPIVMPGYLNQ [1020414] (subtask.c:1414)
2022-08-21T13:34:59 [SOURCE_UNLOAD ]E: Stream component 'st_5_STAX7TAMIRB2R3PAIOSXO6TO7KT6PPIVMPGYLNQ' terminated [1020414] (subtask.c:1594)
2022-08-21T13:34:59 [TASK_MANAGER ]E: Task error notification received from subtask 5, thread 0 [1020414] (replicationtask.c:2880)
2022-08-21T13:34:59 [TASK_MANAGER ]E: Endpoint is disconnected; Error executing source loop; Stream component failed at subtask 5, component st_5_STAX7TAMIRB2R3PAIOSXO6TO7KT6PPIVMPGYLNQ; Stream component 'st_5_STAX7TAMIRB2R3PAIOSXO6TO7KT6PPIVMPGYLNQ' terminated [1020414] (replicationtask.c:2888)
Also, I noticed that DMS job tries to do this import 10 times and each time it takes around 1 hour to get this message and at the end it ends up in the FAILED stage.
We have tried to increase the timeout on the SQL server side (QueryTimeOut) to 2 hours, but that didn't help.
Can someone advice what else can be done here? Also, I would like for the DMS job not to "retry" for 10 times, since probably 3-4 times would be enough.