/// <exception cref="Org.Apache.Hadoop.Yarn.Exceptions.YarnException"/>
/// <exception cref="System.IO.IOException"/>
public virtual NodeHeartbeatResponse NodeHeartbeat(NodeHeartbeatRequest request)
{
NodeStatus remoteNodeStatus = request.GetNodeStatus();
NodeId nodeId = remoteNodeStatus.GetNodeId();
// 1. Check if it's a valid (i.e. not excluded) node
if (!this.nodesListManager.IsValidNode(nodeId.GetHost()))
{
string message = "Disallowed NodeManager nodeId: " + nodeId + " hostname: " + nodeId
.GetHost();
Log.Info(message);
shutDown.SetDiagnosticsMessage(message);
return(shutDown);
}
// 2. Check if it's a registered node
RMNode rmNode = this.rmContext.GetRMNodes()[nodeId];
if (rmNode == null)
{
/* node does not exist */
string message = "Node not found resyncing " + remoteNodeStatus.GetNodeId();
Log.Info(message);
resync.SetDiagnosticsMessage(message);
return(resync);
}
// Send ping
this.nmLivelinessMonitor.ReceivedPing(nodeId);
// 3. Check if it's a 'fresh' heartbeat i.e. not duplicate heartbeat
NodeHeartbeatResponse lastNodeHeartbeatResponse = rmNode.GetLastNodeHeartBeatResponse
();
if (remoteNodeStatus.GetResponseId() + 1 == lastNodeHeartbeatResponse.GetResponseId
())
{
Log.Info("Received duplicate heartbeat from node " + rmNode.GetNodeAddress() + " responseId="
+ remoteNodeStatus.GetResponseId());
return(lastNodeHeartbeatResponse);
}
else
{
if (remoteNodeStatus.GetResponseId() + 1 < lastNodeHeartbeatResponse.GetResponseId
())
{
string message = "Too far behind rm response id:" + lastNodeHeartbeatResponse.GetResponseId
() + " nm response id:" + remoteNodeStatus.GetResponseId();
Log.Info(message);
resync.SetDiagnosticsMessage(message);
// TODO: Just sending reboot is not enough. Think more.
this.rmContext.GetDispatcher().GetEventHandler().Handle(new RMNodeEvent(nodeId, RMNodeEventType
.Rebooting));
return(resync);
}
}
// Heartbeat response
NodeHeartbeatResponse nodeHeartBeatResponse = YarnServerBuilderUtils.NewNodeHeartbeatResponse
(lastNodeHeartbeatResponse.GetResponseId() + 1, NodeAction.Normal, null, null, null
, null, nextHeartBeatInterval);
rmNode.UpdateNodeHeartbeatResponseForCleanup(nodeHeartBeatResponse);
PopulateKeys(request, nodeHeartBeatResponse);
ConcurrentMap <ApplicationId, ByteBuffer> systemCredentials = rmContext.GetSystemCredentialsForApps
();
if (!systemCredentials.IsEmpty())
{
nodeHeartBeatResponse.SetSystemCredentialsForApps(systemCredentials);
}
// 4. Send status to RMNode, saving the latest response.
this.rmContext.GetDispatcher().GetEventHandler().Handle(new RMNodeStatusEvent(nodeId
, remoteNodeStatus.GetNodeHealthStatus(), remoteNodeStatus.GetContainersStatuses
(), remoteNodeStatus.GetKeepAliveApplications(), nodeHeartBeatResponse));
return(nodeHeartBeatResponse);
}
