data node shutdown abnormally (2 replies)

I have two data nodes with NoOfReplicas=2. I tried to run a over-night testing, I next morning I found ndbmtd on node 1 was dead. I found following message in management node's log file:


2011-12-05 17:45:07 [MgmtSrvr] WARNING -- Node 1: Transporter to node 64 reported error 0x16: The send buffer was full, but sleeping for a while solved
2011-12-05 17:45:07 [MgmtSrvr] WARNING -- Node 1: Transporter to node 65 reported error 0x16: The send buffer was full, but sleeping for a while solved
2011-12-05 17:45:07 [MgmtSrvr] WARNING -- Node 1: Transporter to node 65 reported error 0x16: The send buffer was full, but sleeping for a while solved
2011-12-05 17:45:07 [MgmtSrvr] WARNING -- Node 1: Transporter to node 64 reported error 0x16: The send buffer was full, but sleeping for a while solved
2011-12-05 17:45:07 [MgmtSrvr] WARNING -- Node 2: Transporter to node 65 reported error 0x16: The send buffer was full, but sleeping for a while solved
2011-12-05 17:45:07 [MgmtSrvr] WARNING -- Node 1: Transporter to node 65 reported error 0x16: The send buffer was full, but sleeping for a while solved
2011-12-05 17:45:07 [MgmtSrvr] WARNING -- Node 1: Transporter to node 65 reported error 0x16: The send buffer was full, but sleeping for a while solved
2011-12-05 17:45:07 [MgmtSrvr] ALERT -- Node 1: Forced node shutdown completed. Caused by error 2300: 'Generic error(Restart error). Temporary error, restart node'.
2011-12-05 17:45:07 [MgmtSrvr] ALERT -- Node 2: Node 1 Disconnected

What's the problem? Any help would be greatly appreciated.