Hi Sean, On Tue, 2005-06-07 at 14:50, Sean Hefty wrote: > Hal Rosenstock wrote: > > <---------------------------- SA GetTableResp > > RMPP flags 0x03 (Data, First) > > SegmentNumber 1 > > PayloadLength 0x370 > > TID 8 > > SA GetTable ----------------------------> > > RMPP flags 0x02 (ACK) > > SegmentNumber 1 > > NewWindowLast 6 > > TID 8 > > I'm not clear why RMPP flags is set to 0x02. I would have expected 0x01 to > indicate that RMPP is active. If the RMPP active flag is not set, the > OpenIB RMPP code will process the packet as if it were a non-RMPP packet. > Maybe RMPP flags here indicates the type? (It looks like the flags field on > the SA side.)
My bad. Type was 0x02 and flags were 0x71 (resp time 0xE and RMPP active). > > <---------------------------- SA GetTableResp > > > > RMPP flags 0x01 (Data) > > SegmentNumber 2 > > PayloadLength 0x370 > > TID 8 > > <---------------------------- SA GetTableResp > > > > RMPP flags 0x01 (Data) > > SegmentNumber 3 > > PayloadLength 0x370 > > TID 8 > > <---------------------------- SA GetTableResp > > > > RMPP flags 0x05 (Data, Last) > > SegmentNumber 4 > > PayloadLength 0x34 > > TID 8 > > SA GetTable ----------------------------> > > RMPP flags 0x02 (ACK) > > SegmentNumber 1 > > NewWindowLast 6 > > TID 8 > > Assuming that the RMPP active flag is set, this should be seen as a > duplicated ACK and discarded since it doesn't carry any new information. Correct. That's what I called a reACK. > > <---------------------------- SA GetTableResp > > RMPP flags 0x01 (Data) > > SegmentNumber 5 > > PayloadLength 0x34 > > TID 8 > > I'm clueless yet as to how this MAD could have been generated... If I add > in some debug checks, can you rerun this test? Yes. I'm working on this right now to limited success so any help is appreciated. Thanks. -- Hal _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
