Re: [OMPI devel] Device failover in dr pml

2009-04-15 Thread Rolf Vandevaart
Hi, We are also looking to get device failover working. However, for the reasons cited by Ralph, we are using the OB1 PML as the starting point. Also, similar to you, we do not need the checksumming feature or the timed out retransmission that the dr PML provides. Rolf Ralph Castain wrot

Re: [OMPI devel] Device failover in dr pml

2009-04-15 Thread Ralph Castain
Last anyone knew, the dr pml was dead - way out of date and unmaintained. I gather that you folks have revived it and sync'd it back up to the current ob1 module? I don't think anyone really cares what is done with the dr module itself. There are others working on failover modules, and ther

[OMPI devel] Device failover in dr pml

2009-04-15 Thread Mouhamed Gueye
Hi all, We are currently working on the dr pml component and specifically on device failover. The failover mecanism seems to work fine on different components, but if we want to do it on different modules of the same component - say 2 Infiniband rails - the code seems to be broken. Actually,