At 11:54 AM 11/2/2007, Sean Hefty wrote: >> Why wouldn't you just leave the timeout to TCP, and make CM's infinite? > >I'm more concerned about IB, but would like the rdma cm interface usable >by iWarp as well. The last request I had was to make the timeout >smaller, not larger. (With the MRA patch that recently went in, I don't >think we'll need to support longer timeouts in IB.) > >At least on linux, it appears that a user can control the number of SYN >retries using a socket option. I don't see anything that allows them to >control the timeout however.
I still don't understand why you would want to do this. TCP already implements the best timer you could hope for. But, if all you want to do is abort an in-progress connection attempt, can't you just run a timer to signal you and thereby interrupt the connect(2) in progress? Tom. _______________________________________________ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
