[openib-general] [PATCH ] RFC IB/cm do not track remote QPN in timewait state

Sean Hefty mshefty at ichips.intel.com
Mon Aug 28 14:56:50 PDT 2006


Michael S. Tsirkin wrote:
> Another problem that  I see is that CMA currently seems to completely 
> mask timewait exit.

This is correct.

> So there's no way to properly handle timewait on top of cma that I can see.

I don't think so, which is what brought up the problem with Arlin.  (He's using 
DAPL above the userspace CMA.)  I'm not sure what the proper fix is for this 
though because of the disconnect between the CM states and the destruction of 
the QP.

- Sean




More information about the general mailing list