[openib-general] Re: [PATCH] [1/2] SQE handling on MAD QPs

2004-11-12 Thread Hal Rosenstock
On Fri, 2004-11-12 at 12:54, Sean Hefty wrote: > Can you try this version? Thanks. Applied. -- Hal ___ openib-general mailing list [EMAIL PROTECTED] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailm

[openib-general] Re: [PATCH] [1/2] SQE handling on MAD QPs

2004-11-12 Thread Hal Rosenstock
On Fri, 2004-11-12 at 12:54, Sean Hefty wrote: > On Fri, 12 Nov 2004 12:18:32 -0500 > Can you try this version? I'll also revert back to the original code and see > if > I can apply the patch. Don't bother (if you haven't already). This patch worked. -- Hal ___

[openib-general] Re: [PATCH] [1/2] SQE handling on MAD QPs

2004-11-12 Thread Sean Hefty
On Fri, 12 Nov 2004 12:18:32 -0500 Hal Rosenstock <[EMAIL PROTECTED]> wrote: > On Fri, 2004-11-12 at 12:13, Sean Hefty wrote: > > Not sure what the issue is. Let me make sure that I've pulled the latest > > code and > > resubmit the patch. > > It looks right to me. Does it work for you ? Can y

[openib-general] Re: [PATCH] [1/2] SQE handling on MAD QPs

2004-11-12 Thread Hal Rosenstock
On Fri, 2004-11-12 at 12:13, Sean Hefty wrote: > Not sure what the issue is. Let me make sure that I've pulled the latest > code and > resubmit the patch. It looks right to me. Does it work for you ? Can you send a normal rather than unified diff ? -- Hal _

[openib-general] Re: [PATCH] [1/2] SQE handling on MAD QPs

2004-11-12 Thread Sean Hefty
Hal Rosenstock wrote: On Thu, 2004-11-11 at 20:41, Sean Hefty wrote: This patch recovers from send queue errors on QP 0/1. (It should also "work" in the case of fatal errors, but does not try to recover.) Code was tested by forcing send errors and checking that the port could still go to active

[openib-general] Re: [PATCH] [1/2] SQE handling on MAD QPs

2004-11-12 Thread Hal Rosenstock
On Thu, 2004-11-11 at 20:41, Sean Hefty wrote: > This patch recovers from send queue errors on QP 0/1. (It should also "work" > in the case > of fatal errors, but does not try to recover.) Code was tested by forcing > send errors and > checking that the port could still go to active. > > Pat