>>> On 02.06.16 at 09:31, <quan...@intel.com> wrote: > On May 27, 2016 10:06 PM, Jan Beulich <jbeul...@suse.com> wrote: >> >>> On 27.05.16 at 15:34, <wei.l...@citrix.com> wrote: >> > On Fri, May 27, 2016 at 06:16:30AM -0600, Jan Beulich wrote: >> >> >>> On 27.05.16 at 12:39, <wei.l...@citrix.com> wrote: >> >> > Is this a regression? Does it work on previous versions of Xen? >> >> >> >> I think this is what was already reported by other Intel people, see >> >> e.g. Quan's most recent reply: >> >> http://lists.xenproject.org/archives/html/xen-devel/2016-05/msg01896. >> >> html It is not clear where the problem is, and not seeing the issue >> >> myself makes it hard to analyze. In any event this quite likely is a >> >> regression. >> >> >> > >> > My reading of that email thread and all relevant links (including the >> > KVM bug report) is that there is a regression vf driver, but not in Xen. >> >> Just from reading that I would tend to agree. But the report here is about >> Win2K8. > > Do you know which commit is a regression one? I try to find out the > regression commit. That may be helpful to find out the root cause.
Indeed. There was a lot of rework of MSI-X. Iirc one of your colleagues had actually narrowed it down a while ago, but I can't seem to find that mail right now. Nor did it really help understand what's going wrong (or else we would likely have found a fix for it already). My primary suspicion was that the interrupt doesn't get enabled when it should, but the respective fix didn't help that case (while it did help others). Hence my continued request for someone being able to observe the problem to simply log guest actions and what the hypervisor does for them (plus of course provide all relevant debug information, like debug key output of interest, for a guest in the broken state). Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel
