Hyper-V / VMM 2012 R2, VMQ & QLogic, Part 4

We received an update from our Dell team today. It looks like politics of who’s the root cause are going to make all of us suffer for another 6 months at least. Read on…

3Sept2014 BG – We investigated this issue. Looks like it is due to anomalous behavior of HyperV NDIS stack. Driver allocates MSIX interrupts for VMQs at load time and sets interrupt affinity bases on the RSS processor set returned by NdisGetRssProcessorInformation call as per MSDN documentation. None of the host CPU is in the list of RSS processors below the base RSS Processor number RssBaseProcNumber.

Later on NDIS specifies cpu0 when it send OID to allocate VMQ. Driver doesn’t find any MSIX interrupt to satisfy the VMQ allocate OID and hence driver fails the OID.

Microsoft team is investigating this issue.

Dell Comms team has deferred this to the next project Q1FY16.  Qlogic indicates this is a Microsoft problem and doesn’t expect a solution for approx. six months.

If you are affected by this issue, I recommend opening up cases with Microsoft and your hardware vendor to put pressure on QLogic to expedite the driver development. Only through collective effort are we likely to see this resolved before mid-2015.

3 Comments

  1. Martin said:

    Your not the only one seeing this… We run R815’s, 820’s and 920’s all with QLE8262’s. There are serious stability issues around VMQ on the 8262’s… We have disabled VMQ all together and we seem more stable, with it enabled, pushing the hardware we either get the driver stuck in a loop (host hung) or on the 815’s a BSOD! We have escalated to MS and to Dell, i’m awaiting contract from QLogic via out TAM.

    February 12, 2015
    Reply
    • Martin said:

      We tested a private hotfix which sorted us out, but yes we have also had confirmation that the public hotfix is available at the above URL as of this morning.

      March 12, 2015
      Reply

Leave a Reply