Thanks Nicholas, I understood the qlogic discussion to mean that there was a bigger underlying issue, so I as waiting on their patch. If testing of the 4.4 kernel patch you created is still relevant then I'll get to work on the kernel recompile. On Sun, Feb 7, 2016 at 2:32 PM, Nicholas A. Bellinger <nab@xxxxxxxxxxxxxxx> wrote: > Hi Dan, > > On Sun, 2016-02-07 at 13:48 -0500, Dan Lane wrote: >> Did anything ever result from this? Is there a kernel patch available >> that should resolve the issue? >> > > I'm waiting for your feedback using the target-pending/4.4-stable > branch as previously discussed. Have you been able to test..? > > Beyond that, the QLogic folks are currently testing the patch series to > address the root cause, and I expect it to be merged upstream next week > and it will make it into older stable kernels the following weeks. > >> I'm considering rebuilding my server with RHEL7 since it uses Linux >> kernel 3.10, which I've had great luck with in the past. I would hate >> to lose VAAI, but I haven't had any success with LIO in the years >> since that was implemented, despite spending thousands of dollars on >> hardware and countless hours troubleshooting. Is there no testing >> done with ESXi connect via FC? The wiki doesn't even mention anything >> newer than ESX/ESXi 4... >> > > Note the bug your hitting is not specific to ESX versions, FC, or to > VAAI. > > But note as previously mentioned, if your still seeing constant > ABORT_TASKS from ESX + FC then your backend is unable to keep up. > You'll seriously want to consider looking into the ESX tunables > mentioned in the previous email. > -- To unsubscribe from this list: send the line "unsubscribe target-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
