On 9/30/20 10:26 AM, Ju Hyung Park wrote: > Hi everyone. > > I have recently switched to a setup running QEMU 5.0(which supports > io_uring) for a Windows 10 guest on Linux v5.4.63. > The QEMU hosts /dev/nvme0n1p3 to the guest with virtio-blk with > discard/unmap enabled. > > I've been having a weird issue where the system would randomly hang > whenever I turn on or shutdown the guest. The host will stay up for a > bit and then just hang. No response on SSH, etc. Even ping doesn't > work. > > It's been hard to even get a log to debug the issue, but I've been > able to get a show-backtrace-all-active-cpus sysrq dmesg on the most > recent encounter with the issue and it's showing some io_uring > functions. > > Since I've been encountering the issue ever since I switched to QEMU > 5.0, I suspect io_uring may be the culprit to the issue. > > While I'd love to try out the mainline kernel, it's currently not > feasible at the moment as I have to stay in linux-5.4.y. Backporting > mainline's io_uring also seems to be a non-trivial job. > > Any tips would be appreciated. I can build my own kernel and I'm > willing to try out (backported) patches. I'll see if I can reproduce this, thanks for the report! -- Jens Axboe
