similar to: [PATCH 0/1] vhost: add vhost_blk driver

On Fri, Nov 02, 2018 at 06:21:22PM +0000, Vitaly Mayatskikh wrote: > vhost_blk is a host-side kernel mode accelerator for virtio-blk. The > driver allows VM to reach a near bare-metal disk performance. See IOPS > numbers below (fio --rw=randread --bs=4k). > > This implementation uses kiocb interface. It is slightly slower than > going directly through bio, but is simpler and

On 2018/11/3 ??12:07, Vitaly Mayatskikh wrote: > Hi, > > I stumbled across poor performance of virtio-blk while working on a > high-performance network storage protocol. Moving virtio-blk's host > side to kernel did increase single queue IOPS, but multiqueue disk > still was not scaling well. It turned out that vhost handles events > from all virtio queues in one helper

On Fri, Nov 02, 2018 at 06:21:23PM +0000, Vitaly Mayatskikh wrote: > This driver accelerates host side of virtio-blk. > > Signed-off-by: Vitaly Mayatskikh <v.mayatskih at gmail.com> > --- > drivers/vhost/Kconfig | 13 ++ > drivers/vhost/Makefile | 3 + > drivers/vhost/blk.c | 510 +++++++++++++++++++++++++++++++++++++++++ > 3 files changed, 526 insertions(+)

On Fri, Nov 02, 2018 at 06:21:23PM +0000, Vitaly Mayatskikh wrote: > This driver accelerates host side of virtio-blk. Did you look at vhost-user-blk? It does things slightly differently: more of the virtio-blk device model is handled by the vhost-user device (e.g. config space). That might be necessary to implement virtio_blk_config.writeback properly. > +#define VHOST_BLK_SET_BACKEND

On 2018/11/5 ??11:23, Vitaly Mayatskih wrote: > On Sun, Nov 4, 2018 at 10:00 PM Jason Wang <jasowang at redhat.com> wrote: > >>> # fio num-jobs >>> # A: bare metal over block >>> # B: bare metal over file >>> # C: virtio-blk over block >>> # D: virtio-blk over file >>> # E: vhost-blk bio over block >>> # F: vhost-blk kiocb

On 2018/11/5 ??11:23, Vitaly Mayatskih wrote: > On Sun, Nov 4, 2018 at 10:00 PM Jason Wang <jasowang at redhat.com> wrote: > >>> # fio num-jobs >>> # A: bare metal over block >>> # B: bare metal over file >>> # C: virtio-blk over block >>> # D: virtio-blk over file >>> # E: vhost-blk bio over block >>> # F: vhost-blk kiocb

Hi Vitaly, Thank you for the patch! Yet something to improve: [auto build test ERROR on vhost/linux-next] [also build test ERROR on v4.19 next-20181102] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system] url: https://github.com/0day-ci/linux/commits/Vitaly-Mayatskikh/vhost-add-vhost_blk-driver/20181103-084141 base:

On Fri, Nov 02, 2018 at 03:24:13PM -0400, Vitaly Mayatskih wrote: > On Fri, Nov 2, 2018 at 2:36 PM Michael S. Tsirkin <mst at redhat.com> wrote: > > > > + if (type == VIRTIO_BLK_T_GET_ID) { > > > + char s[] = "vhost_blk"; > > > > Isn't this supposed to return the serial #? > > Yes, that gets a bit tricky here... Disk

On Mon, Nov 05, 2018 at 11:15:04AM -0500, Vitaly Mayatskih wrote: > On Mon, Nov 5, 2018 at 10:48 AM Christian Borntraeger > <borntraeger at de.ibm.com> wrote: > > > For the record, we still do use virtio-blk a lot. As we see new things like discard/write zero > > support it seems that others do as well. > > Yes, trim/discard and writesame support is planned, at

On Tue, Nov 06, 2018 at 10:45:08AM +0800, Jason Wang wrote: > > Storage industry is shifting away from SCSI, which has a scaling > > problem. > > > Know little about storage. For scaling, do you mean SCSI protocol itself? If > not, it's probably not a real issue for virtio-scsi itself. The above is utter bullshit. There is a big NVMe hype, but it is not because

vhost-blk is an in-kernel virito-blk device accelerator. Due to lack of proper in-kernel AIO interface, this version converts guest's I/O request to bio and use submit_bio() to submit I/O directly. So this version any supports raw block device as guest's disk image, e.g. /dev/sda, /dev/ram0. We can add file based image support to vhost-blk once we have in-kernel AIO interface. There are

vhost-blk is an in-kernel virito-blk device accelerator. Due to lack of proper in-kernel AIO interface, this version converts guest's I/O request to bio and use submit_bio() to submit I/O directly. So this version any supports raw block device as guest's disk image, e.g. /dev/sda, /dev/ram0. We can add file based image support to vhost-blk once we have in-kernel AIO interface. There are

vhost-blk is an in-kernel virito-blk device accelerator. Due to lack of proper in-kernel AIO interface, this version converts guest's I/O request to bio and use submit_bio() to submit I/O directly. So this version any supports raw block device as guest's disk image, e.g. /dev/sda, /dev/ram0. We can add file based image support to vhost-blk once we have in-kernel AIO interface. There are

vhost-blk is an in-kernel virito-blk device accelerator. Due to lack of proper in-kernel AIO interface, this version converts guest's I/O request to bio and use submit_bio() to submit I/O directly. So this version any supports raw block device as guest's disk image, e.g. /dev/sda, /dev/ram0. We can add file based image support to vhost-blk once we have in-kernel AIO interface. There are

vhost-blk is an in-kernel virito-blk device accelerator. Due to lack of proper in-kernel AIO interface, this version converts guest's I/O request to bio and use submit_bio() to submit I/O directly. So this version any supports raw block device as guest's disk image, e.g. /dev/sda, /dev/ram0. We can add file based image support to vhost-blk once we have in-kernel AIO interface. There are

vhost-blk is an in-kernel virito-blk device accelerator. Due to lack of proper in-kernel AIO interface, this version converts guest's I/O request to bio and use submit_bio() to submit I/O directly. So this version any supports raw block device as guest's disk image, e.g. /dev/sda, /dev/ram0. We can add file based image support to vhost-blk once we have in-kernel AIO interface. There are

vhost-blk is an in-kernel virito-blk device accelerator. Due to lack of proper in-kernel AIO interface, this version converts guest's I/O request to bio and use submit_bio() to submit I/O directly. So this version any supports raw block device as guest's disk image, e.g. /dev/sda, /dev/ram0. We can add file based image support to vhost-blk once we have in-kernel AIO interface. There are

vhost-blk is an in-kernel virito-blk device accelerator. Due to lack of proper in-kernel AIO interface, this version converts guest's I/O request to bio and use submit_bio() to submit I/O directly. So this version any supports raw block device as guest's disk image, e.g. /dev/sda, /dev/ram0. We can add file based image support to vhost-blk once we have in-kernel AIO interface. There are

Hi All, Here is the latest version of vhost-blk implementation. Major difference from my previous implementation is that, I now merge all contiguous requests (both read and write), before submitting them. This significantly improved IO performance. I am still collecting performance numbers, I will be posting in next few days. Comments ? Todo: - Address hch's comments on annontations -

Hi All, Here is the latest version of vhost-blk implementation. Major difference from my previous implementation is that, I now merge all contiguous requests (both read and write), before submitting them. This significantly improved IO performance. I am still collecting performance numbers, I will be posting in next few days. Comments ? Todo: - Address hch's comments on annontations -