[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v4 0/3] linux-aio: introduce submit I/O as a bat
From: |
Stefan Hajnoczi |
Subject: |
Re: [Qemu-devel] [PATCH v4 0/3] linux-aio: introduce submit I/O as a batch |
Date: |
Thu, 3 Jul 2014 14:36:46 +0200 |
User-agent: |
Mutt/1.5.23 (2014-03-12) |
On Wed, Jul 02, 2014 at 08:18:45PM +0800, Ming Lei wrote:
> Hi,
>
> The commit 580b6b2aa2(dataplane: use the QEMU block layer for I/O)
> introduces ~40% throughput regression on virtio-blk dataplane, and
> one of causes is that submitting I/O as a batch is removed.
>
> This patchset trys to introduce this mechanism on block, at least,
> linux-aio can benefit from that.
>
> With these patches, it is observed that thoughout on virtio-blk
> dataplane can be improved a lot, see data in commit log of patch
> 3/3.
>
> It should be possible to apply the batch mechanism to other devices
> (such as virtio-scsi) too.
>
> TODO:
> - support queuing I/O to multi files which need lots of change
> to linux-aio for scsi devies
>
> V4:
> - support other non-raw formats with under-optimized performance
> - use reference counter for plug & unplug
> - flush io queue before sending flush command
>
> V3:
> - only support submitting I/O as a batch for raw format, pointed by
> Kevin
>
> V2:
> - define return value of bdrv_io_unplug as void, suggested by Paolo
> - avoid busy-wait for handling io_submit
> V1:
> - move queuing io stuff into linux-aio.c as suggested by Paolo
>
>
> Thanks,
> --
> Ming Lei
Nice performance fix. Together with the other fixes we've been
discussing I think we can fight a dataplane performance regression from
QEMU 2.0 to 2.1.
Looking forward to the next revision.
Stefan
pgpgr9i8Qy4cG.pgp
Description: PGP signature