From: Bin Wu <wu.wubin@huawei.com>
To: Fam Zheng <famz@redhat.com>, qemu-devel@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>, Benoit Canet <benoit@irqsave.net>,
Peter Lieven <pl@kamp.de>, Stefan Hajnoczi <stefanha@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Liu Yuan <namei.unix@gmail.com>
Subject: Re: [Qemu-devel] [PATCH v5 00/22] block: Asynchronous request cancellation
Date: Wed, 10 Sep 2014 17:09:11 +0800 [thread overview]
Message-ID: <54101537.1010905@huawei.com> (raw)
In-Reply-To: <1410328814-12560-1-git-send-email-famz@redhat.com>
On 2014/9/10 13:59, Fam Zheng wrote:
> v5: Fix IDE callback. (Paolo)
> Fix blkdebug. (Paolo)
> Drop the DMA fix which is independent of this series. (Paolo)
> Incorperate Yuan's patch on quorum_aio_cancel. (Benoît)
> Commit message wording fix. (Benoît)
> Rename qemu_aio_release to qemu_aio_unref. (Benoît)
>
> v4: Drop AIOCBInfo.cancel.
>
> This series adds a new block layer API:
>
> void bdrv_aio_cancel_async(BlockDriverAIOCB *acb);
>
> And use it to emulate bdrv_aio_cancel.
>
> The function is similar to bdrv_aio_cancel in that it cancels an AIO request,
> but different that it doesn't block until the request is completely cancelled
> or done.
>
> More importantly, the completion callback, BlockDriverAIOCB.cb, is guaranteed
> to be called, so that the cb can take care of resource releasing and status
> reporting to guest, etc.
>
> In the following work, scsi emulation code will be shifted to use the async
> cancelling.
>
> One major benefit would be that when guest tries to cancel a request, where the
> request cannot be cancelled easily, (due to throttled BlockDriverState, a lost
> connection, or a large request queue), we don't need to block the whole vm with
> a busy loop, which is how bdrv_aio_cancel is implemented now.
First, I think this series is really useful. However, I tested the v4
series and found virtio-scsi disk(scsi-hd) was still blocked when the IO
could not come back because of
virtio_scsi_do_tmf->scsi_cancel_io->bdrv_aio_cancel. can we just change
the bdrv_aio_cancel to bdrv_aio_cancel_async to solve this problem?
>
> A test case that is easy to reproduce is, throttle a scsi-disk to a very low
> limit, for example 50 bps, then stress the guest block device with dd or fio.
>
> Currently, the vm will quickly hang when it loses patience and send a tmf
> command to cancel the request, at which point we will busy wait in
> bdrv_aio_cancel, until the request is slowly spit out from throttled_reqs.
>
> Later, we will change scsi device code to make this asynchronous, on top of
> bdrv_aio_cancel_async.
>
> Fam
>
>
> Fam Zheng (21):
> ide/ahci: Check for -ECANCELED in aio callbacks
> block: Add refcnt in BlockDriverAIOCB
> block: Add bdrv_aio_cancel_async
> block: Drop bdrv_em_co_aiocb_info.cancel
> block: Convert bdrv_em_aiocb_info.cancel to .cancel_async
> thread-pool: Convert thread_pool_aiocb_info.cancel to cancel_async
> linux-aio: Convert laio_aiocb_info.cancel to .cancel_async
> dma: Convert dma_aiocb_info.cancel to .cancel_async
> iscsi: Convert iscsi_aiocb_info.cancel to .cancel_async
> archipelago: Drop archipelago_aiocb_info.cancel
> blkdebug: Drop blkdebug_aiocb_info.cancel
> blkverify: Drop blkverify_aiocb_info.cancel
> curl: Drop curl_aiocb_info.cancel
> qed: Drop qed_aiocb_info.cancel
> quorum: Convert quorum_aiocb_info.cancel to .cancel_async
> rbd: Drop rbd_aiocb_info.cancel
> sheepdog: Convert sd_aiocb_info.cancel to .cancel_async
> win32-aio: Drop win32_aiocb_info.cancel
> ide: Convert trim_aiocb_info.cancel to .cancel_async
> block: Drop AIOCBInfo.cancel
> block: Rename qemu_aio_release -> qemu_aio_unref
>
> Liu Yuan (1):
> quorum: fix quorum_aio_cancel()
>
> block.c | 69 ++++++++++++++++++++++++++++--------------------
> block/archipelago.c | 19 ++-----------
> block/blkdebug.c | 17 ++----------
> block/blkverify.c | 21 +--------------
> block/curl.c | 16 ++++-------
> block/iscsi.c | 23 ++++------------
> block/linux-aio.c | 34 +++++++-----------------
> block/qed.c | 23 +---------------
> block/quorum.c | 11 ++++----
> block/rbd.c | 25 ++----------------
> block/sheepdog.c | 54 ++++++++++++++++---------------------
> block/win32-aio.c | 18 ++-----------
> dma-helpers.c | 20 +++-----------
> hw/ide/ahci.c | 3 +++
> hw/ide/core.c | 26 ++++++++++++------
> include/block/aio.h | 7 +++--
> include/block/block.h | 1 +
> tests/test-thread-pool.c | 34 ++++++++++++++++++------
> thread-pool.c | 36 +++++++++++--------------
> 19 files changed, 172 insertions(+), 285 deletions(-)
>
next prev parent reply other threads:[~2014-09-10 9:09 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-10 5:59 [Qemu-devel] [PATCH v5 00/22] block: Asynchronous request cancellation Fam Zheng
2014-09-10 5:59 ` [Qemu-devel] [PATCH v5 01/22] ide/ahci: Check for -ECANCELED in aio callbacks Fam Zheng
2014-09-10 5:59 ` [Qemu-devel] [PATCH v5 02/22] block: Add refcnt in BlockDriverAIOCB Fam Zheng
2014-09-10 5:59 ` [Qemu-devel] [PATCH v5 03/22] block: Add bdrv_aio_cancel_async Fam Zheng
2014-09-10 5:59 ` [Qemu-devel] [PATCH v5 04/22] block: Drop bdrv_em_co_aiocb_info.cancel Fam Zheng
2014-09-10 5:59 ` [Qemu-devel] [PATCH v5 05/22] block: Convert bdrv_em_aiocb_info.cancel to .cancel_async Fam Zheng
2014-09-10 8:20 ` Paolo Bonzini
2014-09-10 9:36 ` Fam Zheng
2014-09-10 9:46 ` Paolo Bonzini
2014-09-10 5:59 ` [Qemu-devel] [PATCH v5 06/22] thread-pool: Convert thread_pool_aiocb_info.cancel to cancel_async Fam Zheng
2014-09-10 5:59 ` [Qemu-devel] [PATCH v5 07/22] linux-aio: Convert laio_aiocb_info.cancel to .cancel_async Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 08/22] dma: Convert dma_aiocb_info.cancel " Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 09/22] iscsi: Convert iscsi_aiocb_info.cancel " Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 10/22] archipelago: Drop archipelago_aiocb_info.cancel Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 11/22] blkdebug: Drop blkdebug_aiocb_info.cancel Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 12/22] blkverify: Drop blkverify_aiocb_info.cancel Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 13/22] curl: Drop curl_aiocb_info.cancel Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 14/22] qed: Drop qed_aiocb_info.cancel Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 15/22] quorum: fix quorum_aio_cancel() Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 16/22] quorum: Convert quorum_aiocb_info.cancel to .cancel_async Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 17/22] rbd: Drop rbd_aiocb_info.cancel Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 18/22] sheepdog: Convert sd_aiocb_info.cancel to .cancel_async Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 19/22] win32-aio: Drop win32_aiocb_info.cancel Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 20/22] ide: Convert trim_aiocb_info.cancel to .cancel_async Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 21/22] block: Drop AIOCBInfo.cancel Fam Zheng
2014-09-10 6:00 ` [Qemu-devel] [PATCH v5 22/22] block: Rename qemu_aio_release -> qemu_aio_unref Fam Zheng
2014-09-10 9:09 ` Bin Wu [this message]
2014-09-10 9:20 ` [Qemu-devel] [PATCH v5 00/22] block: Asynchronous request cancellation Fam Zheng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=54101537.1010905@huawei.com \
--to=wu.wubin@huawei.com \
--cc=benoit@irqsave.net \
--cc=famz@redhat.com \
--cc=kwolf@redhat.com \
--cc=namei.unix@gmail.com \
--cc=pbonzini@redhat.com \
--cc=pl@kamp.de \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).