From: "Michael S. Tsirkin" <mst@redhat.com>
To: Raphael Norwitz <raphael.norwitz@nutanix.com>
Cc: Li Feng <fengli@smartx.com>, Kevin Wolf <kwolf@redhat.com>,
Hanna Reitz <hreitz@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>, Fam Zheng <fam@euphon.net>,
"open list:Block layer core" <qemu-block@nongnu.org>,
"open list:All patches CC here" <qemu-devel@nongnu.org>,
"lifeng1519@gmail.com" <lifeng1519@gmail.com>
Subject: Re: [PATCH] vhost-user-scsi: support reconnect to backend
Date: Mon, 24 Jul 2023 16:30:22 -0400 [thread overview]
Message-ID: <20230724162933-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <DDDB71EA-E549-4325-9CDC-E9C746AE2E9B@nutanix.com>
On Mon, Jul 24, 2023 at 05:21:37PM +0000, Raphael Norwitz wrote:
> Very excited to see this. High level looks good modulo a few small things.
>
> My major concern is around existing vhost-user-scsi backends which don’t support VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD. IMO we should hide the reconnect behavior behind a VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD check. We may want to do the same for vhost-user-blk.
>
> The question is then what happens if the check is false. IIUC without an inflight FD, if a device processes requests out of order, it’s not safe to continue execution on reconnect, as there’s no way for the backend to know how to replay IO. Should we permanently wedge the device or have QEMU fail out? May be nice to have a toggle for this.
No, device itself can store the state somewhere. And if it wants to,
it can check VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD and fail reconnect.
--
MST
next prev parent reply other threads:[~2023-07-24 20:31 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-21 10:51 [PATCH] vhost-user-scsi: support reconnect to backend Li Feng
2023-07-24 17:21 ` Raphael Norwitz
2023-07-24 20:30 ` Michael S. Tsirkin [this message]
2023-07-25 10:19 ` Li Feng
2023-07-27 21:21 ` Raphael Norwitz
2023-07-28 7:48 ` Li Feng
2023-07-30 22:09 ` Raphael Norwitz
2023-07-31 11:32 ` Li Feng
2023-07-25 10:42 ` [PATCH v2 0/4] Implement reconnect for vhost-user-scsi Li Feng
2023-07-25 10:42 ` [PATCH v2 1/4] vhost: fix the fd leak Li Feng
2023-07-30 22:09 ` Raphael Norwitz
2023-07-25 10:42 ` [PATCH v2 2/4] vhost-user-common: send get_inflight_fd once Li Feng
2023-07-28 6:04 ` Michael S. Tsirkin
2023-07-28 7:49 ` Li Feng
2023-07-30 22:13 ` Raphael Norwitz
2023-07-31 11:38 ` Li Feng
2023-07-31 23:11 ` Raphael Norwitz
2023-07-25 10:42 ` [PATCH v2 3/4] vhost: move and rename the conn retry times Li Feng
2023-07-30 22:13 ` Raphael Norwitz
2023-07-25 10:42 ` [PATCH v2 4/4] vhost-user-scsi: support reconnect to backend Li Feng
2023-07-25 10:58 ` Li Feng
2023-07-30 22:14 ` Raphael Norwitz
2023-07-31 10:24 ` Li Feng
2023-07-31 12:10 ` [PATCH v3 0/5] Implement reconnect for vhost-user-scsi Li Feng
2023-07-31 12:10 ` [PATCH v3 1/5] vhost: fix the fd leak Li Feng
2023-08-03 13:41 ` Fiona Ebner
2023-07-31 12:10 ` [PATCH v3 2/5] vhost-user-common: send get_inflight_fd once Li Feng
2023-07-31 23:34 ` Raphael Norwitz
2023-07-31 12:10 ` [PATCH v3 3/5] vhost: move and rename the conn retry times Li Feng
2023-07-31 12:10 ` [PATCH v3 4/5] vhost-user-scsi: support reconnect to backend Li Feng
2023-07-31 23:35 ` Raphael Norwitz
2023-09-01 12:00 ` Markus Armbruster
2023-09-12 8:29 ` Li Feng
2023-07-31 12:10 ` [PATCH v3 5/5] vhost-user-scsi: start vhost when guest kicks Li Feng
2023-07-31 23:35 ` Raphael Norwitz
2023-09-01 11:44 ` Markus Armbruster
2023-09-12 7:53 ` Li Feng
2023-09-12 8:52 ` [PATCH v4 0/5] Implement reconnect for vhost-user-scsi Li Feng
2023-09-12 8:52 ` [PATCH v4 1/5] vhost-user-common: send get_inflight_fd once Li Feng
2023-09-12 8:52 ` [PATCH v4 2/5] vhost: move and rename the conn retry times Li Feng
2023-09-12 8:52 ` [PATCH v4 3/5] vhost-user-scsi: support reconnect to backend Li Feng
2023-09-12 8:52 ` [PATCH v4 4/5] vhost-user-scsi: start vhost when guest kicks Li Feng
2023-09-12 8:52 ` [PATCH v4 5/5] vhost-user: fix lost reconnect Li Feng
2023-09-19 11:40 ` [PATCH v5 0/5] Implement reconnect for vhost-user-scsi Li Feng
2023-09-19 11:40 ` [PATCH v5 1/5] vhost-user-common: send get_inflight_fd once Li Feng
2023-09-19 11:40 ` [PATCH v5 2/5] vhost: move and rename the conn retry times Li Feng
2023-09-19 11:40 ` [PATCH v5 3/5] vhost-user-scsi: support reconnect to backend Li Feng
2023-09-19 11:40 ` [PATCH v5 4/5] vhost-user-scsi: start vhost when guest kicks Li Feng
2023-09-19 11:40 ` [PATCH v5 5/5] vhost-user: fix lost reconnect Li Feng
2023-09-22 11:46 ` [PATCH v6 0/5] Implement reconnect for vhost-user-scsi Li Feng
2023-09-22 11:46 ` [PATCH v6 1/5] vhost-user-common: send get_inflight_fd once Li Feng
2023-09-29 0:54 ` Raphael Norwitz
2023-10-08 8:49 ` Li Feng
2023-10-08 8:50 ` Michael S. Tsirkin
2023-10-08 8:53 ` Li Feng
2023-09-22 11:46 ` [PATCH v6 2/5] vhost: move and rename the conn retry times Li Feng
2023-09-22 11:46 ` [PATCH v6 3/5] vhost-user-scsi: support reconnect to backend Li Feng
2023-09-29 0:55 ` Raphael Norwitz
2023-10-08 8:45 ` Li Feng
2023-09-22 11:46 ` [PATCH v6 4/5] vhost-user-scsi: start vhost when guest kicks Li Feng
2023-09-29 0:55 ` Raphael Norwitz
2023-09-22 11:46 ` [PATCH v6 5/5] vhost-user: fix lost reconnect Li Feng
2023-09-29 0:55 ` Raphael Norwitz
2023-09-29 0:55 ` Raphael Norwitz
2023-10-08 8:49 ` [PATCH v6 0/5] Implement reconnect for vhost-user-scsi Michael S. Tsirkin
2023-10-08 8:53 ` Li Feng
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=20230724162933-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=fam@euphon.net \
--cc=fengli@smartx.com \
--cc=hreitz@redhat.com \
--cc=kwolf@redhat.com \
--cc=lifeng1519@gmail.com \
--cc=pbonzini@redhat.com \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=raphael.norwitz@nutanix.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).