qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Peter Xu <peterx@redhat.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Prasad Pandit <ppandit@redhat.com>,
	qemu-devel@nongnu.org, Fabiano Rosas <farosas@suse.de>,
	Jason Wang <jasowang@redhat.com>,
	mcoqueli@redhat.com, Prasad Pandit <pjp@fedoraproject.org>
Subject: Re: [PATCH 0/2] Postcopy migration and vhost-user errors
Date: Wed, 17 Jul 2024 09:33:01 -0400	[thread overview]
Message-ID: <ZpfIDUwS9vawpzT5@x1n> (raw)
In-Reply-To: <20240717045335-mutt-send-email-mst@kernel.org>

Hi, Michael,

On Wed, Jul 17, 2024 at 04:55:52AM -0400, Michael S. Tsirkin wrote:
> I just want to understand how we managed to have two threads
> talking in parallel. BQL is normally enough, which path
> manages to invoke vhost-user with BQL not taken?
> Just check BQL taken on each vhost user invocation and
> you will figure it out.

Prasad mentioned how the race happened in the cover letter:

https://lore.kernel.org/r/20240711131424.181615-1-ppandit@redhat.com

     Thread-1                                  Thread-2

vhost_dev_start                        postcopy_ram_incoming_cleanup
 vhost_device_iotlb_miss                postcopy_notify
  vhost_backend_update_device_iotlb      vhost_user_postcopy_notifier
   vhost_user_send_device_iotlb_msg       vhost_user_postcopy_end
    process_message_reply                  process_message_reply
     vhost_user_read                        vhost_user_read
      vhost_user_read_header                 vhost_user_read_header
       "Fail to update device iotlb"          "Failed to receive reply to postcopy_end"

The normal case should be that thread-2 is postcopy_ram_listen_thread(),
and this happens when postcopy migration is close to the end.

Thanks,

-- 
Peter Xu



  reply	other threads:[~2024-07-17 13:33 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-11 13:14 [PATCH 0/2] Postcopy migration and vhost-user errors Prasad Pandit
2024-07-11 13:14 ` [PATCH 1/2] vhost-user: add a write-read lock Prasad Pandit
2024-07-11 14:39   ` Michael S. Tsirkin
2024-07-15 10:57     ` Prasad Pandit
2024-07-11 15:41   ` Peter Xu
2024-07-15  8:14     ` Prasad Pandit
2024-07-15 13:27       ` Peter Xu
2024-07-16 10:19         ` Prasad Pandit
2024-07-20 19:41   ` Michael S. Tsirkin
2024-07-23  4:58     ` Prasad Pandit
2024-07-11 13:14 ` [PATCH 2/2] vhost: fail device start if iotlb update fails Prasad Pandit
2024-07-11 15:38 ` [PATCH 0/2] Postcopy migration and vhost-user errors Peter Xu
2024-07-15 10:14   ` Prasad Pandit
2024-07-15 13:39     ` Peter Xu
2024-07-16 10:14       ` Prasad Pandit
2024-07-16 22:02         ` Peter Xu
2024-07-17  8:55           ` Michael S. Tsirkin
2024-07-17 13:33             ` Peter Xu [this message]
2024-07-17 13:40               ` Michael S. Tsirkin
2024-07-17 13:47                 ` Peter Xu
2024-07-20 19:41                   ` Michael S. Tsirkin
2024-07-23  5:03                     ` Prasad Pandit
2024-07-23 17:52                       ` Peter Xu
2024-07-23 17:57                       ` Prasad Pandit

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=ZpfIDUwS9vawpzT5@x1n \
    --to=peterx@redhat.com \
    --cc=farosas@suse.de \
    --cc=jasowang@redhat.com \
    --cc=mcoqueli@redhat.com \
    --cc=mst@redhat.com \
    --cc=pjp@fedoraproject.org \
    --cc=ppandit@redhat.com \
    --cc=qemu-devel@nongnu.org \
    /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).