From: Christian Borntraeger <borntraeger@de.ibm.com>
To: Paolo Bonzini <pbonzini@redhat.com>, Fam Zheng <famz@redhat.com>,
qemu-devel@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>,
qemu-block@nongnu.org, "Michael S. Tsirkin" <mst@redhat.com>,
tubo@linux.vnet.ibm.com, Stefan Hajnoczi <stefanha@redhat.com>,
cornelia.huck@de.ibm.com
Subject: Re: [Qemu-devel] [PATCH 0/4] Tweaks around virtio-blk start/stop
Date: Wed, 16 Mar 2016 12:24:12 +0100 [thread overview]
Message-ID: <56E9425C.8030201@de.ibm.com> (raw)
In-Reply-To: <56E93ECE.10103@redhat.com>
On 03/16/2016 12:09 PM, Paolo Bonzini wrote:
>
>
> On 16/03/2016 11:49, Christian Borntraeger wrote:
>> Seems to lockup.
>
> That's an improvement actually. :)
>
>> Thread 3 (Thread 0x3ff888dc910 (LWP 88958)):
>> #0 0x000003ff8ca90cd4 in __lll_lock_wait () at /lib64/libpthread.so.0
>> #1 0x000003ff8ca93e74 in __lll_lock_elision () at /lib64/libpthread.so.0
>
> Off-topic, I love how s390 backtraces always have a little bit of
> showing off in them! :)
So I understood your first remark (about _working_ transactional memory) but I
cannot parse your 2nd one. For Conny it is exactly the opposite, so I will let
Conny answer belows discussion ;-)
>
>> #3 0x00000000800b713e in virtio_blk_data_plane_start (s=0xba232d80) at /home/cborntra/REPOS/qemu/hw/block/dataplane/virtio-blk.c:224
>> #4 0x00000000800b4ea0 in virtio_blk_handle_output (vdev=0xb9eee7e8, vq=0xba305270) at /home/cborntra/REPOS/qemu/hw/block/virtio-blk.c:590
>> #5 0x00000000800ef3dc in virtio_queue_notify_vq (vq=0xba305270) at /home/cborntra/REPOS/qemu/hw/virtio/virtio.c:1095
>> #6 0x00000000800f1c9c in virtio_queue_host_notifier_read (n=0xba3052c8) at /home/cborntra/REPOS/qemu/hw/virtio/virtio.c:1785
>> #7 0x00000000800f1e14 in virtio_queue_set_host_notifier_fd_handler (vq=0xba305270, assign=false, set_handler=false) at /home/cborntra/REPOS/qemu/hw/virtio/virtio.c:1817
>> #8 0x0000000080109c50 in virtio_ccw_set_guest2host_notifier (dev=0xb9eed6a0, n=0, assign=false, set_handler=false) at /home/cborntra/REPOS/qemu/hw/s390x/virtio-ccw.c:97
>> #9 0x0000000080109ef2 in virtio_ccw_stop_ioeventfd (dev=0xb9eed6a0) at /home/cborntra/REPOS/qemu/hw/s390x/virtio-ccw.c:154
>
> One bug is here: virtio_ccw_stop_ioeventfd, in this case, should pass
> assign=true to virtio_ccw_set_guest2host_notifier. (Assuming my
> understanding of assign=true is correct; I think it means "I'm going to
> set up another host notifier handler").
>
> In dataplane, instead, all calls to
> virtio_queue_set_host_notifier_fd_handler and
> virtio_queue_aio_set_host_notifier_handler should have assign=true. The
> ioeventfd is just being moved from one aiocontext to another.
>
> Paolo
>
>> #10 0x000000008010d5aa in virtio_ccw_set_host_notifier (d=0xb9eed6a0, n=0, assign=true) at /home/cborntra/REPOS/qemu/hw/s390x/virtio-ccw.c:1211
>> #11 0x00000000800b722c in virtio_blk_data_plane_start (s=0xba232d80) at /home/cborntra/REPOS/qemu/hw/block/dataplane/virtio-blk.c:242
>> #12 0x00000000800b4ea0 in virtio_blk_handle_output (vdev=0xb9eee7e8, vq=0xba305270) at /home/cborntra/REPOS/qemu/hw/block/virtio-blk.c:590
>> #13 0x00000000800ef3dc in virtio_queue_notify_vq (vq=0xba305270) at /home/cborntra/REPOS/qemu/hw/virtio/virtio.c:1095
>> #14 0x00000000800f1c9c in virtio_queue_host_notifier_read (n=0xba3052c8) at /home/cborntra/REPOS/qemu/hw/virtio/virtio.c:1785
>> #15 0x00000000802f1cd4 in aio_dispatch (ctx=0xb9e81c70) at /home/cborntra/REPOS/qemu/aio-posix.c:327
>> #16 0x00000000802df31c in aio_ctx_dispatch (source=0xb9e81c70, callback=0x0, user_data=0x0) at /home/cborntra/REPOS/qemu/async.c:232
>
next prev parent reply other threads:[~2016-03-16 11:24 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-16 10:10 [Qemu-devel] [PATCH 0/4] Tweaks around virtio-blk start/stop Fam Zheng
2016-03-16 10:10 ` [Qemu-devel] [PATCH 1/4] block: Use drained section in bdrv_set_aio_context Fam Zheng
2016-03-16 10:27 ` Paolo Bonzini
2016-03-16 10:51 ` Fam Zheng
2016-03-16 10:10 ` [Qemu-devel] [PATCH 2/4] block-backend: Introduce blk_drained_begin/end Fam Zheng
2016-03-16 10:10 ` [Qemu-devel] [PATCH 3/4] virtio-blk: Use blk_drained_begin/end around dataplane stop Fam Zheng
2016-03-16 10:10 ` [Qemu-devel] [PATCH 4/4] virtio-blk: Clean up start/stop with mutex and BH Fam Zheng
2016-03-17 15:00 ` [Qemu-devel] [Qemu-block] " Stefan Hajnoczi
2016-03-17 15:07 ` Paolo Bonzini
2016-03-22 12:52 ` Fam Zheng
2016-03-22 18:05 ` Paolo Bonzini
2016-03-23 8:10 ` Cornelia Huck
2016-03-23 9:08 ` Paolo Bonzini
2016-03-23 9:12 ` Christian Borntraeger
2016-03-24 8:19 ` tu bo
2016-03-24 8:32 ` Cornelia Huck
2016-03-24 8:47 ` Cornelia Huck
2016-03-24 9:31 ` Cornelia Huck
2016-03-16 10:28 ` [Qemu-devel] [PATCH 0/4] Tweaks around virtio-blk start/stop Paolo Bonzini
2016-03-16 10:49 ` Christian Borntraeger
2016-03-16 11:09 ` Paolo Bonzini
2016-03-16 11:24 ` Christian Borntraeger [this message]
2016-03-16 12:55 ` Paolo Bonzini
2016-03-16 13:38 ` Christian Borntraeger
2016-03-16 13:45 ` Paolo Bonzini
2016-03-17 0:39 ` Fam Zheng
2016-03-17 11:03 ` tu bo
2016-03-21 10:57 ` Fam Zheng
2016-03-21 11:15 ` Cornelia Huck
2016-03-21 12:45 ` Fam Zheng
2016-03-21 13:02 ` Cornelia Huck
2016-03-21 23:45 ` Fam Zheng
2016-03-22 8:06 ` Cornelia Huck
2016-03-22 7:10 ` tu bo
2016-03-22 7:18 ` Fam Zheng
2016-03-22 9:07 ` Cornelia Huck
2016-03-22 9:46 ` Paolo Bonzini
2016-03-22 11:59 ` Cornelia Huck
2016-03-22 12:11 ` Paolo Bonzini
2016-03-22 12:54 ` Cornelia Huck
2016-03-17 12:22 ` tu bo
2016-03-17 12:39 ` Christian Borntraeger
2016-03-17 13:02 ` Cornelia Huck
2016-03-17 15:02 ` Paolo Bonzini
2016-03-17 15:07 ` Christian Borntraeger
2016-03-17 15:15 ` Christian Borntraeger
2016-03-17 15:16 ` Christian Borntraeger
2016-03-17 16:08 ` Christian Borntraeger
2016-03-18 15:03 ` Paolo Bonzini
2016-03-21 9:42 ` Fam Zheng
2016-03-21 11:10 ` Christian Borntraeger
2016-03-21 12:17 ` Cornelia Huck
2016-03-21 13:47 ` TU BO
2016-03-21 13:54 ` Paolo Bonzini
2016-03-21 14:19 ` Cornelia Huck
2016-03-22 0:31 ` Fam Zheng
2016-03-16 11:32 ` Cornelia Huck
2016-03-16 11:48 ` Paolo Bonzini
2016-03-16 11:56 ` Cornelia Huck
2016-03-16 11:59 ` Paolo Bonzini
2016-03-16 12:22 ` Cornelia Huck
2016-03-16 12:32 ` Paolo Bonzini
2016-03-16 12:42 ` Cornelia Huck
2016-03-16 12:49 ` Paolo Bonzini
2016-03-16 13:04 ` Cornelia Huck
2016-03-16 13:10 ` Paolo Bonzini
2016-03-16 13:14 ` Cornelia Huck
2016-03-16 13:15 ` Paolo Bonzini
2016-03-16 11:52 ` Cornelia Huck
2016-03-16 11:54 ` Paolo Bonzini
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=56E9425C.8030201@de.ibm.com \
--to=borntraeger@de.ibm.com \
--cc=cornelia.huck@de.ibm.com \
--cc=famz@redhat.com \
--cc=kwolf@redhat.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
--cc=tubo@linux.vnet.ibm.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).