From: Kevin Wolf <kwolf@redhat.com>
To: Klaus Jensen <its@irrelevant.dk>
Cc: qemu-block@nongnu.org, richard.henderson@linaro.org,
qemu-devel@nongnu.org, stefanha@redhat.com
Subject: Re: [PULL 11/23] Revert "graph-lock: Disable locking for now"
Date: Mon, 10 Jul 2023 14:40:50 +0200 [thread overview]
Message-ID: <ZKv8UvKOHo6VX5g/@redhat.com> (raw)
In-Reply-To: <ZKv4G4A0l8EhMZoy@cormorant.local>
[-- Attachment #1: Type: text/plain, Size: 910 bytes --]
Am 10.07.2023 um 14:22 hat Klaus Jensen geschrieben:
> On Jun 28 16:15, Kevin Wolf wrote:
> > Now that bdrv_graph_wrlock() temporarily drops the AioContext lock that
> > its caller holds, it can poll without causing deadlocks. We can now
> > re-enable graph locking.
> >
> > This reverts commit ad128dff0bf4b6f971d05eb4335a627883a19c1d.
> >
>
> I'm seeing a pretty major performance regression on iothread-enabled
> virtio-blk (and on some on-going iothread hw/nvme work) with this
> applied. Something like ~300k iops prior to this vs ~200k after on my
> set up. On master, virtio-blk is currently faster without an iothread
> (~215k) than with (~200k).
>
> I bisected the change in iops to this revert.
Is CONFIG_DEBUG_GRAPH_LOCK enabled in your build? If so, this is
expected to cost some performance. If not, we need to take a look at
what else is causing the regression.
Kevin
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2023-07-10 12:41 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-28 14:15 [PULL 00/23] Block layer patches Kevin Wolf
2023-06-28 14:15 ` [PULL 01/23] iotests: Test active commit with iothread and background I/O Kevin Wolf
2023-06-28 14:15 ` [PULL 02/23] qdev-properties-system: Lock AioContext for blk_insert_bs() Kevin Wolf
2023-06-28 14:15 ` [PULL 03/23] test-block-iothread: " Kevin Wolf
2023-06-28 14:15 ` [PULL 04/23] block: Fix AioContext locking in bdrv_open_child() Kevin Wolf
2023-06-28 14:15 ` [PULL 05/23] block: Fix AioContext locking in bdrv_attach_child_common() Kevin Wolf
2023-06-28 14:15 ` [PULL 06/23] block: Fix AioContext locking in bdrv_reopen_parse_file_or_backing() Kevin Wolf
2023-06-28 14:15 ` [PULL 07/23] block: Fix AioContext locking in bdrv_open_inherit() Kevin Wolf
2023-06-28 14:15 ` [PULL 08/23] block: Fix AioContext locking in bdrv_open_backing_file() Kevin Wolf
2023-06-28 14:15 ` [PULL 09/23] blockjob: Fix AioContext locking in block_job_add_bdrv() Kevin Wolf
2023-06-28 14:15 ` [PULL 10/23] graph-lock: Unlock the AioContext while polling Kevin Wolf
2023-06-28 14:15 ` [PULL 11/23] Revert "graph-lock: Disable locking for now" Kevin Wolf
2023-07-10 12:22 ` Klaus Jensen
2023-07-10 12:40 ` Kevin Wolf [this message]
2023-07-10 14:03 ` Klaus Jensen
2023-06-28 14:15 ` [PULL 12/23] file-posix: remove incorrect coroutine_fn calls Kevin Wolf
2023-06-28 14:15 ` [PULL 13/23] qed: mark more functions as coroutine_fns and GRAPH_RDLOCK Kevin Wolf
2023-06-28 14:15 ` [PULL 14/23] vpc: " Kevin Wolf
2023-06-28 14:15 ` [PULL 15/23] bochs: " Kevin Wolf
2023-06-28 14:15 ` [PULL 16/23] block: mark another function as coroutine_fns and GRAPH_UNLOCKED Kevin Wolf
2023-06-28 14:15 ` [PULL 17/23] cloop: mark more functions as coroutine_fns and GRAPH_RDLOCK Kevin Wolf
2023-06-28 14:15 ` [PULL 18/23] dmg: " Kevin Wolf
2023-06-28 14:15 ` [PULL 19/23] vmdk: " Kevin Wolf
2023-06-28 14:15 ` [PULL 20/23] vhdx: " Kevin Wolf
2023-06-28 14:15 ` [PULL 21/23] qcow2: " Kevin Wolf
2023-06-28 14:15 ` [PULL 22/23] block: use bdrv_co_getlength in coroutine context Kevin Wolf
2023-06-28 14:15 ` [PULL 23/23] block: use bdrv_co_debug_event " Kevin Wolf
2023-06-29 6:11 ` [PULL 00/23] Block layer patches Richard Henderson
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=ZKv8UvKOHo6VX5g/@redhat.com \
--to=kwolf@redhat.com \
--cc=its@irrelevant.dk \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=richard.henderson@linaro.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).