From: Yuanhan Liu <yuanhan.liu@linux.intel.com>
To: "Matias Bjørling" <m@bjorling.me>
Cc: Ming Lei <tom.leiming@gmail.com>,
Fengguang Wu <fengguang.wu@intel.com>,
Huang Ying <ying.huang@intel.com>, Jens Axboe <axboe@kernel.dk>,
LKML <linux-kernel@vger.kernel.org>,
Yuanhan Liu <yuanhan.liu@linux.intel.com>
Subject: Re: changes caused by 0d11e6ac("blk-mq: fix use-after-free of request")
Date: Thu, 19 Dec 2013 22:37:13 +0800 [thread overview]
Message-ID: <20131219143713.GX31783@yliu-dev.sh.intel.com> (raw)
In-Reply-To: <52B1790A.5070105@bjorling.me>
On Wed, Dec 18, 2013 at 11:29:30AM +0100, Matias Bjørling wrote:
> On 12/18/2013 09:50 AM, Yuanhan Liu wrote:
> >Hi,
> >
> >FYI, we noticed some changes caused by 0d11e6ac("blk-mq: fix use-after-free of request"):
> >
>
> The blk-mq accounting was faulty up to that commit. We should
> compare the blk-mq with the previous block layer.
>
> Could you try to revert the following patches:
>
> f02b9ac virtio-blk: virtqueue_kick() must be ordered with other...
> 1cf7e9c virtio_blk: blk-mq support
>
> and compare the two runs (upto 0d11e6ac applied, and the same, with
> the two patches reverted)
Hi Matias,
You are right. Those counter restore back with the two patches reverted(d1b4e3825c8848b0ea0f).
959a35f13eb785f982d7 0d11e6aca396e679c07b d1b4e3825c8848b0ea0f
--------------- ------------------------- -------------------------
0.00 60.02 ~42% 0.00 vpx/micro/xfstests/4HDD-btrfs-generic-quick
0.00 367.81 ~27% 0.00 vpx/micro/xfstests/4HDD-ext4-generic-mid
0.00 411.64 ~13% 0.00 vpx/micro/xfstests/4HDD-xfs-generic-mid
0.00 208.39 ~10% 0.00 vpx/micro/xfstests/4HDD-xfs-generic-quick
0.00 1047.86 0.00 TOTAL iostat.vdd.await
959a35f13eb785f982d7 0d11e6aca396e679c07b d1b4e3825c8848b0ea0f
--------------- ------------------------- -------------------------
0.00 301.60 ~34% 0.00 vpx/micro/xfstests/4HDD-btrfs-generic-mid
0.00 249.16 ~12% 0.00 vpx/micro/xfstests/4HDD-btrfs-generic-quick
0.00 51.45 ~26% 0.00 vpx/micro/xfstests/4HDD-ext4-generic-mid
0.00 91.51 ~21% 0.04 vpx/micro/xfstests/4HDD-xfs-generic-127
0.00 1919.27 ~43% 0.00 vpx/micro/xfstests/4HDD-xfs-generic-mid
0.00 121.04 ~11% 0.00 vpx/micro/xfstests/4HDD-xfs-generic-quick
0.00 2734.03 0.04 TOTAL iostat.vda.r_await
959a35f13eb785f982d7 0d11e6aca396e679c07b d1b4e3825c8848b0ea0f
--------------- ------------------------- -------------------------
0.00 406.12 ~10% 0.00 vpx/micro/xfstests/4HDD-btrfs-generic-mid
0.00 433.66 ~ 7% 0.00 vpx/micro/xfstests/4HDD-btrfs-generic-quick
0.00 807.79 ~15% 0.00 vpx/micro/xfstests/4HDD-ext4-generic-mid
0.00 42.94 ~67% 0.51 vpx/micro/xfstests/4HDD-xfs-generic-127
0.00 592.20 ~16% 0.00 vpx/micro/xfstests/4HDD-xfs-generic-mid
0.00 401.74 ~12% 0.00 vpx/micro/xfstests/4HDD-xfs-generic-quick
0.00 2684.45 0.51 TOTAL iostat.vda.w_await
--yliu
prev parent reply other threads:[~2013-12-19 14:36 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-12-18 8:50 changes caused by 0d11e6ac("blk-mq: fix use-after-free of request") Yuanhan Liu
2013-12-18 10:29 ` Matias Bjørling
2013-12-19 14:37 ` Yuanhan Liu [this message]
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=20131219143713.GX31783@yliu-dev.sh.intel.com \
--to=yuanhan.liu@linux.intel.com \
--cc=axboe@kernel.dk \
--cc=fengguang.wu@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=m@bjorling.me \
--cc=tom.leiming@gmail.com \
--cc=ying.huang@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.