From: Damien Le Moal <damien.lemoal@opensource.wdc.com>
To: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>,
Chaitanya Kulkarni <chaitanyak@nvidia.com>
Cc: "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
Jens Axboe <axboe@kernel.dk>,
Damien Le Moal <Damien.LeMoal@wdc.com>,
"linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>,
Keith Busch <kbusch@kernel.org>, Christoph Hellwig <hch@lst.de>
Subject: Re: [bug report] block/005 hangs with NVMe device and linux-block/for-next
Date: Tue, 2 Nov 2021 17:28:06 +0900 [thread overview]
Message-ID: <4e6c0a41-b70f-bcc2-31f3-761b7c8dcd3a@opensource.wdc.com> (raw)
In-Reply-To: <20211102081929.s6eyxawq32phvufr@shindev>
+linux-nvme (Keith and Christoph)
On 2021/11/02 17:19, Shinichiro Kawasaki wrote:
> On Nov 02, 2021 / 03:07, Chaitanya Kulkarni wrote:
>>
>>> The NVMe device I use is a U.2 NVMe ZNS SSD. It has a zoned name space and
>>> a regular name space, and the hang is observed with both name spaces. I have
>>> not yet tried other NVME devices, so I will try them.
>
> I tried another NVMe device, WD Black SN750, but it did not recreate the hang.
>
>>>
>>
>> See if you can produce this with QEMU NVMe emulation (ZNS and NON-ZNS
>> mode), if you can then it will be easier to reproduce for everyone.
>
> Chaitanya, thank you for the advice. I have managed to reproduce the hang with
> QEMU NVMe emulation. Actually, ZNS mode is not required. I tried some device
> set up configuration with QEMU, and the hang was recreated when a single NVMe
> device has two namespaces. With single namespace in a single NVMe device, the
> hang is not observed.
>
> So it looks like that the number of namespaces may be related to the cause. The
> WD Black SN750 without hang has single namespace. I reduced the number of
> namespaces of the U.2 NVMe ZNS SSD from 2 to 1, then the hang was not observed.
>
> FYI, the QEMU command line options that I used was as follows. It prepares
> /dev/nvme0n1 and /dev/nvme0n2, and the block/005 run on /dev/nvme0n1 recreated
> the hang.
>
> -device nvme,id=nvme0,serial=qemunvme,logical_block_size=4096,physical_block_size=4096 \
> -drive file=(path)/nvme0n1.img,id=nvme0n1,format=raw,if=none \
> -device nvme-ns,drive=nvme0n1,bus=nvme0,nsid=1 \
> -drive file=(path)/nvme0n2.img,id=nvme0n2,format=raw,if=none \
> -device nvme-ns,drive=nvme0n2,bus=nvme0,nsid=2
>
> Regarding the two image files, I created them beforehand with the command below:
>
> $ qemu-img create -f raw "${image_file_path}" 1024M
>
> Hope this helps.
>
--
Damien Le Moal
Western Digital Research
next prev parent reply other threads:[~2021-11-02 8:28 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-01 8:34 [bug report] block/005 hangs with NVMe device and linux-block/for-next Shinichiro Kawasaki
2021-11-01 12:41 ` Jens Axboe
2021-11-01 23:01 ` Jens Axboe
2021-11-02 2:22 ` Shinichiro Kawasaki
2021-11-02 3:07 ` Chaitanya Kulkarni
2021-11-02 8:19 ` Shinichiro Kawasaki
2021-11-02 8:28 ` Damien Le Moal [this message]
2021-11-02 3:44 ` Ming Lei
2021-11-02 8:28 ` Shinichiro Kawasaki
2021-11-02 9:02 ` Shinichiro Kawasaki
2021-11-02 10:48 ` Ming Lei
2021-11-02 11:24 ` Shinichiro Kawasaki
2021-11-02 12:26 ` Ming Lei
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=4e6c0a41-b70f-bcc2-31f3-761b7c8dcd3a@opensource.wdc.com \
--to=damien.lemoal@opensource.wdc.com \
--cc=Damien.LeMoal@wdc.com \
--cc=axboe@kernel.dk \
--cc=chaitanyak@nvidia.com \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=shinichiro.kawasaki@wdc.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