Message-ID: <68172a9e-cf68-4962-8229-68e283e894e1@huaweicloud.com>
Date: Thu, 8 May 2025 20:17:14 +0800
From: Zhang Yi <yi.zhang@...weicloud.com>
To: Christoph Hellwig <hch@....de>
Cc: "Darrick J. Wong" <djwong@...nel.org>, linux-fsdevel@...r.kernel.org,
 linux-ext4@...r.kernel.org, linux-block@...r.kernel.org,
 dm-devel@...ts.linux.dev, linux-nvme@...ts.infradead.org,
 linux-scsi@...r.kernel.org, linux-xfs@...r.kernel.org,
 linux-kernel@...r.kernel.org, tytso@....edu, john.g.garry@...cle.com,
 bmarzins@...hat.com, chaitanyak@...dia.com, shinichiro.kawasaki@....com,
 brauner@...nel.org, yi.zhang@...wei.com, chengzhihao1@...wei.com,
 yukuai3@...wei.com, yangerkun@...wei.com
Subject: Re: [RFC PATCH v4 07/11] fs: statx add write zeroes unmap attribute

On 2025/5/8 13:01, Christoph Hellwig wrote:
> On Wed, May 07, 2025 at 03:33:23PM +0800, Zhang Yi wrote:
>> On 2025/5/6 20:11, Christoph Hellwig wrote:
>>> On Tue, May 06, 2025 at 07:16:56PM +0800, Zhang Yi wrote:
>>>> Sorry, but I don't understand your suggestion. The
>>>> STATX_ATTR_WRITE_ZEROES_UNMAP attribute only indicate whether the bdev
>>>> and the block device that under the specified file support unmap write
>>>> zeroes commoand. It does not reflect whether the bdev and the
>>>> filesystems support FALLOC_FL_WRITE_ZEROES. The implementation of
>>>> FALLOC_FL_WRITE_ZEROES doesn't fully rely on the unmap write zeroes
>>>> commoand now, users simply refer to this attribute flag to determine
>>>> whether to use FALLOC_FL_WRITE_ZEROES when preallocating a file.
>>>> So, STATX_ATTR_WRITE_ZEROES_UNMAP and FALLOC_FL_WRITE_ZEROES doesn't
>>>> have strong relations, why do you suggested to put this into the ext4
>>>> and bdev patches that adding FALLOC_FL_WRITE_ZEROES?
>>>
>>> So what is the point of STATX_ATTR_WRITE_ZEROES_UNMAP?
>>
>> My idea is not to strictly limiting the use of FALLOC_FL_WRITE_ZEROES to
>> only bdev or files where bdev_unmap_write_zeroes() returns true. In
>> other words, STATX_ATTR_WRITE_ZEROES_UNMAP and FALLOC_FL_WRITE_ZEROES
>> are not consistent, they are two independent features. Even if some
>> devices STATX_ATTR_WRITE_ZEROES_UNMAP are not set, users should still be
>> allowed to call fallcoate(FALLOC_FL_WRITE_ZEROES). This is because some
>> devices and drivers currently cannot reliably ascertain whether they
>> support the unmap write zero command; however, certain devices, such as
>> specific cloud storage devices, do support it. Users of these devices
>> may also wish to use FALLOC_FL_WRITE_ZEROES to expedite the zeroing
>> process.
> 
> What are those "cloud storage devices" where you set it reliably,
> i.e.g what drivers?

I don't have these 'cloud storage devices' now, but Ted had mentioned
those cloud-emulated block devices such as Google's Persistent Desk or
Amazon's Elastic Block Device in. I'm not sure if they can accurately
report the BLK_FEAT_WRITE_ZEROES_UNMAP feature, maybe Ted can give more
details.

https://lore.kernel.org/linux-fsdevel/20250106161732.GG1284777@mit.edu/

> 
>> Therefore, I think that the current point of
>> STATX_ATTR_WRITE_ZEROES_UNMAP (possibly STATX_WRITE_ZEROES_UNMAP) should
>> be to just indicate whether a bdev or file supports the unmap write zero
>> command (i.e., whether bdev_unmap_write_zeroes() returns true). If we
>> use standard SCSI and NVMe storage devices, and the
>> STATX_ATTR_WRITE_ZEROES_UNMAP attribute is set, users can be assured
>> that FALLOC_FL_WRITE_ZEROES is fast and can choose to use
>> fallocate(FALLOC_FL_WRITE_ZEROES) immediately.
> 
> That's breaking the abstracton again.  An attribute must say something
> about the specific file, not about some underlying semi-related feature.

OK.

> 
>> Would you prefer to make STATX_ATTR_WRITE_ZEROES_UNMAP and
>> FALLOC_FL_WRITE_ZEROES consistent, which means
>> fallcoate(FALLOC_FL_WRITE_ZEROES) will return -EOPNOTSUPP if the block
>> device doesn't set STATX_ATTR_WRITE_ZEROES_UNMAP ?
> 
> Not sure where the block device comes from here, both of these operate
> on a file.

I am referring to the block device on which the filesystem is mounted.
The support status of the file is directly dependent on this block
device.

> 
>> If so, I'd suggested we need to:
>> 1) Remove STATX_ATTR_WRITE_ZEROES_UNMAP since users can check the
>>    existence by calling fallocate(FALLOC_FL_WRITE_ZEROES) directly, this
>>    statx flag seems useless.
> 
> Yes, that was my inital thought.
> 
>> 2) Make the BLK_FEAT_WRITE_ZEROES_UNMAP sysfs interface to RW, allowing
>>    users to adjust the block device's support state according to the
>>    real situation.
> 
> No, it's a feature and not a flag.
> 

I am a bit confused about the feature and the flag, I checked the other
features, and it appears that features such as BLK_FEAT_ROTATIONAL allow
to be modified, is this flexibility due to historical reasons or for the
convenience of testing?

Think about this again, I suppose we should keep the
BLK_FEAT_WRITE_ZEROES_UNMAP as read-only and add a new flag,
BLK_FALG_WRITE_ZEROES_UNMAP_DISABLED, to disable the
FALLOC_FL_WRITE_ZEROES. Since the Write Zeroes does not guarantee
performance, and some devices may claim to support **UNMAP** Write Zeroes
but exhibit extremely slow write-zeroes speeds. Users may want be able to
disable it. Thoughts？

Thanks,
Yi.

Powered by blists - more mailing lists