[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250506054722.GA28781@lst.de>
Date: Tue, 6 May 2025 07:47:22 +0200
From: Christoph Hellwig <hch@....de>
To: "Darrick J. Wong" <djwong@...nel.org>
Cc: Christoph Hellwig <hch@....de>, Zhang Yi <yi.zhang@...weicloud.com>,
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 Mon, May 05, 2025 at 10:36:54PM -0700, Darrick J. Wong wrote:
> I think STATX_* (i.e. not STATX_ATTR_*) flags have two purposes: 1) to
> declare that specific fields in struct statx actually have meaning, most
> notably in scenarios where zeroes are valid field contents; and 2) if
> filling out the field is expensive, userspace can elect not to have it
> filled by leaving the bit unset. I don't know how userspace is supposed
> to figure out which fields are expensive.
Yes.
> (I'm confused about the whole premise of /this/ patch -- it's a "fast
> zeroing" fallocate flag that causes the *device* to unmap, so that the
> filesystem can preallocate and avoid unwritten extent conversions?
Yes.
> What happens if the block device is thinp and it runs out of space?
> That seems antithetical to fallocate...)
While the origin posix_fallocate was about space preallocatіon, these
days fallocate seems to be more about extent layout and/or fast
zeroing.
I'm not a huge fan of either this or the hardware atomics as they
force a FTL layer world view which is quite ingrained but also
rather stupid, but some folks really want to go down there full
throttle, so..
Powered by blists - more mailing lists