[PATCH v6 00/10] block atomic writes

[Kent Overstreet]

On Thu, Mar 28, 2024 at 07:31:45AM +1100, Dave Chinner wrote:
> On Wed, Mar 27, 2024 at 03:50:07AM +0000, Matthew Wilcox wrote:
> > On Tue, Mar 26, 2024 at 01:38:03PM +0000, John Garry wrote:
> > > The goal here is to provide an interface that allows applications use
> > > application-specific block sizes larger than logical block size
> > > reported by the storage device or larger than filesystem block size as
> > > reported by stat().
> > > 
> > > With this new interface, application blocks will never be torn or
> > > fractured when written. For a power fail, for each individual application
> > > block, all or none of the data to be written. A racing atomic write and
> > > read will mean that the read sees all the old data or all the new data,
> > > but never a mix of old and new.
> > > 
> > > Three new fields are added to struct statx - atomic_write_unit_min,
> > > atomic_write_unit_max, and atomic_write_segments_max. For each atomic
> > > individual write, the total length of a write must be a between
> > > atomic_write_unit_min and atomic_write_unit_max, inclusive, and a
> > > power-of-2. The write must also be at a natural offset in the file
> > > wrt the write length. For pwritev2, iovcnt is limited by
> > > atomic_write_segments_max.
> > > 
> > > There has been some discussion on supporting buffered IO and whether the
> > > API is suitable, like:
> > > https://lore.kernel.org/linux-nvme/ZeembVG-ygFal6Eb@casper.infradead.org/
> > > 
> > > Specifically the concern is that supporting a range of sizes of atomic IO
> > > in the pagecache is complex to support. For this, my idea is that FSes can
> > > fix atomic_write_unit_min and atomic_write_unit_max at the same size, the
> > > extent alignment size, which should be easier to support. We may need to
> > > implement O_ATOMIC to avoid mixing atomic and non-atomic IOs for this. I
> > > have no proposed solution for atomic write buffered IO for bdev file
> > > operations, but I know of no requirement for this.
> > 
> > The thing is that there's no requirement for an interface as complex as
> > the one you're proposing here.  I've talked to a few database people
> > and all they want is to increase the untorn write boundary from "one
> > disc block" to one database block, typically 8kB or 16kB.
> > 
> > So they would be quite happy with a much simpler interface where they
> > set the inode block size at inode creation time, and then all writes to
> > that inode were guaranteed to be untorn.  This would also be simpler to
> > implement for buffered writes.
> 
> You're conflating filesystem functionality that applications will use
> with hardware and block-layer enablement that filesystems and
> filesystem utilities need to configure the filesystem in ways that
> allow users to make use of atomic write capability of the hardware.
> 
> The block layer functionality needs to export everything that the
> hardware can do and filesystems will make use of. The actual
> application usage and setup of atomic writes at the filesystem/page
> cache layer is a separate problem.  i.e. The block layer interfaces
> need only support direct IO and expose limits for issuing atomic
> direct IO, and nothing more. All the more complex stuff to make it
> "easy to use" is filesystem level functionality and completely
> outside the scope of this patchset....

A CoW filesystem can implement atomic writes without any block device
support. It seems to me that might have been the easier place to start -
start by getting the APIs right, then do all the plumbing for efficient
untorn writes on non CoW filesystems...