Re: [PATCH v7 0/3] FDP and per-io hints

[Jens Axboe <axboe@kernel.dk>]

On 10/3/24 4:00 PM, Bart Van Assche wrote:
> On 10/3/24 2:48 PM, Keith Busch wrote:
>> The only "bonus" I have is not repeatedly explaining why people can't
>> use h/w features the way they want.
> 
> Hi Keith,
> 
> Although that's a fair argument, what are the use cases for this patch
> series? Filesystems in the kernel? Filesystems implemented in user
> space? Perhaps something else?
> 
> This patch series adds new a new user space interface for passing hints
> to storage devices (in io_uring). As we all know such interfaces are
> hard to remove once these have been added.

It's a _hint_, I'm not sure how many times that has to be stated. The
kernel is free to ignore it, and in the future, it may very well do
that. We already had fcntl interfaces for streams, in the same vein, and
we yanked those in the sense that they ended up doing _nothing_. Did
things break because of that? Of course not. This is no different.

> We don't need new user space interfaces to support FDP for filesystems
> in the kernel.
> 
> For filesystems implemented in user space, would using NVMe pass-through
> be a viable approach? With this approach, no new user space interfaces
> have to be added.
> 
> I'm wondering how to unblock FDP users without adding a new
> controversial mechanism in the kernel.

pass-through already works, obviously - this is more about adding a
viable real interface for it. If it's a feature that is in devices AND
customers want to use, then pointing them at pass-through is a cop-out.

-- 
Jens Axboe