Re: [RFC PATCH] Introduce generalized data temperature estimation framework

[Hans Holmberg <hans@owltronix.com>]

On Thu, Jan 30, 2025 at 7:31 PM Viacheslav Dubeyko
<Slava.Dubeyko@ibm.com> wrote:
>
> On Wed, 2025-01-29 at 11:23 +0100, Hans Holmberg wrote:
> > On Tue, Jan 28, 2025 at 11:31 PM Viacheslav Dubeyko
> > <Slava.Dubeyko@ibm.com> wrote:
> > >
> > >
>
> <skipped>
>
> > > >
> > >
> > > Another trouble here. What is the way to measure write amplification, from your
> > > point of view? Which benchmarking tool or framework do you suggest for write
> > > amplification estimation?
> >
> > FDP drives expose this information. You can retrieve the stats using
> > the nvme cli.
>
> Do you mean that FDP drives has some additional info in S.M.A.R.T subsystem?
> Does it some special subsystem in FDP drives? Is it regular statistics or some
> debug feature of the device?

It's mandatory for FDP drives.

The "nvme fdp stats" nvme-cli command will report host and media bytes written,
and you can calculate write amplification based on that.


>
> > If you are using zoned storage, you can add write amp metrics inside
> > the file system
> > or just measure the amount of blocks written to the device using iostat.
> >
>
> I see the point with iostat or blktrace, for example. But what do you imply by
> adding write amp metric inside the file system? Especially, if you are
> mentioning zoned storage. What is the difference here between conventional and
> zoned storage devices?

Since garbage collection happens on the host side for zoned storage, you have to
measure the write amp there. It would be convenient to have the write
amp statistics
in the file system for this case (otherwise you have to count user
writes and device
writes through some other method). It adds some overhead though.

Cheers,
Hans