Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 8 Nov 2022 09:00:49 -0500
From:   Stefan Hajnoczi <stefanha@redhat.com>
To:     Jens Axboe <axboe@kernel.dk>
Cc:     linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Subject: Re: [PATCHSET v3 0/5] Add support for epoll min_wait
Message-ID: <Y2phEZKYuSmPL5B5@fedora>
References: <Y2lw4Qc1uI+Ep+2C@fedora>
 <4281b354-d67d-2883-d966-a7816ed4f811@kernel.dk>
MIME-Version: 1.0
Content-Type: multipart/signed; micalg=pgp-sha256;
        protocol="application/pgp-signature"; boundary="hTnBuHsELfudnVi0"
Content-Disposition: inline
In-Reply-To: <4281b354-d67d-2883-d966-a7816ed4f811@kernel.dk>
Precedence: bulk


--hTnBuHsELfudnVi0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Mon, Nov 07, 2022 at 02:38:52PM -0700, Jens Axboe wrote:
> On 11/7/22 1:56 PM, Stefan Hajnoczi wrote:
> > Hi Jens,
> > NICs and storage controllers have interrupt mitigation/coalescing
> > mechanisms that are similar.
>=20
> Yep
>=20
> > NVMe has an Aggregation Time (timeout) and an Aggregation Threshold
> > (counter) value. When a completion occurs, the device waits until the
> > timeout or until the completion counter value is reached.
> >=20
> > If I've read the code correctly, min_wait is computed at the beginning
> > of epoll_wait(2). NVMe's Aggregation Time is computed from the first
> > completion.
> >=20
> > It makes me wonder which approach is more useful for applications. With
> > the Aggregation Time approach applications can control how much extra
> > latency is added. What do you think about that approach?
>=20
> We only tested the current approach, which is time noted from entry, not
> from when the first event arrives. I suspect the nvme approach is better
> suited to the hw side, the epoll timeout helps ensure that we batch
> within xx usec rather than xx usec + whatever the delay until the first
> one arrives. Which is why it's handled that way currently. That gives
> you a fixed batch latency.

min_wait is fine when the goal is just maximizing throughput without any
latency targets.

The min_wait approach makes it hard to set a useful upper bound on
latency because unlucky requests that complete early experience much
more latency than requests that complete later.

Stefan

--hTnBuHsELfudnVi0
Content-Type: application/pgp-signature; name="signature.asc"

-----BEGIN PGP SIGNATURE-----

iQEzBAEBCAAdFiEEhpWov9P5fNqsNXdanKSrs4Grc8gFAmNqYREACgkQnKSrs4Gr
c8j6IAgAm0QuhdsF3vs+1ncuRN5NYEZR5+zZERrQFEnMQhQmAHn/muP+4tm7MlIT
LTqG5r89ymGz+LSyEUPJ8T9NnoLBoyyrTtrz9TpCk9SICPO7jPgiPTMf69quEO6j
h0pRVntr50Q9neNYG5J+zErj9TYz6cO1qAwm3903cmGti1I8IM4fjKCN+cPQmqoJ
rkfmh4PKOYxfNLVmKjSrdlF47ouFpRV3mpIZYJbejmg0CzSPwZ1is2slHVptRhsX
6HhnxvExdDKsjFORf6boC/Z/YodUbAzdMo+9B6uZH9BEz52EXFK+Inn4Kan0yvT2
vbeMPMmnzuCjpKMv5E2VMClg0EtBZg==
=Bq7R
-----END PGP SIGNATURE-----

--hTnBuHsELfudnVi0--