From mboxrd@z Thu Jan  1 00:00:00 1970
Content-Type: multipart/mixed; boundary="===============3696212379269309704=="
MIME-Version: 1.0
From: Walker, Benjamin <benjamin.walker at intel.com>
Subject: Re: [SPDK] SPDK + user space appliance
Date: Fri, 19 Jan 2018 17:28:38 +0000
Message-ID: <1516382916.25907.15.camel@intel.com>
In-Reply-To: AM5PR04MB307489E0EB9C162E7F761E3D89150@AM5PR04MB3074.eurprd04.prod.outlook.com
List-ID: <spdk@lists.01.org>
To: spdk@lists.01.org

--===============3696212379269309704==
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable

On Sun, 2018-01-14 at 09:09 +0000, Shahar Salzman wrote:
> We have been integrating spdk into our system using a blockdev module,
> currently only a POC version.
> Our use case is a user space appliance processing IOs, with an SPDK front=
end
> to do the NVMeF.
> =

> Currently all of the user bdevs are created via configuration file, but w=
e are
> working to add functions + rpc's which allow creation/deletion of these
> namespaces.

Ok - so you have our NVMe-oF target in front and it routes I/Os to your sys=
tem
via a custom bdev module that you wrote. This is exactly how we intended fo=
r you
to use it, so it looks good to me.

> IO is sent to user space via callback, implementation is up to user space=
, but
> obviously the longer it lingers there the lower the performance, we use a=
 set
> of rings + threads processing them, so that the time spent in the applian=
ce is
> minimal.
> Going back from user space we use a single ring (multiple producers single
> consumer) onto which the completions are inserted, and the ring poll func=
tion
> is registered with spdk core (spdk_poller_register).

What do you mean by I/O is sent to user space via callback? When was the I/O
ever in kernel space? Is your storage system running in the kernel?

--===============3696212379269309704==--