From mboxrd@z Thu Jan  1 00:00:00 1970
Content-Type: multipart/mixed; boundary="===============2348470837522170945=="
MIME-Version: 1.0
From: Walker, Benjamin <benjamin.walker at intel.com>
Subject: Re: [SPDK] Problem with Blobstore when write 65MB continously
Date: Wed, 10 Jan 2018 16:32:58 +0000
Message-ID: <1515601977.6063.28.camel@intel.com>
In-Reply-To: 6CE0D7EB-15CC-44A2-888B-C283A1C54050@intel.com
List-ID: <spdk@lists.01.org>
To: spdk@lists.01.org

--===============2348470837522170945==
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable

On Wed, 2018-01-10 at 16:21 +0000, Harris, James R wrote:
> Hi Paul and Zhengyu,
> =

> The problem is that the app is not giving the block device a chance to
> complete any I/O while submitting the 520 back-to-back requests.  Blobsto=
re is
> passive here =E2=80=93 it does not do any polling on the block device =E2=
=80=93 that is up to
> the application.

To additionally clarify - the bdev layer will poll for completions on your
behalf, but it does so on the same thread that you are submitting I/O from.=
 If
you are in a tight loop submitting I/O and never yield back to the event
reactor, the polling won't have a chance to occur. You can either increase =
the
number of reqs per channel or submit smaller batches at a time. Basically, =
do
what Jim said below.

> Increasing the number of channel reqs would work =E2=80=93 but at some po=
int these
> will still run out.  So it really depends on your application =E2=80=93 e=
ither
> increase the channel reqs to the absolutely maximum you will ever need, o=
r add
> ENOMEM handling.
--===============2348470837522170945==--