From mboxrd@z Thu Jan  1 00:00:00 1970
From: Sambath Kumar Balasubramanian <sambath.balasubramanian-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Subject: Re: Question on the Ring Library
Date: Wed, 4 Dec 2013 13:49:12 -0800
Message-ID: <CAPrcauNOJ8iUc5iiFsqik27c5Zm_1tKX+WsO3-=AC_r79TGf-A@mail.gmail.com>
References: <CAPrcauPLZrC5ve4ZX47de5JzT8fSDi6Za3Oe2wKKLpKNTuc6_g@mail.gmail.com>
 <03b201cef0f7$5fba0d20$1f2e2760$@com>
 <CAPrcauMiBS=T8p9bd1w9_DsGoke7VY2xk=fhDXvPf_YEMrzVHQ@mail.gmail.com>
 <03ee01cef12b$c56d85a0$504890e0$@com>
Mime-Version: 1.0
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: quoted-printable
Cc: "dev-VfR2kkLFssw@public.gmane.org" <dev-VfR2kkLFssw@public.gmane.org>
To: =?ISO-8859-1?Q?Fran=E7ois=2DFr=E9d=E9ric_Ozog?= <ff-SpBG2i6TTxU@public.gmane.org>
Return-path: <dev-bounces-VfR2kkLFssw@public.gmane.org>
In-Reply-To: <03ee01cef12b$c56d85a0$504890e0$@com>
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev-VfR2kkLFssw@public.gmane.org>
List-Help: <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=subscribe>
Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org
Sender: "dev" <dev-bounces-VfR2kkLFssw@public.gmane.org>

Thanks Fran=E7ois-Fr=E9d=E9ric. Trying to embark on a small prototype and s=
ee the
results. Thanks for the timing data. Really helpful.

Regards,
Sambath


On Wed, Dec 4, 2013 at 12:02 PM, Fran=E7ois-Fr=E9d=E9ric Ozog <ff-SpBG2i6TTxU@public.gmane.org>=
 wrote:

> You are welcome !
>
>
>
> Even if you insert packets in batch into a fifo, the mutex is still
> unpredictable. If one pthread_lock costs 1ms, you are going to lose
> packets, regardless of the number of RSS queues and ring sizes=85 Batchin=
g
> comes with another issue: need to flush a batch after a certain timeout i=
f
> you do not have packets. Userland timer resolution is such that you are
> introducing port to port latency quite a lot: DPDK native, you can manage
> to get a 2=B5s latency (including PCI express), while with batch it may b=
e
> 1ms=85 You may find smarter algorithms but still you will be an order of
> magnitude higher than DPDK.
>
>
>
> Hope this helps.
>
>
>
> Fran=E7ois-Fr=E9d=E9ric
>
>
>
> *De :* Sambath Kumar Balasubramanian [mailto:
> sambath.balasubramanian-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org]
> *Envoy=E9 :* mercredi 4 d=E9cembre 2013 15:01
> *=C0 :* Fran=E7ois-Fr=E9d=E9ric Ozog
> *Cc :* dev-VfR2kkLFssw@public.gmane.org
> *Objet :* Re: [dpdk-dev] Question on the Ring Library
>
>
>
> Thanks Fran=E7ois-Fr=E9d=E9ric. That puts real good perspective on the co=
st for
> the vent assuming each packet in the fast will result
>
> in an event. If event rate is orders of magnitude less than the packet
> rate, then I guess we can still achieve 10G since the "extra cost" will b=
e
> in the event thread and not in the fast path thread.
>
>
>
> Regards,
>
> Sambath
>