Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 27 Mar 2017 13:30:34 -0400
From:      John Jasen <jjasen@gmail.com>
To:        Navdeep Parhar <np@FreeBSD.org>, "Caraballo-vega, Jordan A. (GSFC-6062)[COMPUTER SCIENCE CORP]" <jordancaraballo87@gmail.com>
Cc:        freebsd-net@freebsd.org, slw@zxy.spb.ru
Subject:   Re: bad throughput performance on multiple systems: Re: Fwd: Re: Disappointing packets-per-second performance results on a Dell,PE R530
Message-ID:  <06a0309b-8e5a-8857-4394-3a714d251cda@gmail.com>
In-Reply-To: <ba172cd1-8a09-f42b-91f4-fda51c4c4874@FreeBSD.org>
References:  <20170312231826.GV15630@zxy.spb.ru> <74654520-b8b6-6118-2e46-902a8ea107ac@gmail.com> <CAPFoGT9k4HfDCQ7wJPDFMTrJTtDyc9uK_ma9ubneDhVSsS-jcA@mail.gmail.com> <173fffac-7ae2-786a-66c0-e9cd7ab78f44@gmail.com> <CAPFoGT-BAMpj34wtB06dxMKk%2B87OEOs5-qu%2BRLVz=aPrhX6hDA@mail.gmail.com> <CAACLuR29xQhDWATRheBaOU2vtiYp61JgDKHaXum%2BU32MBDLBzw@mail.gmail.com> <20170317100814.GN70430@zxy.spb.ru> <9924b2d5-4a72-579c-96c6-4dbdacc07c95@gmail.com> <CAPFoGT8C1%2BZYDSFVGjCuT8v5%2B=izfXgHXEn5P2dqxAq6N6ypCA@mail.gmail.com> <9694e9f2-daec-924d-e9f6-7b22a634acb5@gmail.com> <20170318052837.GA21730@ox> <dbfa3693-3306-8bf8-1e9a-b305f8007239@gmail.com> <0a4e3073-bf5f-9bf8-533f-bd9ec3c0f60c@FreeBSD.org> <ae0fae6c-0ee9-4705-5360-3ffd99dbf817@gmail.com> <ba172cd1-8a09-f42b-91f4-fda51c4c4874@FreeBSD.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On 03/24/2017 08:51 PM, Navdeep Parhar wrote:

> On 03/24/2017 16:53, Caraballo-vega, Jordan A. (GSFC-6062)[COMPUTER
> SCIENCE CORP] wrote:
>> It looks like netmap is there; however, is there a way of figuring out
>> if netmap is being used?
>
> If you're not running netmap-fwd or some other netmap application,
> it's not being used.  You have just 1 txq/rxq and that would explain
> the difference between cxl and vcxl.

Using netmap-fwd, we seem to hover between 2.2m and 3.6m pps, depending
on luck and how many streams.

netmap-fwd does complain often about running out of tx rings and/or
buffer space during these runs.

CPU usage clocks in at about 10%-12% across CPUs engaged with a queue.

>
> # sysctl -a | grep tx_pause

Pause was enabled, but allegedly silent during the netmap tests.





Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?06a0309b-8e5a-8857-4394-3a714d251cda>