Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 8 Aug 2016 16:01:20 +0200
From:      Ben RUBSON <ben.rubson@gmail.com>
To:        freebsd-net@freebsd.org
Subject:   Re: Unstable local network throughput
Message-ID:  <BD0B68D1-CDCD-4E09-AF22-34318B6CEAA7@gmail.com>
In-Reply-To: <5D6DF8EA-D9AA-4617-8561-2D7E22A738C3@gmail.com>
References:  <3C0D892F-2BE8-4650-B9FC-93C8EE0443E1@gmail.com> <bed13ae3-0b8f-b1af-7418-7bf1b9fc74bc@selasky.org> <3B164B7B-CBFB-4518-B57D-A96EABB71647@gmail.com> <5D6DF8EA-D9AA-4617-8561-2D7E22A738C3@gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help

> On 04 Aug 2016, at 11:40, Ben RUBSON <ben.rubson@gmail.com> wrote:
>=20
>=20
>> On 02 Aug 2016, at 22:11, Ben RUBSON <ben.rubson@gmail.com> wrote:
>>=20
>>> On 02 Aug 2016, at 21:35, Hans Petter Selasky <hps@selasky.org> =
wrote:
>>>=20
>>> The CX-3 driver doesn't bind the worker threads to specific CPU =
cores by default, so if your CPU has more than one so-called numa, =
you'll end up that the bottle-neck is the high-speed link between the =
CPU cores and not the card. A quick and dirty workaround is to "cpuset" =
iperf and the interrupt and taskqueue threads to specific CPU cores.
>>=20
>> My CPUs : 2x E5-2620v3 with DDR4@1866.
>=20
> OK, so I cpuset all Mellanox interrupts to one NUMA, as well as the =
iPerf processes, and I'm able to reach max bandwidth.
> Choosing the wrong NUMA (or both, or one for interrupts, the other one =
for iPerf, etc...) totally kills throughput.
>=20
> However, full-duplex throughput is still limited, I can't manage to =
reach 2x40Gb/s, throttle is at about 45Gb/s.
> I tried many different cpuset layouts, but I never went above 45Gb/s.
> (Linux allowed me to reach 2x40Gb/s so hardware is not a bottleneck)

OK, I then found a workaround.

In the motherboards' BIOS, I disabled the following option :
Advanced / ACPI Settings / NUMA

And I'm now able to go up to 2x40Gb/s !
I'm then even able to achieve this throughput without any cpuset !

Strange that Linux was able to deal with this setting, but I'm pretty =
sure production performance will be easier to maintain with only 1 NUMA.

Feel free to ask me if you want further testing with 2 NUMA.

Ben




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?BD0B68D1-CDCD-4E09-AF22-34318B6CEAA7>