Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 16 Jul 2012 21:56:55 +0200
From:      Andre Oppermann <oppermann@networx.ch>
To:        Ihsan Junaidi Ibrahim <ihsan@grep.my>
Cc:        freebsd-net@freebsd.org, Jack Vogel <jfvogel@gmail.com>
Subject:   Re: Enable LRO by default on igb
Message-ID:  <50047207.8060004@networx.ch>
In-Reply-To: <0FF9D20C-4D88-484F-AEB9-E6F10094E018@grep.my>
References:  <3AC8C112-A80B-4D8F-89DA-DA38E4AB524F@grep.my> <CAFOYbcn6ETrNFGLBS1r46Jovr7p5QbdcuCKyheA_xw18GiYgtw@mail.gmail.com> <0FF9D20C-4D88-484F-AEB9-E6F10094E018@grep.my>

next in thread | previous in thread | raw e-mail | index | archive | help
On 13.07.2012 02:21, Ihsan Junaidi Ibrahim wrote:
> I did a quick file download test on the LRO-enabled device (forwarding is turned on) and there's
> no perceive drop-off in forwarding performance.

LRO must not be active on any interface when forwarding is enabled.
This has been fixed by bz@ in current and stable/9 within the LRO
code and is automatic.

The only remaining unhandled case is hardware-LRO where the driver
must tell the hardware to stop doing it.  Eventually we need an
eventhandler for that and hardware-LRO cards have to register with
it to get informed on changes there.

-- 
Andre

> The test is very unscientific (over the Internet) as I don't have access to a local test bed
> where I can do more in-depth testing.
>
> Sysctl LRO stats gave me these: dev.igb.0.queue0.lro_queued: 53 dev.igb.0.queue0.lro_flushed: 53
> dev.igb.0.queue1.lro_queued: 121 dev.igb.0.queue1.lro_flushed: 120 dev.igb.0.queue2.lro_queued:
> 14895 dev.igb.0.queue2.lro_flushed: 8200 dev.igb.0.queue3.lro_queued: 77
> dev.igb.0.queue3.lro_flushed: 76
>
> Just curious on why flushed and queued numbers did not seem to match.
>
> ihsan
>
> On Jul 8, 2012, at 12:26 AM, Jack Vogel wrote:
>
>> Because of problems with forwarding when it was turned on, however this has recently been fixed
>> supposedly, if someone using the driver in an environment with forwarding could verify that
>> there is no problem with it enabled I'd be happy to change it to be on by default.
>>
>> Jack
>>
>>
>> On Sat, Jul 7, 2012 at 9:01 AM, Ihsan Junaidi Ibrahim <ihsan@grep.my> wrote:
>>
>>> Hi folks,
>>>
>>> Just curious is there a reason why LRO isn't turned on by default for igb(4) like for other
>>> capabilities?
>>>
>>> I have a couple of 82575EB igb devices and LRO had to be turned on manually.
>>>
>>> Thanks._______________________________________________ freebsd-net@freebsd.org mailing list
>>> http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to
>>> "freebsd-net-unsubscribe@freebsd.org"
>>>
>> _______________________________________________ freebsd-net@freebsd.org mailing list
>> http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to
>> "freebsd-net-unsubscribe@freebsd.org"
>
> _______________________________________________ freebsd-net@freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to
> "freebsd-net-unsubscribe@freebsd.org"
>
>





Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?50047207.8060004>