Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 21 Oct 2013 11:52:51 +0300
From:      Andriy Kopystyansky <anri@polynet.lviv.ua>
To:        freebsd-net@freebsd.org
Subject:   Re: Intel 82580 lagg(4) problem
Message-ID:  <20131021115251.Horde.GEMc-A7kT55W11hnsIFv3g1@mail.polynet.lviv.ua>
In-Reply-To: <CAJ-VmonBsXjGGijkeMjE0nkimGGnZDfM0=JmzaNxiZk87mNhpA@mail.gmail.com>
References:  <20130930121027.Horde.taTEbLTlKvRSSUADQ3_q1_A@webmail.polynet.lviv.ua> <CAJ-Vmo=00SzCNtcKAxnQpWXdDi4CGo5=_u_Wpejt8SA0Dh=M%2Bw@mail.gmail.com> <BLU0-SMTP4326F14A3FD47A82C423723AE180@phx.gbl> <20131018112519.Horde.OAQo4gNXUK8BEHk3Ha0pIw2@mail.polynet.lviv.ua> <CAJ-Vmo=Z1pemHx0sHeG0BQtO2FDTn=LUzaK3qX%2BnxTNPavW1Uw@mail.gmail.com> <CAJ-VmonBsXjGGijkeMjE0nkimGGnZDfM0=JmzaNxiZk87mNhpA@mail.gmail.com>

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

Actually, it was <mybsd@hotmail.com> running FreeBSD 8.4 with driver  
from 8.3, and by his advise i'm using this driver on my FreeBSD 9.1.  
Native driver came with FreeBSD9.1, or the new one downloaded from  
Intel site (igb-2.3.10) seems to be useless in LACP lagg(4).

Цитую Adrian Chadd <adrian.chadd@gmail.com>:

> So.. Diff the driver between 8.3 and 8.4. What changed?
>
> Adrian
> On Oct 18, 2013 1:48 PM, "Adrian Chadd" <adrian@freebsd..org> wrote:
>
>> Oh wait a sec - you mean that you're running freebsd-8.4 but with the
>> freebsd-8.3 driver (and freebsd-8.4 lagg?)
>>
>>
>> -adrian
>>
>>
>>
>> On 18 October 2013 01:25, Andriy Kopystyansky <anri@polynet.lviv.ua>wrote:
>>
>>>
>>> Цитую mybsd <mybsd@hotmail.com>:
>>>
>>>
>>>  Set net.link.lagg.0.use_flowid=0 not solve the problem..
>>>>
>>>> My system is freebsd 8.4, use the e1000 driver from freebsd 8.3 solves
>>>> this problem .
>>>> Should confirm that the problem is driver
>>>>
>>>> I have already submitted the BUG.
>>>> http://www.freebsd.org/cgi/**query-pr.cgi?pr=182917<http://www.freebsd.org/cgi/query-pr.cgi?pr=182917>;
>>>>
>>>>
>>> I can confirm, e1000 driver from freebsd 8.3 works as expected, i've got
>>> almost 1.8 Gb/s over lagg(4) interface, whereas using default driver from
>>> 9.1 couldnt get more than 1.2Gb/s.
>>> Trying iperf test to two different dst:
>>> 1) [SUM]  0.0-54.5 sec  5.50 GBytes   867 Mbits/sec
>>> 2) [SUM]  0.0-90.1 sec  9.25 GBytes   882 Mbits/sec
>>>
>>> ifstat on lagg,igb using 8.3 driver:
>>> anri@host:[11:01]~#ifstat -i lagg1,igb0,igb2
>>>       lagg1                igb0                igb2
>>>
>>>  KB/s in  KB/s out   KB/s in  KB/s out   KB/s in  KB/s out
>>> 21748.67  221021.3  10419.36  122968.5  11442.13  150645.1
>>> 22010.81  222652.2  10954.49  125154.8  11161.90  150698.2
>>>
>>> Test above was performed with net.link.lagg.1.use_flowid=1
>>> Setting this to =0 leads to slightly less throughput, and noticable cpu
>>> overhead. (I havent any non-ip traffic).
>>>
>>> --
>>>
>>>
>>>
>>>
>>>
>>> ______________________________**_________________
>>> freebsd-net@freebsd.org mailing list
>>> http://lists.freebsd.org/**mailman/listinfo/freebsd-net<http://lists.freebsd.org/mailman/listinfo/freebsd-net>;
>>> To unsubscribe, send any mail to  
>>> "freebsd-net-unsubscribe@**freebsd.org<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?20131021115251.Horde.GEMc-A7kT55W11hnsIFv3g1>