Re: How's the nforce4 support in Linux?

[Indrek Kruusa <indrek.kruusa@tuleriit.ee>]

Jeff Garzik wrote:

> Indrek Kruusa wrote:
>
>> Jeff Garzik wrote:
>>
>>> Andi Kleen wrote:
>>>
>>>> Jeff Garzik <jgarzik@pobox.com> writes:
>>>>
>>>>> I won't disagree with your experiences.  For me, outside of one brief
>>>>> moment when the r8169 driver didn't work on Athlon64, it has worked
>>>>> flawlessly for me.
>>>>>
>>>>> RealTek 8169 is currently my favorite gigabit chip.
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> It does not seem to support DAC (or rather it breaks with DAC 
>>>> enabled), which makes it not very useful on any machine with >3GB 
>>>> of memory.
>>>
>>>
>>>
>>>
>>> Driver bug.  I can futz with it and get it to do 64-bit on my Athlon64.
>>
>>
>>
>>
>> Continuing with off-topic questions: is this "checksum off-load" 
>> usable with r8169? Is there any other reason (performance?) to use 
>> hardware TCP/IP checksumming than just "cool, a little chunk of 
>> software is hardwired again"?
>
>
> It's usable, and enables "zero copy" feature.
>
>
>> I have seen you mentioned that this causes mainly troubles if you try 
>> to set it with ethtool. Is it still true?
>
>
> Not sure what you are referring to.




Sorry  - my brains interpretation was classic rumor case: discussion I 
remembered was about broken NIC not about enabling hw checksum. I 
referred to this one:

http://www.ussg.iu.edu/hypermail/linux/kernel/0503.3/0369.html


Jeff Garzik wrote:

> Evgeniy Polyakov wrote:
>
>> Noone will complain on Linux if NIC is broken and produces wrong
>> checksum
>> and HW checksum offloading is enabled using ethtools.
>
>
>
> Actually, that is a problem and people have definitely complained 
> about it in the past.