Skip to contentSkip to conversation

How's the nforce4 support in Linux?

DISCUSSION Asfand Yar Qazi 8 participants 13 messages Mar 24, 2005 – Mar 30, 2005

lore
Share & tools
lore
#0 lore raw

Hi,

I'm currently contemplating going for an Athlon 64 system. However, I'll primarily be using a Linux-based OS (Gentoo, namely), so I need to know how well the chipsets are supported currently.

I'd really like to go Via - but the crummy KT890 / VT8237 combo sucks - mainly due to the lack of SATA II with NCQ. I share the sentiments of the person in a post in the AnandTech forums (http://tinyurl.com/6d9bx) who says:

"The feature set on the K8T890 sucks. It was supposed to use the VT8251 southbridge, bringing SATA-II/NCQ, HD Audio, etc. Unfortunately, this southbridge has since dissappeared off the face of the earth, and all the current K8T890 boards use the old VT8237. nForce4, on the other hand, has SATA-II/NCQ, hardware firewall, nice software overclocking/monitoring tools (ntune), gigabit lan, etc. On top of that, performance and overclocking is pretty damn good. I was at one point looking forward to the K8T890, but considering how much of a joke the whole product line has been (lacking features, months of delays with no explanation, lack of any variety of retail boards), I have to say I'd avoid it like the plague."

NForce4 Ultra is brilliant - in many ways. Except it requires binary drivers, which I really don't want to use. And apparently, the hardware firewall seems to restrict bandwidth a bit. And even when its off, external chips that end up being faster (http://tinyurl.com/4zssp)

So, I'm wondering, are my assumptions correct? Do I have to use binary drivers to make absolutely full use of the Nforce4 chipset? Or is there sufficient support for me to make use of the features on it without using binary drivers?

Sorry for asking something that may have been asked before, but I've tried searching several times through the mailing list and on a search engine, but have had little luck.

Thanks,
Asfand Yar

p.s. Here's something for the search engines to latch on to, so this post and any repies are easier to find: via nvidia nforce4 nforce 4 kt890 kt 890 vt8237 comparison feature set supported compatibility binary drivers

#1 lore raw
Quoted 11 lines · Asfand Yar Qazi

Hi,

I'm currently contemplating going for an Athlon 64 system. However, I'll primarily be using a Linux-based OS (Gentoo, namely), so I need to know how well the chipsets are supported currently.

I'd really like to go Via - but the crummy KT890 / VT8237 combo sucks
- mainly due to the lack of SATA II with NCQ. I share the sentiments of the person in a post in the AnandTech forums
(http://tinyurl.com/6d9bx) who says:

Quoted 11 lines

"The feature set on the K8T890 sucks. It was supposed to use the VT8251 southbridge, bringing SATA-II/NCQ, HD Audio, etc. Unfortunately, this southbridge has since dissappeared off the face of the earth, and all the current K8T890 boards use the old VT8237. nForce4, on the other hand, has SATA-II/NCQ, hardware firewall, nice software overclocking/monitoring tools (ntune), gigabit lan, etc. On top of that, performance and overclocking is pretty damn good. I was at one point looking forward to the K8T890, but considering how much of a joke the whole product line has been (lacking features, months of delays with no explanation, lack of any variety of retail boards), I have to say I'd avoid it like the plague."

Well, let's cut through the B.S. ;-)

* Even when the SATA core is updated to support NCQ, nForce will not support it under Linux. No hardware info.

* "hardware firewall" -- sounds silly. Pretty sure Linux doesn't support it in any case.

* overclocking -- overclockers are always playing with fire. any overclocked hardware is suspect and unsupportable.

* via comes with gigabit lan these days. My own VIA-based Athlon64 system comes with r8169 gigabit.

Jeff

#2 lore raw
Quoted 5 lines

* "hardware firewall" -- sounds silly. Pretty sure Linux doesn't support it in any case.

probably just one of those things implemented in the binary drivers in software, just like the "hardware" IDE raid is most of the time (3ware being the positive exception there)

#3 lore raw
Quoted 10 lines · Arjan van de Ven
Quoted 5 lines

* "hardware firewall" -- sounds silly. Pretty sure Linux doesn't support it in any case.

probably just one of those things implemented in the binary drivers in software, just like the "hardware" IDE raid is most of the time (3ware being the positive exception there)

Incorrect. While the logic is is almost certainly implemented in the drivers, there is silicon acceleration of the functionality built into the Nforce4 chipset (unlike the nforce3), and requires almost no CPU time to do its job. Nvidia calls this chipset support ActiveArmor.

-Tupshin

#4 lore raw
In reply to Jeff Garzik
Quoted 4 lines · Jeff Garzik

Well, let's cut through the B.S. ;-)

* Even when the SATA core is updated to support NCQ, nForce will not support it under Linux. No hardware info.

Hmm, either that or someone will figure it out anyhow, like they did with forcedeth. Would be nice if nvidia would realize just how dumb not releasing programing specs is. How can that be considered a secret. Maybe they just have a company wide policy of "release nothing" rather than "don't release the clever 3D acceleration in our drivers that ATI can't have". Some comapnies just don't seem to realize they are in the business of _selling_ hardware, not hardware interface specifications.

Quoted 8 lines

* "hardware firewall" -- sounds silly. Pretty sure Linux doesn't support it in any case.

* overclocking -- overclockers are always playing with fire. any overclocked hardware is suspect and unsupportable.

* via comes with gigabit lan these days. My own VIA-based Athlon64 system comes with r8169 gigabit.

I think the r8139 has ruined realtek for me forever. I like the Marvell Yukon chip Asus includes on many boards (although some people have reported problems with some Asus boards using them with Linux).

Len Sorensen

#5 lore raw
Quoted 3 lines · Lennart Sorensen

I think the r8139 has ruined realtek for me forever. I like the Marvell Yukon chip Asus includes on many boards (although some people have reported problems with some Asus boards using them with Linux).

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.

WRT Marvell Yukon, make sure it is not the Yukon2. Yukon2 isn't supported by any driver in the kernel, presently.

Jeff

#6 lore raw
Quoted 6 lines · Jeff Garzik

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.

-Andi

#7 lore raw
Quoted 10 lines · Andi Kleen
Quoted 5 lines · Jeff Garzik

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.

Jeff

#8 lore raw
Quoted 8 lines · Jeff Garzik
Quoted 6 lines · Andi Kleen
Quoted 4 lines · Jeff Garzik

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.

Quoted 8 lines
Quoted 5 lines
Quoted 1 line

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"? I have seen you mentioned that this causes mainly troubles if you try to set it with ethtool. Is it still true?

Indrek

#9 lore raw
Quoted 19 lines · Indrek Kruusa
Quoted 17 lines · Jeff Garzik
Quoted 12 lines · Andi Kleen
Quoted 5 lines · Jeff Garzik

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.

Quoted 5 lines
Quoted 1 line

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.

Quoted 1 line

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.

Jeff

#10 lore raw
Quoted 31 lines · Jeff Garzik
Quoted 21 lines · Indrek Kruusa
Quoted 19 lines · Jeff Garzik
Quoted 13 lines · Andi Kleen
Quoted 5 lines · Jeff Garzik

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.

Quoted 6 lines
Quoted 1 line

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"?

Quoted 7 lines

It's usable, and enables "zero copy" feature.

Quoted 1 line

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

Quoted 9 lines · Jeff Garzik
Quoted 3 lines · Evgeniy Polyakov

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.

#11 lore raw
In reply to Jeff Garzik

Jeff Garzik <[email protected]> :

Quoted 1 line

Andi Kleen wrote:

[r8169 driver]

Quoted 4 lines
Quoted 2 lines

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.

Care to send a patch ?

--
Ueimor

#12 lore raw
Quoted 4 lines · Francois Romieu

Jeff Garzik <[email protected]> :

Quoted 1 line

Andi Kleen wrote:

Quoted 8 lines

[r8169 driver]

Quoted 3 lines
Quoted 1 line

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.

Care to send a patch ?

Not globally applicable, judging from the reports :(

Jeff