Piotr Jasiukajtis wrote:
On Thu, Jul 17, 2008 at 2:20 PM, James Carlson <[EMAIL PROTECTED]> wrote:
Piotr Jasiukajtis writes:
On Thu, Jul 17, 2008 at 1:26 PM, James Carlson <[EMAIL PROTECTED]> wrote:
Piotr Jasiukajtis writes:
Any news on this?
The original problem posted sounds to me like an MTU problem on the
poster's network, but I don't see that there's been any serious
analysis or testing done (or that it affects other users).
I confirm that this is an MTU issue.
With lower MTU my e1000g NIC works well.
Oddly, I've got three different x86 systems (two Ultra 24s and one
custom-built Tyan 2882) that all have e1000g interfaces in them, all
running 91 or higher, and none with the described problem.
I think there has to be something more to the recipe.
Maybe something with e1000g on lenovo's laptops?
e1000g is a generic driver for lots of intel chipsets. As we are
learning in the performance work not all of them behave the same, in
case of e1000g you really have to look at the chipset to make any
comparison.
Rao.
_______________________________________________
networking-discuss mailing list
[email protected]
