Which brings us back to my original point - the larger frame sizes available
in standard token ring allows the technology to exceed Ethernet performance
even if one bothers to implement Jumbo Frames technology.
-----Original Message-----
From: Alan Cox [mailto:[EMAIL PROTECTED]]
Sent: Friday, November 19, 1999 11:18 AM
To: [EMAIL PROTECTED]
Cc: [EMAIL PROTECTED]; [EMAIL PROTECTED]
Subject: Re: What is better?
> What Ethernet standard or even non-standard practice allows for the
> transmission of frames larger than 8K? My understanding is that "Jumbo
> Frames" is the only other initiative to address this issue. Am I missing
> something big???
The jumbo frame stuff takes you to 8 or 9K. That gets the acenic driver
using a fair percentage of the bandwidth.
> Regarding CPU utilization, I have seen the effects of gig Ethernet on CPU
> utilization in a lab environment where we literally pound the server with
> packets (ttcp, Chariot as test tools) and it isn't pretty! I'm not sure
what
I bet it isnt. But for the data rate the only thing you are likely to get
that is more efficient for bulk transfer and even vaguely commodity is
HIPPI (64K mtu)
-
To unsubscribe from this list: send the line "unsubscribe linux-net" in
the body of a message to [EMAIL PROTECTED]
-
To unsubscribe from this list: send the line "unsubscribe linux-net" in
the body of a message to [EMAIL PROTECTED]
