|
Posted by Walter Roberson on October 2, 2006, 11:12 am
If you were Registered and logged in, you could reply and use other advanced thread options
>This is a general switch architecture question. Let's say there are 2
>workstations communicating with a server. All three nodes are using gigabit
>NICs and they're connected to a gigabit switch. Workstation A can send data
>to the server at 35MB/s when only workstation A is sending. Likewise
>workstation B can send data to the server at 35MB/s when only workstation B
>is sending. When both workstation A & workstation B send data to the server
>simultaneously however, the transfer rate for both drops to about 6MB/s.
Sounds like a duplex mismatch.
>The 6MB/s figure seems to me to be well below the rate that it should be.
>What is typical transfer rate one should expect in this scenario?
"gigabit NICs" and "gigabit switch" doesn't tell us anything about the
real throughput capacities of the PCs or of the switch. You can put
a gigabit interface onto a tin-can telephone, if you have a way of
dealing with the buffering.
>Also what
>woud be a likely cause of such a dramatic decrease in performance like this?
>(Assume that the workstations and server are not to blame for the
>bottleneck) Would the switch buffers be to blame? If the switch is doing
>store-and-forward as opposed to cut-through processing, could that be a
>factor?
Very few full-duplex switches do cut-through: cut-through does not
work when you have differences in rates between ports, and cut-through
does not support multicast (or ARP broadcasts) unless it -happens-
that all the output port queues are empty. Cut-through also doesn't
work with priority queuing, or packet filtering or rate shaping.
Cut-through is effectively a thing of the past.
Overflowing a switch's buffers is possible but when you get that big
of a difference in speeds, the reason is almost always duplex mismatches.
| 
NewsGroups 
Yahoo! 
Google 
Windows Live 
del.icio.us 
digg 
Netscape 
XML site map