[snip lots]AFAIK this actually happened ages ago. So there's no real reason to trot this out now unless people are griping that GEN3 isn't doing much for them.
ICTS has implemented Packeteer Packetshaper
[snip lots more]
And there's no mention of what will happen once:
- UCT transitions to SANReN and has a 10 Gbps link to the local node, and
- TENET moves to the 10 Gbps overseas pipe due mid-2009
Consider this paper on web search clickstreams http://doi.acm.org/10.1145/1177080.1177110]:
The MWN [Munich Scientific Network] provides a 10Gbit/s singly-homed Internet connection to roughly 50,000 hosts at two major universities along with additional institutes; link utilization is typically only around 200–500 Mbit/s in each direction.Now this might have been back in 2006; it doesn't really matter if the traffic demand has doubled since then. Also, since major local and international peering will then be in effect, actual transit pressure should decrease.
C'mon ICTS - plan ahead now!
2 comments:
Firstly, the Packeteer already cost mega $$$, and I'd be surprised to see it handle > 100Mbps. There is a reason why large networks don't shape traffic - it costs a fortune.
UCT's internal infrastructure probably can't sink 10GBps right now. I think the inter-campus backbone is only about 5x1Gbps.
Also, UCT's firewall infrastructure won't be able to handle much more than it does now, never mind 10Gbps. They are looking at equipment that can do multi-Gbps (millions of ZAR). Again, there is a reason why large networks don't have firewalls. You put your firewalls on the end host, or near the end host where the traffic is light and the potential for problems is minimised.
I agree with you: hmph. And that article read like a press release. journalism--
UCT internal infrastructure will need to start sinking multi Gbps soon, especially for Physics and Electrical Engineering work on KAT / SKA, in addition to the new collider experiments.
The original document for the new campus network touted the ability to upgrade the campus backbone to 10 Gbps links as necessary (with no mention of cost...).
Maybe some cheap [Open|Free]BSD + pf/CARP clusters located closer to the end users (e.g. within each building) would scale a bit better.
Journalism? I've heard of it...
Post a Comment