Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Cisco Systems, Inc. (CSCO) -- Ignore unavailable to you. Want to Upgrade?

To: StockMan who wrote (12605)	2/22/1998 4:54:00 PM
From: Scott C. Lemon	Read Replies (2) \| Respond to of 77400

Hello Stockman, You stated: > That may very well be true, but if the lower layers form the > bottleneck, no amount of "intelligence" at higher layers can > alleviate that. The speed of the slowest link within the OSI model. So there are two ways to deal with the lower layer bottlenecks ... fix them by optimizing the routing and switching infrastructure ... or eliminate the need for lower layer routed and switched traffic. That is what the "higher layer" object routing does ... it replaces end-to-end packet routing with point-to-point object routing. In other words, if we can reduce the dependencies on packet routing and switching then we have reduced or eliminated the lower layer bottleneck. Scott C. Lemon

To: StockMan who wrote (12605)	2/26/1998 2:27:00 AM
From: Clare	Respond to of 77400

<<Re -- I believe the real solution will be routing at much higher layers than layer 3! That may very well be true, but if the lower layers form the bottleneck, no amount of "intelligence" at higher layers can alleviate that. The speed of the slowest link within the OSI model.>> Layer 4 switching only makes sense when you are dealing with priority and quality of service. Otherwise, why make any distinction between type of traffic? Think of intelligence at higher layers as the car pool lane. You may give priority to some, but if all lanes are full, you'll still get congestion. Increasing lower layer capacity and throughput is still high priority, no matter what fancy higher layer schemes come along.