If you use frames at your site, requests for the different frames will come from different IPs. Very difficult to load-balance effectively if you keep state on your servers.
Another load balancing issues comes from loading a helper app that loads a URL (like RealPlayer). The helper app may not use the AOL proxy servers, so it'll appear as a different IP address than the web client, and it probably won't support cookies.
Cisco has details on dealing with the "AOL problem" on its web site.
Also, don't pass very long query strings around--they'll chop 'em.
While I agree that SMP is becoming much more commonplace than it used to be, I don't see Apple's moves to sell SMP on its systems a portent of its (SMP's) widespread use. USB is a technology that is easier to use than its predecessors, and this fits with Apple's focus on simple interfaces and products that appeal to the mass-market. Selling SMP, on the other hand, I think is Apple's response to the growing and embarassing MHz differential between the G4 processors and the x86 processors.
For most desktops, I don't see SMP being all that beneficial, because people don't truly multitask that much. Having efficient multibranch execution in a single CPU I'm sure has much more apparent performance gains to the average user than having multiple CPUs would. In applications where increased parallelization is helpful--for example, 3D rendering--it's being added due to market demand for speed increases that would be difficult to meet otherwise.
I'm not sure continuing increases in MHz will be all that apparent to users except of demanding apps, though, since a 400-500MHz Celeron is plenty for office apps and the like. Intel will continue to up its clock rate, though, as long as it can demand a higher margin on its faster processors. Since Apple cannot compete with the G4 chips Motorola is producing, it must differentiate itself on other ways, including SMP. I've read (on Ars Technica, I think) that Apple is considering moving to the Altivec-less G5s from IBM, which have higher clock rates.
As for the use of SMP on high-end systems, yes, it's true it's being used here. When performance matters most, you must parallelize. But in servers, you get to amortize the higher cost of the boxes across multiple users--that's the point--so having multiple processors makes sense. This still doesn't mean that this will inevitably lead to SMP on the desktop.
I'm curious what Intel will do if the market for the biggest MHz number chips starts to slow down. Of course it can sell other products, but how will it maintain its margins? Will it be successful integrating things like 3D chipsets into a single, high-margin CPU?
Slashdot Mirror
Another load balancing issues comes from loading a helper app that loads a URL (like RealPlayer). The helper app may not use the AOL proxy servers, so it'll appear as a different IP address than the web client, and it probably won't support cookies.
Cisco has details on dealing with the "AOL problem" on its web site.
Also, don't pass very long query strings around--they'll chop 'em.
While I agree that SMP is becoming much more commonplace than it used to be, I don't see Apple's moves to sell SMP on its systems a portent of its (SMP's) widespread use. USB is a technology that is easier to use than its predecessors, and this fits with Apple's focus on simple interfaces and products that appeal to the mass-market. Selling SMP, on the other hand, I think is Apple's response to the growing and embarassing MHz differential between the G4 processors and the x86 processors.
For most desktops, I don't see SMP being all that beneficial, because people don't truly multitask that much. Having efficient multibranch execution in a single CPU I'm sure has much more apparent performance gains to the average user than having multiple CPUs would. In applications where increased parallelization is helpful--for example, 3D rendering--it's being added due to market demand for speed increases that would be difficult to meet otherwise.
I'm not sure continuing increases in MHz will be all that apparent to users except of demanding apps, though, since a 400-500MHz Celeron is plenty for office apps and the like. Intel will continue to up its clock rate, though, as long as it can demand a higher margin on its faster processors. Since Apple cannot compete with the G4 chips Motorola is producing, it must differentiate itself on other ways, including SMP. I've read (on Ars Technica, I think) that Apple is considering moving to the Altivec-less G5s from IBM, which have higher clock rates.
As for the use of SMP on high-end systems, yes, it's true it's being used here. When performance matters most, you must parallelize. But in servers, you get to amortize the higher cost of the boxes across multiple users--that's the point--so having multiple processors makes sense. This still doesn't mean that this will inevitably lead to SMP on the desktop.
I'm curious what Intel will do if the market for the biggest MHz number chips starts to slow down. Of course it can sell other products, but how will it maintain its margins? Will it be successful integrating things like 3D chipsets into a single, high-margin CPU?