[snip]
Python is a real CPU sponge, and for this kind of load I'd definitely bump the horsepower up to a dual Pentium III Xeon 500MHz, 512KB L2 cache. Around $1100 per CPU. That said, however, I don't know how well Linux scales to two CPUs; for web serving, recent benchmarks have pointed out that it doesn't scale well at all.
Cough, cough. Are you referring to the Mindcraft benchmarks? They didn't cover *dynamic* websites at all, I think, and definitely they didn't benchmark Zope. Also for static pages, Linux scales well enough to drown most network connections anyway.
Secondarily Mindcraft (the second round), primarily a recent ZDNet benchmark published in, iirc, PC Magazine. So it was testing Stronghold -- the commercial distribution of Apache -- but in the end, NT proved to scale a lot better. Linux is a great server OS (except on API level and wrt kernel services, imho, but that's just me), but it does not scale very well *just* yet. [snip]
But indeed RAM is the biggest bottleneck of these all.
Not necessarily. RAM is significant for large databases requiring fast response times. A good rule of thumb (if you're in an "enterprise", to wit) is to have as much RAM as the size of database. Disk swapping is the enemy of database performance.
Multiple-port or multiple network cards. Multiport NICs support port failover and typically come with load balancing. Coupled with one or more switches, these are real killers when it comes to bandwidth and responsiveness.
This sounds like way overkill.
2000 networked PCs and one server. Unless your users just spend all day surfing the net, you have a saturated segment right there. Where's the overkill?
I'm no hardware guy, but to support this you'd need a couple of fulltime engineers and some OS extensions, I'd think. :)
Why? I thought Linux had multiport NIC support in the box.
Perhaps the best option is to try it out on a reasonable system first. If it gets too slow later (usage first has to pick up a lot, too, internally, this takes time), you can always upgrade the RAM, or switch to a more powerful system. Prices of these systems will have come down too in the mean time. All in all you might end up spending less money going this route than buying a possibly overpowered system now.
Wise words, but another good rule is: "Don't underspend". Match your investment with your requirements, and research carefully.
Regards,
Martijn
-- Alexander Staubo http://www.mop.no/~alex/ "QED?" said Russell. "It's Latin," said Morgan. "It means, 'So there you bastard'." --Robert Rankin, _Nostramadus Ate My Hamster_
Alexander Staubo wrote: [Linux scalability discussion] The issue I was raising was that Linux may very well scale *well enough* for dynamic web pages. But I'm no hardware guy or OS guy at all, actually. :)
[snip]
But indeed RAM is the biggest bottleneck of these all.
Not necessarily. RAM is significant for large databases requiring fast response times. A good rule of thumb (if you're in an "enterprise", to wit) is to have as much RAM as the size of database. Disk swapping is the enemy of database performance.
I'm influenced by being on a Linux box with 32 megs (local netscape, local Zope). Zope functions fine, but netscape leaks memory like crazy and causes Zope to swap out (or parts of itself), which slows response times. :) So memory is *my* biggest bottleneck, sorry. :)
Multiple-port or multiple network cards. Multiport NICs support port failover and typically come with load balancing. Coupled with one or more switches, these are real killers when it comes to bandwidth and responsiveness.
This sounds like way overkill. [debate on whether it is]
I'm no hardware guy, so you may well be right. Let others do this debate. :)
Perhaps the best option is to try it out on a reasonable system first. If it gets too slow later (usage first has to pick up a lot, too, internally, this takes time), you can always upgrade the RAM, or switch to a more powerful system. Prices of these systems will have come down too in the mean time. All in all you might end up spending less money going this route than buying a possibly overpowered system now.
Wise words, but another good rule is: "Don't underspend". Match your investment with your requirements, and research carefully.
Well, they're still wise words, so that's where our agreement lies. :) There just isn't enough data yet about Zope hardware requirements, I think, to give a good answer (though of course you may answer the relational database story). Regards, Martijn
participants (2)
-
Alexander Staubo -
Martijn Faassen