Each with 1gig of RAM. Which one would do better for web servers and game servers? Your opinion?

I would get the Dual P3 over a single P4. You will be able to handle a larger load with everything spread through two processors :)

Ditto, Dual P3 :D

Definately the dual. If it has one processor, it's just a computer, not a server! :D

What about Dual P3 850mhz vs. P4 2.0ghz... which is better? (im a n00b)

I would still pick the Dual P3, however the more the better :D

Definately depends on what you're doing with the server. You should probably keep in mind that the p3 850 is probably a 256k cache rather than a 512, which makes a huge difference. If that were the case, I might go for the p4.

I'd still get the dual P3s

yeah, I probably would too...lol

I would go with dual rather than P4

Dual is my opinion also

There isn't a P3 in a 1.3Ghz model - but either the 1.26 or 1.4 model will smoke a P4 when run in a dual configuration, and will give a P4 a good run for it's money as a single processor too. We run some dual P3 1.4Ghz's and they fly - highly recommended.

At least matt does his homework..

** Now tonight boys and girls i want you to tell me if their is such a thing as a DUAL P4 **

I will be marking the work tomorrow :D

what about dual p4's? or Athlon MP's? If you're running a game server , lets say counterstrike , it will only make use of one processor . Now if you have multiple games running on one server , it will utilize more then one cpu . As far as webhosting is concerned , what will you be serving , and what is your best estimate of the load you will be putting on the cpu(s) . I think more information is needed in order to make a realistic decision .

Dual P3 1.26s over P4 2.0Ghz any day of the year, the Tualatins give P4s at higher clock speed a serious run for their money even with single CPU, in dual they just outclass a single P4 no end.

LOL

all this talk dual, p3 , single p4...

Did you guys forget the XEON ?

I wold get a (1) Xeon p4 2.0 rather than a dual p3 our a p4 :)


PS : I loved the UCG that they put...

Dual XEON 2.4 Gz - 1 Gb ram - 160 Gb 7200 RPM

I really thing if i get this server i will have anh orgams :D :beer:


http://www.unitedcolo.com/servers/xeon.htm

Depends on the chip maker/model and cache, but most likely I'd take a dual board with a nice amount of ram over any higher speed chip.

Originally posted by hostingsp
LOL

all this talk dual, p3 , single p4...

Did you guys forget the XEON ?

I wold get a (1) Xeon p4 2.0 rather than a dual p3 our a p4 :)


PS : I loved the UCG that they put...

Dual XEON 2.4 Gz - 1 Gb ram - 160 Gb 7200 RPM

I really thing if i get this server i will have anh orgams :D :beer:


http://www.unitedcolo.com/servers/xeon.htm

is that a racklogic box?

the picture looks the same =)

well i wasnt sure if xeons were included or not , im sure anyone rather have a xeon when it comes to hosting . After thinking about this again , i think i rather have a one of those new p4 3.06 ghz chips with hyperthreading as opposed to a simple dual p3 chipset . Im sure it would givbe the dual chipset a run for the money , not to mention , you'll have tons of bragging rights for the next couple of weeks until the 3.2 ghz comes out

Xeon is powerful for its hyperthreading technology which is now in the P4. 3ghz chips. So P4 3ghz is actually Xeons but with a much faster speed. It will be sweet to do Dual P4 3ghz if that's possible :D

Originally posted by silversurfer
Xeon is powerful for its hyperthreading technology which is now in the P4. 3ghz chips. So P4 3ghz is actually Xeons but with a much faster speed. It will be sweet to do Dual P4 3ghz if that's possible :D

Yeah much people does not know what tecnology does the Xeon has and speaks lott's off ****...

The Xeon has more tecno. than the new p4 3.0 ... but i think beacuse it has a higher clock it shold be fastert than a Xeon 2.4 but not that much faster..

I still prefer a xeon rather than a normal p4... the xeon was made for servers diferent from the pentium's that is for home use,,,

Yup definitely. ;) I am not too sure what other significant technology that are in Xeons other than that it is designed for multi-threading, and that hyperthreading is one of the key technology that gives it the edge. Hostingsp, do you have more details?

btw. Intel did launch 2.8Ghz Xeons just a couple of weeks ago. Thus the difference in clock speed is probably negligible now. However I doubt they will be cheap :D

(and there's always the Xeons MP... lol) Anyway I guess we can't say for sure or conclude anything till someone gets a few of them and run some benchmarking. If anyone do come across any, please do share :D

as for what use it is make for, nowadays, with the servers getting faster and faster, the lines are getting blurred. And with Intel putting in the same hyperthreading technology in the P4 3ghz, the lines are even more blurred. P4 3ghz btw are targeted at the workstation market currently and not home users. And I am sure more and more people will use it as servers anyway ;)

silversurfer,

I din't search nothing about the XEON but from what i know...

The Xeon comes it 512 Kb, 1 MB, 2 MB, off Cache...

soh the 512 KB cache it's the poor version ( the basic ) off the xeon..


I wold rather get a Xeon 2.0 it 1MB our 2 MB rather than a p4 3.0


And from what i know all it's cache and memory and etc it's bigger and Xeon handles better the 24 Hours use... and the heating up isues... :)

Originally posted by silversurfer
So P4 3ghz is actually Xeons but with a much faster speed.

No. You are wrong.

I apologise for the over-generalising statement :blush: My intent or intention rather was to mention a key technology used in Xeon is now in P4.

Originally posted by silversurfer
I apologise for the over-generalising statement :blush: My intent or intention rather was to mention a key technology used in Xeon is now in P4.

OK, agreed there, the implemntation (which was improved upon in many of the typical uses of a desktop as opposed to a server) of SMT is a gerat gain for the normal P4 line.

But to say a P4 is like a Xeon is selling the Xeon short in many aspects and the P4 in some others. For instance very conservative timings on Xeon hardware as opposed to more agressive ones on P4 stuff. There are architextural differeces as well, in additoin to the already mention varying amounts of larger cache.

I believe the cache sizes, bus speeds etc are the same between the newest Xeons and P4s (3ghz). Checked the Intel site on that one... The Xeons with more cache I believe is branded as Xeon MP which has 1-2MB cache. I wouldn't want to know the prize though. lol. It will probably be rather demoralising

the xeon is an uber p4, it has core changes to io handling and a larger cache in certain models. of course id take a dual xeon over a p3. but then again the cost difference doesnt make this an option for everybody. ok theres always some smartarse who can build a quad xeon server with 128 GB of ram for 700 bucks, but in reality a quality dual xeon server is going to be 3-4000 with the potential to cost a lot more if you want. a p3 server could be had for what 600 bucks? 1000 if you buy moderate quality.

Intel Xeon PIII 700MhzCPU with 1mb cache
Consistent 100 MHz front side bus design
Advanced Transfer Cache (L2), scalable to 2 MB, with advanced system buffering
Functional redundancy checking
Thermal sensors
System management bus,On-cartridge voltage management
0.18-micron process core technology


See look *
P III 700 Mhz CPU with 1 MB cache * ( Not L2 )
CACHE (L2) 2 MB


From this servers config. you can see the simple cache that this PIII Xeon 700 Mhz has i wold bet this to be faster than a P4 1.4

If it was just plain old web hosting then 1mb and 2mb of cache probably wouldn't make all that much difference, where you would gain would be where complex operations are carried out on data sets - such as with databases.

Agreed, while more cache is usually better, not everything will take advantage of it, or rather take the full advantage of it. Especially things that aren't CPU intensive at all, such as plain html serving. Database work, and number crunching will show the most performance increase.

This link will explain in detail without getting technical (not many people can read white papers, you know?) on how cpu's and more specifically caching work:

http://arstechnica.com/paedia/c/caching/caching-1.html

...To visualize the effect that this widening speed gap has on overall system performance, imagine the CPU as a downtown furniture maker's workshop and the main memory as a lumberyard that keeps getting moved further and further out into the suburbs. Even if we start using bigger trucks to cart all the wood, it's still going to take longer from the time the workshop places an order to the time that order gets filled...

...Sticking with our furniture workshop analogy, one solution to this problem would be to rent out a smaller warehouse in-town and store the most recently requested types of lumber, there. This smaller, closer warehouse would act as a cache for the workshop, and we could keep a driver on-hand who could run out at a moment's notice and quickly pick up whatever we need from the warehouse. Of course, the bigger our warehouse the better, because it allows us to store more types of wood, thereby increasing the likelihood that the raw materials for any particular order will be on-hand when we need them. In the event that we need a type of wood that isn't in the closer warehouse, we'll have to drive all the way out of town to get it from our big, suburban warehouse. This is bad news, because unless our furniture workers have another task to work on while they're waiting for our driver to return with the lumber, they're going to sit around in the break room smoking and watching Oprah. And we hate paying people to watch Oprah.

I'm sure you've figured it out already, but the warehouse in our analogy is the level 1 (or L1) cache. The L1 can be accessed very quickly by the CPU, so it's a good place to keep the code and data that the CPU is most likely to request, next. (In a moment, we'll talk in more detail about how the L1 can "predict" what the CPU will probably want.) The L1's quick access time is a result of the fact that it's made of the fastest and most expensive type of static RAM, or SRAM. Since each SRAM memory cell is made up of four to six transistors (compared to the one-transistor-per-cell configuration of DRAM) its cost-per-bit is quite high. This high cost-per-bit means that we generally can't afford to have a very large L1 cache unless we really want to drive up the total cost of the system.

In most current CPUs the L1 sits on the same piece of silicon as the rest of the processor. In terms of the warehouse analogy, this is a bit like having the warehouse on the same block as the workshop. This has the advantage of giving the CPU some very fast, very close storage, but the disadvantage is that now the main memory (our suburban warehouse) is just as far away from the L1 cache as it is from the processor. So if some data that the CPU needs isn't in the L1, a situation called a cache miss, it's going to take quite a while to retrieve that data from memory. Furthermore, remember that as the processor gets faster, the main memory gets "further" away all the time. So while our warehouse may be on the same block as our workshop, the lumber yard has now moved not just out of town but out of the state. For an ultra-high-clockrate processor like the P4, being forced to wait for data to load from main memory in order to complete an operation is like our workshop having to wait a few days for lumber to ship in from out of state...

...The solution to this dilemma is to add more cache. At first you might think we could get more cache by enlarging the L1, but as I said above the cost considerations are a major factor limiting L1 cache size. In terms of our workshop analogy, we could say that rents are much higher in-town than in the suburbs, so we can't afford much warehouse space without the cost of rent eating into our bottom line to the point where the added costs of the warehouse space would outweigh the benefits of increased worker productivity. So we have to fine tune the amount of warehouse space that we rent by weighing all the costs and benefits so that we get the maximum output for the least cost.

A better solution than adding more L1 would be to rent some cheaper, larger warehouse space right outside of town to act as a cache for the L1 cache. Hence processors like the P4 and G4e have a Level 2 (L2) cache that sits between the L1 cache and main memory. The L2 cache usually contains all of the data that's in the L1 plus, some extra. The common way to describe this situation is to say that the L1 cache subsets the L2 cache, because the L1 contains a subset of the data in the L2...

...This series of caches, starting with the page file on the hard disk (the lumber yard in our analogy) and going all the way up to the registers on the CPU (the workshop's workbenches), is called a cache hierarchy. As we go up the cache hierarchy towards the CPU, the caches get smaller, faster, and more expensive to implement; conversely, as we go down the cache hierarchy they get larger, cheaper, and much slower. The data contained in each level of the hierarchy is usually mirrored in the level below it, so that for a piece of data that's in the L1 cache there are usually copies of that same data in the L2, main memory, and page file. So each level in the hierarchy subsets the level below it. We'll talk later about how all of those copies are kept in sync...

There are many more pages to this article, and the sources in the bibliography are worth checking out as well. Also read about cache misses.

Definitly Dual P3

regards
D
:dgrin:

How about Dual P4 Xeon 2.2Ghz with 2GB RAM. :D

The P4 is a bad intel joke.

Dual anything P3.

Better yet Dual Athlon MP's, for gaming.