G5 vs. x86 and Mac OS X vs. Linux

demonbug writes "Anandtech has an article up comparing performance of dual G5s to AMD Opteron and Intel Xeon workstations. The article also takes a look at performance under Mac OS X versus Linux. It provides an interesting look at some of the strengths and weaknesses of the different CPUs." From the article: "This article is written solely from the frustration that I could not get a clear picture on what the G5 and Mac OS X are capable of. So, be warned; this is not an all-round review. It is definitely the worst buyer's guide that you can imagine. This article cares about speed, performance, and nothing else! No comments on how well designed the internals are, no elaborate discussions about user friendliness, out-of-the-box experience and other subjective subjects. But we think that you should have a decent insight to where the G5/Mac OS X combination positions itself when compared to the Intel & AMD world at the end of this article."

Comments

No PowerPC Linux in the Review?!

[Noksagt]

The article also takes a look at performance under OSX versus Linux.

They look at PowerPC running Darwin 8.1 and two Xeons and an Opteron running Linux 2.4/2.6. Why not show the PowerPC running Linux?! I want to see how Linux on PPC compares to Linux on x386 these days!

Anyway..here's the article summary:

Mac OS X is incredibly slow, between 2 and 5(!) times slower, in creating new threads, as it doesn't use kernel threads, and has to go through extra layers (wrappers). No need to continue our search: the G5 might not be the fastest integer CPU on earth - its database performance is completely crippled by an asthmatic operating system that needs up to 5 times more time to handle and create threads.

So, forget OS X in the server room, but have fun if you want a desktop OS.

Re:No PowerPC Linux in the Review?!

[fimbulvetr]

Don't forget this:

The server performance of the Apple platform is, however, catastrophic. When we asked Apple for a reaction, they told us that some database vendors, Sybase and Oracle, have found a way around the threading problems. We'll try Sybase later, but frankly, we are very sceptical. The whole "multi-threaded Mach microkernel trapped inside a monolithic FreeBSD cocoon with several threading wrappers and coarse-grained threading access to the kernel", with a "backwards compatibility" millstone around its neck sounds like a bad fusion recipe for performance.

Re:No PowerPC Linux in the Review?!

[lederhosen]

I totaly agree that they should have done a comparison using Linux/PPC.

I would allso like to see them use the latest Intel compiler.

I dont, however, agree on the microkernel stuff. darwin is no microkernel design at all, all the
driver, filesystem and memory management is done
in kernel space. There is nothing in that design that makes the OS more stable.

Re:No PowerPC Linux in the Review?!

[dduck]

Your Linux on G5 performance figures are here . It does appear that the performance (or rather, lack of wrt. forking and threads) is due to tue architecture of Darwin/OS-X.

I will point out that this is hardly relevant for a desktop OS, and that I am more than happy with my dual G5/1.8GHz. Getting things done faster and neater due to elegant interaction design is much more important to me than being able to spawn threads quickly ;)

Re:No PowerPC Linux in the Review?!

[RickHunter]

Except that they used Apache 1.3 and MySQL, two of the worst possible choices. If they'd gone for Apache 2.x (which actually uses threading, instead of processes) and PostgreSQL, things would've looked much nicer.

Re:No PowerPC Linux in the Review?!

[molnarcs]

I think Sybase and Oracle found the linuxthreads package :) FreeBSD 4.x and early 5.x had problems with multithreaded applications like mysql, which has been solved in the newer versions. That's what the article says as well:

"This means that applications use slower user-level threads like in FreeBSD and not fast kernel threads like in Linux. It seems that FreeBSD 5.x has somewhat solved the performance problems that were typical for user-level threads, but we are not sure if Mac OS X has been able to take advantage of this.

In order to maintain binary compatibility, Apple might not have been able to implement some of the performance improvements found in the newer BSD kernels."

Yes, server performance with the xserve seems terrible right now, but I think that will be solved in the future, as apple will incorporate the enhanchements from fbsd 5, and more importantly 6. They are cooperating (freebsd and apple) it seems on many issues.

Flawed comparison

[Amoeba]

This comparison is flawed. A more direct comparison that would have resulted in better information would have been Mac/OS X vs. x86/BSD.

What performance is he measuring? The hardware or the OS? Comparing both with no baseline control for each is about as informative as pulling numbers out of my ass.

Re:Flawed comparison

[Medievalist]

That comparison is easy. OSX hacks a BSD kernel into a Mach microkernel, and thus performance is nearly as bad as Mach despite the existence of the mature, standardized interfaces of a BSD.

MacOSX is not about performance. It's about interface. I don't think Apple (or Next for that matter) has ever tried to deny their intention to overcome the performance problems caused by tremendously complex software through the use of immensely powerful hardware.

Summary

[varmittang]

The G5 woops when it comes to floating point, and stays just behind in everything else. AMD of course takes top honors in almost everything. The find out that OS X kernel doesn't do so well on the server when it comes to multiple threads created while using MySQL and other possible open source software, so they conclude OS X a good desktop, but Linux is better on the Server. They will look into Linux on PPC to see which is better next time, PPC or x86 when it comes to a Linux server.

Re:Summary

[kylef]

The G5 woops when it comes to floating point, and stays just behind in everything else.

Uh, that's not what I read:

The conclusion is that the Opteron has, by far, the best FPU, especially when more complex instructions such a FDIV (divisions) are used. When the code is using something close to the ideal 50% FADD/FSUB and 50% FMUL mix and is optimised for Altivec, the G5 can roll its muscles. The normal FPU is rather mediocre though.

That hardly sounds like the G5 is "whooping" when it comes to floating point...

First

[pocketfullofshells]

Anandtech has an article up comparing performance of dual G5s to AMD Opteron and Intel Xeon workstations.

Ok, Rule #1 - its a performance comparison...

It is definitely the worst buyer's guide that you can imagine. This article cares about speed, performance, and nothing else!

Calm down, did we forget Rule #1 already?

No comments on how well designed the internals are, no elaborate discussions about user friendliness, out-of-the-box experience and other subjective subjects.

OK... Rule #2, no more posting news for you.

I wonder if he uses a mac or pc....

Re:Where's the Apples to Apples comparison?

[pkhuong]

Agreed. Once they'd found that the kernel was crumbling when there were lots of threads, why did they not try the same tests on Linux/PPC?

I was trying to take them serious

[Anonymous Coward]

Until I saw the blatanly placed & scantily clad woman with the words "Root Me" written with MS Paint on the desktop.

Apples to Oranges (this is not redundant... yet)

[UnapprovedThought]

As some people have pointed out (but not completely), you should be comparing:

• PPC vs. x86 on Linux, or
• PPC vs. x86 on BSD, or
• Linux vs. OSX on PPC, or
• Linux vs. OSX on x86(!), or
• OSX vs. Windohs on PPC, or
• OSX vs. Windohs on x86
• x86 vs. PPC for TPM/DRM BS
• PPC Altivec vs. x86 SSE3 on Linux

Linux forks 5 times faster than BSD, but that's been known for years. You didn't need a new benchmark/ad for that. Finally, the article doesn't have a benchmark that uses Altivec to its full potential, so it might be a hack piece as well.

They lost me right here...

[mark_wilkins]

"Thirdly, hardcore gamers are not the ones buying Apples, but rather, creative professionals.

So, we focus on workstation and server applications..."

How could anyone who has ever met a "creative professional" think they care about "workstation and server applications" like MySQL and Apache??

Sorry, guys, but being a sysadmin does not make you a "creative professional..."

-- Mark

Re:They lost me right here...

[otis wildflower]

Sorry, guys, but being a sysadmin does not make you a "creative professional..."

Are you kidding?

I've seen perl scripts that outdo Jackson Pollock or De Kooning...

MacGCC?

[Doc Ruby]

Most of the benchmark data is bottlenecked by gcc, as the review mentions. That's fair, because that's what so many of us use to compile on these kinds of platforms. But I do think that Apple would do well to throw some of their programmers at the GCC project, at least adding their expertise to some of the Altivec modules. It would show off their platform, and return some value to the gcc project surely used extensively by Apple.

Re:MacGCC?

[mr_burns]

Apple actually does work on GCC and it gives patches back to the project. The way they do this was actually used as a counterexample in the recent khtml/webcore spat.

I think that a better choice on OS X Tigger would have been GCC 4 for this test, as that's what the OS is built with and it's the native compiler for the OS.. IIRC.

Re:There Is No Comparison

[Reverberant]

The odds are pretty good that you'll need to do some CLI sorcery to get an X-Server to run under OSX.

Umm, no.

Re:SLES 9 - Kernel 2.6.5?

[Brandybuck]

Buddha on a diet! I've been hearing this crock ever since the 1.x days! Linux never has any performance problems because you're perpetually using an outdated kernel...

Re:Ummmm......

[AusG4]

1. MySQL -does- have a thread pool.

2. The threading engine on OS X really does suck. This is not new information. Apple says as much if you ask them.

This will all get fixed in due course anyways - Linux is more than a decade older than MacOS X is, and Apple is already doing very well.

Re:Apples to Oranges (this is not redundant... yet

[Atomizer]

There's no OpenLinux, FreeLinux or NetLinux. I think that proves that *BSD forks at least 3 times faster than Linux.

Re:Wooohooo

[NeedleSurfer]

isn't it sad that racist, homophobic and sexist comment systematicaly get rated funny on Slashdot?..

Re:Wooohooo

[That's Unpossible!]

A comment can't be homophobic, only a person can.

I am not homophobic, and I see the humor in the joke you are replying to. It's called absurd humor... half the joke is in the stereotyping. Macs are stereotypically the favorite computer of gays, and Linux geeks have a strong correlation with the "dirty hippie" and "pinko commie" crowd.

So don't get your panties all in a bunch.

(I'm assuming you're either a P.C. blowhard, or a homo. See, wasn't that funny?)