Apple releases octo-core Mac Pro

[Praxis]

Praxis, I'm certain the lack of TPM chips in newer Macs has already been mentioned to RThurmont by either you or Durandal.

Not in this thread; and RThurmont clearly has memory problems.

[Durandal]

But that's my point, who would want to legally run OS X?

The 20 million or so Mac users out there? The people who are switching?

It's basically BSD,

No, it's not.

but retarded with layers and layers of unneccessary, poorly designed GUI,

No, there's one layer (called Quartz), and according to most reviews, it's very well-designed. Much better than the trash coming out of Redmond or the Linux distros these days.

no built-in virtualization capability

Why does this matter?

(though this is rumored for Leopard), and proprietary APIs.

So?

BTW, my source for saying OS X is slow is my own experience. However, here is some benchmarking to back it up. In my experience though, whenever I have more than five tabs open in Safari, the system will slow to an absolute crawl.

That benchmark is essentially a test of how fast you allocate and free 35 kB blocks of memory. Since Mac OS X's malloc() switches to the kernel's allocator for allocations above 15 kB. No one just allocates and immediately frees memory without doing something with it. And keeping memory around can lead to it being paged to disk.

Since the allocations go straight back on the heap, there is no potential for memory fragmentation, which can also cause performance degradation. Mac OS X's malloc() threshold is 15 kB, it will transition into kernel space more often than Linux, which is at 128 kB. But since Linux's malloc() will take larger allocations off the heap, you'll end up with a larger potential for memory fragmentation due to unused holes.

Put simply, it's not a realistic or useful test. But I'm sure you didn't bother doing any additional research. You jumped straight to the conclusion and thought "Oooh I could use this to back up my opinions!"

By the way, if you compile that test with the optimized malloc() that Linux uses, the performance gap basically disappears.

[Praxis]

Durandel wins the thread.
Do you just memorize OS trivia all day, or did you have to look that up?

[RThurmont]

Praxis, I'm certain the lack of TPM chips in newer Macs has already been mentioned to RThurmont by either you or Durandal.

Yes it had been, but my suggestion is that Apple might well resume shipping Macs with them, and additionally have the new version potentially use them, out of the box.

Dang, the stupidity continues. Where does this even come from?

Mac OS X is about 2 GB. It comes with about 13 GB of extra software (iDVD, iPhoto, iTunes, GarageBand, etc, etc, etc).

That's MINISCULE compared to the stock 250 GB hard drive and the maxed-out 3 TB of space that system can have.

Woah hold it for a minute. Nowhere did I imply that Mac OS X would take up the entire hard disk. What I intended to convey was that it would be dumb to waste the entire HD on the OS X operating system, as opposed to, at a minimum, creating another partition, and installing Linux to it.

Yeah great idea. Then you could do ... um, what, with it, exactly?

Enjoy the benefits of open source software, get hardware virtualization out of the box (assuming the Xeon supports that, and I'd assume it does, considering that a fair number of lower end Intels also have that feature), and get an overall improvement in system performance.

[RThurmont]

No, there's one layer (called Quartz), and according to most reviews, it's very well-designed. Much better than the trash coming out of Redmond or the Linux distros these days.

To be clear, I did not literally mean that there were multiple layers, I meant layers and layers in a metaphorical sense, however, I admit that looked vague, and I concede that point. However, I do not concede that the OS X GUI is well designed, and I am of the opinion that the KDE UI, at the very least, is vastly superior to that of OS X in most respects. GNOME is superior, I would argue, if for no other reason than it's quite a bit faster.

Also, in my opinion, you're taking an unjustified dump on the massive amounts of UI research Microsoft conducted in the early 1990s, that lead to such innovations as the task bar and start menu, which IMO are one heck of a lot better than the messy kludge known as the "Dock" that OS X uses for program launching/switching.

One of my biggest gripes with Apple is a company is its continual, unwarranted bashing of its competitors, which, in my opinion, is unethical, obnoxious, and in some cases, downright offensive. Microsoft is also guilty of this, although to a much lesser degree in my opinion.

By the way, if you compile that test with the optimized malloc() that Linux uses, the performance gap basically disappears.

Then why doesn't OS X use that malloc by default??? Could it be, gasp, bad design?

EDIT (as I didn't want to add a third post for something on the previous page), I also agree for the most part with your previous post, Stark. However, I maintain that a number of Linux distros are equally n00b friendly relative to Windows or OS X (and are in some cases, arguably, better, for certain lightweight tasks).

[Praxis]

Yes it had been, but my suggestion is that Apple might well resume shipping Macs with them, and additionally have the new version potentially use them, out of the box.

ROFL, are you even serious?


You said

I would be really suprised if Leopard in fact does not in fact utilize Apple's trusted platform module to ensure that it only is used on Apple hardware.

You would be REALLY SURPRISED if Apple didn't do this? You would be SURPRISED if Apple did not lock out every single Mac Pro or Core 2 Duo Mac owner from upgrading to Leopard?

I guess I shouldn't plan to upgrade my mom's Core 2 Duo Macbook Pro to Leopard, seeing as it doesn't have a TPM chip.

I expect you are going to be rather surprised.

Woah hold it for a minute. Nowhere did I imply that Mac OS X would take up the entire hard disk. What I intended to convey was that it would be dumb to waste the entire HD on the OS X operating system, as opposed to, at a minimum, creating another partition, and installing Linux to it.

Why?

If one was using it as a server, they'd by XServes or something from someone other than Apple.

If someone's buying a Mac Pro, they're using it as a high end workstation, not as a server, and likely for software that will be best suited by OS X.

Enjoy the benefits of open source software, get hardware virtualization out of the box (assuming the Xeon supports that, and I'd assume it does, considering that a fair number of lower end Intels also have that feature), and get an overall improvement in system performance.

Open source software is availabe for OS X and Linux can run in a VM. So who cares if virtualization isn't out of the box? There's multiple products to do it (like VMWare Fusion, Parallels, etc). And the system performance improvement bit has already been refuted.

Sigh.

[RThurmont]

Nowhere, Praxis, in the above post, did I state that I thought that Apple would prevent people with Macs lacking the TPM to upgrade. However, what I did say is that I would not be suprised if Apple enabled the feature, for the Macs that had it. Assuming they did enable this feature, they would probably include code to detect Macs that didn't have the TPM, and supply some alternative DRM scheme (perhaps analogous to the Windows activation feature) for those systems. If you attempted to install on a machine lacking a TPM, the specifications of which were not the same as a Mac known to not have the TPM, then it would of course refuse to install.

So who cares if virtualization isn't out of the box? There's multiple products to do it (like VMWare Fusion, Parallels, etc)

Yes, and the aforementioned products are proprietary, and at least in the case of Parallels, expensive (I don't know if VMWare is going to give away Fusion or not, but somehow, I doubt it). KVM ships with the Linux 2.6.20 Kernel, and is fully open source.

And the system performance improvement bit has already been refuted.

No it hasn't.

[Praxis]

Nowhere, Praxis, in the above post, did I state that I thought that Apple would prevent people with Macs lacking the TPM to upgrade. However, what I did say is that I would not be suprised if Apple enabled the feature, for the Macs that had it. Assuming they did enable this feature, they would probably include code to detect Macs that didn't have the TPM, and supply some alternative DRM scheme (perhaps analogous to the Windows activation feature) for those systems. If you attempted to install on a machine lacking a TPM, the specifications of which were not the same as a Mac known to not have the TPM, then it would of course refuse to install.

Then what is the logic in Apple removing TPM?

No, you're just grasping at straws.

So who cares if virtualization isn't out of the box? There's multiple products to do it (like VMWare Fusion, Parallels, etc)

Yes, and the aforementioned products are proprietary, and at least in the case of Parallels, expensive (I don't know if VMWare is going to give away Fusion or not, but somehow, I doubt it). KVM ships with the Linux 2.6.20 Kernel, and is fully open source.

There are open-source virtualization software for Mac too, such as Q.

Nothing has the polish of Parallels though. Parallels installs special drivers, + Kaperski antivirus, if you're running Windows that streamlines interface with the virtual machine...much better than anything else I've used.

And the system performance improvement bit has already been refuted.

No it hasn't.

Okay, if that memory allocation benchmark wasn't your source, then I guess I should say that your system performance claim hasn't been substantiated. You've provided no source.

The Linux distros I've used ran slower than OS X in my experience (Red Hat and Mandrake, specifically). And slower than Windows on my 2.6 GHz Pentium 4.

[Durandal]

To be clear, I did not literally mean that there were multiple layers, I meant layers and layers in a metaphorical sense, however, I admit that looked vague, and I concede that point. However, I do not concede that the OS X GUI is well designed, and I am of the opinion that the KDE UI, at the very least, is vastly superior to that of OS X in most respects. GNOME is superior, I would argue, if for no other reason than it's quite a bit faster.

What's not well designed about the OS X GUI? What's better-designed about Gnome and KDE?

Also, in my opinion, you're taking an unjustified dump on the massive amounts of UI research Microsoft conducted in the early 1990s, that lead to such innovations as the task bar and start menu, which IMO are one heck of a lot better than the messy kludge known as the "Dock" that OS X uses for program launching/switching.

I could easily make the argument that Spotlight is poised to be a general application launcher. Anyone who's used QuickSilver on OS X can tell you how much easier it is to launch by typing what you want than digging through a Start menu or running around in a file browser.

As to the Dock, as an application launcher, it's more equivalent to the quick launch area on Windows XP's task bar. But it serves its purpose decently. It's not perfect, but it does okay.

One of my biggest gripes with Apple is a company is its continual, unwarranted bashing of its competitors, which, in my opinion, is unethical,

Why? Are you unfamiliar with capitalism?

obnoxious, and in some cases, downright offensive.

Awwww. Did Apple offend you with the "Get a Mac" ads? Poor widduw baby.

Microsoft is also guilty of this, although to a much lesser degree in my opinion.

Their mass-advertising doesn't target their competitors. Microsoft's approach is not even acknowledge their competition exists.

Then why doesn't OS X use that malloc by default??? Could it be, gasp, bad design?

Did you read anything I wrote? It's a malloc() optimized for that test. And that test isn't a useful test because it doesn't simulate any realistic allocation patterns.

There are reasons, like the desire to avoid memory fragmentation, which can also kill performance. Believe it or not, Apple's engineers are not morons.

[Stark]

Nobody I know uses Dock like a start menu - like Durandal says, it's a quick launch bar. It's primary role for me is to keep me informed about what's running and let me use the app/right click menu etc. Spotlight is useful, but Finder/Apps IS THE FUCKING START MENU. It's exactly the same - you can even make subfolders if you want to organise. I find there's no point - I use Finder/Apps to poke around and spotlight to start a specific app. I don't need a huge, screen-covering chaotic mess generated by all the apps I've installed creating nested shortcut mazes like the Start Menu.

[atg]

Nowhere, Praxis, in the above post, did I state that I thought that Apple would prevent people with Macs lacking the TPM to upgrade. However, what I did say is that I would not be suprised if Apple enabled the feature, for the Macs that had it. Assuming they did enable this feature, they would probably include code to detect Macs that didn't have the TPM, and supply some alternative DRM scheme (perhaps analogous to the Windows activation feature) for those systems. If you attempted to install on a machine lacking a TPM, the specifications of which were not the same as a Mac known to not have the TPM, then it would of course refuse to install.

Bull. Shit. You said:

I would be really suprised if Leopard in fact does not in fact utilize Apple's trusted platform module to ensure that it only is used on Apple hardware.

No refererence then to 'on macs that have it (TPM)', no reference to using something like Windows activation. You've heavily implied that Macs use TPM and only pulled the other crap out your arse when you were called on it.

Yes, and the aforementioned products are proprietary, and at least in the case of Parallels, expensive (I don't know if VMWare is going to give away Fusion or not, but somehow, I doubt it). KVM ships with the Linux 2.6.20 Kernel, and is fully open source.

1. Who gives a shit if its proprietary or not if it does the job it is needed for?
2. Who gives a shit if its open source or not? Wait, let me guess, by the way you've been going on about open source and Linux in this thread I'm betting your one of these open source morons who likes to loudly force their view of the computing world on others, "0pen S0urce PWNS all!!!!!111!!!!".

I'm in IT myself, I use various versions of Windows, OS X, and Linux everyday, and guess how much inclination I have to look at or modify source code? NONE. I don't give a crap that I can look at the source, I do give a crap about price, and if a free open source program will give me what I need then chances are I'll use it. The "Free as in speech, not as in beer" mantra of open source zealots I hear using all the time has got to be one of the most stupid things I've ever heard, because outside of a hard core inner group NO ONE GIVE A DAMM ABOUT THE SOURCE CODE.

I've had to build programs from source before, mainly to get it working with a particular system, but guess what? If I've downloaded or installed a closed-source program I find it generally "just works" out of the box and doesn't need to be fucked around with like many open source programs. I'll use an open source program if needs be, if it does what is required, but it being open source doesn't give it an instant win over the competition.

[RThurmont]

There are open-source virtualization software for Mac too, such as Q.

Q is nice, but it's an emulator, and as a result can't compete with KVM or other hardware virtualization systems in terms of performance. I do really applaud the efforts of the Q team though in bringing open source software into the OS X virtualization market, which is, IMO, sorely in need of more of the same.

Why? Are you unfamiliar with capitalism?

No. However, I do consider bashing competitors to be unethical, and certainly also lacking in class. The FTC actually used to prohibit comparative advertising like Apple's, so every company's advertising was Microsoft-style, in that it did not acknowledge the existence of competition. I think that this was a much better approach all around, as it forced companies to focus on the actual reasons to buy their product, as opposed to allowing them to spread (in many cases false) FUD about their competitors.

Note, that, by the way, since I am not a distributor of Linux (unless you count a non-workable distro I built as a toy using rPath), that I can bash OS X freely without being a hypocrite at this point.

[Xisiqomelir]

Thurmont, what on earth.

Do you think everyone is lying to you about their preferences? What could their motive for that possibly be?

[Ace Pace]

I think the problem is that Rthurmont dreams about the 'utopia' of everyone running open source software and OSs, without troubles, in the magical fairy land where open source software is magically faster, better and more stable.

Ignoring that OSX has an open source kernel.

[RThurmont]

Ignoring that OSX has an open source kernel.

Open source according to the OSI, but not Free Software according to the FSF. The APSL requires that all changes be submitted upstream to Apple, which, in my opinion, is obnoxious.

[Ace Pace]

Ignoring that OSX has an open source kernel.

Open source according to the OSI, but not Free Software according to the FSF. The APSL requires that all changes be submitted upstream to Apple, which, in my opinion, is obnoxious.

So you're going to nitpick things now?

[Instant Sunrise]

Ignoring that OSX has an open source kernel.

Open source according to the OSI, but not Free Software according to the FSF. The APSL requires that all changes be submitted upstream to Apple, which, in my opinion, is obnoxious.

Richard Stallman and the FSF can blow me. I can't even begin to count the number of times I've heard mindless GPL wankers say that Free Software and Open Source Software are different things. Nice dodge there, asshole.

EDIT: Just because Darwin isn't in your RMS circle-jerk doesn't mean you can arbitrarily exclude it from being Open Source. When the OSI, the body that SAYS what the fuck is and isn't OSS, says that the APSL is an Open Source license, that means it's Open fucking Source.

[RThurmont]

EDIT: Just because Darwin isn't in your RMS <censored> doesn't mean you can arbitrarily exclude it from being Open Source. When the OSI, the body that SAYS what the <censored> is and isn't OSS, says that the APSL is an Open Source license, that means it's Open <censored> Source.

Note, however, that I did not deny that it was Open Source. Also, to be clear, I also think that RMS is rather annoying, but that does not get around the fact that the APSL is one of the lamest Open Source licenses around. In fact, I would argue that it's lamer than most of the Microsoft Shared Source licenses (except for the MS-lCL, which restricts development to the Windows platform, although IMO an equivalent license for open source OSes would be a great idea), and is only mildly less annoying than "badgeware" licenses like SugarCRM's.

EDIT:

One other thing I also really feel that I want to clarify in this thread is that I do not think that OS X is a bad operating system at all. It has less of a malware problem than Windows, a number of interesting design features, and its graphics are elegant. However, I do have a number of gripes with it in terms of licensing, interaction design, performance, and features, and for those reasons, that's why in this thread I've advocated the use of Linux instead (until hopefully, Apple fixes the problems).

[Xisiqomelir]

The GUI is certainly better than Linux's inconsistency.

Linux GUIs can suck sheep dick (GNOME comes to mind), but they can be pretty ok too, and pretty consistant if you take the right collection of apps. Depends on your own preferences and needs. But certainly not for everyone.

Of course, the Mac isn't for everyone either. I personally can't stand it, and would pick Linux over it any time, any dayy.

Maybe I'm reading this a little too critically, but it seems to imply that any random person is equally likely to prefer either a Linux GUI or Aqua, which I disagree with.

Obligatory:

For example, Windows is stable

[Pu-239]

Ignoring that OSX has an open source kernel.

Open source according to the OSI, but not Free Software according to the FSF. The APSL requires that all changes be submitted upstream to Apple, which, in my opinion, is obnoxious.

AFAIK, this isn't applicable to the current APSL.

Seriously, give it up- I'm a hardcore Linux user and I think you're grasping at straws.

[Praxis]

Time to call out the translator.

I do have a number of gripes with it in terms of licensing,

Wah wah everything that is not 100% open source is teh suxx0rs wah wah

interaction design,

Wah wah I hate the dock wah wah

performance,

I'm going to complain about performance despite having failed to provide any evidence for such a complaint outside of a quickly-refuted completely invalid optimized memory allocation test.

and features,

And now I'm going to complain that Mac OS X doesn't have built in virtualization software, something every commercial OS lacks and only Linux has, and can be quickly found open source and free online or commercially at the nearest CompUSA.


Concession accepted.

[Xisiqomelir]

EDIT: Interestingly, Intel doesn't sell quad-core 3 GHz Xeons; Cloverton is 2.66. Does Apple have early release chips, or are they overclocking?

teh rofl. Intel must be ecstatic to have Apple as a partner.

Apple's new Mac Pro uses special-run Xeon
Apple's updated Mac Pro uses a special version of Intel's Xeon workstation-class processor, the semiconductor company said in an e-mail note. The 3GHz quad-core CPU at the heart of the fastest system is currently an unannounced model that sits at the top of the company's performance range and is presently used only by Apple.

"We are indeed shipping a 3.0GHz Xeon version [and] expect to see faster gigahertz speeds for our high-end [Core 2] Extreme PCs very soon, too," said Intel's Bill Kircos. "For now, the product is in limited production and Apple has chosen to adopt it. We will introduce another 3.0GHz Xeon SKU later on as well."

The model in question is the Xeon X5365, according to additional comments by Intel's Italian PR director Ruben Simpliciano. The chip currently outpaces the official fastest quad-core processor from Intel, the 2.66GHz Xeon 5355, while maintaining the 8MB of total level 2 cache and 1333MHz system bus of its predecessors.

Apple has recently been found using special Intel processors in some of its devices, such as the 1GHz Pentium M modified to run at lower power levels inside the Apple TV media hub.

[The Kernel]

I'm going to complain about performance despite having failed to provide any evidence for such a complaint outside of a quickly-refuted completely invalid optimized memory allocation test.

I'm pretty sure he's referring to this...

Yes it's a G5 test, but it's the OS that is the problem here, not the chip.

"Mac OS X Server starts with Darwin, the same open source foundation used in Mac OS X, Apple's operating system for desktop and mobile computers. Darwin is built around the Mach 3.0 microkernel, which provides features critical to server operations, such as fine-grained multi-threading, symmetric multiprocessing (SMP), protected memory, a unified buffer cache (UBC), 64-bit kernel services and system notifications. Darwin also includes the latest innovations from the open source BSD community, particularly the FreeBSD development community."

While there are many very good ideas in Mac OS X, it reminds me a lot of fusion cooking, where you make a hotch-potch of very different ingredients. Let me explain.
Darwin is indeed the open Source project around the Mach kernel 3.0. This operating system is based around the idea of a microkernel, a kernel that only contains the essence of the operating system, such as protected memory, fine-grained multithreading and symmetric multiprocessing support. This in contrast to "monolithic" operating systems, which have all of the code in a single large kernel.

Everything else is located in smaller programs, servers, which communicate with each other via ports and an IPC (Inter Process Communication) system. Explaining this in detail is beyond the scope of this article (read more here). But in a nutshell, a Mach microkernel should be more elegant, easier to debug and better at keeping different processes from writing in eachother's protected memory areas than our typical "monolithic" operating systems such as Linux and Windows NT/XP/2000. The Mach microkernel was believed to be the future of all operating systems.

However, you must know that applications (in the userspace) need, of course, access to the services of the kernel. In Unix, this is done with a Syscall, and it results in two context switches (the CPU has to swap out one process for another): from the application to the kernel and back.

The relatively complicated memory management (especially if the server process runs in user mode instead of kernel) and IPC messaging makes a call to the Mach kernel a lot slower, up to 6 times slower than the monolithic ones!

It also must be remarked that, for example, Linux is not completely a monolithic OS. You can choose whether you like to incorporate a driver in the kernel (faster, but more complex) or in userspace (slower, but the kernel remains slimmer).

Now, while Mac OS X is based on Mach 3, it is still a monolithic OS. The Mach microkernel is fused into a traditional FreeBSD "system call" interface. In fact, Darwin is a complete FreeBSD 4.4 alike UNIX and thus monolithic kernel, derived from the original 4.4BSD-Lite2 Open Source distribution.

The current Mac OS X has evolved a bit and consists of a FreeBSD 5.0 kernel (with a Mach 3 multithreaded microkernel inside) with a proprietary, but superb graphical user interface (GUI) called Aqua.

Performance problems
As the mach kernel is hidden away deep in the FreeBSD kernel, Mach (kernel) threads are only available for kernel level programs, not applications such as MySQL. Applications can make use of a POSIX thread (a " pthread"), a wrapper around a Mach thread.


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.

Another problem is the way threads could/can get access to the kernel. In the early versions of Mac OS X, only one thread could lock onto the kernel at once. This doesn't mean only one thread can run, but that only one thread could access the kernel at a given time. So, a rendering calculation (no kernel interaction) together with a network access (kernel access) could run well. But many threads demanding access to the memory or network subsystem would result in one thread getting access, and all others waiting.

This "kernel locked bottleneck" situation has improved in Tiger, but kernel locking is still very coarse. So, while there is a very fine grained multi-threading system (The Mach kernel) inside that monolithic kernel, it is not available to the outside world.

So, is Mac OS X the real reason why MySQL and Apache run so slow on the Mac Platform? Let us find out... with benchmarks, of course!

........


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.

........


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.

And before anyone tries to shoot the author, I should remind everyone that Johan De Gelas (formerly of Ace's Hardware) is as good as they come.

[The Kernel]

Intel must be ecstatic to have Apple as a partner.

The nice thing about Apple for Intel is that they can launch with them with limited quantities and show off a new high end chip without having to worry about keeping Apple stocked up (the number of Mac Pros shipped will always be low).

[The Kernel]

You know, it occurs to me after having had a chance to reread Johan's article on OSX performance after a few years that the problems with threading in OSX could cause some huge problems for Apple down the line now that we are moving towards heavily threaded workstation applications to match the rush of multi-core CPUs.

Time will tell of course, but that article is just scathing on this topic and it doesn't look like an easy fix kind of situation.