OS X 10.10 vs. Ubuntu 15.04 vs. Fedora 21 Tests: Linux Sweeps The Board

[Michael]

I would have liked to see Fedora 22 vs. Ubuntu 15.04, since they're both still development versions.

Fedora 22's default kernel (sans installing the non-default nodebug kernel) has various debug options enabled by default that could affect the performance so last time I ran any Fedora devel tests without the nodebug kernel was quickly criticized.

[user82]

It just works?


1) but dead slow

[johnc]

inb4 the two posters stuck in the apple reality distortion field show up

[edoantonioco]

Are Apple people trying to solve those terrible performance problems? Or do they would have to write the whole system from scratch, and thats because it hasn't been fixed? Or maybe they just want a product than just works, even if they sacrifice performance.

[johnc]

Are Apple people trying to solve those terrible performance problems? Or do they would have to write the whole system from scratch, and thats because it hasn't been fixed? Or maybe they just want a product than just works, even if they sacrifice performance.

Well, HFS+ isn't exactly an example of a filesystem that "just works"... if you like your data at least.

[jacob]

Um they didnt measure the perceived quality of user interface or launch animations of dock icons or the smoothness of animation when maximizing windows. Those are the most important Os X features. Oh and blurred fonts.

There is much more to OSX than that. To give a fairer comparison between the two, the benchmarks should include:
- how tightly is the OS locked down;
- how much BSD and other open source code it reuses without giving anything back;
- how mediocre but overpriced is the hardware it runs on;
- how long do security vulnerabilities remain unpatched; and
- how easily it can be sold to zealots who would buy virtually any junk as long as it has an apple-shaped logo on it.

See, OSX may be slow, but some things are just worth it.

[liam]

There is much more to OSX than that. To give a fairer comparison between the two, the benchmarks should include:
- how tightly is the OS locked down;
- how much BSD and other open source code it reuses without giving anything back;
- how mediocre but overpriced is the hardware it runs on;
- how long do security vulnerabilities remain unpatched; and
- how easily it can be sold to zealots who would buy virtually any junk as long as it has an apple-shaped logo on it.

See, OSX may be slow, but some things are just worth it.

I'm not entirely sure what side of this debate you're on...
From the list...it's honestly a bit of a mixed bag. Apple has a pretty locked down os (not necessarily a good thing, but TENDS to be pretty secure...but unknown if being locked down is the cause). They give back a decent amount to various oss projects (xorg, llvm, cups, etc. probably many more). Their hardware is neither mediocre nor overpriced (they're quite cheap, for what you buy). I think they're fairly similar to msft, rht, ora as far as major vulnerabilities are concerned. Heh, well, the last is pretty clear.
I'm going to guess you're not an apple fan.

[adakite]

I'm using Mac OS X and Red-Hat based distros (CentOS and Fedora) on everyday basis,

HFS+ and OpenGL are, IMHO, the two huge weaknesses of Apple's products and these benchmarks are clearly a good illustration of it.

Apple should have switch to ZFS a while ago, when they were considered it few years ago, too bad. As for the graphic support, I still do not understand while they claim to be a designer-oriented platform. The only thing they do better than linux on that side, is the GPU switch between Intel and Nvidia on their laptops. This is really nicely supported as opposed to what optirun/bumblebee offers on Linux side.

Would it be interested to see some BSD on that benchmark, for some of the tests presented here, BSD is pretty slow as well.

[varikonniemi]

I'm not entirely sure what side of this debate you're on...
From the list...it's honestly a bit of a mixed bag. Apple has a pretty locked down os (not necessarily a good thing, but TENDS to be pretty secure...but unknown if being locked down is the cause). They give back a decent amount to various oss projects (xorg, llvm, cups, etc. probably many more). Their hardware is neither mediocre nor overpriced (they're quite cheap, for what you buy). I think they're fairly similar to msft, rht, ora as far as major vulnerabilities are concerned. Heh, well, the last is pretty clear.
I'm going to guess you're not an apple fan.

I'm going to guess you are an apple fan

If there is one thing most people can agree on it is that apple is expensive. Overpriced comes as a natural feature from that if you don't use the product as a fashion statement. Everyone knows fashion cannot be overpriced because in that world more expensive == better.

And everyone knows fashion is not supposed to be practical, it is just supposed to be. So there is no need for apple to be fast. The important thing is that it must be different, so why not add cheesy compiz animations for the ui that hide the slowness in a design feature?

[Greijoan]

I hope to hear from some Apple authority (not necessarily directly working in the company) what he/she has to say about those results. I would understand 5% differencies, but this?

Part of the bad performance seems to be linked with worse code generation of Clang, because Fedora + Clang exhibits similar tendencies, sometimes. It's still better than OSX though. Maybe it's because the compiler of the kernel?

Anyway I was very surprised by this benchmark.

By the way: does anyone even uses OSX Server edition?