OS X 10.8 vs. Ubuntu On Apple Hardware, Benchmarked

← Back to Stories (view on slashdot.org)

OS X 10.8 vs. Ubuntu On Apple Hardware, Benchmarked

Posted by timothy on Thursday August 23, 2012 @06:01AM from the apt-get-me-a-new-version dept.

An anonymous reader writes "OS X 10.8 has been benchmarked against Ubuntu Linux with some interesting results. From the tests on a Apple Mac Mini and Apple MacBook Pro, OS X Mountain Lion was clearly superior when it came to the graphics performance, but the rest of the time the operating systems performed quite closely with no clear winner. OS X also seems to have greater performance issues with solid-state drives than Linux."

83 of 130 comments (clear)

Min score:

Reason:

Sort:

surprise surprise by shentino · 2012-08-23 06:03 · Score: 5, Informative

Apple hardware performs better when run by Apple device drivers.
News at 11.
1. Re:surprise surprise by Sparticus789 · 2012-08-23 06:04 · Score: 1
  
  Stole my line....
  
  --
  sudo make me a sandwich
2. Re:surprise surprise by haystor · 2012-08-23 06:07 · Score: 1
  
  No kidding.
  What are the benchmarks on all the non Apple hardware platforms?
  
  --
  t
3. Re:surprise surprise by maccodemonkey · 2012-08-23 06:43 · Score: 4, Informative
  
  For graphics, what Apple device drivers?
  The graphics drivers are written in house at NVidia and AMD. Apple doesn't actually write their own drivers. And the GPUs are just bog standard AMD, NVidia, and Intel GPUs (expect for some of the graphics switching.). There is not reason Linux should be at a disadvantage.
  And if they did I'd expect worse performance. Back when Apple used to write their own drivers they were totally awful. Apple has less experience writing graphics drivers, I'm not actually sure why you'd expect Apple written drivers to perform better.
4. Re:surprise surprise by SwedishPenguin · 2012-08-23 06:49 · Score: 2
  
  The hardware tested had an Intel HD 3000 integrated graphics, the Linux Intel drivers are known for being slow, but the Nvidia drivers are just as fast (or slightly faster in some cases) as the Windows-equivalent and presumably OSX as well. ATI I'm not sure, but they're at least closer to Windows performance than Intel is.
5. Re:surprise surprise by Gr8Apes · 2012-08-23 07:01 · Score: 2
  
  What would you like run? Pretty sure you can go do a little research at www.insanelymac.com or www.tonymacx86.com for example and see some benchmarks on hackintoshes.
  
  --
  The cesspool just got a check and balance.
6. Re:surprise surprise by burne · 2012-08-23 07:38 · Score: 1, Funny
  
  Intel HD 3000 or NVIDIA GeForce GT 330M graphics is Apple hardware? That would be real news...
7. Re:surprise surprise by Tamran · 2012-08-23 07:41 · Score: 1
  
  That. Seems like kind of a no-brainer.
  I think that was haystor's point ... but in reverse.
8. Re:surprise surprise by hairyfeet · 2012-08-23 08:36 · Score: 2, Insightful
  
  I just wish people would be happy with what they like instead of the constant "X is better than Y" flamewars. If OSX is to your liking and you think Apple hardware is worth the extra scratch? Then please enjoy, wish you nothing but luck. If you think Linux is worth the hassle, are a programmer and need the ability to script, or one of the lucky few that manages to find hardware that is never broken by an update? Great, I wish you nothing but luck and happiness. If you are one of those people for whom the large software library of Windows is required and are able to avoid the crappy releases like Vista and 8, or want to play AAA gaming? Please enjoy, nothing but luck to you.
  But please just stop with the ridiculous notion that what works for you will work for everyone else because ya know what? It don't. If the programs I need run on Windows then Linux really isn't gonna help. If my workflow is built around OSX then Windows is gonna drive me batshit and if I need to be able to futz with the low level internals than Windows and OSX is gonna be worthless.
  I do have to wonder though, who in their right mind is gonna pay the extra cost associated with Apple hardware to run...Ubuntu? That don't make no damned sense at all, if you want to run Ubuntu you can buy any OEM, many of which has better hardware specs than Apple for cheaper, or even better buy a machine actually BUILT for Ubuntu from someone like System76 and support a market for FOSS systems. Paying all that extra money just to run on a free OS on Apple gear just seems...well kinda retarded to me.
  
  --
  ACs don't waste your time replying, your posts are never seen by me.
9. Re:surprise surprise by maccodemonkey · 2012-08-23 09:02 · Score: 2
  
  The only reason is that they can throw $billions are getting the most experienced coders (e.g. from the linux community) to trim nanoseconds off the drivers they rely on most....
  Not seeing how that matters. The end user experience is what it is. What you said is an excuse, not a solution.
10. Re:surprise surprise by shentino · 2012-08-23 10:03 · Score: 4, Interesting
  
  I love how you're biased in calling linux a hassle to program and saying that one must know how to script to use it properly.
  There are actually, contrary to rumor, a few user friendly distros out there that don't require a PhD in computer science to make use of.
  And Microsoft at least HAS been caught hiding APIs that gives its own programs a performance advantage.
  My comment isn't about which is better, anyway. It's about which ones cheat on their benchmarks by giving themselves a proprietary boost not available to the competition.
  See also the scandal of either nvidia or ati making its own hardware's performance deliberately go down the crapper when it detected the competition's chips.
11. Re:surprise surprise by CAIMLAS · 2012-08-23 12:57 · Score: 5, Insightful
  
  The graphics drivers are written in house at NVidia and AMD. Apple doesn't actually write their own drivers. And the GPUs are just bog standard AMD, NVidia, and Intel GPUs (expect for some of the graphics switching.). There is not reason Linux should be at a disadvantage.
  What, you mean aside from the fact that Linux drivers for all those respective device manufacturers don't really get a whole lot of attention from the developers compared to Windows and OS X?
  But really, that's not important. What people need to pay attention to is that this is something done by Phoronix. This means you need to consider a couple things:
  * This benchmark is almost meaningless. Time and time again, I have seen them (falsely) correlate data with an assumption.
  * The review was done by someone who doesn't really know what they're talking about.
  * These are synthetics. Without context or understanding of what the benchmarks are doing (there is no explanation) or what may have led to the
  * The discrepancies are, in most cases, severe enough that you have to assume (at least) one of the following: their benchmark suite was not properly/identically configured for all architectures, or there are drastic implementation discrepancies within the benchmark tool they're using (eg. it wasn't designed but with a specific use case in mind).
  The reason there is "no clear winner" is because it's all rubbish. They're throwing 100 things at two different targets and comparing what misses and saying "no conclusion". Really? You'd have better consistency with an ink blot test of random participants, with ink blots generated by a true random number generator.
  Some of the graphics benchmarks don't stand out; the ones that stand out the most are the computational ones involving (very) standard libraries or frameworks which then contradict later results.
  For instance, CompileBench and Threaded I/O Tester: OS X falls flat on its face. The threaded I/O tester I believe, because I've seen the same with db and server performance. But earlier, they've got bgbench giving OS X four times the performance for postgresql as Linux. Is that even rational, given that even FileMaker has shyed away from OS X as a preferred platform due to threading and filesystem performance?
  Then, they go on to fail to explain these things and why they're fundamentally inconsistent. Not just "this doesn't quite line up, we can write it off due to different library version overhead" but in line with "this car goes faster because its engine is smaller". What?
  On a more personal level, I have used their suite of benchmark tools and come away fairly underwhelmed by the results. They're inconsistent and inexplicable, such as those seen in this review.
  Here's a hint, benchmarkers:
  * when you benchmark something, you must compare things and try to figure out why they are performing as they do.
  * If there are gross discrepancies which belay a reasonable expectation or contradicts other information, investigate it, because it's probably important
  * Be sure of what you're comparing. If you've got (more or less) identical binaries on different platforms and the hardware, you're just comparing the kernel. Is that what's happening here? Are their tools linked against native libraries (which would, you know, be an honest benchmark of said platform) or do they use their own stack?
  Anyway, I could go on, but you get the idea. This benchmark is stupid on its face. The only benchmarks I'd trust from this roundup here are those that are straight up "measure something real" (frames per second in x, time to complete concrete task y). They make a very different picture than when the synthetics are thrown in to the whole: overall OS X performance is pretty abysmal, but is marginally better at graphical things than Linux. This fits pretty close with my (personal) observation that OS X is about 10-15% slower than linux on general things, markedly slower on threaded things, and a dog at file manipulations while having a firm grasp on display management/graphical stuff - so it might just be my "uneducated Apple-hating bias" speaking. :)
  
  --
  ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
12. Re:surprise surprise by Anonymous Coward · 2012-08-23 13:13 · Score: 1
  
  Apple is for boys who don't have anything to shave.
  FTFY
13. Re:surprise surprise by epyT-R · 2012-08-23 13:17 · Score: 2
  
  ..the bias shows because his initial point is that all of them are hassles to different people, then he explicitly suggests linux is a hassle by default.
14. Re:surprise surprise by jbolden · 2012-08-23 16:17 · Score: 1
  
  This isn't about running Ubuntu, its a way to test out areas where the Linux kernel needs improvement. For example 9 watts OSX vs. 21 watts Ubuntu shows an area where Linux could use some help. Or the problems Linux has with dual video subsystems, an area for improvement. On the other hand the fact that Ubuntu was able to outperform OSX on SSD performance is likely an area in which XNU could use some help.
15. Re:surprise surprise by ardor · 2012-08-23 18:54 · Score: 1
  
  This isn't just because of the drivers. Its because Quartz is clearly superior to X11. Built from the ground up to make use of HW acceleration , most likely with a scenegraph-like approach, it outclasses X11 easily, which has an architecture that is an anachronism these days.
  An interesting comparison would be to run an OpenGL 2/3 benchmark tool on Linux, then on OSX, with nvidia hardware, then with ati/amd hardware.
  
  --
  This sig does not contain any SCO code.
16. Re:surprise surprise by hairyfeet · 2012-08-24 10:19 · Score: 1
  
  Sure they don't...until you update the thing and Linus takes a steaming dump all over your drivers! But don't take MY word for it, how about one of the Red Hat Developers who says the desktop is "suckage" and the entire system is broken? Are you claiming HE has a "bias" too? How about a list of things horribly broken in Linux and please note the date of the list is 2012 AND it has links to every. single. example. so you can check them for yourself.
  I repeat if you are willing to put up with a broken driver model (and don't give us the "If they'll only open their specs!" excuse because the other two work just fine without specs which makes it YOUR problem not ours) and updates breaking shit like its Win9X all over again, or have a reason such as server management or programming to run Linux? Enjoy, wish you nothing but luck. But expecting the average user to deal with that shit is like telling them "Hey want a free TV?" and when they say yes you hand them a pile of transistors andsome breadboards and say "Good luck LOL!". Because while there are plenty of "friendly" distros frankly they don't STAY friendly, that is unless you are willing to disable ALL updates and risk the machine ending up a broken mess or a zombie because it isn't patched. And oh yes Linux DOES have malware, I'll be happy to wallpaper the page with links to it if you'd like.
  
  --
  ACs don't waste your time replying, your posts are never seen by me.
and...? by Anonymous Coward · 2012-08-23 06:06 · Score: 1

How is any of this surprising and/or news? Mac OS X has been designed with the graphics card of MacBooks in mind. Other parts of the hardware don't require as much magic, so there's less difference...
Why is Linux's SSD performance so terrible? by MrEricSir · 2012-08-23 06:06 · Score: 4, Interesting

I made the mistake of "upgrading" two Ubuntu 12.04 desktops to solid state drives, only to find the performance increase was trivial.
What gives? The difference between magnetic drives and SSDs on OS X is incredible. Is this a driver issue, or what?

--
There's no -1 for "I don't get it."
1. Re:Why is Linux's SSD performance so terrible? by Sparticus789 · 2012-08-23 06:13 · Score: 5, Interesting
  
  PEBKAC. When I upgraded my Ubuntu laptop to SSD, boot time was under 10 seconds and my battery life while surfing the internet went from 3 hours to almost 5 hours. Not all SSDs are made the same, you have to research the performance of each, power draw, etc.
  That being said, I bought the SSD with the second-lowest power usage and middle-of-the-road performance.
  
  --
  sudo make me a sandwich
2. Re:Why is Linux's SSD performance so terrible? by Hatta · 2012-08-23 06:15 · Score: 4, Informative
  
  Linux caches disk reads pretty aggressively. If you have plenty of RAM, you might only notice a difference the first time you start an app.
  
  --
  Give me Classic Slashdot or give me death!
3. Re:Why is Linux's SSD performance so terrible? by cpu6502 · 2012-08-23 06:17 · Score: 5, Insightful
  
  That's Not what the article said. It said OS X had performance issues with solid state drives.
  Also I'm kinda curious: Why would spend twice as much to buy an Intel Mac PC if they're just running linux? I'd buy a regular PC for 1/2 to 2/3rd the cost.
  
  --
  My AC stalker: " I personally agree with your posts most of the time, but that won't keep me from modding you troll"
4. Re:Why is Linux's SSD performance so terrible? by 0123456 · 2012-08-23 06:35 · Score: 5, Informative
  
  I made the mistake of "upgrading" two Ubuntu 12.04 desktops to solid state drives, only to find the performance increase was trivial.
  If a process isn't disk-intensive, an SSD will make no difference. If it's not seek intensive, a cheap SSD may actually be worse; if I remember correctly, sustained reads from my 'Green' hard drive are 80-100MB per second, whereas one of my SSDs only gets about 40MB per second.
  The big benefit is reduced seek time, and a lesser benefit from faster sustained reads on the more modern and/or expensive SSDs. It won't make games run faster unless they're streaming from disk, or improve CPU-intensive 3D rendering, or anything much else that doesn't require a lot of disk seeks.
5. Re:Why is Linux's SSD performance so terrible? by 0123456 · 2012-08-23 06:37 · Score: 1
  
  Oh, and that cheap and crappy SSD cut my Ubuntu netbook's boot time from about 45 seconds to about 15 seconds.
6. Re:Why is Linux's SSD performance so terrible? by idsfa · 2012-08-23 06:42 · Score: 2
  
  Linux default config is optimized for spinning platters. You have to tweak a few things to get the best performance.
7. Re:Why is Linux's SSD performance so terrible? by Gothmolly · 2012-08-23 06:48 · Score: 1
  
  noatime
  Mounting filesystems with atime imposes a 15-20% penalty on IO due to increased writes. Troll the linux kernel lists for details.
  
  --
  I want to delete my account but Slashdot doesn't allow it.
8. Re:Why is Linux's SSD performance so terrible? by ByOhTek · 2012-08-23 06:48 · Score: 2
  
  True for notebooks, but I've know a lot of people who've gotten mac displays and put them on PCs... Though, there is some competition now, if you don't mind spending some absurd money. http://www.newegg.com/Product/Product.aspx?Item=N82E16824002660 Not sure how it's image quality compares with an Apple monitor though - usually you can't do better, only get parity.
  
  --
  Self proclaimed typo king, and inventor of the bear destroying coffee table (patent not pending).
9. Re:Why is Linux's SSD performance so terrible? by farble1670 · 2012-08-23 06:53 · Score: 1
  
  If a process isn't disk-intensive, an SSD will make no difference
  and almost all apps are relatively disk intensive (vs. CPU intensive) and hence IO bound. unless you are running something like BOINC that just crunches numbers.
  on my mac laptop (without SSD), the only time i see the CPU go above ~20% is when i start eclipse, and that's with 16GB of RAM.
10. Re:Why is Linux's SSD performance so terrible? by Anonymous Coward · 2012-08-23 06:57 · Score: 1
  
  What about Dell Ultra Sharps? I thought they were actually the same display as Apples. Once upon a time anyway.
11. Re:Why is Linux's SSD performance so terrible? by willy_me · 2012-08-23 07:06 · Score: 3, Interesting
  
  I would guess it is because OS X defragments the drive as it is being written. The overhead is largely not noticed when writing to a traditional hard drive while. Due to SSDs greater speed, it will make it appear that OS X has performance issues. The thing about performing inline defragmentation is it improves speed as the computer ages and as the HD begins to fill. Because all of the benchmarks were performed with fresh systems, the benefits of a defragmented drive would not be noticed.
  The question I have is with the low seek times of SSDs, is there still a need to defragment drives? Probably, but to what degree as it surely is not as important as when one is using a traditional hard drive.
12. Re:Why is Linux's SSD performance so terrible? by hobarrera · 2012-08-23 07:16 · Score: 1
  
  Some applications might break (such as mutt), though it's generaly safe.
  It should be noted that linux now uses relatime by default, which seems to be more efficiente than atime, but not break anything (like noatime).
13. Re:Why is Linux's SSD performance so terrible? by Sparticus789 · 2012-08-23 07:24 · Score: 4, Informative
  
  Defragmenting SSDs is not recommended, as it causes unnecessary use of the storage transistors. The speed associated with a SSD is a result of any block of data being accessible at any time, no hardware movement required.
  
  --
  sudo make me a sandwich
14. Re:Why is Linux's SSD performance so terrible? by Richard_J_N · 2012-08-23 07:31 · Score: 1
  
  Just double-check your BIOS: are you using the SSDs in the SATA native (AHCI) mode, or the old fashioned IDE mode? Also, are you using a SATA II (or III) rather than SATA I port? Remember that SSDs shine on random reads and writes: if you try to benchmark with something like hdparm -tT. you won't see much improvement.
15. Re:Why is Linux's SSD performance so terrible? by omnichad · 2012-08-23 07:49 · Score: 5, Informative
  
  Hope you mean TRIM and not defragmenting, which occurs when a file is deleted on an SSD, not when one is written. You don't defragment an SSD, as there's no gain at all.
16. Re:Why is Linux's SSD performance so terrible? by reallocate · 2012-08-23 07:59 · Score: 1
  
  I sure wouldn't buy a new MacBook to run Linux. But, I might switch this one to Linux if/when it can't handle a new OS X release.
  
  --
  -- Slashdot: When Public Access TV Says "No"
17. Re:Why is Linux's SSD performance so terrible? by SatiricComet · 2012-08-23 08:04 · Score: 1
  
  Isn't it obvious? Because you like the design of the hardware, and feel that the price difference is worth it. It's precisely the same reason someone would go buy a ThinkPad or similar upper-tier laptop and run Linux on it.
18. Re:Why is Linux's SSD performance so terrible? by CharlyFoxtrot · 2012-08-23 08:35 · Score: 3, Insightful
  
  Footprint, noise (or lack thereof), the ability to run all major OS (OSX, Windows, Linux) on the same machine, low power usage and nice looking sturdy construction. If you're going to be putting it on a desk the Mini is a nice little package.
  
  --
  If all else fails, immortality can always be assured by spectacular error.
19. Re:Why is Linux's SSD performance so terrible? by Daas · 2012-08-23 09:10 · Score: 1
  
  They still are but the 27" is in the same price range as the Apple. (Especially if you consider the purchase of the Dual-Link DVI Adaptor)
  You can buy some cheap 27" displays shipped from Korea for about 350$ that use the same panel as Apple and Dell. The stands are crap but the display itself looks amazing.
20. Re:Why is Linux's SSD performance so terrible? by willy_me · 2012-08-23 16:37 · Score: 1, Redundant
  
  Hope you mean TRIM and not defragmenting, which occurs when a file is deleted on an SSD, not when one is written.
  No, TRIM is not defragmenting. TRIM only occurs on SSD and is a result of how FLASH has to be written/erased.
  Traditional storage devices have storage elements with only two states - 1 or 0. These elements are then written to and read by the OS. SSDs are different as their storage elements have the same two states - 1 or 0, but also have an "empty" flag. You see, to write to a storage element that is not empty requires a rather lengthy erase procedure to be performed before the write. So to speed things up, SSDs maintain an "empty" status.
  But how does an SSD know when a storage element is empty? When a file is deleted all that happens is the FAT table is changed - the actual data does not get deleted. Over time, all available blocks in an SSD get marked as "not-empty" and that lengthy erase procedure is required all the time. This is where TRIM comes in, it allows for the OS to give the SSD hints by telling it certain blocks are in fact empty. The SSD can then pre-erase these blocks to ensure speedy future write operations.
  So that is TRIM - defragmenting is something else entirely. Look it up, it's basic stuff. But because SSDs do not offer truly random access, there is an advantage in having the file system defragmented. How much of an advantage is what I would like to know. If I had to guess I would say minimal.
21. Re:Why is Linux's SSD performance so terrible? by twistedcubic · 2012-08-23 16:44 · Score: 1
  
  I own two OCZ 30GB drives, one 60GB, and one 120GB. In every computer I placed them in, the difference was HUGE. Debian Squeeze and formerly Debian Lenny.
22. Re:Why is Linux's SSD performance so terrible? by twistedcubic · 2012-08-23 16:49 · Score: 1
  
  Seven hours of battery life, and very high resale values compared to Windows laptops. From my experience, 4 year old Windows laptops go for less than $100, while a similarly aged Macbook usually goes for 40%-50% original purchase price. Seriously, most cheap Windows laptops feel like toys. Macs don't.
23. Re:Why is Linux's SSD performance so terrible? by Sparticus789 · 2012-08-24 01:19 · Score: 2
  
  By PEBKAC, I mean the user is at fault for not doing his/her research and making sure the right SSD was purchased. He/she could have bought the wrong kind of SSD for what the user is doing, sequential read/writes or random read/writes.
  I saw a large performance increase in Ubuntu 12.04 by going to SSD, in boot time, application launch time, and any program which used swap space.
  
  --
  sudo make me a sandwich
24. Re:Why is Linux's SSD performance so terrible? by macshome · 2012-08-24 04:37 · Score: 1
  
  Apple disables the on the fly defrag if you are using an SSD
  
  http://opensource.apple.com/source/xnu/xnu-2050.7.9/bsd/hfs/hfs_readwrite.c
25. Re:Why is Linux's SSD performance so terrible? by Sparticus789 · 2012-08-24 04:42 · Score: 1
  
  Good to know. Also good to know that Windows 7 DOES NOT disable scheduled de-fragmenting. At least on my Windows laptop. User be warned.
  
  --
  sudo make me a sandwich
Summary of tests? by GoNINzo · 2012-08-23 06:10 · Score: 5, Interesting

15 pages of a review, with a poor summary of the results, results in the most number of page views. It would have been nice if they had some sort of summary or benchmark to compare the two against rather than individual tests spread across this. Perhaps a summary chart?

Also, comparing a well tuned video device driver versus the (usually) hastily written Linux one is a poor comparison.

I really doubt people choose a mac over Linux over this kind of test. There more solid reasons to choose one or the other.

--
Gonzo Granzeau
"Nothing the god of biomechanics wouldn't let you into heaven for.." -Roy Batty
1. Re:Summary of tests? by butalearner · 2012-08-23 06:14 · Score: 2
  
  15 pages of a review, with a poor summary of the results, results in the most number of page views. It would have been nice if they had some sort of summary or benchmark to compare the two against rather than individual tests spread across this. Perhaps a summary chart?
  Funny, I never bothered looking at the link, but from this comment alone it was obvious that it's a Phoronix article.
2. Re:Summary of tests? by farble1670 · 2012-08-23 06:55 · Score: 1
  
  I really doubt people choose a mac over Linux over this kind of test.
  i really doubt many people would be dull enough to pay top dollar for mac hardware just to run linux.
3. Re:Summary of tests? by wile_e_wonka · 2012-08-23 06:55 · Score: 1
  
  comparing a well tuned video device driver versus the (usually) hastily written Linux one is a poor comparison.
  Uhhhh, why? That was the point of the test. Same hardware, different software, what is the performance difference?
4. Re:Summary of tests? by Anonymous Coward · 2012-08-23 07:40 · Score: 1
  
  Well, Linus Torvalds is apparently "dull enough" to use a Macbook Air.
5. Re:Summary of tests? by farble1670 · 2012-08-23 07:49 · Score: 1
  
  and linus torvalds has the same sensibilities and motivations as the average consumer, right? sheesh.
  also, did you know bill gates is running windows on his laptop? did you know sergey brin has an android phone? other shocking facts omitted for brevity.
6. Re:Summary of tests? by GoNINzo · 2012-08-23 08:52 · Score: 1
  
  Uhhhh, why? That was the point of the test. Same hardware, different software, what is the performance difference?
  Er, the point of the test was to generate page views. But yes, a graph showing the clear winners and losers at the end in the summary would have been helpful. At least with Tom's Hardware, they put a summary of the different pages.
  
  --
  Gonzo Granzeau
  "Nothing the god of biomechanics wouldn't let you into heaven for.." -Roy Batty
7. Re:Summary of tests? by styrotech · 2012-08-23 09:12 · Score: 1
  
  Funny, I never bothered looking at the link, but from this comment alone it was obvious that it's a Phoronix article.
  I find you can usually pick them by the Slashdot article title alone.
  If it is the latest Ubuntu benchmarked against anything else, or comparison benchmarks of some recent GPU on Linux or the latest Xorg drivers etc - 98 times out of 100 it will be Phoronix.
  Nobody else ever bothers - or if they do, it never makes it to slashdot. Which is a shame, it would be nice to see those comparisons done properly.
8. Re:Summary of tests? by savuporo · 2012-08-23 09:33 · Score: 1
  
  Also, comparing a well tuned video device driver versus the (usually) hastily written Linux one is a poor comparison.
  
  I read this as : Linux is not for critics, because hastily written graphics drivers that mostly suck is what you get with it ?
  
  --
  http://validator.w3.org/check?uri=http%3A%2F%2Fwww.slashdot.org Errors found while checking this document as HTML5!
9. Re:Summary of tests? by farble1670 · 2012-08-23 18:33 · Score: 1
  
  if you were able to follow a simple conversation thread, you would have understood that i wasn't saying linus is abnormal for liking mac hardware, he's abnormal for wanting to install linux over osx.
Graphics by Anonymous Coward · 2012-08-23 06:32 · Score: 1

The graphics tests were run with Intel graphics. Linux results may have been more competitive if AMD or Nvidia graphics were used. Ubuntu 12.04 has gotten a large FPS jump in some games using AMD or Nvidia. I don't have the magazine in front of me right now.
Worthless... by Thinine · 2012-08-23 06:48 · Score: 5, Insightful

Yet another worthless benchmarking from Phoronix (Moronix, amirite?). They switch between compilers, compiler versions, and even use Xcode itself for some of these comparisons, which make it essentially worthless. Add to that absolutely zero investigations of the reason for differences between the platforms (aside from the obvious mention of graphics drivers) and this is yet another piece of benchmark porn from a site dedicated to it.
1. Re:Worthless... by Gothmolly · 2012-08-23 12:45 · Score: 1
  
  They're the OSNews of the 2010 decade.
  
  --
  I want to delete my account but Slashdot doesn't allow it.
2. Re:Worthless... by F.Ultra · 2012-08-23 21:14 · Score: 1
  
  But still, how many out there installs custom compilers and recompile everything with that instead of using the supplied version by the distribution?
Re: Why an Intel Mac PC to run linux? by sl956 · 2012-08-23 07:00 · Score: 5, Informative

Also I'm kinda curious: Why would spend twice as much to buy an Intel Mac PC if they're just running linux? I'd buy a regular PC for 1/2 to 2/3rd the cost.
I looked for a silent small footprint linux pc. I was unable to find one. That's why I bought a Mac Mini. It runs Linux flawlessly... and silently thanks to the fanless design and SSD.
People wanting an HD screen on a laptop might also have to buy Apple hardware even though they plan to use only Linux.
Re:Bottom line.. by Anonymous Coward · 2012-08-23 07:35 · Score: 2, Funny

Not if the cancer gets you first.
Wrong interpretation of the results, favors OSX by tstrunk · 2012-08-23 07:36 · Score: 3, Informative

If you read the whole article you will see that there are many computing intensive benchmarks, where Linux outperforms OSX by nearly a factor of two. Saying that there is no noticeable difference is simply wrong (see Page 11, Page 12).
1. Re:Wrong interpretation of the results, favors OSX by tlhIngan · 2012-08-23 07:58 · Score: 2
  
  If you read the whole article you will see that there are many computing intensive benchmarks, where Linux outperforms OSX by nearly a factor of two. Saying that there is no noticeable difference is simply wrong (see Page 11, Page 12).
  That makes sense. Mac OS X is a "microkernel" based system and does a lot stuff passing around Mach messages.
  OS X is also inefficient in that each process gets its own address space - for a 32-bit process, that's 4GB of address space it can use all of (no 2/2 or 3/1 user/kernel split - every process, including the kernel gets it's own independent 4GB area). The problem with this is that in order to access application buffers (system calls, say), the kernel must map the buffer into its address space first, which is far more expensive than translating a pointer and dereferencing that.
  OS X should be slower purely because it's a higher overhead OS.
2. Re:Wrong interpretation of the results, favors OSX by tstrunk · 2012-08-23 08:06 · Score: 1
  
  way to cherry pick results and ignore the overall scores.
  Let me read the article for you, if you don't believe me. Btw. there are no overall scores, there's just a biased conclusion.
  Page 11 and 12 were simple examples, where there was a factor of two.
  Page 1: no benchmarks
  Page 2: Ubuntu is faster in three benchmarks, two ties
  Page 3: Graphics, OSX wins
  Page 4: Graphics, OSX wins
  Page 5: Ubuntu loses in all SciMark benchmarks, wins in two others (once by a factor of 4)
  Page 6: Ubuntu wins in Imagemagick (against 10.8) loses in Php compilation (but not by much)
  Page 7: Ubuntu wins by a large margin twice, loses by a small margin twice
  Page 8: Ubuntu wins by a large margin twice
  Page 9: Ubuntu, tie, win, big win
  Page 10: Graphics, OSX wins
  Page 11: Tie, big win, big win, tie
  Page 12: 4*Tie, big win
  Page 13: Tie, win, win, lose/tie(12.04/12.10)
  Page 14: Tie, big win, big win
  Page 15: conclusions.
  So let me tell you: All the "big wins" are DEVASTATING for OSX. They mean that you need to wait DOUBLE the time for your results.
  I did not contest that OSX won graphics wise, but it is very clear that linux won the number crunching.
3. Re:Wrong interpretation of the results, favors OSX by CAIMLAS · 2012-08-23 13:07 · Score: 1
  
  The whole thing is a sham, but you're right: aside from the graphics drivers, Linux hands OS X its ass.
  Look through it again (with adblock on, don't let those bastards have another cent of deceptively gained ad revenue), this time mentally excluding all of the synthetic benchmarks (which all seem to be grossly wrong on this review, in favor of OS X). What do you notice? Aside from a couple linear and potentially single core tasks, OS X gets trounced. They were probably paid for these modifications to skew towards OS X - or they had a hidden desire to favor OS X. That, or they wanted more page views and to do that, they needed a controversial article...
  
  --
  ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
4. Re:Wrong interpretation of the results, favors OSX by Anonymous Coward · 2012-08-23 14:56 · Score: 1
  
  If you read the whole article you will see that there are many computing intensive benchmarks, where Linux outperforms OSX by nearly a factor of two. Saying that there is no noticeable difference is simply wrong (see Page 11, Page 12).
  That makes sense. Mac OS X is a "microkernel" based system and does a lot stuff passing around Mach messages.
  I'm afraid you are wrong two ways, here.
  One is that OS X is not a microkernel OS. It does still support Mach messages -- but only for userspace IPC. The kernel itself is monolithic. Mach code, BSD code, and Apple's custom code all live in the same address space, using function calls for internal communication. A true microkernel would partition bits and pieces into independent address spaces and use messaging to communicate between them. (It's best to think of Mach as a bit of foundation code you can build a full OS on top of. It has a lot of facilities useful for building microkernels, but you don't have to use them that way.)
  The other is that it doesn't actually make sense for number crunching performance to be heavily dependent on mono-vs-microkernel performance issues. Number crunching software is often the least sensitive to that sort of thing. Ideally all it should care about is being handed memory and as close to 100% of the CPU as it can get.
  
  OS X is also inefficient in that each process gets its own address space - for a 32-bit process, that's 4GB of address space it can use all of (no 2/2 or 3/1 user/kernel split - every process, including the kernel gets it's own independent 4GB area). The problem with this is that in order to access application buffers (system calls, say), the kernel must map the buffer into its address space first, which is far more expensive than translating a pointer and dereferencing that.
  You're out of date. IIRC, the 4/4 split does not exist in 64-bit Darwin. Instead they use the larger address space to map userland and kernel simultaneously, much like 2/2 or 3/1 splits in 32-bit kernels. TFA's tests covered 10.7 and 10.8; as of 10.7, the 64-bit Darwin kernel is the default on most supported Macs. And as of 10.8, the 64-bit kernel is the only one available (the 32-bit one went away).
5. Re:Wrong interpretation of the results, favors OSX by jbolden · 2012-08-23 16:25 · Score: 1
  
  XNU is not nearly as good a kernel as the Linux kernel. And in terms of filesystems OSX has fallen way behind everyone.
  There are areas where Apple is excellent, deep plumbing is not one of them.
Re: Why an Intel Mac PC to run linux? by dfghjk · 2012-08-23 07:59 · Score: 2

Mac Minis are not fanless designs nor are they silent.
Isn't Hybrid Video the Big MacBook Issue for Linux by reallocate · 2012-08-23 08:04 · Score: 1

Isn't the biggest video hassle with Linux on MacBooks the hybrid graphics?
Rather than being able to switch back and forth, I'd prefer just disabling use of the onboard Intel graphics altogether, assuming fan control was well in hand.

--
-- Slashdot: When Public Access TV Says "No"
Re:Isn't Hybrid Video the Big MacBook Issue for Li by jo_ham · 2012-08-23 08:15 · Score: 1

Isn't the biggest video hassle with Linux on MacBooks the hybrid graphics?
Rather than being able to switch back and forth, I'd prefer just disabling use of the onboard Intel graphics altogether, assuming fan control was well in hand.
That will affect battery life though, assuming that matters to you. For day to day desktop tasks, the HD3000/HD4000 is more than adequate and sucks down much less power than the dedicated GPU. Were I running Linux on a hybrid GPU system I'd want it to be able to use the integrated GPU when the demand was low.
Re: OS X Mountain Lion was clearly superior by jo_ham · 2012-08-23 08:16 · Score: 2

LOL. Lin-sux loses AGAIN. Time to give up, dipshits. Open source should be renamed open failure.
Think different.
Think BETTER.
Think Apple!
I think you're trying too hard, kid.
0/10.
Lots of graphs, worthless analysis by CadentOrange · 2012-08-23 08:35 · Score: 3, Insightful

The compilation benchmarks are not comparable as the compilers are different, not only in version number but in architecture! OS X ships with llvm-gcc, which is a different compiler from GCC. Think of it a LLVM pretending to be GCC (accepting GCC options, etc) for backward compatibility. This would explain the huge discrepancies between the results of the compilation benchmarks
Disk performance is another thorny issue. The Postmark benchmark shows Ubuntu 12.04 being 3x faster than OS X 10.8 (246 tps vs 80 tps), yet the postgresql database benchmark shows OS X to be 3x faster than Ubuntu. No explanation is even attempted. Why? Readers would like to know! How can OS X be faster at a database benchmark when a raw disk benchmark shows it to be a lot slower than Ubuntu?! Perhaps there's something screwy with the configuration of Postgres on Ubuntu? Does this mean that OS X is *THE* choice for hosting busy databases? My suspicion is that this is due to fsync (http://www.postgresql.org/docs/8.1/static/runtime-config-wal.html). If fsync is enabled, the database waits for the transaction log to be flushed to disk every time a transaction is committed. It's basically down to defaults, and who knows what the default values are for Postgresql on OS X vs Ubuntu?
The graphs raise far too many questions that are not addressed. Many of them should have raised warning flags, like the one about disk performance vs actual database performance. As such, the results are thoroughly suspect and no reasonable conclusions can be drawn. Pity, because they clearly have the kit just not the knowhow.
1. Re:Lots of graphs, worthless analysis by gsnedders · 2012-08-24 00:18 · Score: 1
  
  XNU is not a microkernel, and never has been. Yes, it's ultimately derived from Mach, but it contains large parts of BSD-derived code in the kernel too (originally from BSD4.3, now FreeBSD). Everything within the kernel is done by direct function calls, not message passing as with a microkernel.
Re: Why an Intel Mac PC to run linux? by CharlyFoxtrot · 2012-08-23 08:41 · Score: 4, Informative

I have the older style Mini and when the HDD goes to sleep and it runs on SSD-only it's damn near completely silent. The fan will only come on when really stressing the cpu.

--
If all else fails, immortality can always be assured by spectacular error.
Open source drivers by Chemisor · 2012-08-23 08:42 · Score: 2

Intel graphics on Linux uses the open source Mesa/Gallium stack, which still has significantly lower performance than the proprietary drivers. Frankly, I'm wondering if the GPU is being used at all. I have a Radeon 6870, and with open source radeon driver I don't see any acceleration. For example, a full-screen xterm with Midnight Commander takes a full half-second to draw the frame with only 160x50 char cells. With fglrx 12.8, the drawing time is not noticeable at all. The Mesa radeon feature matrix says R600 should have full GPU acceleration for all X calls, but something is just not working right. I'm guessing something similar might have happened with the benchmarks.
1. Re:Open source drivers by Vegemeister · 2012-08-23 11:44 · Score: 1
  
  Are you actually using xterm, or is it one of the libvte based terminals (gnome-terminal, xfce4-terminal, ect.)? I recently encountered some pretty serious performance issues with libvte. Try Konsole, or urxvt if you want something less heavy.
2. Re:Open source drivers by Chemisor · 2012-08-23 12:21 · Score: 1
  
  Are you actually using xterm, or is it one of the libvte based terminals (gnome-terminal, xfce4-terminal, ect.)?
  I'm using xterm. gnome-terminal is actually faster because it uses Xrender to draw the text, while xterm relies on Xft. Under fglrx gnome-terminal is awesomely fast, with no flicker at all. Unfortunately, vte-based terminals flash the gray background when you switch to them. They also have that ugly resize handle in the lower right corner that nothing can remove. Oh, and gnome-terminal captures F10 (which you need to quit Midnight Commander). So, no thanks. With fglrx xterm is fast enough.
Re:Isn't Hybrid Video the Big MacBook Issue for Li by reallocate · 2012-08-23 09:22 · Score: 1

Battery life isn't an issue for me. I'd rather have a stable system that defaulted to one or the other GPU than a flaky one that tried to do the automatic switch.

--
-- Slashdot: When Public Access TV Says "No"
Re: Why an Intel Mac PC to run linux? by VortexCortex · 2012-08-23 10:06 · Score: 1

I have the older style Mini and when the HDD goes to sleep and it runs on SSD-only it's damn near completely silent. The fan will only come on when really stressing the cpu.
Psh, that's not fixing the real issue. You should solve the problem at it's source. My heatsink fans could be a pair of turbo props, and I still wouldn't hear it them.
Now, where was I? Look, I don't know or care if this is my lawn or not, but you better get to stepping!
Now do this... by Anonymous Coward · 2012-08-23 10:28 · Score: 1

Put OSX and Ubuntu on a PC based system then compare, or better yet: compare the averages. This would be a more accurate comparison.
Re: Why an Intel Mac PC to run linux? by SimonTheSoundMan · 2012-08-23 11:11 · Score: 1

Apple have had either 1440x900 or 1680x1050 for their 15 inch line.
Re: Why an Intel Mac PC to run linux? by gerardrj · 2012-08-23 11:54 · Score: 1

The fan is ALWAYS on. I think idle for the older Mini's fan is 1,200 RPM and max of about 5,500RPM.

--
Article X: The powers not delegated... by the Constitution...are reserved...to the people
Would Wayland do better? (hypothetically) by belgianguy · 2012-08-23 23:02 · Score: 1

Isn't the 'low score' region of Ubuntu (graphics performance) being worked on by the Wayland compositor? While still a release or two down the road, would that be able to improve said tests? Or is the problem broader than that?
Re: OS X Mountain Lion was clearly superior by jo_ham · 2012-08-24 02:03 · Score: 1

LOL. What's sadder, that I keep checking back for responses or that you keep making them? Eh "pops"? You keep trying to make your comebacks sound edgy and cool and you keep failing. Kind of like Linux! LOSER!
Think Different.
Think BETTER.
Think Apple!
Like I said, slashdot emails me when I get a response to my logged-in comment, so it's easy for me to click on the link and reply. I don't have to spend time checking back on all my responses - if someone replies, slashdot lets me know!
Hopefully one day you'll discover the convenience of logging in and replying by clicking on an email link!
It looks like you haven't quite mastered it yet. Keep trying! You'll get it eventually! One day you'll make us proud!