Is Ubuntu Getting Slower? 544
An anonymous reader writes "Phoronix has a new article where they provide Ubuntu 7.04, 7.10, 8.04, and 8.10 benchmarks and had ran many tests. In that article, when using an Intel notebook they witness major slowdowns in different areas and ask the question, Is Ubuntu getting slower? From the article: 'A number of significant kernel changes had went on between these Ubuntu Linux releases including the Completely Fair Scheduler, the SLUB allocator, tickless kernel support, etc. We had also repeated many of these tests to confirm we were not experiencing a performance fluke or other issue (even though the Phoronix Test Suite carries out each test in a completely automated and repeatable fashion) but nothing had changed. Ubuntu 7.04 was certainly the Feisty Fawn for performance, but based upon these results perhaps it would be better to call Ubuntu 7.10 the Gooey Gibbon, 8.04 the Hungover Heron, and 8.10 the Idling Ibex.'"
Ubuntu isn't getting slower, no. (Score:0, Insightful)
Your laptop IS, on the other hand, getting OLDER, and while your hardware might not be changing the requirements put upon hardware are.
Complete bullshit article, doesn't offer any useful information beyond a completely obvious conclusion -- the more features that are added to a given piece of software, the higher the demands on your PC. The only reason they've turned this into an "Ubuntu is getting slower" argument is precisely so that they can start debates like these and drag more people onto their ad laden site.
Not a lot different from the tactics that Slashdot has been using for years, really.
What hardware? (Score:5, Insightful)
Were they testing each distribution on exactly the same hardware?
If so, that sounds completely fair to me that it would be slower. Go and (try to) install Vista on a machine that originally came with XP (pre-SP1) and see how much slower it is. Is that a fair test either? I think not.
As software gets more useful (and Ubuntu has, Vista not so much) it gets bigger and thus gets slower on the same hardware. Hardware advances at the same time though, so in real terms they keep about equal. When you test new software on old hardware of course it's going to be slower though.
Re:Performance isn't its raison detre (Score:5, Insightful)
It's nice to see that the Ubuntu fanboys have moved so quickly to 'shut up and like it'.
It took Windows fanboys a decade to get there...
Re:Had went on? (Score:5, Insightful)
Why should I read this FA if the author apparently didn't finish high school?
The anonymous submitter and CmdrTaco's grammar skills have little to do with performance in Ubuntu. RTFA; it makes a good point and I for one hope that this observation is accepted by the Ubuntu developer's and something is done about it.
Maybe (Score:1, Insightful)
Yeah I know - all these new Linux users don't like Slackware. It's so.. Linux like, and not Windows like. Perhaps Ubuntu can work on optimization and take care of the problem.
Re:Ubuntu isn't getting slower, no. (Score:0, Insightful)
xubuntu (Score:3, Insightful)
Re:Had went on? (Score:5, Insightful)
Why should I read this FA if the author apparently didn't finish high school?
Because intelligence and wisdom have nothing to do with "finishing high school"? I've got nothing past GCSE [wikipedia.org]s. Luckily for me, employers in the UK see past that.
Re:What hardware? (Score:5, Insightful)
Re:Ubuntu isn't getting slower, no. (Score:5, Insightful)
Complete bullshit article, doesn't offer any useful information beyond a completely obvious conclusion -- the more features that are added to a given piece of software, the higher the demands on your PC.
I would think that those increased demands should be mostly in the form of slightly (a few MB) higher memory requirements to store the extra code for those features. Adding new functionality should not impact existing functionality. Haven't you heard of the zero-cost principle (idea from C++ and apparently Perl, "you don't pay for (as in take a performance hit from) what you don't use")?
Comment removed (Score:5, Insightful)
Re:Had went on? (Score:2, Insightful)
Reasons include:
1. Determining if the error is in the article or in the summary.
2. Determining if the article is riddled with errors or if the summary highlights an uncommon occurrence.
3. Determining if the article's substance is good despite presentation and communication problems.
4. Not having a knee-jerk impulse to ignorantly flame strangers on the internet.
The article could be written by a dyslexic, Sumatran orangutan, yet full of useful data. You'll never know.
Re:What hardware? (Score:5, Insightful)
I heard this argument a wee too often. Maybe software should be more useful while at the same time NOT getting slower? Maybe that would be a good thing, as it would then run well on netbooks as well, what do you think?
Re:What hardware? (Score:5, Insightful)
You make it sound like it is inevitable and acceptable that newer software is slower than older software. I disagree. For one thing, one way to improve software is to make it faster. This is actually done sometimes. Secondly, even if you add features to software (which is another way to improve software), that doesn't have to make the software slower. In some cases, this may be inevitable, but in many cases it is not.
I personally see computers, and software, as tools for making life more efficient. When software becomes slower, efficiency is actually lost. When this isn't offset by providing me with a more efficient work flow, I lose efficiency. Since efficiency is the main reason I use computers in the first place, this is a big deal.
Slackware? No easy way. (Score:1, Insightful)
Doesn't "Slackware" mean "I am too lazy to make it easy to install." ?
Re:How significant? (Score:3, Insightful)
``As we add complexity and layers of abstraction things tend to slow down in general. If hardware keeps up, and actual human productivity increases, do we have an issue?''
You have that exactly right. Software getting slower is bad, but it's ok if it is offset by other changes, such as faster hardware or new, more efficient ways to perform tasks. In the end, it's our productivity that counts. Now the real question is, how do we measure that, how has it developed over time, and what changes have had the greatest impact (both positive and negative) on it?
Re:Ubuntu? No way. (Score:5, Insightful)
"Ubuntu" -- an African word, meaning "I'm sick of fucking with Linux in order to get it to do what I want but I really don't like the alternatives."
Yeah, I rocked Gentoo for a couple of years. I just want something that is fast, easy to use and gives me as little of a headache as possible. Linux is Linux and most of the knowledge learned in one distro will carry-over to another.
Re:What hardware? (Score:3, Insightful)
That would be true if software was given 100% CPU devotion. But software doesn't operate in a bubble like that and hence other needs are given CPU time, in turn slowing things like the LAME encoder down.
It's something worth noting though, it's a real performance hit and perhaps something can be done about it in future releases.
Comment removed (Score:5, Insightful)
Re:What hardware? (Score:3, Insightful)
GTK performance stats? (Score:5, Insightful)
The GTK+ statistics are mind-boggling slow. That's what I notice most when I use Ubuntu or Fedora. On my non-Ubuntu laptop, I get the following results for GTK performance:
GtkDrawingArea - Pixbufs: 3.73s (on mine) vs 43-55s (Ubuntu)
GtkRadioButton: 13s vs 29-60s
I just think that's ridiculous. What did they do to GTK+ to make it so slow?
Re:Ubuntu isn't getting slower, no. (Score:3, Insightful)
Re:Maybe (Score:2, Insightful)
Because Ubuntu uses generic kernel builds and starts up unneeded shit at boot time. You also have frontend apps for a lot of apps that don't really need it - that can explain the reason the memory is being eaten up. Suggestions? Learn how to compile a kernel, or use a distribution that doesn't have a list of memory eating apps specific to itself, like Slackware for example. I've never had issues with it, and I've gotten the kernel to finish booting in 6-7 seconds with only the device support and services i only need. Yeah I know - all these new Linux users don't like Slackware. It's so.. Linux like, and not Windows like. Perhaps Ubuntu can work on optimization and take care of the problem.
Because Ubuntu uses generic kernel builds and starts up unneeded shit at boot time. You also have frontend apps for a lot of apps that don't really need it - that can explain the reason the memory is being eaten up. Suggestions? Learn how to compile a kernel, or use a distribution that doesn't have a list of memory eating apps specific to itself, like Slackware for example. I've never had issues with it, and I've gotten the kernel to finish booting in 6-7 seconds with only the device support and services i only need. Yeah I know - all these new Linux users don't like Slackware. It's so.. Linux like, and not Windows like. Perhaps Ubuntu can work on optimization and take care of the problem.
what a way to waste my mod points but anyway here goes...
:)
There's no need to be so smug and condescending. If you're a supporter of F/OSS, then you should be happy people are trying out some distro. Of course you'll never get the same performance out of the one-size-fits-all approach of Ubuntu, but that's not the point of the more newbie friendly distros. The whole point of them (i'd include openSUSE, Mandriva and Scientific Linux) is to 'just work', or with as little mucking about in the terminal as possible. It takes time to learn the intricacies of a different OS, especially if you've never used any *NIX OS. Personally I started on a Sinclair Spectrum
If you have the time, desire, or need to have a highly optimised kernel, the you have the choice to use something like Gentoo or Slackware. For the rest of us, precompiled binaries work fine, thank you (with exceptions of course), and that kind of negative attitude puts people off trying out, and learning about GNU/Linux.
Re:What hardware? (Score:3, Insightful)
Flexibility and freedom are its raison d'Ãtre (Score:5, Insightful)
I currently have three Ubuntu-based systems. I have customized the GNU/Linux distribution for each system. Anyone can do it.
One of the computers is an old (1998) Thinkpad notebook that doesn't have the video capability to run the full Ubuntu-Gnome GUI well. I do a minimal installation (the minimal CD is an official distribution of Ubuntu), then install about 25 select packages using a script that I call "Thinbuntu". This gives me a very functional GNU/Linux desktop for the old Thinkpad with the Long Term Support of the Ubuntu package system, including updates. It has all the features I need.
Microsoft simply can't compete with this.
Re:Had went on? (Score:5, Insightful)
I just read it and found it pretty devoid of information. It is one of those mindless performance reviews in as many pages as possible.
Where are any measurements that look at where performance was lost? Running just the distros does nothing to isolate what got slower. Trying different kernels and different X servers would at least show an attempt at understanding what's going on. Why didn't they compare at least one Ubuntu version with a similar Fedora version, let alone Kubuntu or xubuntu?
As I expected: If a site employs people who can't write and has no editorial control that would weed out a glaring error like this you can't expect anything but quick and dirty superficial work. If an error like this that just jumps at you isn't caught, how many subtle errors in the data should I expect?
Re:Performance isn't its raison detre (Score:5, Insightful)
Why do you think this? I mean do you have a good reason or is it just because you don't like mono?
Take a look at some of the tests.
"Computational: The Dhrystone 2 performance within the BYTE Unix Benchmark was also the fastest on Ubuntu 7.04. There was approximately a 20% drop in performance between 7.04 and 7.10 that remained consistent even in the 8.04 and 8.10 releases. "
This is NOT in mono.
"Database: In our SQLite test of measuring the time to perform 2,500 SQL inserts, the performance hadn't dropped off after Ubuntu 7.04 but instead after 8.04 LTS. In this performance drop it was over 2.5x slower. "
SQLlite isn't written in mono.
"but in our compilation benchmarks we spotted major performance losses following the Feisty Fawn release. It was noticeably slower to compile Apache, PHP, and ImageMagick in the 7.10, 8.04, and 8.10 releases."
GCC isn't written in mono.
I could go on and on but many of the benchmarks have nothing to do with mono at all.
Heck I am not a big fan of mono but your statment is baseless.
You're completely wrong (Score:5, Insightful)
In other words, Ubuntus' not getting slower. The software that Ubuntu bundles is getting slower.
It's likely due to GCC's epic failure to better optimize code as 4.x progresses, but I'm not putting my money on anything until they've tested at least one other distro which builds with a different GCC version.
Re:Ubuntu? No way. (Score:5, Insightful)
Ubuntu gives me some of the strengths I liked (such as a simple, straightforward package manager, wide amount of customization without too much screwing around) without too many of the weaknesses (compiling all software, praying emerging the world doesn't break my desktop, so on and so forth).
It's not a bad distro at all and it's tiring to hear of people slamming it for not being Slackware or Gentoo. This may come as a revelation, but Linux is about choice.
Too much Python (Score:1, Insightful)
Subject says all *AC hides under rock*
Re:What hardware? (Score:3, Insightful)
That assumption, that software gets slower as newer versions come out, is the "Windows Effect". People have grown up with Windows bloatware and assume that behavior is the norm. They are more concerned with adding new bells and whistles and not revisting existing code. When I work on software releases one of the main things we do is not only add new functionality but improve the performance of existing code, especially by taking advantage of new hardware/db tech features.
Re:Ubuntu? No way. (Score:5, Insightful)
I was pretty much exactly the same.
Turning point for me was realizing that I was compiling more and more in, just in case I needed it, because rebuilding world just to enable that new USE flag was getting kind of old.
In other words, I was using it like Ubuntu. The only advantage I had was I would compile for -march=i686, and other optimizations which produce binaries which only work on recent CPUs (the '686' class) -- whereas Ubuntu was -mtune=i686, if I remember, so it was possible to run on a 486, but would run best on a 686.
And, hey, there were other things I would turn on that were Athlon XP specific, and so on... then I realized that, on amd64, the optimizations were basically exactly the same -- merely compiling for x86_64 gave me all the benefits anyway. At which point, what the hell -- Ubuntu would necessarily be at least as optimized as my Gentoo.
And, more recently, I've realized that since switching to Ubuntu, I spend much more time actually using the OS, rather than tweaking it. Despite having it already much more customized than any version of Windows ever was, I still don't spend as much time tweaking it as it takes to maintain Windows, let alone Gentoo.
Re:Flexibility and freedom are its raison d'Ã (Score:3, Insightful)
I can disable services I don't want. I can uninstall (or simply not install at the outset) components I don't need. I have the control panel to customize, e.g., the video depth and turn off video-hungry components.
In all seriousness: at this level (not the recompile level), what's the difference?
Linux (and Unix for the most part) tends to be a lot more modular than Windows. Windows does provide options. But not to the same degree. If you want to really dig in to a Windows system, it takes a lot more shennanigans than it does with a Linux distro (and then you're at the risk of losing all your changes at the next service pack).
Note that this isn't an Open Source thing. Proprietary Unix environments tend to work much in the same way.
One final point - Linux is no silver bullet. You still have to make trade-offs. There are still dependencies involved and removing something might mean removing a desired application. However, I've rarely run in to a situation where that decision is all that difficult or unexpected.
Re:Flexibility and freedom are its raison d'Ã (Score:3, Insightful)
Apart from XP Embedded, where you can choose which parts of the OS are installed.
I've heard of such a beast but never have seen it. I would hazard to guess that XP Embedded isn't accessible to most folks; it's not an option with their standard XP install. In contract, anyone who has access to Ubuntu could go this "Thinbuntu" route.
Re:Flexibility and freedom are its raison d'Ã (Score:2, Insightful)
Re:Performance isn't its raison detre (Score:2, Insightful)
It's nice to see that the Ubuntu fanboys have moved so quickly to 'shut up and like it'.
It took Windows fanboys a decade to get there...
That's because today's Ubuntu fanbois are yesterday's Windows fanbois.
Re:Flexibility and freedom are its raison d'Ã (Score:2, Insightful)
Linux (and Unix for the most part) tends to be a lot more modular than Windows. Windows does provide options. But not to the same degree. If you want to really dig in to a Windows system, it takes a lot more shennanigans than it does with a Linux distro
Indeed. I might have to go install something like XPLite or create my own installation media with nlite/vlite. It's really taxing firing up a GUI and unticking a few boxes.
Re:Progress vs Motion (Score:3, Insightful)
What goal do you perceive Ubuntu to be moving toward
Fixing bug #1 [launchpad.net], of course.
No wonder you posted AC (Score:4, Insightful)
"If you really want performance, run FreeDOS. Otherwise, shut up and get used to progress."
Jeez you're an idiot. I wouldn't have posted that under a registered nick either.
So people should just settle for bloat simply because of the advance of technology? Apple manages to make OS X faster than older versions. Other Linux distros do. Bad software isn't "progress".
Re:No wonder you posted AC (Score:3, Insightful)
let me fix that for you.
"Apple manages to make OSX faster on new hardware"
i seriously doubt anyone will say that OSX 10.0 runs slower on a 4 year old 1gb ram intel chip than OSX 1.5.whatever.
it's callled progress.
More features are added because people want them.
thus after a while, the original hardware is no longer the best solution to run the latest version of the OS.
So Xorg, Linux, GCC == Ubuntu? (Score:3, Insightful)
This would remain true if Ubuntu were replaced with $DISTRO.
Re:Flexibility and freedom are its raison d'Ã (Score:5, Insightful)
Not even talking about the advantage of being free:
- for optimization, I can select the window manager
- for optimization, I can select the desktop environment
- I get full compatibility with the open-source ecosystem
- I can install programs from the huge apt-get application universe (including programming languages and tools)
- I run it all from a very short script, unattended
- it is fully supported, with automatic updates and no nonsense
Re:No wonder you posted AC (Score:2, Insightful)
Oh, so "RAM Intensive" is Apple fan boi speak for "Slower" than, right?
Turtle Necked Gentleman: Whoa, the new version of Mac OSX is totally RAM Intensive!
Turtle Necked Gentleman's Companion: Why are you surprised? Apple is always working hard on adding new features!
Turtle Necked Gentleman: No joke! The new version's Ram intensivity is radical!
Re:Why a laptop? What about a desktop? (Score:4, Insightful)
First, I use ThinkPads regularly (due to deep discount available through a workplace contract with Lenovo). The closed-source ATI video drivers are constantly a little off (for example, compiz users will find that videos tend to flicker). I'd really want to exclude that can of worms if I could. Your question about other power-reducing features is also a good one. In any case, though...
The real thing the tests appear to show is that Ubuntu has evolved in such a way that any single process may be slower. However, we rarely use our computers as single-process systems. We want it to be doing multiple simultaneous tasks without allowing any single task to dramatically reduce performance in other areas.
I *believe* the new resource allocation methods in Ubuntu (and the kernel and elsewhere) have improved exactly this sort of performance. However, by not allowing single tasks to hog resources in a way that would degrade the user interface and other running software any benchmark run against that single task would appear to indicate that the system is slower.
The SYSTEM is not slower. The TASK is slower.
That's a trade-off. Do you want single tasks to be faster or the overall responsiveness of the system to be greater?
Re:Performance isn't its raison detre (Score:3, Insightful)
Wow. +20 jerk-off points for using other people (women, in this case) as props for your own ego.
I mean, misogyny may be the rule at old Slash U more days than not, but you, sir, are a grade-a special asshole.
Re:Performance isn't its raison detre (Score:2, Insightful)
Yeah, cause women aren't people, awesome.
Seriously, get the fuck out of my gender, you waste of sperm.
Anyone who's not a fucked-up case of arrested development eventually realizes that women ARE PEOPLE. It's not cool or a sign of your manliness to reduce them to just sexual objects; what it is is a sign that you are going to have one-sided, unfulfilling relationships, that you're going to be a bad lover (probably physically, but certainly over any span of more than a couple sexual encounters), and that you're going to hurt people who don't deserve it. Making you an asshole.
Seriously, grow the fuck up. You are pathetic, and there's no excuse for this kind of bullshit, anywhere.
Re:Performance isn't its raison detre (Score:3, Insightful)
From time to time I download the newest Ubuntu and check it out to see what all the new fuss is. I am continually disappointed though, and it rarely makes it a week before being purged.
It's not just the bugs and the long app-launch times. It's more than just the gratuitous resource consumption. It's the whole thing... It's bloat on top of eye-candy bloat with a hefty helping of fanboy zealotry.
I love *NIX very much but it is precisely because I love it that I have to point out that something is rotten in the state of Denmark.
When did the userbase of linux go so wrong? When did it start? Those of us that have been around for quite a while have watched the rockstar rise and subsequent plummet in the communities surrounding it. 10+ years ago you could jump into IRC type /join #[your distro] and be surrounded by people that truly loved their systems and would help you without being condescending, resorting to ad hominem attacks, or calling other *nix variants crap. A lot of those guys, myself included, were using Solaris, HP-UX, Tru64, AIX, etc. during the day and spending some of our evenings just helping out others that were interested in or 'testing the water' with linux. The slackware community was great. Even a little more recently when Gentoo first really got rolling between 1.0 and 1.2 the community on EFNET in #gentoo was a shining example of what a userbase should be. I spent many an hour in there helping people figure out their CFLAGS, configuring their XF86Config, and the like.
With the influx of more and more folks that seem to be vastly more focused on hating Windows, Mac OSX, and even other UNIX variants, the face of linux has changed. People that used to use *NIX as a personal choice did so because they truly loved computers. Now it seems to be the equivalent of a battle standard. Your Operating System is your country, your flag, and your religion. Thousands of angry people focused on their hatred of anything that is unlike themselves. It's GNU/Xenophobia.
The programming ramifications of this have become pervasive throughout many of the more popular distributions. In fact, the fundamental idea of the ideological Bazaar has been replaced by the Cathedral of intolerance. Instead of a focus on excellence and listening to the end-users, more and more developers are dismissive and prone to flame. More time is spent developing completely worthless and unrelated 'features' than in solidifying and optimizing the current code. Instead of, say fixing GNOME's inability to remember where I want my launch icons on the panel, we get wobbly windows that add absolutely nothing to the value of the desktop. Instead of writing just one really, really good IDE for C development, we get oodles of feature-incomplete environments that can't even compete with older Visual Studios or XCode; and this is supposed to be forte of *NIX. As children we are reinforced to eat our meat and vegetables before we get dessert. Yet more and more developers focus on the candy and leave the meat (optimizing) and vegetables (squashing bugs) virtually untouched. It's not as exciting of course, but it is necessary. In *buntu I struggle with yet another audio layer to cover the other layers to figure out why my sound card is doing a darn good impression of a french mime when I try to play some music. Meanwhile, a thousand fanboys upload yet another Youtube video of a spinning desktop cube with a Moby soundtrack.
Perhaps it is the fate of those of us from the previous generation to make way for the new one, but as we do so there should be some guidance, some hope, and some direction given. Reading through the comments in this story really drive home how far this has gone and the need for a gentle hand to remind people not just of the Bazaar, but also that we need to eat our meat and vegetables before we get dessert. This reply has gotten much longer than I originally planned though, but perhaps this conversation can continue in another venue.
Re:So Xorg, Linux, GCC == Ubuntu? (Score:3, Insightful)
"In this case, Ubuntu is the sum of the software it packages. But if one piece of software is slower, then Ubuntu's not slower, that piece of software is slower. 1 + 1 + 1 = 3, 3 != 1. "
I find your definition of 'sum' interesting.
1 + 1 + 1 = 3
1 + 1 + 2 = 4
If one piece of software gets bigger, sure seems to me like the sum gets bigger too...
Re:Performance isn't its raison detre (Score:2, Insightful)
I agree about cars. I want to replace my 1990 MR2 Turbo which I bought in 2000 for NZ1313K. Now if I try and find a new car for $13,000 there is no way I can find any mod engined 200HP rice rockets. They are all old slow junkers or much more expensive than my budget allows.
They are also loaded with extra features like ABS brakes, adaptive dampers, airbags, pretensioning seatbelits, CD changers, run flat tyres, and all manner of other goodies that just add weight, not performance.
Just like new OS's I guess