Intel's Clear Linux Distribution Offers Fast Out-Of-The-Box Performance (phoronix.com) 137
An anonymous reader writes: In a 10-way Linux distribution battle including OpenSUSE, Debian, Ubuntu, Fedora, and others, one of the fastest out-of-the-box performers was a surprising contender: Intel's Clear Linux Project that's still in its infancy. Clear Linux ships in an optimized form for delivering best performance on x86 hardware with enabling many compiler optimizations by default, highly-tuned software bundles, function multi-versioning for the most performant code functions based upon CPU, AutoFDO for automated feedback-direct optimizations and other performance-driven features. Clear Linux is a rolling-release-inspired distribution that issues new versions a few times a day and is up to version 5700.
Different compiler (Score:5, Informative)
Re:Different compiler (Score:5, Interesting)
Not everything can be compiled with Intel's compiler...
I believe Gentoo has offered an option to build with Intel's compiler for a while, but not all packages will work that way.
Re:Different compiler (Score:5, Informative)
Clear uses gcc-5.3.0 - see https://download.clearlinux.or... [clearlinux.org]
Re: (Score:3, Interesting)
And what it look like when running an AMD core?
Re:Different compiler (Score:4, Funny)
It steals your credit card to order you a $3000 dell then swats your family as a warning.
Re:Different compiler (Score:5, Informative)
Clear Linux also comes packaged with spyware [clearlinux.org]
From the 1st paragraph at that link:
Re:Different compiler (Score:5, Insightful)
Clear Linux also comes packaged with spyware [clearlinux.org]
From the 1st paragraph at that link:
Not the point. Telemetry collection should be opt-in, not opt-out.
Re:Different compiler (Score:5, Interesting)
1 That is an opinion.
2. It is opt in. You opt in when you download and install ClearLinux.
3. They make it very transparent how it works and what it does.
4. ClearLinux is not some mainstream Linux for the average joe. Read the docs folks.
Wrong point to address. (Score:3)
Clear Linux also comes packaged with spyware [clearlinux.org]
From the 1st paragraph at that link:
That's what Canonical (Ubuntu) and a few others think, and it's wrong. Clever wording like "We send only minimal stuff without your knowledge" and "it's for your own good and so that we can make it better" don't change the default state of the software in question. I refuse to load Ubuntu on anything because Canonical installed their software in an always on state and hid it from consumers. I will never ever trust them again, just like I have not trusted Microsoft after their shenanigans (yeah, you have
Re: (Score:2)
Any kind of telemetry that's concealed or "opt out" is an issue, and I too view it as unacceptable.
But at least with Linux you can go to a different distro. What do you do if you're stuck with Windows?
With Linux you can just say, "okay, Ubuntu is doing shady stuff, I'll just use Mint instead"; with Windows you live with it, fight it --- or in the end ditch it, if you aren't already tied to some Windows-only necessity.
Re: (Score:2)
That's what Canonical (Ubuntu) and a few others think, and it's wrong.
At least Ubuntu is finally changing their stance on this [whizzy.org], not before time. (All online search functions will be off by default in 16.04, the way they always should have been.)
Bullshit, and more bullshit. (Score:3, Insightful)
The only person using false drama is you. I never stated that it was an evil plot, you did that. You also attempted to claim I said it, which is bullshit.
Telemetry requires a consumer dig through details to find it, and to turn it off. How hard is it to do like Redhat does, and give a prompt to users during the install which asks them if they want the service on or off? Don't bother stopping to think about why Redhat does this as opposed to just turning it on, because that may be more "false drama".
You
Re: (Score:2)
Well, to be fair, there are big flashing lights and a click-through on installing Ubuntu warning you that your search queries will be sent somewhere, and a single button to disable it that isn't obfuscated or hidden.
NOW there is, but there was no such warning initially. Initially Canonical was not honest about what they were doing and sending to Amazon. It took a short time for a 3rd party to publish what it was really doing contrary to what the documentation page said.
Claiming that telling you about something and forcing you to acknowledge it is "hiding it" and then crowing about your righteous refusal to use it on that basis is just being a drama queen.
So if I change what I do, that means I never did otherwise? I am (insert ad hominem) if I distrust them after that happens? Nope, that is not reality. You and the AC are both drama queens for attempting to use ad hominem against a fact based post.
Re: (Score:1)
"The end users may disable the telemetry component of Clear Linux OS for Intel Architecture or even redirect where records go if they wish to collect for themselves."
Re: (Score:2, Informative)
TFA says that GCC was used, not ICC.
Re:Different compiler (Score:5, Informative)
Re: (Score:1)
My guess is the hard to find (because they host it as an image file instead of in plain text) optimization notice for intel compilers probably applies here. In other words purposely compiling poorly for AMD processors. https://software.intel.com/en-us/articles/optimization-notice/
NFB v. Target (Score:2)
That image is not accessible to blind people. Have you reported this inaccessible image to your local branch of Intel and to disability advocates? I wonder what they'll do if reminded of National Federation of the Blind v. Target Corp. [wikipedia.org]
Re: (Score:1)
When you dig into a default kernel config for a major distribution you find a ton of options that have performance hits, but you might never need. Specifically, debug options and certain features that according to the inbuilt description have a small impact on performance. When you turn off two dozen such options and a few debug options (build a secondary debug orientated kernel from a separate config if you need it for bug hunting), you stack quite a few performance improvements together.
Re: Different compiler (Score:3)
I think you are mistaken. You can still tune GCC, but it defaults to safe compiler optimzation flags.
I use Funtoo, and I have my CFLAGS tuned to my architecture. Things run real zippy even on older or low end hardware when optimized for your architecture.
Re:Different compiler (Score:5, Insightful)
WTF are you talking about? That is patently false.
Re: (Score:1)
Re: (Score:2)
What else would I use all of those cores for?
Re: (Score:1)
Running Gentoo has *always* made sense.
Re: (Score:2)
But how does it work on AMD's CPUs? does it still disables the all the optimizations if the CPU isn't a Genuine Intel Processor?
My guess is very poorly. This is probably an intel compiler with certain flags enabled for maximum features of modern cpus that are not on by default with GCC which are not IEEE compliant like the FPU not working well etc.
the problem is make and linux have large gcc integration and can't be seperated easily. The whole kernel and suite was probably heavily patched including a custom version of libtool, automake, and make in addition to the intel compiler so it can compile.
Re: (Score:2)
It's always been possible for compilers to achieve different results. What planet have you been living on?
Telemetry (Score:2, Informative)
"In support of the goal to provide an agile Linux* distribution that rapidly detects and responds to quality issues in the field, Clear Linux for Intel® Architecture includes a telemetry solution, which notes events of interest and reports them back to the development team."
https://clearlinux.org/feature... [clearlinux.org]
Re:Telemetry (Score:4, Funny)
Linux 10?
Re: (Score:2)
I can see situations where using a kernel optimized to a specific hardware platform would be advantageous. Certainly there are embedded Linux installations where the kernel has been highly optimized.
Re: (Score:3)
Easily done with slackware. in fact most slackware installs rarely stay with the stock kernel beyond installation. you compile a custom one for your use and gain dramatic speed increases.
Re: (Score:2)
The optimizations for the kernel are important, but for specific workloads you still have to optimize those specific components, like the Python stack, various parts of glibc and other standard libraries, etc..
Just replacing your kernel is nice, but it's not nearly the end of it.
Re: (Score:2)
The first paragraph there says the end user can disable it.
Re: (Score:2)
Re: (Score:2)
Note how nobody has said how.
Well, I imagine rm -rf libtelemetry.so would do the trick ... :)
Seriously, though, it's pretty clear that Clear Linux is designed for server deploys, in situations where I'd guess the telemetry service might catch issues in order to make an admin's task easier. It's touted by Intel as a feature of the distro, after all, so they obviously think some people will find it useful. They also note that the telemetry service is open source, so I imagine you could vet the code if really wanted to.
Would I want a te
Re: (Score:2)
You actually think enterprise environments are LESS concerned about their data leaking to unauthorized third parties? Hardly. In fact, depending on what data leaks through such a service it could even be a PCI compliance violation, illegal and/or open them to liability.
"It's touted by Intel as a feature of the distro, after all, so they obviously think some people will find it useful."
If
Re: (Score:1)
The first paragraph there says the end user can disable it.
And you take their word for it? Also, who's to say that they won't pull an MS and re-enable it after an update?
Several times a day? (Score:1, Troll)
Having started programming before a lot of you were born, I'd say that's called management too cheap to hire a testing group, and the programmers are trying something out, see if it works for them, and pushing it out.
In other words, sounds like M$ std. development system....
mark
Be Serious (Score:1)
There are SO many things that you can bash Microsoft for, but this is not one of them.
They spend a lot of time testing, regression testing, and backward compatibility testing. They almost-only release updates and patches once per month. When you consider the vastness and diversity of their ecosystem and the number of issues that they constantly deal with and the very few instances of breakage that occur, you cannot reasonably deny that they do a fantastic job of developing and testing and deploying.
Be serio
Re: (Score:2)
Re: (Score:3)
Just because something is (fairly) new, we cannot safely conclude that it is better than traditional methods. Unfortunately, fashion is far more powerful than judicious evaluation.
"The computer industry is the only industry that is more fashion-driven than women's fashion. Maybe I'm an idiot, but I have no idea what anyone is talking about. What is it? It's complete gibberish. It's insane. When is this idiocy going to stop?"
- Larry Ellison at Oracle OpenWorld, September 2008.
Re: (Score:2)
It has it's ups and downs and a similar development model is spreading everywhere as devops take over and developers are being given the keys to the castle. Unfortunately, in the past young an enthusiastic developers have been restrained both by more experienced programmers and experienced admins. When a young but talented programmer ignores a more experienced programmer the admins could be c
Re: (Score:2)
Well, it seems that several moderators must have marked this as "troll". I can't work out whether that's from resentment of the (perhaps) implied superiority of "before a lot of you were born", or from natural resentment that Mark permitted himself to criticize M$.
I'm standing back to back with Mark, so please moderate this reply "troll" to your heart's content. Or stop and think for a few moments about what he actually said.
Re: (Score:1, Interesting)
Does it use (Score:1, Insightful)
Systemd? Hopefully they chuck it.
Re: (Score:3, Interesting)
There's one thing about systemd that I don't understand: If it is terrible (and I have no doubt that it is, from its philosophy to its implementation), why have almost all of the major Linux distributions moved to it?
Re: (Score:2)
Re: (Score:2)
No it doesn't. Gnome depends on a kernel feature, not systemd.
Re: (Score:2)
Seriously? People are stupid and compliant. Look at the incompetent boob occupying the white hut for the last 7 years. That was by popular vote - twice. And before anyone jumps down my throat, look at the last 27 years of boobs that were installed as president.
Re: (Score:2)
You're saying that many distros have decided in favour of systemd[1], and surely they can't all be wrong? Except they aren't really independent decisions. Most distros are either respins of RedHat or rely heavily on source provided by them, just due to their sheer size. The downstreams made the decision, rightly or wrongly, that excising it is either not possible or not feasible. Some suspect it's been intentionally written that way.
So the decision was made once - by, or under the influence of, Lennart
Re: (Score:2)
Nope. That's not what I'm saying. The question is meant to b'e taken quite literally: "systemd seems to have quite a lot of flaws, so why are so many distributions accepting it so quickly?" I apologize if you ended up taking more meaning out of that than what was intended - it's really that simple a question.
I did a bit of searching around and found this [zd.net], but it seems tin-foil-hatty and I don't have the deep, low-level linux experience to tell if it is true or not.
The whole open source thing is great, in th
Re:Does it use (Score:4, Insightful)
Because maybe it isn't as terrible as it seems?
Sure, there's a lot of NEW things in it, but isn't Linux all about new? And things are different, which gets people tied up in knots.
And the other thing is, people don't realize the shortcomings of the ever-popular SysVInit - I mean, why do we emulate in SysVInit, init? Init is a daemon manager - in practically all Linux distros, it's managing getty (which spawns login). And when you end your session getty dies, and init duly restarts it, like a good daemon manager does. And you can have daemons kill and restart based on runlevel. This is built in, standard default behavior of init. Yet everyone creates elaborate scripts that do the same thing, or even programs that spawn a child that does the service, and when it crashes or dies, it respawns it. Something init already does. Init even does rate limiting - if a daemon quits too quickly, init stops starting it for a few minutes.
SystemD formalizes this as a fundamental part of the system - init really should manage daemons, not a rough collection of shell scripts that try to mimic its behavior.
Granted, things are more complex, like how PulseAudio made audio more complicated. But then you realize that audio IS complicated these days, especially on a desktop OS. There was a time you could open /dev/dsp and that's it, but those days are long gone, because users have multiple audio devices and not only that, but those audio devices can change suddenly. And no, the hardware can change - perhaps they're listening on wireless headphones through Bluetooth, but then they want to switch to speakers which require switching the underlying hardware, and so forth.
And initialization and startup is similar.
In the end, what's happening to Linux is what Android did to Linux. Android has its own init system (init manages daemons, like it should), its own graphical system, its own audio layer and much more.
And it was done because the demands of mobile make it purposely complex and consumer expectations ensure it isn't easy.
Re: (Score:2)
A simple sane explanation about SystemD? Is this slashdot?
Re: (Score:1)
The people who find it terrible are clearly a minority among distro devs, including Debian, which is made by volunteers.
Apparently from a distro makers viewpoint it is not so terrible to avoid it like the plague.
(Distro) devs who do find it terrible, are still just as free as ever to (fork to) create non-systemd distro's, modifying programs to work without systemd, which some are doing.
Some users/admins are not content with the non-systemd offerings these devs are making, but they are free to become devs (o
Re: (Score:2)
It does mean a lot of server and workstation stuff is going to be stuck on RHEL6 for a few years until the systemd stuff has either settled down or been abandoned. If Lennart moves onto something else someone who just gets the job done instead of striving to be a "r
Re: (Score:2)
Re: (Score:2)
A lot of commercial stuff has init scripts and is too slow moving to go chasing after a moving target like systemd whether it is good or not - hence stuck on RHEL6/CentOS6 where it will work due to b
Re: (Score:2)
Version 5700 (Score:5, Funny)
Clear Linux is a rolling-release-inspired distribution that issues new versions a few times a day and is up to version 5700.
Big deal. Firefox will catch up with that shortly.
Re: (Score:2)
As soon as I see the words "rolling release", I swicth to another piece of software.
Rolling is so much fun (Score:3)
As soon as I see the words "rolling release", I swicth to another piece of software.
Let me guess: you didn't understand Katamari Damacy.
Repetitive... (Score:2)
"Clear Linux Project for Intel Architecture"
In reading a few pages, I don't think they used the word 'Intel' enough....
Buried Lede (Score:2)
Re: (Score:2)
I initially read that as thespian free. Oh well.
But is it free from back-doors and spyware? (Score:1)
Coming from a major U.S corporation who is on NSA's and the U.S gov's leash, this is an important question to ask, and something that people should look into before adopting this.
What would you expect? (Score:2)
What would you expect. Intel is using a custom kernel optimized for Intel processors and chipsets. The other distros ship generic kernels to work with various processors and chipsets. If you prepare custom kernels for the specific hardware at hand, any of those distros listed in the summary will perform wickedly fast.
Clear Linux? (Score:1)
Re: (Score:2)
Re: (Score:2)
If you have 142 machines in your Beowulf cluster (Score:4, Funny)
To me, an extra 0.1% performance increase, even if I am only imagining it to be faster, is certainly worth one day a week recompiling all of the latest packages from source code.
If 1 part in 1000 runtime improvement is worth 1/7 of one machine's time, then you must be running a cluster of at least 142 identical servers.
Re: (Score:2)
...or you just go for that warm fuzzy feeling of having the fastest distribution on the planet...
Until you get that nagging feeling that maybe switching to that other package, compiling it with Clang and set it to... (dang!)
Function multi-versioning. (Score:3, Insightful)
Upon seeing the description of function multi-versioning I thought of three distinct ways to use that for malware in as many minutes, and the ideas are still coming. (And I don't write malware, so someone in the field would probably think of more, faster,)
It's also a great way to make competitors' processors look bad: Detect their processors and fall back on the minimalist defaults or even hand them "grinched" code that does worse, or contains odd kickers. Or just don't support THEIR accelerations. Also: Don't support their implementations of YOUR accelerations.
Re: Function multi-versioning. (Score:2)
What's your idea for malware? I don't see how it helps any.
Re: (Score:3)
Re: (Score:2)
nutty conspiracy rant
Except that Intel had been caught sabotaging AMD performance in the past.
http://www.agner.org/optimize/... [agner.org]
Better solution for a Linux that exploits the CPU (Score:5, Interesting)
Its nice to see this however we really should, in general, have a better way for Linux programs to be able to easily take advantage of the CPU extensions available without recompile. There are dozens of permutations of CPU extensions, so distributing a binary for each permutation is not feasible. Full from source compilation takes too long for many users. Having Linux binaries being able to use the CPUs most advanced features has been a problem. One solution that I favor is to take a page from AS/400, in a variation of that, in each library file, put a copy of the machine code, but also a copy of the abstract syntax tree, the last compilation phase. If the binary is moved to a new CPU, the AST is run through the code generator to regenerate the machine code in the file according to the options the CPU supports. All done in situ. This is much better than storing a copy a binary for each CPU permutation in a library file. It makes things easy to use and is faster than compiling from source as the lexer and parser phase does not need to be repeated.
PNaCl (Score:3)
One solution that I favor is to take a page from AS/400, in a variation of that, in each library file, put a copy of the machine code, but also a copy of the abstract syntax tree, the last compilation phase.
You're thinking of distributing LLVM bitcode. Google was thinking of the same thing when designing PNaCl.
Kind of a silly summary; (Score:5, Insightful)
The rankings in individual benchmarks were all over the place; a composite of those benchmarks is only valid for some theoretical "average" workload that's the average of all the workloads each individual benchmark is supposed to represent; almost nobody is bound to have a workload that resembles that "average".
In fact the whole "shooutout" scenario is silly because Clear Linux is a container-centric distro. It makes no sense at all to compare it to general purpose distros like Ubuntu and plain vanilla Centos then leave out Red Hat/Centos's Atomic Host flavors.
In any case if performance is your paramount concern, then "out-of-the-box" performance is bound to be irrelevant to you because you'll be compiling from source with your own choice of compiler and flags, as well as fiddling with all those bells and whistles exposed in the /sys interface. What's interesting would be an exploration of why various distros did better or worse on individual benchmarks.
Stock kernel, no way. (Score:5, Interesting)
No matter what distro I use for my desktop, I always use the latest pf-kernel [natalenko.name], with bfq scheduler, low latency, cpu optimizations, etc. I can overload the desktop, and music/video is smooth as silk, and compiling is faster. Its a real world performance boost.
I'd love to see how a pf-kernel does vs stock on each distro.
Re: (Score:1)