Slashdot Mirror
Chrome OS Benchmarked Against Moblin, Ubuntu Netbook, More
An anonymous reader writes "Using the latest build of Google's Chromium OS source code, Phoronix built it out to run on a Samsung netbook and ran sixteen benchmarks, putting it up against Moblin 2.1, Ubuntu Netbook Remix 9.10, openSUSE 11.2, and Fedora 12. They ran some of their usual desktop benchmarks (encoding, video, etc..), but more interestingly they ran a number of battery, CPU usage, and memory consumption tests under different settings that show some of the advantages and disadvantages for each of the Linux distributions, and spotted a few bugs along the way."
Similar linux kernels perform mostly similarly on identical hardware, except for the pre-production one that they probably haven't bothered to polish for any particular real-world hardware yet.
Are CPU and memory usage statistics even available in the current build of Chrome OS? I don't remember seeing them when I ran the version that was posted as a VMWare image.
Benchmarking operating system distributions in such a way is only useful for regression testing. Benchmarking operating systems that are designed only to run only on specific hardware against operating systems designed to run on as much hardware as possible won't provide any meaningful results.
They didn't even use the same file system for each install.
Seven pages to tell us that they're pretty much the same? And Chrome's power management sucks? I'm wondering why they didn't do a Windows test, too. I thought that would be a requirement in these types of tests.
All the distros were very close in performance with the exception of one or two benchmarks. 10% is not a perceptable difference. Wake me up when Chrome fever is over and something interesting is posted about it.
After logging in slashdot still does not take you back to the page you were on. It's been that way for 20 years.
There's been an enormous improvement in the Linux scheduler in recent months--in some cases the performance improvements are as high as 60-80% with simple multithreaded apps like video encoders. The instant 2.6.32 comes out officially, expect to start seeing some completely absurd results in stupid "comparisons between Linux distros" like these, where the distros that happened to update to .32 trash the ones that haven't yet.
In sports "benched" usually means taken off the field. I like this tech usage (benchmarked) -- which is new to me.
Face it, "Chrome OS" isn't an operating system in any way. It's a web browser running on a Linux distribution. Nothing more, nothing less.
A more appropriate name for it is "Chrome Fullscreen".
I can give you the results from any Phoronix benchmark article: Ubuntu won.
As I watched the Google Chrome OS rollout, it occurred to me that, when it comes down to it, Chrome isn't so much a full OS as it is a program loader, a la DOS. As the presenter explained, most of what an OS does Chrome *won't* do- no scheduler, no other apps, barely a file system, etc. What it will do is load a Web browser, and then get out of the way. That strikes me as rather similar to the experience I had back in the day using SLIPNot to simulate a graphical browser over a SLIP connection.
This isn't a criticism; far from it. It may just be that precisely what netbooks need is a program loader to start a Web browser + then get out of the way, rather than a full-fledged OS to tax their limited- by design- resources.
Now, if I could just find a way to load SLIPNot on my Eee...
-Z
While Ubuntu Netbook Remix (soon to be "Edition") owns Moblin in most graphs the reason I switched to moblin was because of its fast start up, about about 20 seconds.
Another distro xPUD boots in about 10 seconds, but flash doesn't work out of the box.
However, while youtube runs beautifully in moblin (including fullscreen!) other flash games are too slow and there is still no shockwave, so what I want is a linux that boots fast, runs flash ok and runs shockwave somehow (maybe with wine?) and the more of these features that run out of the box the better, for anything else I can use the terminal.
But... the future refused to change.
Back when Macs still used 68000 series CPUs, Orange Micro made single-board PCs that plugged into a NuBus slot on a Macintosh II, allowing Mac owners to run MS-DOS and Windows and their apps.
At first, Google impressed me quite a bit, but their latest forays into programming languages (Go!) and the OS market ... yawn. Honestly, Chrome in no way compares to FireFox either. It is just a light, quick browser that is light and quick because it doesn't do the truly great things that FireFox can do. The Google "genius club" isn't going to take over the world, no matter how arrogantly they try. However, if they upset the drone army at Microsoft, I applaud their efforts anyway.
The testing concept was pretty absurd - (relatively) stable netbook releases vs a new distro that can barely be considered in 'Alpha' and really doesn't have a platform yet. If Ubuntu, Fedora or Suse had one of their Alpha distros benchmarked vs something stable they would be screaming bloody murder. Wake me when Chromium (much better name for the OS than Chrome by the way) is about to get released.
I call it 'The Aristocrats'
I think ChromeOS will be very useful as a second boot choice, when you are in a hurry (airport, hotspot, whatever) and need some info on the internet quick. Just turn on your netbook and get your info in a few seconds. To do the real job you have the OS of your choice as the primary boot (Linux or Windows)
I know, I know, you can always use hibernation and be also ready in a few more seconds, but note every note(net)book likes the hibernation.
Just my 2 pesos.
7 pages? k thx bye.
WTF, could someone stop these endless Chrome OS advertisement posts on /.
WE HAVE HEARD YOU and know what Chrome OS is, okay? (And no, thanks, I don't need it.)
Chrome OS is long from beta, why bother benchmarking it now? Anyway it's OS who don't do much apart from using mobile phones for exploring the net
i really really like comparizons between diffrent linux distrobutions because they alwayz show U pictores of the desktops
what I want is a linux that boots fast
Ubuntu resumes out of suspend really fast.
Depending on what you do, this may or may not be good enough.
After reading the article, and thinking about the numbers: after all the hype has passed, if you're looking for a good all around featured and decent performing system that has rock-solid stability, large community, and is cater for both users and developers?
OpenSuse 11.2 (and yes, their latest KDE integration is very, very good).
Years ago I worked on something that has some similarities to Chrome OS (http://www.simpc.nl). And of course the same things were being said about it as now on Chrome OS;-) (http://hardware.slashdot.org/story/05/01/13/0033206/simPC---Your-Grandparents-New-Computer?art_pos=1)
It had a lot of the same features: runs on flash, read-only file system, 'firmware approach' mostly online and webbased apps, low requirements on hardware (VIA C3). Resulting in much easier to use, more secure and tamperproof system then a full desktop. Although I believe that Google will do a lot better job.
What most people failed to see then as they do now is that a lot of people don't care about the PC. They care about being online.
I'm glad to see Google building something similar and open source. There are much more uses for a webbased desktop. And other service suppliers could build something with Chromium OS. At the time we thought about Xul applications for companies (we were working with Firefox). But these days I would go for HTML5.
It is not necessarily so that the netbook with such a system is unusable without the internet available. We had a very simple system that checked for the availability of the internet at startup. Without internet it would simply load a local desktop (which can be an html file). And doesn't Google docs have offline capabilities as well?
Personally I'm gonna give Chromium OS a change on my netbook if it allows me to play videofiles, (so if mplayer or VLC can be run, I'm good). I use a netbook daily while commuting in the train. And aside from internet stuff, playing episodes of TV-shows is the only thing I do on that thing in the train.
---
If you express the boot time in hours, then any one of those distributions gets higher marks than adding their times up *including Vista*, then squaring the result.