SlackwareThis Forum is for the discussion of Slackware Linux.
Notices
Welcome to LinuxQuestions.org, a friendly and active Linux Community.
You are currently viewing LQ as a guest. By joining our community you will have the ability to post topics, receive our newsletter, use the advanced search, subscribe to threads and access many other special features. Registration is quick, simple and absolutely free. Join our community today!
Note that registered members see fewer ads, and ContentLink is completely disabled once you log in.
If you have any problems with the registration process or your account login, please contact us. If you need to reset your password, click here.
Having a problem logging in? Please visit this page to clear all LQ-related cookies.
Get a virtual cloud desktop with the Linux distro that you want in less than five minutes with Shells! With over 10 pre-installed distros to choose from, the worry-free installation life is here! Whether you are a digital nomad or just looking for flexibility, Shells can put your Linux machine on the device that you want to use.
Exclusive for LQ members, get up to 45% off per month. Click here for more info.
Phoronix has a reputation for being inaccurate and sensationalist correct? If these tests were performed on different machines with different hardware then they are completely meaningless..
Distribution: Debian Sid AMD64, Raspbian Wheezy, various VMs
Posts: 7,680
Rep:
I know I'll be disregarding anything from Phoronix in future. They're either stupid or deceitful and neither is a good thing.
[Apologies, I' not a Slack user or anything I just can't tolerate bullshit.]
The only faster differences I've seen between some distros is the boot method. Arch can boot in about 15 seconds with it's loader while Slackware can be booted in about 30 seconds with it's loader. However, within the actual OS both are about equal from normal usage.
My system has been sluggish over the last few updates in current. What the culpirt is, or if that might have something to do with these benchmarks, I can't say. I will probably just be doing a full clean install when 14 becomes a final release and will wait until then to spend much time troubleshooting my issues since everything is stable. Seriously though, who would use a beta for comparison anyway? That seems a little silly to me.
Looking at the image of system specifications it is at least two different systems (e.g. different sound cards?), making the comparison bogus and the site suspect.
Looks to me like they were done from the same system, and the differences in sound chip/chipset/memory is due to the way that the hardware is deceted and reported by the OS.
Thats a semi-guess, and if for example they did use a single 8GB stick on some tests, and a 2 x 4GB sticks on other tests, that would be enough to change lots of the results.
Quote:
Originally Posted by disturbed1
Benchmarks can be useful for some people, for some things.
Like benchmarking your own PC to see if that recently upgraded GPU driver made a difference and gave you an extra 5FPS.
Benchmarking the difference between the vorbis stack compiled at stock settings, and -O3 -march=native -mtune=native.
Agreed, 100%.
Quote:
Originally Posted by disturbed1
I have never been in favor of Phoronix's "Distro" nor OS (Mac/Win) benchmarks.
I'm not that harsh, but so often I've seen poeple use phononix benchmarks to 'prove' stupid things I wonder if they should let 'normal' users see them.
Like on this set of benchmarks, we've got-
NAS Parallel Benchmarks- benchmarks for parallel supercomputers
FFTE- fourier transform benchmark.
HMMER- sequence analysis benchmark (for homologous protein or nucleotide sequences)
Byte Unix Benchmark (Dhrystone)- string handling benchmark
SciMark -(various tests, including another fourier transform benchmark)- java based benchamrk.
The only benchmark that is anywhere near 'real world' is Graphicsmagic.
Benchmarks are all very good, IF they mean something. For the vast majority of users, how fast or slow a system is at fourier transforms matters less than what the mother-in-laws favourite colour is.....
Quote:
Originally Posted by disturbed1
It only proves that the settings he chose give those results with that hardware using that specific application.
Possibly. Or maybe the results are cherrypicked to create the most impact, and possibly to keep allies on side?
Have a look at what the Byte Unix Benchmark is meant to be capable of-
Dhrystone, Whetstone, Execl Throughput, File Copy, Pipe Throughput, Pipe-based Context Switching, Process Creation, Shell Scripts, System Call Overhead, Graphical Tests.
Yet they only used Dhrystone? Even though other tests, like Execl Throughput, File Copy, System Call Overhead would be far more useful to the 'average' user.
I belive that phoronix isnt that bad, and benchmarking does have a point.....but worring about a whole boat-load of artificial benchmarks is at best a waste of time.
In my own expereince, ubuntu feels slower to use than slackware, arch or debian (possibly even fedora or centOS, though I'm not that expereicned with fedora/centOS), no matter how good or bad it benchmarks against them.
Last edited by cascade9; 08-01-2012 at 11:46 PM.
Reason: typos..gah, I'll bet there are still some there. *blames headache*
I saw a little increase in memory usage, but the overall feeling is the same: flying low and fast =]
The system is stable (as always) and the logs are clean. I'm very pleased with 14-current.
The only faster differences I've seen between some distros is the boot method. Arch can boot in about 15 seconds with it's loader while Slackware can be booted in about 30 seconds with it's loader. However, within the actual OS both are about equal from normal usage.
Agreed, there wasn't a great difference in normal performance between Arch and Ubuntu a couple of years back. On a lot of modern hardware any differences between distros seem to be diminishing due to their general speed and number of cores etc. Boot times are fun for tweaking to shave those valuable seconds off but it's not an important factor other than the fact that I wouldn't want any system of mine to take as long to boot as a Winslow PC.
Distribution: Debian Sid AMD64, Raspbian Wheezy, various VMs
Posts: 7,680
Rep:
Quote:
Originally Posted by cascade9
Looks to me like they were done from the same system, and the differences in sound chip/chipset/memory is due to the way that the hardware is deceted and reported by the OS.
Thats a semi-guess, and if for example they did use a single 8GB stick on some tests, and a 2 x 4GB sticks on other tests, that would be enough to change lots of the results.
If that's the case they really ought to have given the hardware specs for the machine, rather than the "guess" the OS gave. AS it stands I see no reason to trust their benchmarks as they seem unable to give the facts clearly.
They did give the hardware specs for the machine. Intel Core i7 3960X, Intel DX79SI, 64GB OCZ SSD, HD 4650.
The only difference in the specs are-
Chipset- The chipset cannont change unless you change the motherboard, so in that case it must be due to reporting (or its a really really stupid mistake).
RAM- (could be due to reporting)
GPU- speeds listed under Fedora 17 (and the speeds are standard HD 4650, so I assume its another reporting issues, not because of overclocking)
Sound chip- ALC892 or Intel Patsburg HD Audio. Which can mean the same thing.
The facts are there, just the havent actually specified they are using the same machine, an error of ommission more than anything else.
If you want to pick on phoronix, pick on that awful phoronix test suite insert. Or pick on the i7-3960X 'Processor' output "Intel Core i7-3960X @ 3.30GHz (12 cores)".
3.3GHz, not with turbo its not. Forgivable. 12 cores? No its bloody not. Get it right, Phoronix Test Suite.
Maybe I'm missing something, but testing a beta amongst released distros doesn't seem entirely fair either. Things are still changing in Slackware day to day as far as I can see. Nothing is final yet.
Maybe I'm missing something, but testing a beta amongst released distros doesn't seem entirely fair either. Things are still changing in Slackware day to day as far as I can see. Nothing is final yet.
That plus different hardware and different DE pretty much renders this benchmark useless and misleading. I will also do my own to prove it to myself and others, but only when Slackware 14 is stable and released.
Distribution: Debian Sid AMD64, Raspbian Wheezy, various VMs
Posts: 7,680
Rep:
Quote:
Originally Posted by cascade9
Chipset- The chipset cannont change unless you change the motherboard, so in that case it must be due to reporting (or its a really really stupid mistake).
RAM- (could be due to reporting)
These two are my point though. I'd expect the motherboard may have some impact and I would assume the RAM configuration could have a major impact. If it's the same machine then it's inaccurate reporting (like the 12 cores thing) and if it's different machines then the whole test is invalid. Either way they've proven themselves untrustworthy.
Regardless how stable Slackware-current is, and how close 14.0.-beta will be to 14.0,
it is simply wrong to chose 14.0-beta and not 13.37. But Phoronix is famous for its odd benchmark tests.
LinuxQuestions.org is looking for people interested in writing
Editorials, Articles, Reviews, and more. If you'd like to contribute
content, let us know.