LinuxQuestions.org
Visit the LQ Articles and Editorials section
Go Back   LinuxQuestions.org > Forums > Other *NIX Forums > Other *NIX
User Name
Password
Other *NIX This forum is for the discussion of any UNIX platform that does not have its own forum. Examples would include HP-UX, IRIX, Darwin, Tru64 and OS X.

Notices

Reply
 
Search this Thread
Old 06-05-2013, 05:33 PM   #1
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Rep: Reputation: 80
SphinUX OS: much faster than Linux?


Hi
It's quite late now here in Switzerland but when I read this article and especially the statement...
Quote:
The kernel proved to process 100% faster than the Linux kernel, memory consumption is 300% less, and I/O is 50% better than the Linux kernel.
...I didn't resist the temptation to try out this OS called SphinUX.
Doing a first small initial test I'm really getting crazy performance out of this OS - here is what I did:

I downloaded the multiarch liveDVD, booted, closed the Window asking details about the installation, got some error messages which I dismissed, started on the desktop a terminal and compiled this small program which computes prime numbers...

Code:
#include <stdio.h>
main()
{
   unsigned long n, i = 3, count, c, lastresult;
 
   printf("Enter the number of prime numbers required\n");
   scanf("%lu",&n);
   
      if ( n >= 1 )
   {
      printf("First %lu prime numbers are :\n",n);
      printf("2\n");
   }
 

 
   for ( count = 2 ; count <= n ;  )
   {
      for ( c = 2 ; c <= i - 1 ; c++ )
      {
         if ( i%c == 0 )
            break;
      }
      if ( c == i )
      {
         //printf("%d\n",i);
         lastresult = i;
         count++;
      }
      i++;
   }
   
   printf("The last prime number computed was: %lu\n", lastresult);
}
...with "gcc test.c" and ran it with "time ./a.out" and entered "50000" as the amount of prime numbers to compute (I need ~2 seconds to type and hit return).

Results:
LiveDVD of SphinUX (gcc 4.7.2): 55 seconds
My Gentoo Linux (custom kernel 3.7.10 + gcc 4.5.4): 113 seconds
Sabayon Linux (kernel 3.7.0 + gcc 4.7.2): 114 seconds.

How can it be?
Did I screw up something with the small test? Don't think so - I even rebooted again SphinUX and repeated the test, but the runtime is still 55 seconds.
Can it really be that SphinUX is so much faster than Linux?

Could please somebody run some other test against some other Linux distribution (Ubuntu, CentOS, anything) and share the results? Maybe I'm just tired and did something wrong.

p.s.:
1- SphinUX wiki
2- Download
3- I used for all tests the same PC with an "Intel(R) Xeon(R) CPU E31270 @ 3.40GHz".
 
Old 06-05-2013, 06:35 PM   #2
unSpawn
Moderator
 
Registered: May 2001
Posts: 27,132
Blog Entries: 54

Rep: Reputation: 2790Reputation: 2790Reputation: 2790Reputation: 2790Reputation: 2790Reputation: 2790Reputation: 2790Reputation: 2790Reputation: 2790Reputation: 2790Reputation: 2790
See http://phoronix.com/forums/showthrea...894#post334894
 
Old 06-05-2013, 07:15 PM   #3
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Original Poster
Rep: Reputation: 80
yup, read all those comments - but unluckily so far I was the only one benchmarking something.
 
Old 06-06-2013, 03:47 PM   #4
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Original Poster
Rep: Reputation: 80
Couldn't think of any new quick C/C++ test to do (any idea?) so I tried installing the OS on an old "AMD Sempron(tm) Processor 2600+"-machine but it just doesn't want to work (X crashes or shows weird stuff like empty desktop & windows), even when I changed the AGP (?! yes, I still have 2 of them lying around) graphics card.
Just to give it a try I then copied the Kernel and the initrd from the DVD to my old normal Gentoo Distribution and booted using them but no chance - as soon as it mounts my xfs rootfs it stands still with the HDD led blinking every second - somehow not compatible.

Next:
- attempt to install the OS on my old EeePC.
- think about some other simple C/C++ performance test.
 
Old 06-07-2013, 03:02 PM   #5
jlliagre
Moderator
 
Registered: Feb 2004
Location: Outside Paris
Distribution: Solaris10, Solaris 11, Mint, OL
Posts: 9,492

Rep: Reputation: 355Reputation: 355Reputation: 355Reputation: 355
Your test program doesn't make much sense. Benchmarking an OS should be done with an application that at least make some use of the operating system but your code is not. It is pure CPU computation so you are essentially benchmarking the CPU itself and the compiler optimizer.

In any case, I would never touch such an OS or trust its nonsense claims (300% less memory used) which is currently at best a hoax.
 
Old 06-07-2013, 03:13 PM   #6
TobiSGD
Moderator
 
Registered: Dec 2009
Location: Hanover, Germany
Distribution: Main: Gentoo Others: What fits the task
Posts: 15,559
Blog Entries: 2

Rep: Reputation: 4034Reputation: 4034Reputation: 4034Reputation: 4034Reputation: 4034Reputation: 4034Reputation: 4034Reputation: 4034Reputation: 4034Reputation: 4034Reputation: 4034
It would be nice if it was only a hoax, but Phoronix member chenxiaolong had a deeper look and found out that this OS phones home, sending data about your machine and screenshots: http://phoronix.com/forums/showthrea...NU-Linux/page6
He also found out that this is debian Wheezy, with replaced strings in the kernel, so that it appears as a different kernel when using uname. Since the SphinUX "developers" also badged the GPL 3 license on it, including the kernel, they have broken at least the license of the kernel, but seriously guys, don't install this, nobody knows what they have hidden in the code.
 
Old 06-09-2013, 11:51 AM   #7
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Original Poster
Rep: Reputation: 80
Quote:
Originally Posted by TobiSGD View Post
It would be nice if it was only a hoax, but Phoronix member chenxiaolong had a deeper look and found out that this OS phones home, sending data about your machine and screenshots: http://phoronix.com/forums/showthrea...NU-Linux/page6
He also found out that this is debian Wheezy, with replaced strings in the kernel, so that it appears as a different kernel when using uname. Since the SphinUX "developers" also badged the GPL 3 license on it, including the kernel, they have broken at least the license of the kernel, but seriously guys, don't install this, nobody knows what they have hidden in the code.
You're right - I'd like to add:
- Debian: that it was a derivate/fork of debian was known already since the beginnning as it's posted on their official info-page.
- Licenses: for the time being I'm not caring about it. I'm only interested in the technical part.
- Sending data home: don't really care if true as in the worst case they're seeing in my case only my dummy data.

I've seen that they posted an official reply to most of the questions on their facebook site.

Posting results of the new tests in 20 minutes or so... .
 
Old 06-09-2013, 12:12 PM   #8
273
Senior Member
 
Registered: Dec 2011
Location: UK
Distribution: Debian Sid AMD64, Raspbian Wheezy, various VMs
Posts: 3,342

Rep: Reputation: 773Reputation: 773Reputation: 773Reputation: 773Reputation: 773Reputation: 773Reputation: 773
I think I'll stick it in a VM -- might try to learn how to use wireshark with it as an example.
 
Old 06-09-2013, 12:12 PM   #9
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Original Poster
Rep: Reputation: 80
Quote:
Originally Posted by jlliagre View Post
Your test program doesn't make much sense. Benchmarking an OS should be done with an application that at least make some use of the operating system but your code is not. It is pure CPU computation so you are essentially benchmarking the CPU itself and the compiler optimizer.

In any case, I would never touch such an OS or trust its nonsense claims (300% less memory used) which is currently at best a hoax.
1)
I am lucky as I have spare PCs.

2)
Yep, I agree that I have no clue from where the 300% less mem used would come from - it would especially involve a new compression algorithm blahblahblah and already only with that you could make a lot of money without having to create a whole new os. But I have to admit that I did not read the docs so I don't know if with that they meant an "overall" lower consumption or just in specific cases like caching or buffering or tiny whatever operations.

3)
I can especially agree to the fact that my test program does not make much sense as I expected as well the results to be the same (as as mentioned it could be fully executed in the CPU without external influences), but in the end THEY WEREN'T and because of this I have to continue to drill down and try to understand what's going on... .
In any case let's not forget that whenever any program runs, there is still a huge dialogue going on between programs and the OS and other programs, otherwise I wouldn't even be able to stop the program from running with [ctrl]+[c] from the X-terminal.

Cheers
 
Old 06-09-2013, 01:03 PM   #10
jlinkels
Senior Member
 
Registered: Oct 2003
Location: Bonaire
Distribution: Debian Lenny/Squeeze/Wheezy/Sid
Posts: 4,067

Rep: Reputation: 491Reputation: 491Reputation: 491Reputation: 491Reputation: 491
Ever heard of the magic devices which save 30% on diesel fuel costs? They have invariably been tested somewhere where direct evidence is hard to obtain, and no written test reports exist. Oh wait, it is the oil industry behind it which prohibits the dissemination of the results.

So 100% faster and 300% less memory usage, and fully Linux compatible. Sure. They wrote that kernel between good Friday and Easter Sunday. Because they coded in so little time the the code remained simple and hence fast. Lalala.

jlinkels
 
Old 06-09-2013, 01:15 PM   #11
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Original Poster
Rep: Reputation: 80
Sorry for whoever was expecting any result on Thursday - when I plugged in the EeePC the primary and secondary fuses went off end ended up having a (cold +) candlelight dinner and as I had to leave for the weekend I've been able to restore the electricity only today.

So, today I installed Ubuntu 13.04 and SphinUX on the same EeePC.

Short story:
Results: (almost) absolutely no difference (if you exclude the last lines I posted, which add some "mistery" to the whole story) - the performance improvement I saw in the previous test did not exist in this case.
Next: redo tests on previous platform without installation (for confirmation) + install on previous platform + redo tests


Long story:
Platform + SW:
- In both cases an EeePC with an "Intel(R) Atom(TM) CPU N270 @ 1.60GHz"
- Both fs using ext4 for their rootfs with nothing else (no encryption of home dir, no lvm, etc...).
- Both fs mounted with "noatime".
- Both using Xfce4 desktop.
- No external activity (e.g. updates) going on while the tests were running (checked with "htop").

I left the original settings of the OSs, with the exception of the desktop - Ubuntu was ok but SphinUX with all 3D-thingies was unbearable on the EeePC. I therefore installed in both cases Xfce4 and had therefore almost no CPU used for fancy desktop effects nor anything else.
Both OSs were updated to their latest version.

Details:
Ubuntu:
Code:
uname -a
Linux ubuntupc 3.8.0-23-generic #34-Ubuntu SMP Wed May 29 20:24:54 UTC 2013 i686 i686 i686 GNU/Linux

gcc --version
gcc (Ubuntu/Linaro 4.7.3-1ubuntu1) 4.7.3

cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
performance
SphinUX
Code:
uname -a
SphinUX sphinux 3.2.32 #1 SMP LSX-arch 1.0.12-1 i686 GNU/Linux

gcc --version
gcc (Debian 4.7.2-5) 4.7.2

cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 
ondemand
Tests:
In both cases I:
1) used the program I posted in my first post, but this time hardcoded without needing any keyboard input.
2) zipped a completely random 1GB-file created with "dd if=/dev/urandom of=zipme.random bs=64k count=16384".


Test results:
Ubuntu:
Code:
gcc prime.c
time ./a.out 
Enter the number of prime numbers required
The last 30000 prime number is:
The last prime number computed was: 350377

real	2m59.861s
user	2m59.620s
sys	0m0.000s

_________________________________________________________________
time zip zippy.zip zipme.random 
  adding: zipme.random (deflated 0%)

real	3m0.638s
user	2m37.272s
sys	0m7.204s
SphinUX:
Code:
gcc prime.c
time ./a.out 
Enter the number of prime numbers required
The last 30000 prime number is:
The last prime number computed was: 350377

real	3m0.525s
user	3m0.291s
sys	0m0.020s

_________________________________________________________________
time zip zippy.zip zipme.random
  adding: zipme.random (deflated 0%)

real	3m3.758s
user	2m43.326s
sys	0m8.245s

So, you see that the results practically do not differ.
Ok Ubuntu might have been a tiny bit faster (perhaps because of the fact that it's using the "performance" governor?) but the key-question was if SphinUX was a lot faster than Ubuntu, which resulted this time in an absolute "no".

This would be the end of the story if I didn't see the huge performance improvement on the other PC => what did that mean?
As this benchmark showed no differences, if there is any then it must be because of something which is different between the two platforms.
The first thing that I have to do is therefore to re-validate the old test, this time as antagonist without using Gentoo/Sabayon keeping the same Ubuntu 13 that I used just now => if that one shows again some differences then it might really be that SphinUX has something "different" from the Linux that we all use, on that particular platform.

To end this post, here is something I initially didn't look at:
Code:
nonroot@hostnotebook ~ $ scp zipme.random root@ubuntupc:/root/
root@10.0.123.1's password: 
zipme.random                                100% 1024MB   2.6MB/s   3.0MB/s   06:34    
nonroot@hostnotebook ~ $ scp zipme.random root@sphinux:/root/
root@10.0.123.2's password: 
zipme.random                                100% 1024MB   2.8MB/s   3.3MB/s   06:08
(the names of the target hosts/PCs were overwritten manually so they might not match anything you see above - don't want to review what I have masked)
You see that the transfer of the 1GB-file over wifi to the EeePC (source=wifi, target=ethernet) when running SphinUX constantly (because I repeated it a couple of time as I could not believe it) takes 30 seconds less then when transferring it to Ubuntu - astonishing, as I expected the wifi (a normal g-wifi) to be the overall "break" - I really did not expect this improvement but as on the EeePC-side such a transfer uses 50% of a single hyperthreaded-CPU if SphinUX acutally did any optimizations in the kernel then it might explain the difference.
Mistery...
Is this like one of the hints that you see at the end of a movie that shows that a second chapter might soon be coming?
In any case: about to install SphinUX + Ubuntu 13 on an external HDD on my "big" PC (the one I use for Steam )
Cheers
 
Old 06-09-2013, 01:28 PM   #12
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Original Poster
Rep: Reputation: 80
Quote:
Originally Posted by jlinkels View Post
Ever heard of the magic devices which save 30% on diesel fuel costs? They have invariably been tested somewhere where direct evidence is hard to obtain, and no written test reports exist. Oh wait, it is the oil industry behind it which prohibits the dissemination of the results.

So 100% faster and 300% less memory usage, and fully Linux compatible. Sure. They wrote that kernel between good Friday and Easter Sunday. Because they coded in so little time the the code remained simple and hence fast. Lalala.

jlinkels
The problem is not their test results - the problem is my test results.
 
Old 06-09-2013, 01:33 PM   #13
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Original Poster
Rep: Reputation: 80
Quote:
Originally Posted by 273 View Post
I think I'll stick it in a VM -- might try to learn how to use wireshark with it as an example.
It would be really useful - didn't see so far any analysis presenting facts related to in/outbound communication - just assumptions and preliminary analysis about the files themselves.

(and on my side I'm stalled right now - watching F1 )

Last edited by Pearlseattle; 06-09-2013 at 01:36 PM.
 
Old 06-09-2013, 01:35 PM   #14
273
Senior Member
 
Registered: Dec 2011
Location: UK
Distribution: Debian Sid AMD64, Raspbian Wheezy, various VMs
Posts: 3,342

Rep: Reputation: 773Reputation: 773Reputation: 773Reputation: 773Reputation: 773Reputation: 773Reputation: 773
Quote:
Originally Posted by Pearlseattle View Post
It would be really useful - didn't see so far any analysis presenting facts - just assumptions and preliminary analysis.

(and on my side I'm stalled right now - just watching F1 )
Well, the .iso file just finished downloading (problems with my cable speed ) so I'll pop it in a VM. Will take me a while to get the hang of wireshark or install a firewall OS in another VM to test it though.
 
Old 06-09-2013, 01:44 PM   #15
Pearlseattle
Member
 
Registered: Aug 2007
Location: Switzerland
Distribution: Gentoo
Posts: 703

Original Poster
Rep: Reputation: 80
Quote:
Originally Posted by 273 View Post
Well, the .iso file just finished downloading (problems with my cable speed ) so I'll pop it in a VM. Will take me a while to get the hang of wireshark or install a firewall OS in another VM to test it though.
Hope it works in a VM - the OS might have some "strong" framebuffer (or whatever it is) requirements (from what I saw when it booted on the EeePC and the other PC). If it doesn't work then try perhaps to run it in a pure qemu environment - as we don't know what the hell those people did, a kvm/xen/vmware-environment might screw things up while on the other side a fully-emulated qemu-environment might work... .

Good luck!

Last edited by Pearlseattle; 06-09-2013 at 01:49 PM.
 
  


Reply


Thread Tools Search this Thread
Search this Thread:

Advanced Search

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is Off
HTML code is Off


Similar Threads
Thread Thread Starter Forum Replies Last Post
LXer: Linux 2.6.30 Gets Faster Boot - but is Fedora Faster? LXer Syndicated Linux News 0 06-11-2009 04:40 AM
LXer: Firefox 3.5 Speed Freak: Faster Development, Faster Performance LXer Syndicated Linux News 0 06-10-2009 02:42 AM
LXer: Firefox 3 Beta 4 is 5x faster than IE7, 3x faster than FF2 LXer Syndicated Linux News 0 03-12-2008 05:50 PM
DISCUSSION: Faster and Faster Compilation jeremy LinuxAnswers Discussion 5 12-06-2005 01:41 AM
Faster Linux CatSC Linux - Newbie 5 11-26-2003 05:25 AM


All times are GMT -5. The time now is 03:57 AM.

Main Menu
My LQ
Write for LQ
LinuxQuestions.org is looking for people interested in writing Editorials, Articles, Reviews, and more. If you'd like to contribute content, let us know.
Main Menu
Syndicate
RSS1  Latest Threads
RSS1  LQ News
Twitter: @linuxquestions
identi.ca: @linuxquestions
Facebook: linuxquestions Google+: linuxquestions
Open Source Consulting | Domain Registration