LinuxQuestions.org
Review your favorite Linux distribution.
Go Back   LinuxQuestions.org > Forums > Linux Forums > Linux - Distributions > Slackware
User Name
Password
Slackware This Forum is for the discussion of Slackware Linux.

Notices

Reply
 
Search this Thread
Old 08-03-2012, 01:40 AM   #31
cascade9
Senior Member
 
Registered: Mar 2011
Location: Brisneyland
Distribution: Debian, aptosid
Posts: 3,718

Rep: Reputation: 903Reputation: 903Reputation: 903Reputation: 903Reputation: 903Reputation: 903Reputation: 903Reputation: 903

Quote:
Originally Posted by damgar View Post
6 cores with hyper threading would be seen by the kernel as 12 cores. My i7 920 is seen as 8.
Yers, that doesnt make it a real 12 core (or 8 core in your case) CPU. 12 threads, 6 cores is reality.

Since its possible to get the real core count, having a misleading core count isnt very good work IMO.

Quote:
Originally Posted by 273 View Post
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.
It shouldnt be a different motherboard according to the insert. Even if it was a different motherboard, there are only X79 and X79 based C600 chipsets for LGA 2011 CPUs.

I'd doubt that anyone has pulled 2 x 4GB sticks and replaced them with a single 8GB stick.

As for the sound chip, I'm 100% sure that is reporting. I've got a realtek ALC888 sound chip, and dpending on where you look it will report as ALC888, HDA Codec Realtek, Intel HD Audio, or HDA (High Definition Audio) AMD/ATI South Bridge.

lshw

Quote:
*-multimedia
description: Audio device
product: SBx00 Azalia (Intel HDA)
vendor: Advanced Micro Devices [AMD] nee ATI
physical id: 14.2
bus info: pci@0000:00:14.2
version: 00
width: 64 bits
clock: 33MHz
capabilities: pm bus_master cap_list
configuration: driver=snd_hda_intel latency=32
resources: irq:16 memory:fe024000-fe027ff
lspci

Quote:
00:14.2 Audio device: Advanced Micro Devices [AMD] nee ATI SBx00 Azalia (Intel HDA)
lsmod

Quote:
snd_hda_codec_realtek 48102 1
arecord -l

Quote:
**** List of CAPTURE Hardware Devices ****
card 0: SB [HDA ATI SB], device 0: ALC888 Analog [ALC888 Analog]
Subdevices: 1/1
Subdevice #0: subdevice #0
card 0: SB [HDA ATI SB], device 1: ALC888 Digital [ALC888 Digital]
Subdevices: 1/1
Subdevice #0: subdevice #0
card 0: SB [HDA ATI SB], device 2: ALC888 Analog [ALC888 Analog]
Subdevices: 1/1
Subdevice #0: subdevice #0
cat /proc/asound/cards
Quote:
0 [SB ]: HDA-Intel - HDA ATI SB
HDA ATI SB at 0xfe024000 irq 16
Thats just from debian, I know I've seen other linxu distros give different results again.

*edit- Intel DX79SI does have a ALC892 sound chip. Even though its not listed on the intel site, its 'Intel High Definition Audio (Intel HD Audio) subsystem' there-

http://www.intel.com/content/www/us/...rd-dx79si.html

It is listed on sites that dont have as much to gain from pushing the word 'intel' as much as possible-

http://benchmarkreviews.com/index.ph...=819&Itemid=69
http://www.anandtech.com/show/5123/i...-default-x79/3

There is already a post in the discussion thread on the phoronix forums asking about it ("Looking at the image of system specifications it is at least two different systems (e.g. different sound cards?", page 3, post #26)-

http://phoronix.com/forums/showthrea...s-Fedora/page3

IMO the differences are from 'bad use of a tool'. I wouldnt be so lazy as to get the benchmarking software to post a list of the hardware at all. If I did, and there was differences in the listed hardware, I'd make 100% sure that I was including a hard 'we did' or 'we didnt use the same hardware' (and BIOS settings) in the article.

If a tester is really untrustworthy, its easy to skew figures without changing hardware, just tweak a few BIOS settings.

If theres a sin there, its trusting software designed by the user ("Written by Michael Larabel"). Follow the name link and you get this-

Quote:
Michael Larabel is also the lead developer of the Phoronix Test Suite.
http://www.michaellarabel.com/michael.php

So the lead dev is the guy using the software that has listed the hardware. If he thought there was a issue, it would be fixed, or in the porcess of being fixed.

There is already a post in the discussion thread on the phoronix forums asking about it ("Looking at the image of system specifications it is at least two different systems (e.g. different sound cards?", page 3, post #26)-

http://phoronix.com/forums/showthrea...s-Fedora/page3

Maybe rather than going round and round on the 'its different hardware', 'no its not' discussion, someone should go to the phoronix forums, point out the issues and uncertainties in the hardware list?

Surely its better to bring up issues with a full list of 'problems', where the authour will see them, in the community that has created the testing software? Even if its not 'better', its polite. If we dont give feedback to devs, in a place where they are likely to see it, how are they to know that we have problems with the software they have created.

Last edited by cascade9; 08-03-2012 at 07:20 AM. Reason: addion, minor change
 
Old 08-03-2012, 07:14 AM   #32
GazL
Senior Member
 
Registered: May 2008
Posts: 3,368

Rep: Reputation: 906Reputation: 906Reputation: 906Reputation: 906Reputation: 906Reputation: 906Reputation: 906Reputation: 906
Quote:
Ben Hutchings has announced the release of the 3.2.25 (diffs) stable kernel. It not only has the usual pile of important fixes, but also has a large set of backported fixes for memory management performance issues, courtesy of Mel Gorman.
May, or may not be relevant.
 
1 members found this post helpful.
Old 08-03-2012, 05:55 PM   #33
gargamel
Senior Member
 
Registered: May 2003
Distribution: Slackware, SLAX, OpenSuSE
Posts: 1,594

Rep: Reputation: 142Reputation: 142
Quote:
Originally Posted by akus View Post
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.
While I generally agree with most of what has been said here about Phoronix benchmarks, I think, that if they had used 13.37, they'd be criticised for comparing an almost outdated release with an older kernal against new releases with new kernels, with obviously better optimisations, of the other distros, But if they are serious, they'll repeat the test with 14 release.

Is it possible, that Xfce was a limiting factor? As has been said, on Slackware recent releases of KDE are quite snappy, and, what may come as a surprise for many people, faster than Xfce. As far as I can tell, KDE was slower up to 4.5.5, but after that caught up with and finally passed by Xfce.

Don't get me wrong: Xfce is quite fast, and hasn't gotten any slower than it was, as far as I can tell, just KDE has become so much faster. It's finally back up to the speed I knew from KDE 3.5!

gargamel


EDIT: My statements are not based on stop-watch experiments or serious benchmarks, but just on "user experience", and may therefore be subjective in nature. However, I can assure you, that I use KDE and Xfce on exactly the same hardware.

Last edited by gargamel; 08-03-2012 at 05:58 PM.
 
Old 08-03-2012, 08:13 PM   #34
damgar
Senior Member
 
Registered: Sep 2009
Location: dallas, tx
Distribution: Slackware - current multilib/gsb Arch
Posts: 1,949
Blog Entries: 8

Rep: Reputation: 201Reputation: 201Reputation: 201
Quote:
Originally Posted by gargamel View Post
While I generally agree with most of what has been said here about Phoronix benchmarks, I think, that if they had used 13.37, they'd be criticised for comparing an almost outdated release with an older kernal against new releases with new kernels, with obviously better optimisations, of the other distros, But if they are serious, they'll repeat the test with 14 release.

Is it possible, that Xfce was a limiting factor? As has been said, on Slackware recent releases of KDE are quite snappy, and, what may come as a surprise for many people, faster than Xfce. As far as I can tell, KDE was slower up to 4.5.5, but after that caught up with and finally passed by Xfce.

Don't get me wrong: Xfce is quite fast, and hasn't gotten any slower than it was, as far as I can tell, just KDE has become so much faster. It's finally back up to the speed I knew from KDE 3.5!

gargamel


EDIT: My statements are not based on stop-watch experiments or serious benchmarks, but just on "user experience", and may therefore be subjective in nature. However, I can assure you, that I use KDE and Xfce on exactly the same hardware.
I don't generally use XFCE since I go straight to fluxbox if I need to run something other than KDE, but with the 4.10 upgrade I logged in to see what it was about. I felt the same way, that KDE felt much quicker than XFCE. As is stated in the quote, I have no numbers to back up that statement, just my personal experience.
 
Old 08-03-2012, 08:39 PM   #35
GazL
Senior Member
 
Registered: May 2008
Posts: 3,368

Rep: Reputation: 906Reputation: 906Reputation: 906Reputation: 906Reputation: 906Reputation: 906Reputation: 906Reputation: 906
What aspect do you feel is sluggish? Startup, window operations, or something else? I'm using thunar from 4.10 in my dwm setup and even with the nouveau driver it's snappiness incarnate.
 
1 members found this post helpful.
Old 08-03-2012, 08:52 PM   #36
damgar
Senior Member
 
Registered: Sep 2009
Location: dallas, tx
Distribution: Slackware - current multilib/gsb Arch
Posts: 1,949
Blog Entries: 8

Rep: Reputation: 201Reputation: 201Reputation: 201
Quote:
Originally Posted by GazL View Post
What aspect do you feel is sluggish? Startup, window operations, or something else? I'm using thunar from 4.10 in my dwm setup and even with the nouveau driver it's snappiness incarnate.
The time it takes just to open a program or draw a window are the two things I can say for certain, just because I did not spend much time in it. If it's not faster than KDE there really isn't any reason for me to spend much time with it. I use the Nvidia proprietary driver, but I run KDE with desktop effects enabled, mostly transparency, and it still opens, draws and renders everything faster that I can tell. I'm not limited in anyway by hardware, so on a different machine I might see very different results, but on this machine (the only one running current) KDE feels much faster. It's as close to instant as I can think of with the exception of fluxbox which may actually do things before I tell it too! LMAO.
 
Old 08-03-2012, 09:08 PM   #37
disturbed1
Senior Member
 
Registered: Mar 2005
Location: USA
Distribution: Slackware
Posts: 1,133
Blog Entries: 6

Rep: Reputation: 223Reputation: 223Reputation: 223
Quote:
Originally Posted by damgar View Post
The time it takes just to open a program or draw a window are the two things I can say for certain, LMAO.
Something's not right then.

Using my super scientific counting device , from the time I click on the icon to launch Xfce-terminal until it is displayed I make it to one m - I don't even get the entire first syllable of Mississippi out. Which happens to be the same speed as Fluxbox.

This is on an AMD x6 with 8GiB ram, 7200rpm SATA drive, and Nvidia GTS450. It's also the same with a core2duo laptop, 2GiB ram, intel GPU, and 5400RPM SATA drive. My dellmini 9 that runs Slackware from a 4GiB SD card also launches the GTK apps at near instant speeds (of course this does not include Firefox/Seamonkey).

I'd take a look and make sure that something is not dangling in the background chewing on CPU and/or or disk I/O.
 
Old 08-03-2012, 09:17 PM   #38
damgar
Senior Member
 
Registered: Sep 2009
Location: dallas, tx
Distribution: Slackware - current multilib/gsb Arch
Posts: 1,949
Blog Entries: 8

Rep: Reputation: 201Reputation: 201Reputation: 201
Quote:
Originally Posted by disturbed1 View Post
Something's not right then.

Using my super scientific counting device , from the time I click on the icon to launch Xfce-terminal until it is displayed I make it to one m - I don't even get the entire first syllable of Mississippi out. Which happens to be the same speed as Fluxbox.

This is on an AMD x6 with 8GiB ram, 7200rpm SATA drive, and Nvidia GTS450. It's also the same with a core2duo laptop, 2GiB ram, intel GPU, and 5400RPM SATA drive. My dellmini 9 that runs Slackware from a 4GiB SD card also launches the GTK apps at near instant speeds (of course this does not include Firefox/Seamonkey).

I'd take a look and make sure that something is not dangling in the background chewing on CPU and/or or disk I/O.
Is it the same for non XFCE programs? Google Chrome, VLC, Firefox, etc? You may very well be right, that something isn't right, I've been backing up config files from the beta and plan on doing a clean install of 14 once it becomes final even though this was a clean install of -current about two weeks ago. I know something about KDE's file indexing was absolutely DESTROYING performance until it was disabled. There may be something similar with XFCE that I'm unaware of at this point.
 
Old 08-03-2012, 09:22 PM   #39
animeresistance
Member
 
Registered: Feb 2004
Distribution: Slackware
Posts: 190

Rep: Reputation: 19
Nah !

Slackware is in beta ... No worries ...
 
Old 08-03-2012, 09:31 PM   #40
disturbed1
Senior Member
 
Registered: Mar 2005
Location: USA
Distribution: Slackware
Posts: 1,133
Blog Entries: 6

Rep: Reputation: 223Reputation: 223Reputation: 223
Gedit, Brasero, Gthumb, SpaceFm, mkvmerge GUI, audacious, Abiword .... almost all GTK apps are instant.

For the heavier programs,
From a cold start, Seamonkey takes 2 almost 3 seconds to launch. Google Chrome takes under 2 seconds, Chromium is slightly faster on launch than Google Chrome, those three are instant for a warm start. Even Gimp launches in under 2 seconds.

Don't use VLC, but UMplayer starts instantly.

Last edited by disturbed1; 08-03-2012 at 09:35 PM.
 
Old 08-03-2012, 09:39 PM   #41
the3dfxdude
Member
 
Registered: May 2007
Posts: 316

Rep: Reputation: 87
Quote:
Originally Posted by gargamel View Post
While I generally agree with most of what has been said here about Phoronix benchmarks, I think, that if they had used 13.37, they'd be criticised for comparing an almost outdated release with an older kernal against new releases with new kernels, with obviously better optimisations, of the other distros,
Except that CentOS 6.2 was in the comparison, so they weren't considering kernel versions when making choices. But it still a sloppy comparison, maybe even so more.
 
Old 08-03-2012, 09:41 PM   #42
tty13
Member
 
Registered: Aug 2006
Distribution: Slackware64-current
Posts: 38

Rep: Reputation: 5
I see they all use scaling governor except Slackware, isn't it just because Slack comes with processor set to Pentium, but not multi core ?
 
Old 08-04-2012, 03:55 PM   #43
gargamel
Senior Member
 
Registered: May 2003
Distribution: Slackware, SLAX, OpenSuSE
Posts: 1,594

Rep: Reputation: 142Reputation: 142
Quote:
Originally Posted by GazL View Post
What aspect do you feel is sluggish? Startup, window operations, or something else? I'm using thunar from 4.10 in my dwm setup and even with the nouveau driver it's snappiness incarnate.
There is *nothing* sluggisch in Xfce. It *is* damn' fast. Alas, recent KDE is *feels* even faster. Really, KDE 4.8.4 is up to a speed not known in years in KDE!
One thing is or feels still faster in Xfce, though. Despite the noticeable and significant improvements in Dolphin, Thunar is still a bit (!) faster, when I open directories with several thousands of files (RAW images from my digital camera). But Dolphin is now quite close, except for the largest of directories, and it is finally stable (had few crashes in the past with it, but none with KDE 4.8.4).

gargamel
 
Old 08-04-2012, 04:44 PM   #44
rkfb
Member
 
Registered: Oct 2003
Location: Guildford, England
Distribution: slackware
Posts: 290

Rep: Reputation: 40
I don't really see what there is to worry about to be honest....I use Slackware because I love Slackware and I'm not really too concerned about what it benchmarks at in anyone's test.
 
Old 08-04-2012, 04:52 PM   #45
kabamaru
Member
 
Registered: Dec 2011
Location: Greece
Distribution: Slackware
Posts: 276

Rep: Reputation: 133Reputation: 133
Don't know about benchmarks and the such... I think Slackware 14 will be a _stellar_ release (I'm waiting for the finished product). KDE has really come along, (4.8.4 is a _huge_ improvement over 4.5.5 which was decent enough) and Xfce 4.10 will make a great candidate for my old MacBook Pro.
 
  


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: A Tour Of The Phoronix Office LXer Syndicated Linux News 0 06-10-2012 01:11 AM
Phoronix Benchmarks and Slackware... Alexvader Slackware 13 04-25-2010 07:39 AM
LXer: Please Your Wife With Phoronix, Really LXer Syndicated Linux News 0 07-14-2009 10:11 PM
Phoronix Test Suite anupamjamatia Linux - Software 1 11-13-2008 08:36 AM
LXer: Phoronix To Support Solaris OS LXer Syndicated Linux News 0 04-20-2007 11:01 AM


All times are GMT -5. The time now is 02:00 PM.

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