* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
@ 2002-09-06 7:44 Paolo Ciarrocchi
0 siblings, 0 replies; 12+ messages in thread
From: Paolo Ciarrocchi @ 2002-09-06 7:44 UTC (permalink / raw)
To: phillips, ahu; +Cc: linux-kernel
From: Daniel Phillips <phillips@arcor.de>
[...]
> What kind of arithmetic is this? Why on earth would arithmetic vary
> from one kernel to another?
Yep, you are right!
There is something wrong in that test.
Look at my new tests I've just post using Unix Benchmarks Version 4.1, they more intersting.
Ciao,
Paolo
--
Get your free email from www.linuxmail.org
Powered by Outblaze
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
2002-09-08 22:56 Paolo Ciarrocchi
@ 2002-09-09 10:46 ` Pavel Machek
0 siblings, 0 replies; 12+ messages in thread
From: Pavel Machek @ 2002-09-09 10:46 UTC (permalink / raw)
To: Paolo Ciarrocchi; +Cc: venom, ahu, linux-kernel
Hi!
> > > APM, and I pressed the shift key every few minutes,
> > > therefore no powersafe.
> >
> > That still means APM bios calls when idle, right?
>
> Yes, you are rigth.
> But again, with Byte Unix version 4.1 I got much
> more intersting result with no "strange" numbers,
> I tried that test few hours ago,.
> I know I can disable APM from both the kernel and the BIOS but I'd
> > > like to test the kernel I use in "daily" usage. What do you
> > > think about it? Do you suggest me to use a different
> > > configuration when I run the test?
Disable power managment. What you are doing is test of power managment
subsystem, I believe; that's okay but you did not label it as such.
Pavel
--
Casualities in World Trade Center: ~3k dead inside the building,
cryptography in U.S.A. and free speech in Czech Republic.
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
@ 2002-09-08 22:56 Paolo Ciarrocchi
2002-09-09 10:46 ` Pavel Machek
0 siblings, 1 reply; 12+ messages in thread
From: Paolo Ciarrocchi @ 2002-09-08 22:56 UTC (permalink / raw)
To: pavel; +Cc: venom, ahu, linux-kernel
From: Pavel Machek <pavel@suse.cz>
[...]
> > APM, and I pressed the shift key every few minutes,
> > therefore no powersafe.
>
> That still means APM bios calls when idle, right?
Yes, you are rigth.
But again, with Byte Unix version 4.1 I got much
more intersting result with no "strange" numbers,
I tried that test few hours ago,.
I know I can disable APM from both the kernel and the BIOS but I'd like to test the kernel I use in "daily" usage. What do you think about it? Do you suggest me to use a different configuration when I run the test?
And, what are the "best" benchmark?
I use dbench, LMbench, and Unix Bench Ver4.1.
Cheers {ciao},
Paolo
--
Get your free email from www.linuxmail.org
Powered by Outblaze
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
2002-09-07 12:21 Paolo Ciarrocchi
@ 2002-09-08 19:26 ` Pavel Machek
0 siblings, 0 replies; 12+ messages in thread
From: Pavel Machek @ 2002-09-08 19:26 UTC (permalink / raw)
To: Paolo Ciarrocchi; +Cc: venom, ahu, linux-kernel
Hi!
> > > Yes, I ran the test on a HP Omnibook 600 (PIII@900)
> >
> > APM or ACPI? How did you guarantee not going powersave?
> APM, and I pressed the shift key every few minutes,
> therefore no powersafe.
That still means APM bios calls when idle, right?
Pavel
--
Casualities in World Trade Center: ~3k dead inside the building,
cryptography in U.S.A. and free speech in Czech Republic.
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
2002-09-06 10:28 ` Pavel Machek
@ 2002-09-08 14:09 ` venom
0 siblings, 0 replies; 12+ messages in thread
From: venom @ 2002-09-08 14:09 UTC (permalink / raw)
To: Pavel Machek; +Cc: Paolo Ciarrocchi, ahu, linux-kernel
On Fri, 6 Sep 2002, Pavel Machek wrote:
> Date: Fri, 6 Sep 2002 10:28:50 +0000
> From: Pavel Machek <pavel@suse.cz>
> To: Paolo Ciarrocchi <ciarrocchi@linuxmail.org>
> Cc: venom@sns.it, ahu@ds9a.nl, linux-kernel@vger.kernel.org
> Subject: Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
>
> Hi!
>
> > > I usually run byte bench regularly with every new kernel, so I see some
> > > strange results here.
> > >
> > > From your numbers, I would say you are using a PIII 600/900 Mhz (more or
> > > less). It is not an AMD AThlon or a PIV, since float and double are too
> > > slow, not it is a K6 because they are too fast.
> > Yes, I ran the test on a HP Omnibook 600 (PIII@900)
>
> APM or ACPI? How did you guarantee not going powersave?
>
I suppose Paolo disabled power saving both from bios and from kernel, of
course. If not, then the differences I noticed could be explained easilly,
Thanx
Luigi
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
@ 2002-09-07 12:21 Paolo Ciarrocchi
2002-09-08 19:26 ` Pavel Machek
0 siblings, 1 reply; 12+ messages in thread
From: Paolo Ciarrocchi @ 2002-09-07 12:21 UTC (permalink / raw)
To: pavel; +Cc: venom, ahu, linux-kernel
From: Pavel Machek <pavel@suse.cz>
[...]
> > Yes, I ran the test on a HP Omnibook 600 (PIII@900)
>
> APM or ACPI? How did you guarantee not going powersave?
APM, and I pressed the shift key every few minutes,
therefore no powersafe.
Ciao,
Paolo
--
Get your free email from www.linuxmail.org
Powered by Outblaze
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
2002-09-05 15:37 Paolo Ciarrocchi
@ 2002-09-06 10:28 ` Pavel Machek
2002-09-08 14:09 ` venom
0 siblings, 1 reply; 12+ messages in thread
From: Pavel Machek @ 2002-09-06 10:28 UTC (permalink / raw)
To: Paolo Ciarrocchi; +Cc: venom, ahu, linux-kernel
Hi!
> > I usually run byte bench regularly with every new kernel, so I see some
> > strange results here.
> >
> > From your numbers, I would say you are using a PIII 600/900 Mhz (more or
> > less). It is not an AMD AThlon or a PIV, since float and double are too
> > slow, not it is a K6 because they are too fast.
> Yes, I ran the test on a HP Omnibook 600 (PIII@900)
APM or ACPI? How did you guarantee not going powersave?
Pavel
--
Philips Velo 1: 1"x4"x8", 300gram, 60, 12MB, 40bogomips, linux, mutt,
details at http://atrey.karlin.mff.cuni.cz/~pavel/velo/index.html.
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
2002-09-06 3:23 ` Daniel Phillips
@ 2002-09-06 7:09 ` bert hubert
0 siblings, 0 replies; 12+ messages in thread
From: bert hubert @ 2002-09-06 7:09 UTC (permalink / raw)
To: Daniel Phillips; +Cc: Paolo Ciarrocchi, linux-kernel
On Fri, Sep 06, 2002 at 05:23:48AM +0200, Daniel Phillips wrote:
> On Thursday 05 September 2002 15:48, bert hubert wrote:
> > Arithmetic Test (type = arithoh) 3598100.4 lps 3435944.6 lps
> > Arithmetic Test (type = register) 201521.0 lps 197870.4 lps
> > Arithmetic Test (type = short) 190245.9 lps 145140.8 lps
> > Arithmetic Test (type = int) 201904.5 lps 104440.5 lps
> > Arithmetic Test (type = long) 201906.4 lps 177757.4 lps
> > Arithmetic Test (type = float) 210562.7 lps 208476.4 lps
> > Arithmetic Test (type = double) 210385.9 lps 208443.3 lps
>
> What kind of arithmetic is this? Why on earth would arithmetic vary
> from one kernel to another?
I wasn't involved in this benchmark, I just reformatted the results.
However, it might be that this benchmark is a tad braindead and 'suffers'
from far better timing resolution because of HZ=1000. I'm unsure. I saw that
this benchmark used something like a Sparcstation 5 as a reference platform,
so maybe it is not geared for today's processors.
Regards,
bert hubert
--
http://www.PowerDNS.com Versatile DNS Software & Services
http://www.tk the dot in .tk
http://lartc.org Linux Advanced Routing & Traffic Control HOWTO
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
2002-09-05 13:48 ` side-by-side " bert hubert
2002-09-05 15:11 ` venom
@ 2002-09-06 3:23 ` Daniel Phillips
2002-09-06 7:09 ` bert hubert
1 sibling, 1 reply; 12+ messages in thread
From: Daniel Phillips @ 2002-09-06 3:23 UTC (permalink / raw)
To: bert hubert, Paolo Ciarrocchi; +Cc: linux-kernel
On Thursday 05 September 2002 15:48, bert hubert wrote:
> Arithmetic Test (type = arithoh) 3598100.4 lps 3435944.6 lps
> Arithmetic Test (type = register) 201521.0 lps 197870.4 lps
> Arithmetic Test (type = short) 190245.9 lps 145140.8 lps
> Arithmetic Test (type = int) 201904.5 lps 104440.5 lps
> Arithmetic Test (type = long) 201906.4 lps 177757.4 lps
> Arithmetic Test (type = float) 210562.7 lps 208476.4 lps
> Arithmetic Test (type = double) 210385.9 lps 208443.3 lps
What kind of arithmetic is this? Why on earth would arithmetic vary
from one kernel to another?
--
Daniel
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
@ 2002-09-05 15:37 Paolo Ciarrocchi
2002-09-06 10:28 ` Pavel Machek
0 siblings, 1 reply; 12+ messages in thread
From: Paolo Ciarrocchi @ 2002-09-05 15:37 UTC (permalink / raw)
To: venom, ahu; +Cc: linux-kernel
From: venom@sns.it
> I usually run byte bench regularly with every new kernel, so I see some
> strange results here.
>
> From your numbers, I would say you are using a PIII 600/900 Mhz (more or
> less). It is not an AMD AThlon or a PIV, since float and double are too
> slow, not it is a K6 because they are too fast.
Yes, I ran the test on a HP Omnibook 600 (PIII@900)
[...]
> seeing this I think you had something running in background using your CPU
> while you where running int tests. if you loock at bm/results/log
> (log.accum if you did some other run recently)
> should find lines like:
>
> Arithmetic Test (type = int)|10.0|lps|227163.1|227158.7|6
>
> that is a little more interesting if you are under load.
No other load, just top and a less of a few files.
[...]
> > >Process Creation Test 9078.6 lps 5422.1 lps
> > Execl Throughput Test 998.0 lps 771.6 lps
>
> this is interesting, but seeing previous results about int and short,
> I am curious about your real load. I am quite curious if with 2.5 you are
> using kernel preemption.
No load, but preemption.
> > File Read (10 seconds) 1571652.0 KBps 1553289.0 KBps
> > File Write (10 seconds) 109237.0 KBps 132002.0 KBps
> > >File Copy (10 seconds) 24329.0 KBps 17994.0 KBps
> > File Read (30 seconds) 1562505.0 KBps 1540682.0 KBps
> > File Write (30 seconds) 113152.0 KBps 137781.0 KBps
> > File Copy (30 seconds) 14334.0 KBps 11460.0 KBps
>
> I saw the save with IDE disks... again, are you using kernel preemption?
ang again, yes ;-)
> > C Compiler Test 470.9 lpm 450.9 lpm
> > Shell scripts (1 concurrent) 980.4 lpm 876.7 lpm
> > Shell scripts (2 concurrent) 544.1 lpm 480.3 lpm
> > Shell scripts (4 concurrent) 287.0 lpm 251.0 lpm
> > Shell scripts (8 concurrent) 147.0 lpm 126.0 lpm
>
> In my tests generally shell scripts are faster with 2.5 kernel.
In any case I'll run again the test with the 4.1 version of Unix Bench.
I'll post the result using as "baseline" the results of the 2.4.19 again 2.5.33 and hopefully 2.4.20-pre5aa1.
Ciao,
Paolo
--
Get your free email from www.linuxmail.org
Powered by Outblaze
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: side-by-side Re: BYTE Unix Benchmarks Version 3.6
2002-09-05 13:48 ` side-by-side " bert hubert
@ 2002-09-05 15:11 ` venom
2002-09-06 3:23 ` Daniel Phillips
1 sibling, 0 replies; 12+ messages in thread
From: venom @ 2002-09-05 15:11 UTC (permalink / raw)
To: bert hubert; +Cc: Paolo Ciarrocchi, linux-kernel
I usually run byte bench regularly with every new kernel, so I see some
strange results here.
>From your numbers, I would say you are using a PIII 600/900 Mhz (more or
less). It is not an AMD AThlon or a PIV, since float and double are too
slow, not it is a K6 because they are too fast.
On Thu, 5 Sep 2002, bert hubert wrote:
> Date: Thu, 5 Sep 2002 15:48:30 +0200
> From: bert hubert <ahu@ds9a.nl>
> To: Paolo Ciarrocchi <ciarrocchi@linuxmail.org>
> Cc: linux-kernel@vger.kernel.org
> Subject: side-by-side Re: BYTE Unix Benchmarks Version 3.6
>
> Side-by-side with some marked changes highlighted:
>
> 2.4.19 2.5.33
> -----------------------------------------------------------------------
> Dhrystone 2 without register variable 1499020.6 lps 1488327.9 lps
> Dhrystone 2 using register variables 1501168.4 lps 1488265.3 lps
> Arithmetic Test (type = arithoh) 3598100.4 lps 3435944.6 lps
this could vary a little
> Arithmetic Test (type = register) 201521.0 lps 197870.4 lps
> Arithmetic Test (type = short) 190245.9 lps 145140.8 lps
the difference should never be so big
> Arithmetic Test (type = int) 201904.5 lps 104440.5 lps
the difference should never be so big
> Arithmetic Test (type = long) 201906.4 lps 177757.4 lps
the difference should never be so big
seeing this I think you had something running in background using your CPU
while you where running int tests. if you loock at bm/results/log
(log.accum if you did some other run recently)
should find lines like:
Arithmetic Test (type = int)|10.0|lps|227163.1|227158.7|6
that is a little more interesting if you are under load.
> Arithmetic Test (type = float) 210562.7 lps 208476.4 lps
> Arithmetic Test (type = double) 210385.9 lps 208443.3 lps
> System Call Overhead Test 407402.6 lps 397276.7 lps
> >Pipe Throughput Test 476268.6 lps 434561.9 lps
> >Pipe-based Context Switching Test 218969.9 lps 148653.5 lps
this could vary because of a lot of factors, starting from a bad page
colouring going to sendmail activity.
> >Process Creation Test 9078.6 lps 5422.1 lps
> Execl Throughput Test 998.0 lps 771.6 lps
this is interesting, but seeing previous results about int and short,
I am curious about your real load. I am quite curious if with 2.5 you are
using kernel preemption.
> File Read (10 seconds) 1571652.0 KBps 1553289.0 KBps
> File Write (10 seconds) 109237.0 KBps 132002.0 KBps
> >File Copy (10 seconds) 24329.0 KBps 17994.0 KBps
> File Read (30 seconds) 1562505.0 KBps 1540682.0 KBps
> File Write (30 seconds) 113152.0 KBps 137781.0 KBps
> File Copy (30 seconds) 14334.0 KBps 11460.0 KBps
I saw the save with IDE disks... again, are you using kernel preemption?
> C Compiler Test 470.9 lpm 450.9 lpm
> Shell scripts (1 concurrent) 980.4 lpm 876.7 lpm
> Shell scripts (2 concurrent) 544.1 lpm 480.3 lpm
> Shell scripts (4 concurrent) 287.0 lpm 251.0 lpm
> Shell scripts (8 concurrent) 147.0 lpm 126.0 lpm
In my tests generally shell scripts are faster with 2.5 kernel.
> >Dc: sqrt(2) to 99 decimal places 42311.6 lpm 33530.4 lpm
> Recursion Test--Tower of Hanoi 18915.4 lps 18514.3 lps
>
>
> INDEX VALUES 2.4.19 2.5
> TEST INDEX INDEX
>
> Arithmetic Test (type = double) 82.8 82.0
> Dhrystone 2 without register variables 67.0 66.5
> Execl Throughput Test 60.5 46.8
> File Copy (30 seconds) 80.1 64.0
> Pipe-based Context Switching Test 166.1 112.7
> Shell scripts (8 concurrent) 36.8 31.5
> ========= =========
> SUM of 6 items 493.2 403.6
> AVERAGE 82.2 67.3
>
Luigi
> --
> http://www.PowerDNS.com Versatile DNS Software & Services
> http://www.tk the dot in .tk
> http://lartc.org Linux Advanced Routing & Traffic Control HOWTO
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
^ permalink raw reply [flat|nested] 12+ messages in thread
* side-by-side Re: BYTE Unix Benchmarks Version 3.6
2002-09-04 22:00 Paolo Ciarrocchi
@ 2002-09-05 13:48 ` bert hubert
2002-09-05 15:11 ` venom
2002-09-06 3:23 ` Daniel Phillips
0 siblings, 2 replies; 12+ messages in thread
From: bert hubert @ 2002-09-05 13:48 UTC (permalink / raw)
To: Paolo Ciarrocchi; +Cc: linux-kernel
Side-by-side with some marked changes highlighted:
2.4.19 2.5.33
-----------------------------------------------------------------------
Dhrystone 2 without register variable 1499020.6 lps 1488327.9 lps
Dhrystone 2 using register variables 1501168.4 lps 1488265.3 lps
Arithmetic Test (type = arithoh) 3598100.4 lps 3435944.6 lps
Arithmetic Test (type = register) 201521.0 lps 197870.4 lps
Arithmetic Test (type = short) 190245.9 lps 145140.8 lps
Arithmetic Test (type = int) 201904.5 lps 104440.5 lps
Arithmetic Test (type = long) 201906.4 lps 177757.4 lps
Arithmetic Test (type = float) 210562.7 lps 208476.4 lps
Arithmetic Test (type = double) 210385.9 lps 208443.3 lps
System Call Overhead Test 407402.6 lps 397276.7 lps
>Pipe Throughput Test 476268.6 lps 434561.9 lps
>Pipe-based Context Switching Test 218969.9 lps 148653.5 lps
>Process Creation Test 9078.6 lps 5422.1 lps
Execl Throughput Test 998.0 lps 771.6 lps
File Read (10 seconds) 1571652.0 KBps 1553289.0 KBps
File Write (10 seconds) 109237.0 KBps 132002.0 KBps
>File Copy (10 seconds) 24329.0 KBps 17994.0 KBps
File Read (30 seconds) 1562505.0 KBps 1540682.0 KBps
File Write (30 seconds) 113152.0 KBps 137781.0 KBps
File Copy (30 seconds) 14334.0 KBps 11460.0 KBps
C Compiler Test 470.9 lpm 450.9 lpm
Shell scripts (1 concurrent) 980.4 lpm 876.7 lpm
Shell scripts (2 concurrent) 544.1 lpm 480.3 lpm
Shell scripts (4 concurrent) 287.0 lpm 251.0 lpm
Shell scripts (8 concurrent) 147.0 lpm 126.0 lpm
>Dc: sqrt(2) to 99 decimal places 42311.6 lpm 33530.4 lpm
Recursion Test--Tower of Hanoi 18915.4 lps 18514.3 lps
INDEX VALUES 2.4.19 2.5
TEST INDEX INDEX
Arithmetic Test (type = double) 82.8 82.0
Dhrystone 2 without register variables 67.0 66.5
Execl Throughput Test 60.5 46.8
File Copy (30 seconds) 80.1 64.0
Pipe-based Context Switching Test 166.1 112.7
Shell scripts (8 concurrent) 36.8 31.5
========= =========
SUM of 6 items 493.2 403.6
AVERAGE 82.2 67.3
--
http://www.PowerDNS.com Versatile DNS Software & Services
http://www.tk the dot in .tk
http://lartc.org Linux Advanced Routing & Traffic Control HOWTO
^ permalink raw reply [flat|nested] 12+ messages in thread
end of thread, other threads:[~2002-09-09 10:41 UTC | newest]
Thread overview: 12+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2002-09-06 7:44 side-by-side Re: BYTE Unix Benchmarks Version 3.6 Paolo Ciarrocchi
-- strict thread matches above, loose matches on Subject: below --
2002-09-08 22:56 Paolo Ciarrocchi
2002-09-09 10:46 ` Pavel Machek
2002-09-07 12:21 Paolo Ciarrocchi
2002-09-08 19:26 ` Pavel Machek
2002-09-05 15:37 Paolo Ciarrocchi
2002-09-06 10:28 ` Pavel Machek
2002-09-08 14:09 ` venom
2002-09-04 22:00 Paolo Ciarrocchi
2002-09-05 13:48 ` side-by-side " bert hubert
2002-09-05 15:11 ` venom
2002-09-06 3:23 ` Daniel Phillips
2002-09-06 7:09 ` bert hubert
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).