mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* kernel-x64-smp-multiprocessor-time util problem
@ 2006-06-19 23:04 art
  2006-06-19 23:17 ` Bernd Petrovitsch
  2006-06-21  9:24 ` Andi Kleen
  0 siblings, 2 replies; 5+ messages in thread
From: art @ 2006-06-19 23:04 UTC (permalink / raw)
  To: linux-kernel

on dual core amd-athlon under 64bit-smp core

kernel compilation time:

time make -j 8
...
LD [M]  sound/usb/snd-usb-lib.ko
LD [M]  sound/usb/usx2y/snd-usb-usx2y.ko

real    18m0.948s
user    26m6.270s    ------bad
sys     4m22.256s    ------?bad
[xxx@localhost linux-2.6.17]$
--- real-clock time  is ~18 min -- user and system time doubled?

art@usfltd.com

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: kernel-x64-smp-multiprocessor-time util problem
  2006-06-19 23:04 kernel-x64-smp-multiprocessor-time util problem art
@ 2006-06-19 23:17 ` Bernd Petrovitsch
  2006-06-21  8:17   ` art
  2006-06-21  9:24 ` Andi Kleen
  1 sibling, 1 reply; 5+ messages in thread
From: Bernd Petrovitsch @ 2006-06-19 23:17 UTC (permalink / raw)
  To: art; +Cc: linux-kernel

On Mon, 2006-06-19 at 18:04 -0500, art@usfltd.com wrote:
> on dual core amd-athlon under 64bit-smp core
> 
> kernel compilation time:
> 
> time make -j 8
> ...
> LD [M]  sound/usb/snd-usb-lib.ko
> LD [M]  sound/usb/usx2y/snd-usb-usx2y.ko
> 
> real    18m0.948s
> user    26m6.270s    ------bad
> sys     4m22.256s    ------?bad
> [xxx@localhost linux-2.6.17]$
> --- real-clock time  is ~18 min -- user and system time doubled?

How many virtual CPUs (i.e. HT is "2 CPUs") do you have in that machine?

	Bernd
-- 
Firmix Software GmbH                   http://www.firmix.at/
mobil: +43 664 4416156                 fax: +43 1 7890849-55
          Embedded Linux Development and Services


^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: kernel-x64-smp-multiprocessor-time util problem
  2006-06-19 23:17 ` Bernd Petrovitsch
@ 2006-06-21  8:17   ` art
  2006-06-21  8:33     ` Bernd Petrovitsch
  0 siblings, 1 reply; 5+ messages in thread
From: art @ 2006-06-21  8:17 UTC (permalink / raw)
  To: Bernd Petrovitsch; +Cc: linux-kernel

Quoting Bernd Petrovitsch <bernd@firmix.at>:

> On Mon, 2006-06-19 at 18:04 -0500, art@usfltd.com wrote:
>> on dual core amd-athlon under 64bit-smp core
>>
>> kernel compilation time:
>>
>> time make -j 8
>> ...
>> LD [M]  sound/usb/snd-usb-lib.ko
>> LD [M]  sound/usb/usx2y/snd-usb-usx2y.ko
>>
>> real    18m0.948s
>> user    26m6.270s    ------bad
>> sys     4m22.256s    ------?bad
>> [xxx@localhost linux-2.6.17]$
>> --- real-clock time  is ~18 min -- user and system time doubled?
>
> How many virtual CPUs (i.e. HT is "2 CPUs") do you have in that machine?
>
> 	Bernd
> --
> Firmix Software GmbH                   http://www.firmix.at/
> mobil: +43 664 4416156                 fax: +43 1 7890849-55
>           Embedded Linux Development and Services
>
------------------------------------------------

1 CPU 2 cores = 2 (amd athlon x2 4200+)

xboom

art@usfltd.con

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: kernel-x64-smp-multiprocessor-time util problem
  2006-06-21  8:17   ` art
@ 2006-06-21  8:33     ` Bernd Petrovitsch
  0 siblings, 0 replies; 5+ messages in thread
From: Bernd Petrovitsch @ 2006-06-21  8:33 UTC (permalink / raw)
  To: art; +Cc: linux-kernel

On Wed, 2006-06-21 at 03:17 -0500, art@usfltd.com wrote:
> Quoting Bernd Petrovitsch <bernd@firmix.at>:
> > On Mon, 2006-06-19 at 18:04 -0500, art@usfltd.com wrote:
> >> on dual core amd-athlon under 64bit-smp core
> >>
> >> kernel compilation time:
> >>
> >> time make -j 8
> >> ...
> >> LD [M]  sound/usb/snd-usb-lib.ko
> >> LD [M]  sound/usb/usx2y/snd-usb-usx2y.ko
> >>
> >> real    18m0.948s
> >> user    26m6.270s    ------bad
> >> sys     4m22.256s    ------?bad
> >> [xxx@localhost linux-2.6.17]$
> >> --- real-clock time  is ~18 min -- user and system time doubled?
> >
> > How many virtual CPUs (i.e. HT is "2 CPUs") do you have in that machine?
[...]
> 1 CPU 2 cores = 2 (amd athlon x2 4200+)

What does "real" really measure?
What does "user" and "sys" really measure?

	Bernd
-- 
Firmix Software GmbH                   http://www.firmix.at/
mobil: +43 664 4416156                 fax: +43 1 7890849-55
          Embedded Linux Development and Services


^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: kernel-x64-smp-multiprocessor-time util problem
  2006-06-19 23:04 kernel-x64-smp-multiprocessor-time util problem art
  2006-06-19 23:17 ` Bernd Petrovitsch
@ 2006-06-21  9:24 ` Andi Kleen
  1 sibling, 0 replies; 5+ messages in thread
From: Andi Kleen @ 2006-06-21  9:24 UTC (permalink / raw)
  To: art; +Cc: linux-kernel

art@usfltd.com writes:

> on dual core amd-athlon under 64bit-smp core
> 
> kernel compilation time:
> 
> time make -j 8
> ...
> LD [M]  sound/usb/snd-usb-lib.ko
> LD [M]  sound/usb/usx2y/snd-usb-usx2y.ko
> 
> real    18m0.948s
> user    26m6.270s    ------bad
> sys     4m22.256s    ------?bad
> [xxx@localhost linux-2.6.17]$
> --- real-clock time  is ~18 min -- user and system time doubled?

user/sys accounts how much time the individual CPUs spent on your 
job. real counts how far your wall clock advanced.

Think about it. It's not that difficult to understand.

-Andi

^ permalink raw reply	[flat|nested] 5+ messages in thread

end of thread, other threads:[~2006-06-21  9:24 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2006-06-19 23:04 kernel-x64-smp-multiprocessor-time util problem art
2006-06-19 23:17 ` Bernd Petrovitsch
2006-06-21  8:17   ` art
2006-06-21  8:33     ` Bernd Petrovitsch
2006-06-21  9:24 ` Andi Kleen

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®