[PATCH] remove bogomips from /proc/cpuinfo
STALE7306d
5 messages,
4 authors,
2006-07-31
· open the first message on its own page
Remove bogomips from /proc/cpuinfo.
It is now really bogus since "timebase-frequency" is shown.
Signed-off-by: Olaf Hering <redacted>
---
arch/powerpc/kernel/setup-common.c | 14 --------------
1 file changed, 14 deletions(-)
Index: linux-2.6.18-rc3/arch/powerpc/kernel/setup-common.c
=================================================================== --- linux-2.6.18-rc3.orig/arch/powerpc/kernel/setup-common.c
+++ linux-2.6.18-rc3/arch/powerpc/kernel/setup-common.c @@ -163,14 +163,6 @@ static int show_cpuinfo(struct seq_file
unsigned short min ;
if ( cpu_id == NR_CPUS ) {
- #if defined(CONFIG_SMP) && defined(CONFIG_PPC32)
- unsigned long bogosum = 0 ;
- int i ;
- for_each_online_cpu ( i )
- bogosum += loops_per_jiffy ;
- seq_printf ( m , "total bogomips \t : %lu.%02lu \n " ,
- bogosum / ( 500000 / HZ ), bogosum / ( 5000 / HZ ) % 100 );
- #endif /* CONFIG_SMP && CONFIG_PPC32 */
seq_printf ( m , "timebase \t : %lu \n " , ppc_tb_freq );
if ( ppc_md . name )
seq_printf ( m , "platform \t : %s \n " , ppc_md . name ); @@ -263,12 +255,6 @@ static int show_cpuinfo(struct seq_file
seq_printf ( m , "revision \t : %hd.%hd (pvr %04x %04x) \n " ,
maj , min , PVR_VER ( pvr ), PVR_REV ( pvr ));
- #ifdef CONFIG_PPC32
- seq_printf ( m , "bogomips \t : %lu.%02lu \n " ,
- loops_per_jiffy / ( 500000 / HZ ),
- ( loops_per_jiffy / ( 5000 / HZ )) % 100 );
- #endif
-
#ifdef CONFIG_SMP
seq_printf ( m , " \n " );
#endif
On Monday 31 July 2006 14:59, Olaf Hering wrote: Remove bogomips from /proc/cpuinfo.
It is now really bogus since "timebase-frequency" is shown.
Well, but it's still part of the ABI, right?
How do you determine that there are no broken applications
still relying on it?
Arnd <><
On Mon, Jul 31, Arnd Bergmann wrote:
On Monday 31 July 2006 14:59, Olaf Hering wrote: quoted Remove bogomips from /proc/cpuinfo.
It is now really bogus since "timebase-frequency" is shown.
Well, but it's still part of the ABI, right?
How do you determine that there are no broken applications
still relying on it?
Everything works on a G5, as example. Alpha doesnt have it either.
What pratical value had bogomips for an application?
Olaf Hering [off-list ref] writes:
On Mon, Jul 31, Arnd Bergmann wrote:
quoted On Monday 31 July 2006 14:59, Olaf Hering wrote: quoted Remove bogomips from /proc/cpuinfo.
It is now really bogus since "timebase-frequency" is shown.
Well, but it's still part of the ABI, right?
How do you determine that there are no broken applications
still relying on it?
Everything works on a G5, as example. Alpha doesnt have it either.
What pratical value had bogomips for an application?
What harm does it do?
Andreas.
--
Andreas Schwab, SuSE Labs, schwab@suse.de
SuSE Linux Products GmbH, Maxfeldstraße 5, 90409 Nürnberg, Germany
PGP key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5
"And now for something completely different."
On Mon, Jul 31, 2006 at 08:17:05PM +0200, Andreas Schwab wrote: Olaf Hering [off-list ref] writes:
quoted On Mon, Jul 31, Arnd Bergmann wrote:
quoted On Monday 31 July 2006 14:59, Olaf Hering wrote: quoted Remove bogomips from /proc/cpuinfo.
It is now really bogus since "timebase-frequency" is shown.
Well, but it's still part of the ABI, right?
How do you determine that there are no broken applications
still relying on it?
Everything works on a G5, as example. Alpha doesnt have it either.
What pratical value had bogomips for an application?
What harm does it do?
Kernel bloat.
--linas