[PATCH] remove bogomips from /proc/cpuinfo

STALE7306d

5 messages, 4 authors, 2006-07-31 · open the first message on its own page

[PATCH] remove bogomips from /proc/cpuinfo

From: Olaf Hering <hidden>
Date: 2006-07-31 12:59:10

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

Re: [PATCH] remove bogomips from /proc/cpuinfo

From: Arnd Bergmann <hidden>
Date: 2006-07-31 17:46:30

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 <><

Re: [PATCH] remove bogomips from /proc/cpuinfo

From: Olaf Hering <hidden>
Date: 2006-07-31 17:49:29

 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?

Re: [PATCH] remove bogomips from /proc/cpuinfo

From: Andreas Schwab <hidden>
Date: 2006-07-31 18:17:09

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."

Re: [PATCH] remove bogomips from /proc/cpuinfo

From: Linas Vepstas <hidden>
Date: 2006-07-31 19:14:50

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
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help