Em Mon, May 11, 2015 at 06:29:28PM +0100, Will Deacon escreveu:
> On Mon, May 11, 2015 at 04:59:58PM +0100, a...@redhat.com wrote:
> > Em Mon, May 11, 2015 at 12:58:14PM -0300, a...@redhat.com escreveu:
> > > Em Mon, May 11, 2015 at 02:33:04PM +0200, Ingo Molnar escreveu:
> > > > > That was already
On Mon, May 11, 2015 at 04:59:58PM +0100, a...@redhat.com wrote:
> Em Mon, May 11, 2015 at 12:58:14PM -0300, a...@redhat.com escreveu:
> > Em Mon, May 11, 2015 at 02:33:04PM +0200, Ingo Molnar escreveu:
> > > > That was already proposed here (as part of the fallback from getconf):
> > > >
> > > >
Em Mon, May 11, 2015 at 12:58:14PM -0300, a...@redhat.com escreveu:
> Em Mon, May 11, 2015 at 02:33:04PM +0200, Ingo Molnar escreveu:
> > > That was already proposed here (as part of the fallback from getconf):
> > >
> > > https://lkml.kernel.org/r/20150427190356.gd...@krava.redhat.com
> > >
>
Em Mon, May 11, 2015 at 02:33:04PM +0200, Ingo Molnar escreveu:
>
> * Will Deacon wrote:
>
> > On Mon, May 11, 2015 at 09:21:20AM +0100, Ingo Molnar wrote:
> > > * David Ahern wrote:
> > > > On 4/23/15 5:29 AM, Will Deacon wrote:
> > > > >Commit 6428c59a97de ("perf tools: Set JOBS based on CPU
* Will Deacon wrote:
> On Mon, May 11, 2015 at 09:21:20AM +0100, Ingo Molnar wrote:
> > * David Ahern wrote:
> > > On 4/23/15 5:29 AM, Will Deacon wrote:
> > > >Commit 6428c59a97de ("perf tools: Set JOBS based on CPU or processor")
> > > >causes weird behaviour on arm/arm64 platforms because we
On Mon, May 11, 2015 at 09:21:20AM +0100, Ingo Molnar wrote:
> * David Ahern wrote:
> > On 4/23/15 5:29 AM, Will Deacon wrote:
> > >Commit 6428c59a97de ("perf tools: Set JOBS based on CPU or processor")
> > >causes weird behaviour on arm/arm64 platforms because we use the "CPU"
> > >prefix for thi
* David Ahern wrote:
> On 4/23/15 5:29 AM, Will Deacon wrote:
> >Hi all,
> >
> >Commit 6428c59a97de ("perf tools: Set JOBS based on CPU or processor")
> >causes weird behaviour on arm/arm64 platforms because we use the "CPU"
> >prefix for things like:
> >
> >CPU implementer : 0x41
> >CPU archite
On Mon, Apr 27, 2015 at 04:00:04PM -0300, Arnaldo Carvalho de Melo wrote:
SNIP
> > > 1 file changed, 1 insertion(+), 1 deletion(-)
> > >
> > > diff --git a/tools/perf/Makefile b/tools/perf/Makefile
> > > index c699dc35eef9..bc846b83c295 100644
> > > --- a/tools/perf/Makefile
> > > +++ b/tools/p
Em Mon, Apr 27, 2015 at 08:52:08PM +0200, Jiri Olsa escreveu:
> On Mon, Apr 27, 2015 at 03:45:35PM -0300, Arnaldo Carvalho de Melo wrote:
>
> SNIP
>
> > > > [acme@ssdandy linux]$
> > > >
> > >
> > > how about this one
> >
> > I came up with this one, that doesn't introduces a new file:
>
> o
On Mon, Apr 27, 2015 at 03:45:35PM -0300, Arnaldo Carvalho de Melo wrote:
SNIP
> > > [acme@ssdandy linux]$
> > >
> >
> > how about this one
>
> I came up with this one, that doesn't introduces a new file:
ook
>
> From e8155c06652a05f2307d53823a7937be5dad4e32 Mon Sep 17 00:00:00 2001
> From
Em Mon, Apr 27, 2015 at 08:41:20PM +0200, Jiri Olsa escreveu:
> On Mon, Apr 27, 2015 at 03:39:53PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Mon, Apr 27, 2015 at 07:49:06PM +0200, Jiri Olsa escreveu:
> > > On Mon, Apr 27, 2015 at 02:40:17PM -0300, Arnaldo Carvalho de Melo wrote:
> > > > Em Mon,
On Mon, Apr 27, 2015 at 03:39:53PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Mon, Apr 27, 2015 at 07:49:06PM +0200, Jiri Olsa escreveu:
> > On Mon, Apr 27, 2015 at 02:40:17PM -0300, Arnaldo Carvalho de Melo wrote:
> > > Em Mon, Apr 27, 2015 at 11:13:02AM -0600, David Ahern escreveu:
> > > >
> >
Em Mon, Apr 27, 2015 at 07:49:06PM +0200, Jiri Olsa escreveu:
> On Mon, Apr 27, 2015 at 02:40:17PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Mon, Apr 27, 2015 at 11:13:02AM -0600, David Ahern escreveu:
> > >
> > > I think the right thing to do is to remove JOBS completely.
> >
> > That is up
On Mon, Apr 27, 2015 at 02:40:17PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Mon, Apr 27, 2015 at 11:13:02AM -0600, David Ahern escreveu:
> > On 4/27/15 10:26 AM, Arnaldo Carvalho de Melo wrote:
> > >Em Fri, Apr 24, 2015 at 11:21:54AM -0600, David Ahern escreveu:
> > >>On 4/24/15 10:22 AM, Will D
Em Mon, Apr 27, 2015 at 11:13:02AM -0600, David Ahern escreveu:
> On 4/27/15 10:26 AM, Arnaldo Carvalho de Melo wrote:
> >Em Fri, Apr 24, 2015 at 11:21:54AM -0600, David Ahern escreveu:
> >>On 4/24/15 10:22 AM, Will Deacon wrote:
> >>>I don't have a SPARC machine to hand, but we could check that th
On 4/27/15 10:26 AM, Arnaldo Carvalho de Melo wrote:
Em Fri, Apr 24, 2015 at 11:21:54AM -0600, David Ahern escreveu:
On 4/24/15 10:22 AM, Will Deacon wrote:
I don't have a SPARC machine to hand, but we could check that the character
immediately following "CPU" is a number [0-9].
I have access
Em Fri, Apr 24, 2015 at 11:21:54AM -0600, David Ahern escreveu:
> On 4/24/15 10:22 AM, Will Deacon wrote:
> >I don't have a SPARC machine to hand, but we could check that the character
> >immediately following "CPU" is a number [0-9].
>
> I have access to 1 or 2 or ...
>
> Yes, it needs start wit
On 4/24/15 10:22 AM, Will Deacon wrote:
I don't have a SPARC machine to hand, but we could check that the character
immediately following "CPU" is a number [0-9].
I have access to 1 or 2 or ...
Yes, it needs start with CPU and be all caps (there are other Cpu lines)
and a cpu number follows:
On Fri, Apr 24, 2015 at 05:10:58PM +0100, Arnaldo Carvalho de Melo wrote:
> Em Thu, Apr 23, 2015 at 08:16:15AM -0600, David Ahern escreveu:
> > On 4/23/15 8:04 AM, Will Deacon wrote:
> > >+++ b/tools/perf/Makefile
> > >@@ -24,7 +24,7 @@ unexport MAKEFLAGS
> > > # (To override it, run 'make JOBS=1'
Em Thu, Apr 23, 2015 at 08:16:15AM -0600, David Ahern escreveu:
> On 4/23/15 8:04 AM, Will Deacon wrote:
> >+++ b/tools/perf/Makefile
> >@@ -24,7 +24,7 @@ unexport MAKEFLAGS
> > # (To override it, run 'make JOBS=1' and similar.)
> > #
> > ifeq ($(JOBS),)
> >- JOBS := $(shell egrep -c '^processo
On 4/23/15 5:29 AM, Will Deacon wrote:
Hi all,
Commit 6428c59a97de ("perf tools: Set JOBS based on CPU or processor")
causes weird behaviour on arm/arm64 platforms because we use the "CPU"
prefix for things like:
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x0
CPU part:
On 4/23/15 8:04 AM, Will Deacon wrote:
From 28740111e81aa9247bf48e3125dc43cc31d94e6f Mon Sep 17 00:00:00 2001
From: Will Deacon
Date: Thu, 23 Apr 2015 15:00:16 +0100
Subject: [PATCH] tools: perf: use getconf to determine number of online CPUs
Parsing /proc/cpuinfo is a fiddly, arch-dependent b
On Thu, Apr 23, 2015 at 12:29:16PM +0100, Will Deacon wrote:
> Hi all,
>
> Commit 6428c59a97de ("perf tools: Set JOBS based on CPU or processor")
> causes weird behaviour on arm/arm64 platforms because we use the "CPU"
> prefix for things like:
>
> CPU implementer : 0x41
> CPU architecture: 8
> C
Hi all,
Commit 6428c59a97de ("perf tools: Set JOBS based on CPU or processor")
causes weird behaviour on arm/arm64 platforms because we use the "CPU"
prefix for things like:
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x0
CPU part: 0xd03
CPU revision: 0
in /proc/cpui
24 matches
Mail list logo
