Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-12 Thread Sukadev Bhattiprolu
Ingo Molnar [mi...@kernel.org] wrote: | | * Peter Zijlstra wrote: | | > On Tue, Nov 05, 2013 at 02:31:52PM -0300, Arnaldo Carvalho de Melo wrote: | > > PeterZ, | > > | > > Can I have your Acked-by for this one? I guess now the goal is | > > achieved, no? Being able to profile children with

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-12 Thread Sukadev Bhattiprolu
Ingo Molnar [mi...@kernel.org] wrote: | | * Peter Zijlstra pet...@infradead.org wrote: | | On Tue, Nov 05, 2013 at 02:31:52PM -0300, Arnaldo Carvalho de Melo wrote: | PeterZ, | | Can I have your Acked-by for this one? I guess now the goal is | achieved, no? Being able to profile

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-11 Thread Ingo Molnar
* Peter Zijlstra wrote: > On Tue, Nov 05, 2013 at 02:31:52PM -0300, Arnaldo Carvalho de Melo wrote: > > PeterZ, > > > > Can I have your Acked-by for this one? I guess now the goal is > > achieved, no? > > So this option allows -t/-p/-u to create one buffer per cpu and attach > all the

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-11 Thread Ingo Molnar
* Peter Zijlstra pet...@infradead.org wrote: On Tue, Nov 05, 2013 at 02:31:52PM -0300, Arnaldo Carvalho de Melo wrote: PeterZ, Can I have your Acked-by for this one? I guess now the goal is achieved, no? So this option allows -t/-p/-u to create one buffer per cpu and attach all

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-08 Thread Arnaldo Carvalho de Melo
Em Fri, Nov 08, 2013 at 09:40:01AM +0100, Peter Zijlstra escreveu: > On Tue, Nov 05, 2013 at 02:31:52PM -0300, Arnaldo Carvalho de Melo wrote: > > Can I have your Acked-by for this one? I guess now the goal is > > achieved, no? > So this option allows -t/-p/-u to create one buffer per cpu

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-08 Thread Peter Zijlstra
On Tue, Nov 05, 2013 at 02:31:52PM -0300, Arnaldo Carvalho de Melo wrote: > PeterZ, > > Can I have your Acked-by for this one? I guess now the goal is > achieved, no? So this option allows -t/-p/-u to create one buffer per cpu and attach all the various thread/process/user tasks' their

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-08 Thread Peter Zijlstra
On Tue, Nov 05, 2013 at 02:31:52PM -0300, Arnaldo Carvalho de Melo wrote: PeterZ, Can I have your Acked-by for this one? I guess now the goal is achieved, no? So this option allows -t/-p/-u to create one buffer per cpu and attach all the various thread/process/user tasks' their

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-08 Thread Arnaldo Carvalho de Melo
Em Fri, Nov 08, 2013 at 09:40:01AM +0100, Peter Zijlstra escreveu: On Tue, Nov 05, 2013 at 02:31:52PM -0300, Arnaldo Carvalho de Melo wrote: Can I have your Acked-by for this one? I guess now the goal is achieved, no? So this option allows -t/-p/-u to create one buffer per cpu and

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-07 Thread Adrian Hunter
On 05/11/13 19:31, Arnaldo Carvalho de Melo wrote: > PeterZ, > > Can I have your Acked-by for this one? I guess now the goal is > achieved, no? Ping > > - Arnaldo > > Em Tue, Nov 05, 2013 at 11:25:45AM -0300, Arnaldo Carvalho de Melo escreveu: >> Em Tue, Nov 05, 2013 at 02:30:24PM +0100,

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-07 Thread Adrian Hunter
On 05/11/13 19:31, Arnaldo Carvalho de Melo wrote: PeterZ, Can I have your Acked-by for this one? I guess now the goal is achieved, no? Ping - Arnaldo Em Tue, Nov 05, 2013 at 11:25:45AM -0300, Arnaldo Carvalho de Melo escreveu: Em Tue, Nov 05, 2013 at 02:30:24PM +0100, Jiri Olsa

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Arnaldo Carvalho de Melo
PeterZ, Can I have your Acked-by for this one? I guess now the goal is achieved, no? - Arnaldo Em Tue, Nov 05, 2013 at 11:25:45AM -0300, Arnaldo Carvalho de Melo escreveu: > Em Tue, Nov 05, 2013 at 02:30:24PM +0100, Jiri Olsa escreveu: > > On Tue, Nov 05, 2013 at 03:09:30PM +0200,

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Arnaldo Carvalho de Melo
Em Tue, Nov 05, 2013 at 02:30:24PM +0100, Jiri Olsa escreveu: > On Tue, Nov 05, 2013 at 03:09:30PM +0200, Adrian Hunter wrote: > > > right, I haven't considered the hundreds CPU machine.. I just > > > saw that it disables inherited events in my test ;-) maybe we > > > could mentioned that

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Jiri Olsa
On Tue, Nov 05, 2013 at 03:09:30PM +0200, Adrian Hunter wrote: SNIP > >> Another advantage of per-thread mmaps is that you do not > >> need to sample time (nor cpu), because the events are recorded > >> in order. > >> > >> I was adding a feature. Users can choose per-cpu mmaps if > >> they

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Adrian Hunter
On 05/11/13 11:42, Jiri Olsa wrote: > On Tue, Nov 05, 2013 at 10:28:38AM +0200, Adrian Hunter wrote: >> On 04/11/13 17:29, Jiri Olsa wrote: >>> On Fri, Nov 01, 2013 at 03:51:34PM +0200, Adrian Hunter wrote: By default, when tasks are specified (i.e. -p, -t or -u options) per-thread mmaps

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Jiri Olsa
On Tue, Nov 05, 2013 at 10:28:38AM +0200, Adrian Hunter wrote: > On 04/11/13 17:29, Jiri Olsa wrote: > > On Fri, Nov 01, 2013 at 03:51:34PM +0200, Adrian Hunter wrote: > >> By default, when tasks are specified (i.e. -p, -t > >> or -u options) per-thread mmaps are created. Add > >> an option to

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Adrian Hunter
On 04/11/13 17:29, Jiri Olsa wrote: > On Fri, Nov 01, 2013 at 03:51:34PM +0200, Adrian Hunter wrote: >> By default, when tasks are specified (i.e. -p, -t >> or -u options) per-thread mmaps are created. Add >> an option to override that and force per-cpu mmaps. >> >> Signed-off-by: Adrian Hunter

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Adrian Hunter
On 04/11/13 17:29, Jiri Olsa wrote: On Fri, Nov 01, 2013 at 03:51:34PM +0200, Adrian Hunter wrote: By default, when tasks are specified (i.e. -p, -t or -u options) per-thread mmaps are created. Add an option to override that and force per-cpu mmaps. Signed-off-by: Adrian Hunter

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Jiri Olsa
On Tue, Nov 05, 2013 at 10:28:38AM +0200, Adrian Hunter wrote: On 04/11/13 17:29, Jiri Olsa wrote: On Fri, Nov 01, 2013 at 03:51:34PM +0200, Adrian Hunter wrote: By default, when tasks are specified (i.e. -p, -t or -u options) per-thread mmaps are created. Add an option to override that

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Adrian Hunter
On 05/11/13 11:42, Jiri Olsa wrote: On Tue, Nov 05, 2013 at 10:28:38AM +0200, Adrian Hunter wrote: On 04/11/13 17:29, Jiri Olsa wrote: On Fri, Nov 01, 2013 at 03:51:34PM +0200, Adrian Hunter wrote: By default, when tasks are specified (i.e. -p, -t or -u options) per-thread mmaps are created.

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Jiri Olsa
On Tue, Nov 05, 2013 at 03:09:30PM +0200, Adrian Hunter wrote: SNIP Another advantage of per-thread mmaps is that you do not need to sample time (nor cpu), because the events are recorded in order. I was adding a feature. Users can choose per-cpu mmaps if they want. right, I

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Arnaldo Carvalho de Melo
Em Tue, Nov 05, 2013 at 02:30:24PM +0100, Jiri Olsa escreveu: On Tue, Nov 05, 2013 at 03:09:30PM +0200, Adrian Hunter wrote: right, I haven't considered the hundreds CPU machine.. I just saw that it disables inherited events in my test ;-) maybe we could mentioned that somewhere, because

Re: [PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-05 Thread Arnaldo Carvalho de Melo
PeterZ, Can I have your Acked-by for this one? I guess now the goal is achieved, no? - Arnaldo Em Tue, Nov 05, 2013 at 11:25:45AM -0300, Arnaldo Carvalho de Melo escreveu: Em Tue, Nov 05, 2013 at 02:30:24PM +0100, Jiri Olsa escreveu: On Tue, Nov 05, 2013 at 03:09:30PM +0200, Adrian

[PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-01 Thread Adrian Hunter
By default, when tasks are specified (i.e. -p, -t or -u options) per-thread mmaps are created. Add an option to override that and force per-cpu mmaps. Signed-off-by: Adrian Hunter --- tools/perf/Documentation/perf-record.txt | 6 ++ tools/perf/builtin-record.c | 2 ++

[PATCH V3 06/11] perf record: Add an option to force per-cpu mmaps

2013-11-01 Thread Adrian Hunter
By default, when tasks are specified (i.e. -p, -t or -u options) per-thread mmaps are created. Add an option to override that and force per-cpu mmaps. Signed-off-by: Adrian Hunter adrian.hun...@intel.com --- tools/perf/Documentation/perf-record.txt | 6 ++ tools/perf/builtin-record.c