Re: [PATCH] perf report: Add support to display group output for non group events
Em Fri, Feb 09, 2018 at 08:10:57PM +0100, Jiri Olsa escreveu: > On Fri, Feb 09, 2018 at 03:37:11PM -0300, Arnaldo Carvalho de Melo wrote: > > Em Fri, Feb 09, 2018 at 10:27:34AM +0100, Jiri Olsa escreveu: > > Humm, its a nice hack, but it would be even better if it didn't showed > > it as if it was really a group: > > Samples: 20 of event 'anon group { cycles, instructions }', Event count > > (approx.): 4712980 > > It would be better to instead add another condition to the evlist that > > would trigger the view with all the examples... > > I'm applying it anyway, as it is useful, but would be nice to have the > > same output except for that header, that should read instead: > > Samples: 20 of non grouped events: cycles, instructions, Event count > > (approx.): 4712980 > right, I'll try to post something like that I've pushed out with this patch, so please go on from there. Thanks! - Arnaldo
Re: [PATCH] perf report: Add support to display group output for non group events
Em Fri, Feb 09, 2018 at 08:10:57PM +0100, Jiri Olsa escreveu: > On Fri, Feb 09, 2018 at 03:37:11PM -0300, Arnaldo Carvalho de Melo wrote: > > Em Fri, Feb 09, 2018 at 10:27:34AM +0100, Jiri Olsa escreveu: > > Humm, its a nice hack, but it would be even better if it didn't showed > > it as if it was really a group: > > Samples: 20 of event 'anon group { cycles, instructions }', Event count > > (approx.): 4712980 > > It would be better to instead add another condition to the evlist that > > would trigger the view with all the examples... > > I'm applying it anyway, as it is useful, but would be nice to have the > > same output except for that header, that should read instead: > > Samples: 20 of non grouped events: cycles, instructions, Event count > > (approx.): 4712980 > right, I'll try to post something like that I've pushed out with this patch, so please go on from there. Thanks! - Arnaldo
Re: [PATCH] perf report: Add support to display group output for non group events
On Fri, Feb 09, 2018 at 03:37:11PM -0300, Arnaldo Carvalho de Melo wrote: > Em Fri, Feb 09, 2018 at 10:27:34AM +0100, Jiri Olsa escreveu: > > On Wed, Feb 07, 2018 at 10:52:35AM -0800, Stephane Eranian wrote: > > > > SNIP > > > > > >> Similar to what I get if I do instead: > > > >> $ perf record -e '{branches,branches,branches,branches}' my_test > > > >> $ perf report --group > > > >> > > > >> But here, I would have to ensure all events fits in a group to allow > > > >> the reporting > > > >> I want. So that would limit me to 4 events. > > > >> > > > >> I think perf report --group should work regardless of how the events > > > >> were grouped. > > > >> Is there already a way to work around this? > > > > > > > > no workaround.. please try attached patch, it seems > > > > to work for what you described > > > > > > > Works for me. That's great! > > > Thanks. > > > > > > Tested-By: Stephane Eranian> > > > thanks, full patch attached > > > > jirka > > Humm, its a nice hack, but it would be even better if it didn't showed > it as if it was really a group: > > Samples: 20 of event 'anon group { cycles, instructions }', Event count > (approx.): 4712980 > > It would be better to instead add another condition to the evlist that > would trigger the view with all the examples... > > I'm applying it anyway, as it is useful, but would be nice to have the > same output except for that header, that should read instead: > > Samples: 20 of non grouped events: cycles, instructions, Event count > (approx.): 4712980 right, I'll try to post something like that thanks, jirka
Re: [PATCH] perf report: Add support to display group output for non group events
On Fri, Feb 09, 2018 at 03:37:11PM -0300, Arnaldo Carvalho de Melo wrote: > Em Fri, Feb 09, 2018 at 10:27:34AM +0100, Jiri Olsa escreveu: > > On Wed, Feb 07, 2018 at 10:52:35AM -0800, Stephane Eranian wrote: > > > > SNIP > > > > > >> Similar to what I get if I do instead: > > > >> $ perf record -e '{branches,branches,branches,branches}' my_test > > > >> $ perf report --group > > > >> > > > >> But here, I would have to ensure all events fits in a group to allow > > > >> the reporting > > > >> I want. So that would limit me to 4 events. > > > >> > > > >> I think perf report --group should work regardless of how the events > > > >> were grouped. > > > >> Is there already a way to work around this? > > > > > > > > no workaround.. please try attached patch, it seems > > > > to work for what you described > > > > > > > Works for me. That's great! > > > Thanks. > > > > > > Tested-By: Stephane Eranian > > > > thanks, full patch attached > > > > jirka > > Humm, its a nice hack, but it would be even better if it didn't showed > it as if it was really a group: > > Samples: 20 of event 'anon group { cycles, instructions }', Event count > (approx.): 4712980 > > It would be better to instead add another condition to the evlist that > would trigger the view with all the examples... > > I'm applying it anyway, as it is useful, but would be nice to have the > same output except for that header, that should read instead: > > Samples: 20 of non grouped events: cycles, instructions, Event count > (approx.): 4712980 right, I'll try to post something like that thanks, jirka
Re: [PATCH] perf report: Add support to display group output for non group events
Em Fri, Feb 09, 2018 at 03:37:11PM -0300, Arnaldo Carvalho de Melo escreveu: > Em Fri, Feb 09, 2018 at 10:27:34AM +0100, Jiri Olsa escreveu: > > On Wed, Feb 07, 2018 at 10:52:35AM -0800, Stephane Eranian wrote: > > > > SNIP > > > > > >> Similar to what I get if I do instead: > > > >> $ perf record -e '{branches,branches,branches,branches}' my_test > > > >> $ perf report --group > > > >> > > > >> But here, I would have to ensure all events fits in a group to allow > > > >> the reporting > > > >> I want. So that would limit me to 4 events. > > > >> > > > >> I think perf report --group should work regardless of how the events > > > >> were grouped. > > > >> Is there already a way to work around this? > > > > > > > > no workaround.. please try attached patch, it seems > > > > to work for what you described > > > > > > > Works for me. That's great! > > > Thanks. > > > > > > Tested-By: Stephane Eranian> > > > thanks, full patch attached > > > > jirka > > Humm, its a nice hack, but it would be even better if it didn't showed > it as if it was really a group: > > Samples: 20 of event 'anon group { cycles, instructions }', Event count > (approx.): 4712980 > > It would be better to instead add another condition to the evlist that > would trigger the view with all the examples... > > I'm applying it anyway, as it is useful, but would be nice to have the > same output except for that header, that should read instead: > > Samples: 20 of non grouped events: cycles, instructions, Event count > (approx.): 4712980 Till then, that documentation hunk should help understanding this issue. :-) - Arnaldo
Re: [PATCH] perf report: Add support to display group output for non group events
Em Fri, Feb 09, 2018 at 03:37:11PM -0300, Arnaldo Carvalho de Melo escreveu: > Em Fri, Feb 09, 2018 at 10:27:34AM +0100, Jiri Olsa escreveu: > > On Wed, Feb 07, 2018 at 10:52:35AM -0800, Stephane Eranian wrote: > > > > SNIP > > > > > >> Similar to what I get if I do instead: > > > >> $ perf record -e '{branches,branches,branches,branches}' my_test > > > >> $ perf report --group > > > >> > > > >> But here, I would have to ensure all events fits in a group to allow > > > >> the reporting > > > >> I want. So that would limit me to 4 events. > > > >> > > > >> I think perf report --group should work regardless of how the events > > > >> were grouped. > > > >> Is there already a way to work around this? > > > > > > > > no workaround.. please try attached patch, it seems > > > > to work for what you described > > > > > > > Works for me. That's great! > > > Thanks. > > > > > > Tested-By: Stephane Eranian > > > > thanks, full patch attached > > > > jirka > > Humm, its a nice hack, but it would be even better if it didn't showed > it as if it was really a group: > > Samples: 20 of event 'anon group { cycles, instructions }', Event count > (approx.): 4712980 > > It would be better to instead add another condition to the evlist that > would trigger the view with all the examples... > > I'm applying it anyway, as it is useful, but would be nice to have the > same output except for that header, that should read instead: > > Samples: 20 of non grouped events: cycles, instructions, Event count > (approx.): 4712980 Till then, that documentation hunk should help understanding this issue. :-) - Arnaldo
Re: [PATCH] perf report: Add support to display group output for non group events
Em Fri, Feb 09, 2018 at 10:27:34AM +0100, Jiri Olsa escreveu: > On Wed, Feb 07, 2018 at 10:52:35AM -0800, Stephane Eranian wrote: > > SNIP > > > >> Similar to what I get if I do instead: > > >> $ perf record -e '{branches,branches,branches,branches}' my_test > > >> $ perf report --group > > >> > > >> But here, I would have to ensure all events fits in a group to allow > > >> the reporting > > >> I want. So that would limit me to 4 events. > > >> > > >> I think perf report --group should work regardless of how the events > > >> were grouped. > > >> Is there already a way to work around this? > > > > > > no workaround.. please try attached patch, it seems > > > to work for what you described > > > > > Works for me. That's great! > > Thanks. > > > > Tested-By: Stephane Eranian> > thanks, full patch attached > > jirka Humm, its a nice hack, but it would be even better if it didn't showed it as if it was really a group: Samples: 20 of event 'anon group { cycles, instructions }', Event count (approx.): 4712980 It would be better to instead add another condition to the evlist that would trigger the view with all the examples... I'm applying it anyway, as it is useful, but would be nice to have the same output except for that header, that should read instead: Samples: 20 of non grouped events: cycles, instructions, Event count (approx.): 4712980 - Arnaldo > > --- > Add support to display group output for if non grouped events > are detected and user forces --group option. Now for non-group > events recorded like: > > $ perf record -e 'cycles,instructions' ls > > you can still get group output by using --group option > in report: > > $ perf report --group --stdio > ... > # Overhead Command Shared Object Symbol > # ... .. > # > 17.67% 0.00% ls libc-2.25.so [.] _IO_do_write@@GLIB > 15.59% 25.94% ls ls[.] calculate_columns > 15.41% 31.35% ls libc-2.25.so [.] __strcoll_l > ... > > Requested-and-Tested-by: Stephane Eranian > Link: http://lkml.kernel.org/n/tip-m1ffikw8c3a55b3uaxrmk...@git.kernel.org > Signed-off-by: Jiri Olsa > --- > tools/perf/Documentation/perf-report.txt | 3 ++- > tools/perf/builtin-report.c | 6 +- > 2 files changed, 7 insertions(+), 2 deletions(-) > > diff --git a/tools/perf/Documentation/perf-report.txt > b/tools/perf/Documentation/perf-report.txt > index 907e505b6309..a76b871f78a6 100644 > --- a/tools/perf/Documentation/perf-report.txt > +++ b/tools/perf/Documentation/perf-report.txt > @@ -354,7 +354,8 @@ OPTIONS > Path to objdump binary. > > --group:: > - Show event group information together. > + Show event group information together. It forces group output also > + if there are no groups defined in data file. > > --demangle:: > Demangle symbol names to human readable form. It's enabled by default, > diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c > index 8ef71669e7a0..1eedb1815c4c 100644 > --- a/tools/perf/builtin-report.c > +++ b/tools/perf/builtin-report.c > @@ -938,6 +938,7 @@ int cmd_report(int argc, const char **argv) > "perf report []", > NULL > }; > + bool group_set = false; > struct report report = { > .tool = { > .sample = process_sample_event, > @@ -1057,7 +1058,7 @@ int cmd_report(int argc, const char **argv) > "Specify disassembler style (e.g. -M intel for intel > syntax)"), > OPT_BOOLEAN(0, "show-total-period", _conf.show_total_period, > "Show a column with the sum of periods"), > - OPT_BOOLEAN(0, "group", _conf.event_group, > + OPT_BOOLEAN_SET(0, "group", _conf.event_group, _set, > "Show event group information together"), > OPT_CALLBACK_NOOPT('b', "branch-stack", _mode, "", > "use branch records for per branch histogram filling", > @@ -1174,6 +1175,9 @@ int cmd_report(int argc, const char **argv) > has_br_stack = perf_header__has_feat(>header, >HEADER_BRANCH_STACK); > > + if (group_set && !session->evlist->nr_groups) > + perf_evlist__set_leader(session->evlist); > + > if (itrace_synth_opts.last_branch) > has_br_stack = true; > > -- > 2.13.6
Re: [PATCH] perf report: Add support to display group output for non group events
Em Fri, Feb 09, 2018 at 10:27:34AM +0100, Jiri Olsa escreveu: > On Wed, Feb 07, 2018 at 10:52:35AM -0800, Stephane Eranian wrote: > > SNIP > > > >> Similar to what I get if I do instead: > > >> $ perf record -e '{branches,branches,branches,branches}' my_test > > >> $ perf report --group > > >> > > >> But here, I would have to ensure all events fits in a group to allow > > >> the reporting > > >> I want. So that would limit me to 4 events. > > >> > > >> I think perf report --group should work regardless of how the events > > >> were grouped. > > >> Is there already a way to work around this? > > > > > > no workaround.. please try attached patch, it seems > > > to work for what you described > > > > > Works for me. That's great! > > Thanks. > > > > Tested-By: Stephane Eranian > > thanks, full patch attached > > jirka Humm, its a nice hack, but it would be even better if it didn't showed it as if it was really a group: Samples: 20 of event 'anon group { cycles, instructions }', Event count (approx.): 4712980 It would be better to instead add another condition to the evlist that would trigger the view with all the examples... I'm applying it anyway, as it is useful, but would be nice to have the same output except for that header, that should read instead: Samples: 20 of non grouped events: cycles, instructions, Event count (approx.): 4712980 - Arnaldo > > --- > Add support to display group output for if non grouped events > are detected and user forces --group option. Now for non-group > events recorded like: > > $ perf record -e 'cycles,instructions' ls > > you can still get group output by using --group option > in report: > > $ perf report --group --stdio > ... > # Overhead Command Shared Object Symbol > # ... .. > # > 17.67% 0.00% ls libc-2.25.so [.] _IO_do_write@@GLIB > 15.59% 25.94% ls ls[.] calculate_columns > 15.41% 31.35% ls libc-2.25.so [.] __strcoll_l > ... > > Requested-and-Tested-by: Stephane Eranian > Link: http://lkml.kernel.org/n/tip-m1ffikw8c3a55b3uaxrmk...@git.kernel.org > Signed-off-by: Jiri Olsa > --- > tools/perf/Documentation/perf-report.txt | 3 ++- > tools/perf/builtin-report.c | 6 +- > 2 files changed, 7 insertions(+), 2 deletions(-) > > diff --git a/tools/perf/Documentation/perf-report.txt > b/tools/perf/Documentation/perf-report.txt > index 907e505b6309..a76b871f78a6 100644 > --- a/tools/perf/Documentation/perf-report.txt > +++ b/tools/perf/Documentation/perf-report.txt > @@ -354,7 +354,8 @@ OPTIONS > Path to objdump binary. > > --group:: > - Show event group information together. > + Show event group information together. It forces group output also > + if there are no groups defined in data file. > > --demangle:: > Demangle symbol names to human readable form. It's enabled by default, > diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c > index 8ef71669e7a0..1eedb1815c4c 100644 > --- a/tools/perf/builtin-report.c > +++ b/tools/perf/builtin-report.c > @@ -938,6 +938,7 @@ int cmd_report(int argc, const char **argv) > "perf report []", > NULL > }; > + bool group_set = false; > struct report report = { > .tool = { > .sample = process_sample_event, > @@ -1057,7 +1058,7 @@ int cmd_report(int argc, const char **argv) > "Specify disassembler style (e.g. -M intel for intel > syntax)"), > OPT_BOOLEAN(0, "show-total-period", _conf.show_total_period, > "Show a column with the sum of periods"), > - OPT_BOOLEAN(0, "group", _conf.event_group, > + OPT_BOOLEAN_SET(0, "group", _conf.event_group, _set, > "Show event group information together"), > OPT_CALLBACK_NOOPT('b', "branch-stack", _mode, "", > "use branch records for per branch histogram filling", > @@ -1174,6 +1175,9 @@ int cmd_report(int argc, const char **argv) > has_br_stack = perf_header__has_feat(>header, >HEADER_BRANCH_STACK); > > + if (group_set && !session->evlist->nr_groups) > + perf_evlist__set_leader(session->evlist); > + > if (itrace_synth_opts.last_branch) > has_br_stack = true; > > -- > 2.13.6
[PATCH] perf report: Add support to display group output for non group events
On Wed, Feb 07, 2018 at 10:52:35AM -0800, Stephane Eranian wrote: SNIP > >> Similar to what I get if I do instead: > >> $ perf record -e '{branches,branches,branches,branches}' my_test > >> $ perf report --group > >> > >> But here, I would have to ensure all events fits in a group to allow > >> the reporting > >> I want. So that would limit me to 4 events. > >> > >> I think perf report --group should work regardless of how the events > >> were grouped. > >> Is there already a way to work around this? > > > > no workaround.. please try attached patch, it seems > > to work for what you described > > > Works for me. That's great! > Thanks. > > Tested-By: Stephane Eranianthanks, full patch attached jirka --- Add support to display group output for if non grouped events are detected and user forces --group option. Now for non-group events recorded like: $ perf record -e 'cycles,instructions' ls you can still get group output by using --group option in report: $ perf report --group --stdio ... # Overhead Command Shared Object Symbol # ... .. # 17.67% 0.00% ls libc-2.25.so [.] _IO_do_write@@GLIB 15.59% 25.94% ls ls[.] calculate_columns 15.41% 31.35% ls libc-2.25.so [.] __strcoll_l ... Requested-and-Tested-by: Stephane Eranian Link: http://lkml.kernel.org/n/tip-m1ffikw8c3a55b3uaxrmk...@git.kernel.org Signed-off-by: Jiri Olsa --- tools/perf/Documentation/perf-report.txt | 3 ++- tools/perf/builtin-report.c | 6 +- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 907e505b6309..a76b871f78a6 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -354,7 +354,8 @@ OPTIONS Path to objdump binary. --group:: - Show event group information together. + Show event group information together. It forces group output also + if there are no groups defined in data file. --demangle:: Demangle symbol names to human readable form. It's enabled by default, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 8ef71669e7a0..1eedb1815c4c 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -938,6 +938,7 @@ int cmd_report(int argc, const char **argv) "perf report []", NULL }; + bool group_set = false; struct report report = { .tool = { .sample = process_sample_event, @@ -1057,7 +1058,7 @@ int cmd_report(int argc, const char **argv) "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_BOOLEAN(0, "show-total-period", _conf.show_total_period, "Show a column with the sum of periods"), - OPT_BOOLEAN(0, "group", _conf.event_group, + OPT_BOOLEAN_SET(0, "group", _conf.event_group, _set, "Show event group information together"), OPT_CALLBACK_NOOPT('b', "branch-stack", _mode, "", "use branch records for per branch histogram filling", @@ -1174,6 +1175,9 @@ int cmd_report(int argc, const char **argv) has_br_stack = perf_header__has_feat(>header, HEADER_BRANCH_STACK); + if (group_set && !session->evlist->nr_groups) + perf_evlist__set_leader(session->evlist); + if (itrace_synth_opts.last_branch) has_br_stack = true; -- 2.13.6
[PATCH] perf report: Add support to display group output for non group events
On Wed, Feb 07, 2018 at 10:52:35AM -0800, Stephane Eranian wrote: SNIP > >> Similar to what I get if I do instead: > >> $ perf record -e '{branches,branches,branches,branches}' my_test > >> $ perf report --group > >> > >> But here, I would have to ensure all events fits in a group to allow > >> the reporting > >> I want. So that would limit me to 4 events. > >> > >> I think perf report --group should work regardless of how the events > >> were grouped. > >> Is there already a way to work around this? > > > > no workaround.. please try attached patch, it seems > > to work for what you described > > > Works for me. That's great! > Thanks. > > Tested-By: Stephane Eranian thanks, full patch attached jirka --- Add support to display group output for if non grouped events are detected and user forces --group option. Now for non-group events recorded like: $ perf record -e 'cycles,instructions' ls you can still get group output by using --group option in report: $ perf report --group --stdio ... # Overhead Command Shared Object Symbol # ... .. # 17.67% 0.00% ls libc-2.25.so [.] _IO_do_write@@GLIB 15.59% 25.94% ls ls[.] calculate_columns 15.41% 31.35% ls libc-2.25.so [.] __strcoll_l ... Requested-and-Tested-by: Stephane Eranian Link: http://lkml.kernel.org/n/tip-m1ffikw8c3a55b3uaxrmk...@git.kernel.org Signed-off-by: Jiri Olsa --- tools/perf/Documentation/perf-report.txt | 3 ++- tools/perf/builtin-report.c | 6 +- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 907e505b6309..a76b871f78a6 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -354,7 +354,8 @@ OPTIONS Path to objdump binary. --group:: - Show event group information together. + Show event group information together. It forces group output also + if there are no groups defined in data file. --demangle:: Demangle symbol names to human readable form. It's enabled by default, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 8ef71669e7a0..1eedb1815c4c 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -938,6 +938,7 @@ int cmd_report(int argc, const char **argv) "perf report []", NULL }; + bool group_set = false; struct report report = { .tool = { .sample = process_sample_event, @@ -1057,7 +1058,7 @@ int cmd_report(int argc, const char **argv) "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_BOOLEAN(0, "show-total-period", _conf.show_total_period, "Show a column with the sum of periods"), - OPT_BOOLEAN(0, "group", _conf.event_group, + OPT_BOOLEAN_SET(0, "group", _conf.event_group, _set, "Show event group information together"), OPT_CALLBACK_NOOPT('b', "branch-stack", _mode, "", "use branch records for per branch histogram filling", @@ -1174,6 +1175,9 @@ int cmd_report(int argc, const char **argv) has_br_stack = perf_header__has_feat(>header, HEADER_BRANCH_STACK); + if (group_set && !session->evlist->nr_groups) + perf_evlist__set_leader(session->evlist); + if (itrace_synth_opts.last_branch) has_br_stack = true; -- 2.13.6