perf tools: Add -H short option for --hierarchy
Namhyung Kim
maintainerPATCH RESEND 1/1 perf tools: Add -H short option for --hierarchy
I found the hierarchy mode useful, but it's easy to make a typo when using it. Let's add a short option for that.
Also update the documentation. :)
--- tools/perf/Documentation/perf-report.txt | 29 ++++++++++++++++++++- tools/perf/Documentation/perf-top.txt | 32 +++++++++++++++++++++++- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-top.c | 2 +- 4 files changed, 61 insertions(+), 4 deletions(-)
tools/perf/Documentation/perf-report.txt +28 -1
@@ -531,8 +531,35 @@ include::itrace.txt[] --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +-H:: --hierarchy:: - Enable hierarchical output. + Enable hierarchical output. In the hierarchy mode, each sort key groups + samples based on the criteria and then sub-divide it using the lower + level sort key. + + For example: + In normal output: + + perf report -s dso,sym + # Overhead Shared Object Symbol + 50.00% [kernel.kallsyms] [k] kfunc1 + 20.00% perf [.] foo + 15.00% [kernel.kallsyms] [k] kfunc2 + 10.00% perf [.] bar + 5.00% libc.so [.] libcall + + In hierarchy output: + + perf report -s dso,sym --hierarchy + # Overhead Shared Object / Symbol + 65.00% [kernel.kallsyms] + 50.00% [k] kfunc1 + 15.00% [k] kfunc2 + 30.00% perf + 20.00% [.] foo + 10.00% [.] bar + 5.00% libc.so + 5.00% [.] libcall --inline:: If a callgraph address belongs to an inlined function, the inline stack
tools/perf/Documentation/perf-top.txt +31 -1
@@ -261,8 +261,38 @@ Default is to monitor all CPUS. --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +-H:: --hierarchy:: - Enable hierarchy output. + Enable hierarchical output. In the hierarchy mode, each sort key groups + samples based on the criteria and then sub-divide it using the lower + level sort key. + + For example, in normal output: + + perf report -s dso,sym + # + # Overhead Shared Object Symbol + # ........ ................. ........... + 50.00% [kernel.kallsyms] [k] kfunc1 + 20.00% perf [.] foo + 15.00% [kernel.kallsyms] [k] kfunc2 + 10.00% perf [.] bar + 5.00% libc.so [.] libcall + + In hierarchy output: + + perf report -s dso,sym --hierarchy + # + # Overhead Shared Object / Symbol + # .......... ...................... + 65.00% [kernel.kallsyms] + 50.00% [k] kfunc1 + 15.00% [k] kfunc2 + 30.00% perf + 20.00% [.] foo + 10.00% [.] bar + 5.00% libc.so + 5.00% [.] libcall --overwrite:: Enable this to use just the most recent records, which helps in high core count
tools/perf/builtin-report.c +1 -1
@@ -1410,7 +1410,7 @@ int cmd_report(int argc, const char **argv) "only show processor socket that match with this filter"),OPT_BOOLEAN (0 ,"raw-trace" , &symbol_conf.raw_trace,"Show raw trace event output (do not use print fmt or plugins)" ), -OPT_BOOLEAN (0 ,"hierarchy" , &symbol_conf.report_hierarchy, +OPT_BOOLEAN ('H' ,"hierarchy" , &symbol_conf.report_hierarchy,"Show entries in a hierarchy" ), OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode", "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
tools/perf/builtin-top.c +1 -1
@@ -1573,7 +1573,7 @@ int cmd_top(int argc, const char **argv) "add last branch records to call history"),OPT_BOOLEAN (0 ,"raw-trace" , &symbol_conf.raw_trace,"Show raw trace event output (do not use print fmt or plugins)" ), -OPT_BOOLEAN (0 ,"hierarchy" , &symbol_conf.report_hierarchy, +OPT_BOOLEAN ('H' ,"hierarchy" , &symbol_conf.report_hierarchy,"Show entries in a hierarchy" ),OPT_BOOLEAN (0 ,"overwrite" , &top.record_opts.overwrite, "Use a backward ring buffer, default: no"),
Signature · 1 line
2.43.0.429.g432eaa2c6b-goog
Em Wed, Jan 24, 2024 at 09:51:24PM -0800, Namhyung Kim escreveu:
Quoted 2 lines
I found the hierarchy mode useful, but it's easy to make a typo when using it. Let's add a short option for that.
Fair enough, but:
[root@quaco ~]# perf report --hi + head -15
Error: Ambiguous option: hi (could be --hide-unresolved or --hierarchy)
Usage: perf report [<options>]
-U, --hide-unresolved
Only display entries resolved to a symbol
--hierarchy Show entries in a hierarchy
[root@quaco ~]# perf report --hie | head -15
# To display the perf.data header info, please use --header/--header-only options. #
#
# Total Lost Samples: 0
#
# Samples: 56 of event 'cycles:P'
# Event count (approx.): 13456952
#
# Overhead Command / Shared Object / Symbol
# .............. ........................................
#
72.56% swapper
72.56% [kernel.kallsyms]
72.56% [k] intel_idle_ibrs
18.53% perf
[root@quaco ~]#Quoted 1 line
Also update the documentation. :)
Thanks, as a suggestion maybe we should have a:
$ perf config ui.hierarchy
as we have:
[root@quaco ~]# perf config ui.show-headers=true
[root@quaco ~]# perf config ui.show-headers
ui.show-headers=true
[root@quaco ~]#
- Arnaldo
Quoted 122 lines
Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/Documentation/perf-report.txt | 29 ++++++++++++++++++++- tools/perf/Documentation/perf-top.txt | 32 +++++++++++++++++++++++- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-top.c | 2 +- 4 files changed, 61 insertions(+), 4 deletions(-)tools/perf/Documentation/perf-report.txt +28
-1@@ -531,8 +531,35 @@ include::itrace.txt[] --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +-H:: --hierarchy:: - Enable hierarchical output. + Enable hierarchical output. In the hierarchy mode, each sort key groups + samples based on the criteria and then sub-divide it using the lower + level sort key. + + For example: + In normal output: + + perf report -s dso,sym + # Overhead Shared Object Symbol + 50.00% [kernel.kallsyms] [k] kfunc1 + 20.00% perf [.] foo + 15.00% [kernel.kallsyms] [k] kfunc2 + 10.00% perf [.] bar + 5.00% libc.so [.] libcall + + In hierarchy output: + + perf report -s dso,sym --hierarchy + # Overhead Shared Object / Symbol + 65.00% [kernel.kallsyms] + 50.00% [k] kfunc1 + 15.00% [k] kfunc2 + 30.00% perf + 20.00% [.] foo + 10.00% [.] bar + 5.00% libc.so + 5.00% [.] libcall --inline:: If a callgraph address belongs to an inlined function, the inline stacktools/perf/Documentation/perf-top.txt +31
-1@@ -261,8 +261,38 @@ Default is to monitor all CPUS. --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +-H:: --hierarchy:: - Enable hierarchy output. + Enable hierarchical output. In the hierarchy mode, each sort key groups + samples based on the criteria and then sub-divide it using the lower + level sort key. + + For example, in normal output: + + perf report -s dso,sym + # + # Overhead Shared Object Symbol + # ........ ................. ........... + 50.00% [kernel.kallsyms] [k] kfunc1 + 20.00% perf [.] foo + 15.00% [kernel.kallsyms] [k] kfunc2 + 10.00% perf [.] bar + 5.00% libc.so [.] libcall + + In hierarchy output: + + perf report -s dso,sym --hierarchy + # + # Overhead Shared Object / Symbol + # .......... ...................... + 65.00% [kernel.kallsyms] + 50.00% [k] kfunc1 + 15.00% [k] kfunc2 + 30.00% perf + 20.00% [.] foo + 10.00% [.] bar + 5.00% libc.so + 5.00% [.] libcall --overwrite:: Enable this to use just the most recent records, which helps in high core counttools/perf/builtin-report.c +1
-1@@ -1410,7 +1410,7 @@ int cmd_report(int argc, const char **argv) "only show processor socket that match with this filter"),OPT_BOOLEAN (0 ,"raw-trace" , &symbol_conf.raw_trace,"Show raw trace event output (do not use print fmt or plugins)" ), -OPT_BOOLEAN (0 ,"hierarchy" , &symbol_conf.report_hierarchy, +OPT_BOOLEAN ('H' ,"hierarchy" , &symbol_conf.report_hierarchy,"Show entries in a hierarchy" ), OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode", "'always' (default), 'never' or 'auto' only applicable to --stdio mode",tools/perf/builtin-top.c +1
-1@@ -1573,7 +1573,7 @@ int cmd_top(int argc, const char **argv) "add last branch records to call history"),OPT_BOOLEAN (0 ,"raw-trace" , &symbol_conf.raw_trace,"Show raw trace event output (do not use print fmt or plugins)" ), -OPT_BOOLEAN (0 ,"hierarchy" , &symbol_conf.report_hierarchy, +OPT_BOOLEAN ('H' ,"hierarchy" , &symbol_conf.report_hierarchy,"Show entries in a hierarchy" ),OPT_BOOLEAN (0 ,"overwrite" , &top.record_opts.overwrite, "Use a backward ring buffer, default: no"),Signature · 1 line
2.43.0.429.g432eaa2c6b-goog
Signature · 1 line
- Arnaldo
Namhyung Kim
maintainerHi Arnaldo,
Quoted 37 lines · Arnaldo Carvalho de Melo
Em Wed, Jan 24, 2024 at 09:51:24PM -0800, Namhyung Kim escreveu:
Quoted 2 lines
I found the hierarchy mode useful, but it's easy to make a typo when using it. Let's add a short option for that.
Fair enough, but:
[root@quaco ~]# perf report --hi + head -15
Error: Ambiguous option: hi (could be --hide-unresolved or --hierarchy)Usage: perf report [<options>]
-U, --hide-unresolved
Only display entries resolved to a symbol
--hierarchy Show entries in a hierarchy
[root@quaco ~]# perf report --hie | head -15
# To display the perf.data header info, please use --header/--header-only options. #
#
# Total Lost Samples: 0
#
# Samples: 56 of event 'cycles:P'
# Event count (approx.): 13456952
#
# Overhead Command / Shared Object / Symbol# .............. ........................................ # 72.56% swapper 72.56% [kernel.kallsyms] 72.56% [k] intel_idle_ibrs 18.53% perf [root@quaco ~]#Quoted 1 line
Also update the documentation. :)
Thanks, as a suggestion maybe we should have a:
Quoted 8 lines
$ perf config ui.hierarchyas we have:
[root@quaco ~]# perf config ui.show-headers=true
[root@quaco ~]# perf config ui.show-headers
ui.show-headers=true
[root@quaco ~]#
Yep, I'll think about the config option later. Right now it cannot work with children mode which can be enabled by a config as well.
Quoted 3 lines
Thanks,
Namhyung
Quoted 127 lines
Quoted 121 lines
Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/Documentation/perf-report.txt | 29 ++++++++++++++++++++- tools/perf/Documentation/perf-top.txt | 32 +++++++++++++++++++++++- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-top.c | 2 +- 4 files changed, 61 insertions(+), 4 deletions(-)tools/perf/Documentation/perf-report.txt +28
-1@@ -531,8 +531,35 @@ include::itrace.txt[] --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +-H:: --hierarchy:: - Enable hierarchical output. + Enable hierarchical output. In the hierarchy mode, each sort key groups + samples based on the criteria and then sub-divide it using the lower + level sort key. + + For example: + In normal output: + + perf report -s dso,sym + # Overhead Shared Object Symbol + 50.00% [kernel.kallsyms] [k] kfunc1 + 20.00% perf [.] foo + 15.00% [kernel.kallsyms] [k] kfunc2 + 10.00% perf [.] bar + 5.00% libc.so [.] libcall + + In hierarchy output: + + perf report -s dso,sym --hierarchy + # Overhead Shared Object / Symbol + 65.00% [kernel.kallsyms] + 50.00% [k] kfunc1 + 15.00% [k] kfunc2 + 30.00% perf + 20.00% [.] foo + 10.00% [.] bar + 5.00% libc.so + 5.00% [.] libcall --inline:: If a callgraph address belongs to an inlined function, the inline stacktools/perf/Documentation/perf-top.txt +31
-1@@ -261,8 +261,38 @@ Default is to monitor all CPUS. --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +-H:: --hierarchy:: - Enable hierarchy output. + Enable hierarchical output. In the hierarchy mode, each sort key groups + samples based on the criteria and then sub-divide it using the lower + level sort key. + + For example, in normal output: + + perf report -s dso,sym + # + # Overhead Shared Object Symbol + # ........ ................. ........... + 50.00% [kernel.kallsyms] [k] kfunc1 + 20.00% perf [.] foo + 15.00% [kernel.kallsyms] [k] kfunc2 + 10.00% perf [.] bar + 5.00% libc.so [.] libcall + + In hierarchy output: + + perf report -s dso,sym --hierarchy + # + # Overhead Shared Object / Symbol + # .......... ...................... + 65.00% [kernel.kallsyms] + 50.00% [k] kfunc1 + 15.00% [k] kfunc2 + 30.00% perf + 20.00% [.] foo + 10.00% [.] bar + 5.00% libc.so + 5.00% [.] libcall --overwrite:: Enable this to use just the most recent records, which helps in high core counttools/perf/builtin-report.c +1
-1@@ -1410,7 +1410,7 @@ int cmd_report(int argc, const char **argv) "only show processor socket that match with this filter"),OPT_BOOLEAN (0 ,"raw-trace" , &symbol_conf.raw_trace,"Show raw trace event output (do not use print fmt or plugins)" ), -OPT_BOOLEAN (0 ,"hierarchy" , &symbol_conf.report_hierarchy, +OPT_BOOLEAN ('H' ,"hierarchy" , &symbol_conf.report_hierarchy,"Show entries in a hierarchy" ), OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode", "'always' (default), 'never' or 'auto' only applicable to --stdio mode",tools/perf/builtin-top.c +1
-2@@ -1573,7 +1573,7 @@ int cmd_top(int argc, const char **argv) "add last branch records to call history"),OPT_BOOLEAN (0 ,"raw-trace" , &symbol_conf.raw_trace,"Show raw trace event output (do not use print fmt or plugins)" ), -OPT_BOOLEAN (0 ,"hierarchy" , &symbol_conf.report_hierarchy, +OPT_BOOLEAN ('H' ,"hierarchy" , &symbol_conf.report_hierarchy,"Show entries in a hierarchy" ),OPT_BOOLEAN (0 ,"overwrite" , &top.record_opts.overwrite, "Use a backward ring buffer, default: no"), --Quoted 2 lines
2.43.0.429.g432eaa2c6b-goog
--
- Arnaldo
Quoted 6 lines · Namhyung Kim
I found the hierarchy mode useful, but it's easy to make a typo when using it. Let's add a short option for that.
Also update the documentation. :)
Applied to perf-tools-next, thanks!
Best regards,
Signature · 1 line
Namhyung Kim <[email protected]>