aha/tools/perf/util
Frederic Weisbecker 805d127d62 perf report: Add "Fractal" mode output - support callchains with relative overhead rate
The current callchain displays the overhead rates as absolute:
relative to the total overhead.

This patch provides relative overhead percentage, in which each
branch of the callchain tree is a independant instrumentated object.

This provides a 'fractal' view of the call-chain profile: each
sub-graph looks like a profile in itself - relative to its parent.

You can produce such output by using the "fractal" mode
that you can abbreviate via f, fr, fra, frac, etc...

./perf report -s sym -c fractal

Example:

     8.46%  [k] copy_user_generic_string
                |
                |--52.01%-- generic_file_aio_read
                |          do_sync_read
                |          vfs_read
                |          |
                |          |--97.20%-- sys_pread64
                |          |          system_call_fastpath
                |          |          pread64
                |          |
                |           --2.81%-- sys_read
                |                     system_call_fastpath
                |                     __read
                |
                |--39.85%-- generic_file_buffered_write
                |          __generic_file_aio_write_nolock
                |          generic_file_aio_write
                |          do_sync_write
                |          reiserfs_file_write
                |          vfs_write
                |          |
                |          |--97.05%-- sys_pwrite64
                |          |          system_call_fastpath
                |          |          __pwrite64
                |          |
                |           --2.95%-- sys_write
                |                     system_call_fastpath
                |                     __write_nocancel
[...]

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Anton Blanchard <anton@samba.org>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 10:30:23 +02:00
..
include perf_counter tools: Share list.h with the kernel 2009-07-01 22:37:23 +02:00
abspath.c
alias.c perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
cache.h perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
callchain.c perf report: Add "Fractal" mode output - support callchains with relative overhead rate 2009-07-05 10:30:23 +02:00
callchain.h perf report: Add "Fractal" mode output - support callchains with relative overhead rate 2009-07-05 10:30:23 +02:00
color.c perf_counter tools: Provide helper to print percents color 2009-07-02 21:38:37 +02:00
color.h perf_counter tools: Provide helper to print percents color 2009-07-02 21:38:37 +02:00
config.c perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
ctype.c perf_counter tools: Add and use isprint() 2009-06-18 09:46:00 +02:00
environment.c
exec_cmd.c perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
exec_cmd.h
generate-cmdlist.sh
header.c perf_counter tools: Rework the file format 2009-06-25 21:39:04 +02:00
header.h perf_counter tools: Rework the file format 2009-06-25 21:39:04 +02:00
help.c perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
help.h perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
levenshtein.c
levenshtein.h
module.c perf_counter tools: Add infrastructure to support loading of kernel module symbols 2009-07-02 08:42:20 +02:00
module.h perf_counter tools: Add infrastructure to support loading of kernel module symbols 2009-07-02 08:42:20 +02:00
pager.c perf_counter tools: Remove dead code 2009-06-27 06:06:39 +02:00
parse-events.c perf list: Add cache events 2009-07-01 15:25:03 +02:00
parse-events.h
parse-options.c perf_counter tools: Add new OPT_CALLBACK_DEFAULT option 2009-07-02 20:47:14 +02:00
parse-options.h perf_counter tools: Add new OPT_CALLBACK_DEFAULT option 2009-07-02 20:47:14 +02:00
path.c
PERF-VERSION-GEN
quote.c perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
quote.h perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
run-command.c perf_counter tools: Remove dead code 2009-06-27 06:06:39 +02:00
run-command.h perf_counter tools: Remove dead code 2009-06-27 06:06:39 +02:00
sigchain.c
sigchain.h
strbuf.c perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
strbuf.h perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00
string.c perf_counter tools: Define and use our own u64, s64 etc. definitions 2009-06-19 18:25:47 +02:00
string.h perf_counter tools: Rework the file format 2009-06-25 21:39:04 +02:00
strlist.c perf report: Add --dsos parameter 2009-07-01 00:07:09 +02:00
strlist.h perf_counter tools: Share rbtree.with the kernel 2009-07-01 22:37:22 +02:00
symbol.c perf_counter tools: Adjust symbols in ET_EXEC files too 2009-07-03 08:24:13 +02:00
symbol.h perf_counter tools: Adjust symbols in ET_EXEC files too 2009-07-03 08:24:13 +02:00
types.h perf_counter tools: Rework the file format 2009-06-25 21:39:04 +02:00
usage.c perf top: Fall back to cpu-clock-tick hrtimer sampling if no cycle counter available 2009-06-07 17:31:52 +02:00
util.h perf_counter tools: Remove dead code 2009-06-27 06:06:39 +02:00
wrapper.c perf_counter tools: Add more warnings and fix/annotate them 2009-07-01 12:49:48 +02:00