2009-09-24 18:02:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-12-15 09:39:39 -06:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
2013-10-31 10:17:39 +09:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-05-17 16:22:41 -03:00
|
|
|
|
2014-03-04 10:46:34 +09:00
|
|
|
|
2010-05-17 16:22:41 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-12-06 21:48:05 -08:00
|
|
|
|
|
|
|
|
|
2013-04-01 20:35:20 +09:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-03-08 23:47:48 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf tools: Bind callchains to the first sort dimension column
Currently, the callchains are displayed using a constant left
margin. So depending on the current sort dimension
configuration, callchains may appear to be well attached to the
first sort dimension column field which is mostly the case,
except when the first dimension of sorting is done by comm,
because these are right aligned.
This patch binds the callchain to the first letter in the first
column, whatever type of column it is (dso, comm, symbol).
Before:
0.80% perf [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
| | __fsnotify_parent
After:
0.80% perf [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
| | __fsnotify_parent
Also, for clarity, we don't put anymore the callchain as is but:
- If we have a top level ancestor in the callchain, start it
with a first ascii hook.
Before:
0.80% perf [kernel] [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
[..] [..]
After:
0.80% perf [kernel] [k] __lock_acquire
|
--- __lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
[..] [..]
- Otherwise, if we have several top level ancestors, then
display these like we did before:
1.69% Xorg
|
|--21.21%-- vread_hpet
| 0x7fffd85b46fc
| 0x7fffd85b494d
| 0x7f4fafb4e54d
|
|--15.15%-- exaOffscreenAlloc
|
|--9.09%-- I830WaitLpRing
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Anton Blanchard <anton@samba.org>
LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-22 23:23:23 +02:00
|
|
|
|
perf tools: Remove (null) value of "Sort order" for perf mem report
When '--sort' is not set, 'perf mem report" will print a null pointer as
the output value of sort order, so fix it.
Example:
Before this patch:
$ perf mem report
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 18 of event 'cpu/mem-loads/pp'
# Total weight : 188
# Sort order : (null)
#
...
After this patch:
$ perf mem report
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 18 of event 'cpu/mem-loads/pp'
# Total weight : 188
# Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked
#
...
Signed-off-by: Yunlong Song <yunlong.song@huawei.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1427082605-12881-1-git-send-email-yunlong.song@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-23 11:50:05 +08:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
2012-10-04 21:49:41 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-01-24 16:10:29 +01:00
|
|
|
|
2012-10-04 21:49:41 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-05 16:44:42 +02:00
|
|
|
|
|
|
|
|
|
2015-04-19 13:04:10 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-05 16:44:42 +02:00
|
|
|
|
2015-04-19 13:04:10 +09:00
|
|
|
|
|
|
|
|
|
2012-10-05 16:44:42 +02:00
|
|
|
|
2015-04-19 13:04:10 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-05 16:44:42 +02:00
|
|
|
|
|
|
|
|
|
2016-07-05 08:56:04 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-07-26 17:13:40 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
2011-10-05 17:50:23 -03:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
2012-10-25 14:42:45 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-04 21:49:41 +09:00
|
|
|
|
2012-09-11 13:15:07 +09:00
|
|
|
|
2010-03-24 16:40:17 -03:00
|
|
|
|
2010-04-03 22:44:37 -03:00
|
|
|
|
2013-09-13 16:28:57 +09:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
2013-09-20 07:40:43 -07:00
|
|
|
|
2015-09-04 10:45:42 -04:00
|
|
|
|
2010-06-04 11:27:10 -03:00
|
|
|
|
2014-05-27 12:28:05 -04:00
|
|
|
|
2016-02-25 00:13:34 +09:00
|
|
|
|
2010-07-26 17:13:40 -03:00
|
|
|
|
2012-12-01 21:18:20 +01:00
|
|
|
|
|
|
|
|
|
2016-02-25 00:13:34 +09:00
|
|
|
|
2012-12-01 21:18:20 +01:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
2010-04-03 22:44:37 -03:00
|
|
|
|
2015-04-22 16:18:12 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-04-22 16:18:13 +09:00
|
|
|
|
2015-05-05 23:55:46 +09:00
|
|
|
|
|
|
|
|
|
2016-02-26 21:13:19 +09:00
|
|
|
|
2015-04-22 16:18:12 +09:00
|
|
|
|
|
|
|
|
|
2012-05-30 10:33:24 -03:00
|
|
|
|
2015-08-07 15:54:24 -07:00
|
|
|
|
2010-04-03 16:30:44 -03:00
|
|
|
|
2012-02-09 23:21:01 +01:00
|
|
|
|
2012-10-04 21:49:35 +09:00
|
|
|
|
2013-01-24 16:10:35 +01:00
|
|
|
|
2015-12-24 11:16:17 +09:00
|
|
|
|
|
|
|
|
|
2015-12-23 02:07:03 +09:00
|
|
|
|
2016-03-07 16:44:46 -03:00
|
|
|
|
2016-02-25 00:13:34 +09:00
|
|
|
|
2016-07-05 08:56:04 +02:00
|
|
|
|
2016-02-25 00:13:34 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-01-24 16:10:35 +01:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
|
|
|
|
|
2012-10-25 14:42:45 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-12-13 14:09:00 +01:00
|
|
|
|
|
|
|
|
|
2012-10-25 14:42:45 -02:00
|
|
|
|
2012-12-13 14:09:00 +01:00
|
|
|
|
2012-10-25 14:42:45 -02:00
|
|
|
|
|
|
|
|
|
2013-10-31 10:17:39 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-15 09:34:32 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-10-31 10:17:39 +09:00
|
|
|
|
2016-02-15 09:34:33 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-01 20:35:20 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-03-18 11:31:39 +09:00
|
|
|
|
|
|
|
|
|
2015-12-23 02:07:10 +09:00
|
|
|
|
2013-04-01 20:35:20 +09:00
|
|
|
|
|
|
|
|
|
perf tools: Bind callchains to the first sort dimension column
Currently, the callchains are displayed using a constant left
margin. So depending on the current sort dimension
configuration, callchains may appear to be well attached to the
first sort dimension column field which is mostly the case,
except when the first dimension of sorting is done by comm,
because these are right aligned.
This patch binds the callchain to the first letter in the first
column, whatever type of column it is (dso, comm, symbol).
Before:
0.80% perf [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
| | __fsnotify_parent
After:
0.80% perf [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
| | __fsnotify_parent
Also, for clarity, we don't put anymore the callchain as is but:
- If we have a top level ancestor in the callchain, start it
with a first ascii hook.
Before:
0.80% perf [kernel] [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
[..] [..]
After:
0.80% perf [kernel] [k] __lock_acquire
|
--- __lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
[..] [..]
- Otherwise, if we have several top level ancestors, then
display these like we did before:
1.69% Xorg
|
|--21.21%-- vread_hpet
| 0x7fffd85b46fc
| 0x7fffd85b494d
| 0x7f4fafb4e54d
|
|--15.15%-- exaOffscreenAlloc
|
|--9.09%-- I830WaitLpRing
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Anton Blanchard <anton@samba.org>
LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-22 23:23:23 +02:00
|
|
|
|
2012-12-27 18:11:46 +09:00
|
|
|
|
perf tools: Bind callchains to the first sort dimension column
Currently, the callchains are displayed using a constant left
margin. So depending on the current sort dimension
configuration, callchains may appear to be well attached to the
first sort dimension column field which is mostly the case,
except when the first dimension of sorting is done by comm,
because these are right aligned.
This patch binds the callchain to the first letter in the first
column, whatever type of column it is (dso, comm, symbol).
Before:
0.80% perf [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
| | __fsnotify_parent
After:
0.80% perf [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
| | __fsnotify_parent
Also, for clarity, we don't put anymore the callchain as is but:
- If we have a top level ancestor in the callchain, start it
with a first ascii hook.
Before:
0.80% perf [kernel] [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
[..] [..]
After:
0.80% perf [kernel] [k] __lock_acquire
|
--- __lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
[..] [..]
- Otherwise, if we have several top level ancestors, then
display these like we did before:
1.69% Xorg
|
|--21.21%-- vread_hpet
| 0x7fffd85b46fc
| 0x7fffd85b494d
| 0x7f4fafb4e54d
|
|--15.15%-- exaOffscreenAlloc
|
|--9.09%-- I830WaitLpRing
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Anton Blanchard <anton@samba.org>
LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-22 23:23:23 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-06-04 11:27:10 -03:00
|
|
|
|
|
|
|
|
|
2015-09-04 10:45:43 -04:00
|
|
|
|
2012-12-27 18:11:46 +09:00
|
|
|
|
2015-08-07 15:54:24 -07:00
|
|
|
|
2013-07-18 15:58:53 -07:00
|
|
|
|
|
|
|
|
|
2013-09-20 07:40:43 -07:00
|
|
|
|
2015-12-23 02:07:04 +09:00
|
|
|
|
2012-12-27 18:11:46 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-02-09 23:21:01 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-09-20 07:40:41 -07:00
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:46 -07:00
|
|
|
|
2016-05-20 13:15:08 -07:00
|
|
|
|
|
|
|
|
|
2013-04-03 21:26:11 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-07-18 15:58:53 -07:00
|
|
|
|
2013-04-03 21:26:11 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-01 15:38:29 +02:00
|
|
|
|
2015-10-05 20:06:07 +02:00
|
|
|
|
perf tools: Bind callchains to the first sort dimension column
Currently, the callchains are displayed using a constant left
margin. So depending on the current sort dimension
configuration, callchains may appear to be well attached to the
first sort dimension column field which is mostly the case,
except when the first dimension of sorting is done by comm,
because these are right aligned.
This patch binds the callchain to the first letter in the first
column, whatever type of column it is (dso, comm, symbol).
Before:
0.80% perf [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
| | __fsnotify_parent
After:
0.80% perf [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
| | __fsnotify_parent
Also, for clarity, we don't put anymore the callchain as is but:
- If we have a top level ancestor in the callchain, start it
with a first ascii hook.
Before:
0.80% perf [kernel] [k] __lock_acquire
__lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
[..] [..]
After:
0.80% perf [kernel] [k] __lock_acquire
|
--- __lock_acquire
lock_acquire
|
|--58.33%-- _spin_lock
| |
| |--28.57%-- inotify_should_send_event
| | fsnotify
[..] [..]
- Otherwise, if we have several top level ancestors, then
display these like we did before:
1.69% Xorg
|
|--21.21%-- vread_hpet
| 0x7fffd85b46fc
| 0x7fffd85b494d
| 0x7f4fafb4e54d
|
|--15.15%-- exaOffscreenAlloc
|
|--9.09%-- I830WaitLpRing
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Anton Blanchard <anton@samba.org>
LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-22 23:23:23 +02:00
|
|
|
|
|
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-04-14 19:11:29 +02:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
2010-04-14 19:11:29 +02:00
|
|
|
|
|
|
|
|
|
2014-03-04 11:01:41 +09:00
|
|
|
|
2013-11-05 15:32:36 -03:00
|
|
|
|
2010-04-14 19:11:29 +02:00
|
|
|
|
2016-02-25 00:13:37 +09:00
|
|
|
|
2010-07-20 14:42:52 -03:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-12-23 02:07:01 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-03-04 10:46:34 +09:00
|
|
|
|
2014-05-07 18:42:24 +09:00
|
|
|
|
2013-04-03 21:26:19 +09:00
|
|
|
|
perf tools: Move elide bool into perf_hpp_fmt struct
After output/sort fields refactoring, it's expensive
to check the elide bool in its current location inside
the 'struct sort_entry'.
The perf_hpp__should_skip function gets highly noticable in
workloads with high number of output/sort fields, like for:
$ perf report -i perf-test.data -F overhead,sample,period,comm,pid,dso,symbol,cpu --stdio
Performance report:
9.70% perf [.] perf_hpp__should_skip
Moving the elide bool into the 'struct perf_hpp_fmt', which
makes the perf_hpp__should_skip just single struct read.
Got speedup of around 22% for my test perf.data workload.
The change should not harm any other workload types.
Performance counter stats for (10 runs):
before:
358,319,732,626 cycles ( +- 0.55% )
467,129,581,515 instructions # 1.30 insns per cycle ( +- 0.00% )
150.943975206 seconds time elapsed ( +- 0.62% )
now:
278,785,972,990 cycles ( +- 0.12% )
370,146,797,640 instructions # 1.33 insns per cycle ( +- 0.00% )
116.416670507 seconds time elapsed ( +- 0.31% )
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20140601142622.GA9131@krava.brq.redhat.com
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-23 17:15:47 +02:00
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|
2012-12-06 21:48:05 -08:00
|
|
|
|
|
|
|
|
|
2014-08-22 15:58:38 +02:00
|
|
|
|
2015-10-06 14:25:11 +02:00
|
|
|
|
|
|
|
|
|
2009-09-24 18:02:49 +02:00
|
|
|
|