2009-09-24 16:02:49 +00:00
|
|
|
#ifndef __PERF_SORT_H
|
|
|
|
|
#define __PERF_SORT_H
|
|
|
|
|
#include "../builtin.h"
|
|
|
|
|
|
|
|
|
|
#include "util.h"
|
|
|
|
|
|
|
|
|
|
#include "color.h"
|
|
|
|
|
#include <linux/list.h>
|
|
|
|
|
#include "cache.h"
|
|
|
|
|
#include <linux/rbtree.h>
|
|
|
|
|
#include "symbol.h"
|
|
|
|
|
#include "string.h"
|
|
|
|
|
#include "callchain.h"
|
|
|
|
|
#include "strlist.h"
|
|
|
|
|
#include "values.h"
|
|
|
|
|
|
|
|
|
|
#include "../perf.h"
|
|
|
|
|
#include "debug.h"
|
|
|
|
|
#include "header.h"
|
|
|
|
|
|
|
|
|
|
#include "parse-options.h"
|
|
|
|
|
#include "parse-events.h"
|
|
|
|
|
|
|
|
|
|
#include "thread.h"
|
|
|
|
|
#include "sort.h"
|
|
|
|
|
|
|
|
|
|
extern regex_t parent_regex;
|
2010-05-17 19:22:41 +00:00
|
|
|
extern const char *sort_order;
|
|
|
|
|
extern const char default_parent_pattern[];
|
|
|
|
|
extern const char *parent_pattern;
|
|
|
|
|
extern const char default_sort_order[];
|
2009-09-24 16:02:49 +00:00
|
|
|
extern int sort__need_collapse;
|
|
|
|
|
extern int sort__has_parent;
|
|
|
|
|
extern char *field_sep;
|
|
|
|
|
extern struct sort_entry sort_comm;
|
|
|
|
|
extern struct sort_entry sort_dso;
|
|
|
|
|
extern struct sort_entry sort_sym;
|
|
|
|
|
extern struct sort_entry sort_parent;
|
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 21:23:23 +00:00
|
|
|
extern enum sort_type sort__first_dimension;
|
2009-09-24 16:02:49 +00:00
|
|
|
|
2010-07-26 20:13:40 +00:00
|
|
|
/**
|
|
|
|
|
* struct hist_entry - histogram entry
|
|
|
|
|
*
|
|
|
|
|
* @row_offset - offset from the first callchain expanded to appear on screen
|
|
|
|
|
* @nr_rows - rows expanded in callchain, recalculated on folding/unfolding
|
|
|
|
|
*/
|
2009-09-24 16:02:49 +00:00
|
|
|
struct hist_entry {
|
|
|
|
|
struct rb_node rb_node;
|
2010-05-14 17:19:35 +00:00
|
|
|
u64 period;
|
|
|
|
|
u64 period_sys;
|
|
|
|
|
u64 period_us;
|
|
|
|
|
u64 period_guest_sys;
|
|
|
|
|
u64 period_guest_us;
|
2010-03-24 19:40:17 +00:00
|
|
|
struct map_symbol ms;
|
2010-04-04 01:44:37 +00:00
|
|
|
struct thread *thread;
|
2009-09-24 16:02:49 +00:00
|
|
|
u64 ip;
|
2010-06-04 14:27:10 +00:00
|
|
|
s32 cpu;
|
2010-05-14 17:19:35 +00:00
|
|
|
u32 nr_events;
|
2010-07-26 20:13:40 +00:00
|
|
|
|
|
|
|
|
/* XXX These two should move to some tree widget lib */
|
|
|
|
|
u16 row_offset;
|
|
|
|
|
u16 nr_rows;
|
|
|
|
|
|
|
|
|
|
bool init_have_children;
|
2009-09-24 16:02:49 +00:00
|
|
|
char level;
|
2010-04-04 01:44:37 +00:00
|
|
|
u8 filtered;
|
2010-04-03 19:30:44 +00:00
|
|
|
struct symbol *parent;
|
2009-12-14 22:09:31 +00:00
|
|
|
union {
|
|
|
|
|
unsigned long position;
|
|
|
|
|
struct hist_entry *pair;
|
|
|
|
|
struct rb_root sorted_chain;
|
|
|
|
|
};
|
2010-08-22 18:05:22 +00:00
|
|
|
struct callchain_root callchain[0];
|
2009-09-24 16:02:49 +00:00
|
|
|
};
|
|
|
|
|
|
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 21:23:23 +00:00
|
|
|
enum sort_type {
|
|
|
|
|
SORT_PID,
|
|
|
|
|
SORT_COMM,
|
|
|
|
|
SORT_DSO,
|
|
|
|
|
SORT_SYM,
|
2010-06-04 14:27:10 +00:00
|
|
|
SORT_PARENT,
|
|
|
|
|
SORT_CPU,
|
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 21:23:23 +00:00
|
|
|
};
|
|
|
|
|
|
2009-09-24 16:02:49 +00:00
|
|
|
/*
|
|
|
|
|
* configurable sorting bits
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
struct sort_entry {
|
|
|
|
|
struct list_head list;
|
|
|
|
|
|
2010-04-14 17:11:29 +00:00
|
|
|
const char *se_header;
|
2009-09-24 16:02:49 +00:00
|
|
|
|
2010-04-14 17:11:29 +00:00
|
|
|
int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
|
|
|
|
|
int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *);
|
|
|
|
|
int (*se_snprintf)(struct hist_entry *self, char *bf, size_t size,
|
|
|
|
|
unsigned int width);
|
2010-07-20 17:42:52 +00:00
|
|
|
u8 se_width_idx;
|
2009-09-24 16:02:49 +00:00
|
|
|
bool elide;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
extern struct sort_entry sort_thread;
|
|
|
|
|
extern struct list_head hist_entry__sort_list;
|
|
|
|
|
|
2009-12-14 22:09:29 +00:00
|
|
|
void setup_sorting(const char * const usagestr[], const struct option *opts);
|
|
|
|
|
|
2009-09-24 16:02:49 +00:00
|
|
|
extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int);
|
|
|
|
|
extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int);
|
|
|
|
|
extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int);
|
|
|
|
|
extern size_t sort__sym_print(FILE *, struct hist_entry *, unsigned int __used);
|
|
|
|
|
extern int64_t cmp_null(void *, void *);
|
|
|
|
|
extern int64_t sort__thread_cmp(struct hist_entry *, struct hist_entry *);
|
|
|
|
|
extern int64_t sort__comm_cmp(struct hist_entry *, struct hist_entry *);
|
|
|
|
|
extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *);
|
|
|
|
|
extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *);
|
|
|
|
|
extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *);
|
|
|
|
|
extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *);
|
2010-06-04 14:27:10 +00:00
|
|
|
int64_t sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right);
|
2009-09-24 16:02:49 +00:00
|
|
|
extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int);
|
|
|
|
|
extern int sort_dimension__add(const char *);
|
perf diff: Use perf_session__fprintf_hists just like 'perf record'
That means that almost everything you can do with 'perf report'
can be done with 'perf diff', for instance:
$ perf record -f find / > /dev/null
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.062 MB perf.data (~2699
samples) ] $ perf record -f find / > /dev/null
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.062 MB perf.data (~2687
samples) ] perf diff | head -8
9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal
2.91% -1.00% find [kernel] [k] __kmalloc
2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent
1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock
2.44% find [kernel] [k] half_md4_transform
$
So if you want to zoom into libc:
$ perf diff --dsos libc-2.10.1.so | head -8
37.34% find [.] _IO_vfprintf_internal
10.34% find [.] __GI_memmove
8.25% +2.00% find [.] _int_malloc
5.07% -1.00% find [.] __GI_mempcpy
7.62% +2.00% find [.] _int_free
$
And if there were multiple commands using libc, it is also
possible to aggregate them all by using --sort symbol:
$ perf diff --dsos libc-2.10.1.so --sort symbol | head -8
37.34% [.] _IO_vfprintf_internal
10.34% [.] __GI_memmove
8.25% +2.00% [.] _int_malloc
5.07% -1.00% [.] __GI_mempcpy
7.62% +2.00% [.] _int_free
$
The displacement column now is off by default, to use it:
perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8
37.34% [.] _IO_vfprintf_internal
10.34% [.] __GI_memmove
8.25% +2.00% [.] _int_malloc
5.07% -1.00% +2 [.] __GI_mempcpy
7.62% +2.00% -1 [.] _int_free
$
Using -t/--field-separator can be used for scripting:
$ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8
37.34, , ,[.] _IO_vfprintf_internal
10.34, , ,[.] __GI_memmove
8.25,+2.00%, ,[.] _int_malloc
5.07,-1.00%, +2,[.] __GI_mempcpy
7.62,+2.00%, -1,[.] _int_free
6.99,+1.00%, -1,[.] _IO_new_file_xsputn
1.89,-2.00%, +4,[.] __readdir64
$
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 15:49:27 +00:00
|
|
|
void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
|
|
|
|
|
const char *list_name, FILE *fp);
|
2009-09-24 16:02:49 +00:00
|
|
|
|
|
|
|
|
#endif /* __PERF_SORT_H */
|