OpenCloudOS-Kernel/tools/perf/util/sort.h

220 lines
4.7 KiB
C
Raw Normal View History

#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 "hist.h"
#include "thread.h"
extern regex_t parent_regex;
extern const char *sort_order;
extern const char *field_order;
extern const char default_parent_pattern[];
extern const char *parent_pattern;
extern const char default_sort_order[];
perf report/top: Add option to collapse undesired parts of call graph For example, in an application with an expensive function implemented with deeply nested recursive calls, the default call-graph presentation is dominated by the different callchains within that function. By ignoring these callees, we can collect the callchains leading into the function and compactly identify what to blame for expensive calls. For example, in this report the callers of garbage_collect() are scattered across the tree: $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z] 22.03% ruby [.] gc_mark --- gc_mark |--59.40%-- mark_keyvalue | st_foreach | gc_mark_children | |--99.75%-- rb_gc_mark | | rb_vm_mark | | gc_mark_children | | gc_marks | | |--99.00%-- garbage_collect If we ignore the callees of garbage_collect(), its callers are coalesced: $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z] 72.92% ruby [.] garbage_collect --- garbage_collect vm_xmalloc |--47.08%-- ruby_xmalloc | st_insert2 | rb_hash_aset | |--98.45%-- features_index_add | | rb_provide_feature | | rb_require_safe | | vm_call_method Signed-off-by: Greg Price <price@mit.edu> Tested-by: Jiri Olsa <jolsa@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130623031720.GW22203@biohazard-cafe.mit.edu Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu Cc: Fengguang Wu <fengguang.wu@intel.com> [ remove spaces at beginning of line, reported by Fengguang Wu ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-12-07 13:48:05 +08:00
extern regex_t ignore_callees_regex;
extern int have_ignore_callees;
extern int sort__need_collapse;
extern int sort__has_parent;
extern int sort__has_sym;
extern enum sort_mode sort__mode;
extern struct sort_entry sort_comm;
extern struct sort_entry sort_dso;
extern struct sort_entry sort_sym;
extern struct sort_entry sort_parent;
extern struct sort_entry sort_dso_from;
extern struct sort_entry sort_dso_to;
extern struct sort_entry sort_sym_from;
extern struct sort_entry sort_sym_to;
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>
2009-10-23 05:23:23 +08:00
extern enum sort_type sort__first_dimension;
struct he_stat {
u64 period;
u64 period_sys;
u64 period_us;
u64 period_guest_sys;
u64 period_guest_us;
u64 weight;
u32 nr_events;
};
struct hist_entry_diff {
bool computed;
/* PERF_HPP__DELTA */
double period_ratio_delta;
/* PERF_HPP__RATIO */
double period_ratio;
/* HISTC_WEIGHTED_DIFF */
s64 wdiff;
};
/**
* 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
*/
struct hist_entry {
struct rb_node rb_node_in;
struct rb_node rb_node;
union {
struct list_head node;
struct list_head head;
} pairs;
struct he_stat stat;
struct he_stat *stat_acc;
struct map_symbol ms;
struct thread *thread;
struct comm *comm;
u64 ip;
u64 transaction;
s32 cpu;
struct hist_entry_diff diff;
/* We are added by hists__add_dummy_entry. */
bool dummy;
/* XXX These two should move to some tree widget lib */
u16 row_offset;
u16 nr_rows;
bool init_have_children;
char level;
bool used;
u8 filtered;
perf tools: Add sort by src line/number Using addr2line for now, requires debuginfo, needs more work to support detached debuginfo, aka foo-debuginfo packages. Example: [root@sandy ~]# perf record -a sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.555 MB perf.data (~24236 samples) ] [root@sandy ~]# perf report -s dso,srcline 2>&1 | grep -v ^# | head -5 22.41% [kernel.kallsyms] /home/git/linux/drivers/idle/intel_idle.c:280 4.79% [kernel.kallsyms] /home/git/linux/drivers/cpuidle/cpuidle.c:148 4.78% [kernel.kallsyms] /home/git/linux/arch/x86/include/asm/atomic64_64.h:121 4.49% [kernel.kallsyms] /home/git/linux/kernel/sched/core.c:1690 4.30% [kernel.kallsyms] /home/git/linux/include/linux/seqlock.h:90 [root@sandy ~]# [root@sandy ~]# perf top -U -s dso,symbol,srcline Samples: 1K of event 'cycles', Event count (approx.): 589617389 18.66% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:143 7.83% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:39 6.59% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:38 3.66% [kernel] [k] page_fault /home/git/linux/arch/x86/kernel/entry_64.S:1379 3.25% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:40 3.12% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:37 2.74% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:36 2.39% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:43 2.12% [kernel] [k] ioread32 /home/git/linux/lib/iomap.c:90 1.51% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:144 1.19% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:154 Suggested-by: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-pdmqbng9twz06jzkbgtuwbp8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 21:33:24 +08:00
char *srcline;
struct symbol *parent;
unsigned long position;
struct rb_root sorted_chain;
struct branch_info *branch_info;
struct hists *hists;
struct mem_info *mem_info;
struct callchain_root callchain[0]; /* must be last member */
};
static inline bool hist_entry__has_pairs(struct hist_entry *he)
{
return !list_empty(&he->pairs.node);
}
static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
{
if (hist_entry__has_pairs(he))
return list_entry(he->pairs.node.next, struct hist_entry, pairs.node);
return NULL;
}
static inline void hist_entry__add_pair(struct hist_entry *pair,
struct hist_entry *he)
{
list_add_tail(&pair->pairs.node, &he->pairs.head);
}
static inline float hist_entry__get_percent_limit(struct hist_entry *he)
{
u64 period = he->stat.period;
u64 total_period = hists__total_period(he->hists);
if (unlikely(total_period == 0))
return 0;
if (symbol_conf.cumulate_callchain)
period = he->stat_acc->period;
return period * 100.0 / total_period;
}
enum sort_mode {
SORT_MODE__NORMAL,
SORT_MODE__BRANCH,
SORT_MODE__MEMORY,
SORT_MODE__TOP,
SORT_MODE__DIFF,
};
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>
2009-10-23 05:23:23 +08:00
enum sort_type {
/* common sort keys */
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>
2009-10-23 05:23:23 +08:00
SORT_PID,
SORT_COMM,
SORT_DSO,
SORT_SYM,
SORT_PARENT,
SORT_CPU,
SORT_SRCLINE,
SORT_LOCAL_WEIGHT,
SORT_GLOBAL_WEIGHT,
SORT_TRANSACTION,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
SORT_DSO_FROM = __SORT_BRANCH_STACK,
SORT_DSO_TO,
SORT_SYM_FROM,
SORT_SYM_TO,
SORT_MISPREDICT,
SORT_ABORT,
SORT_IN_TX,
/* memory mode specific sort keys */
__SORT_MEMORY_MODE,
SORT_MEM_DADDR_SYMBOL = __SORT_MEMORY_MODE,
SORT_MEM_DADDR_DSO,
SORT_MEM_LOCKED,
SORT_MEM_TLB,
SORT_MEM_LVL,
SORT_MEM_SNOOP,
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>
2009-10-23 05:23:23 +08:00
};
/*
* configurable sorting bits
*/
struct sort_entry {
struct list_head list;
const char *se_header;
int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *);
int64_t (*se_sort)(struct hist_entry *, struct hist_entry *);
int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
unsigned int width);
u8 se_width_idx;
};
extern struct sort_entry sort_thread;
extern struct list_head hist_entry__sort_list;
int setup_sorting(void);
int setup_output_field(void);
void reset_output_field(void);
extern int sort_dimension__add(const char *);
void sort__setup_elide(FILE *fp);
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 23:15:47 +08:00
void perf_hpp__set_elide(int idx, bool elide);
perf report/top: Add option to collapse undesired parts of call graph For example, in an application with an expensive function implemented with deeply nested recursive calls, the default call-graph presentation is dominated by the different callchains within that function. By ignoring these callees, we can collect the callchains leading into the function and compactly identify what to blame for expensive calls. For example, in this report the callers of garbage_collect() are scattered across the tree: $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z] 22.03% ruby [.] gc_mark --- gc_mark |--59.40%-- mark_keyvalue | st_foreach | gc_mark_children | |--99.75%-- rb_gc_mark | | rb_vm_mark | | gc_mark_children | | gc_marks | | |--99.00%-- garbage_collect If we ignore the callees of garbage_collect(), its callers are coalesced: $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z] 72.92% ruby [.] garbage_collect --- garbage_collect vm_xmalloc |--47.08%-- ruby_xmalloc | st_insert2 | rb_hash_aset | |--98.45%-- features_index_add | | rb_provide_feature | | rb_require_safe | | vm_call_method Signed-off-by: Greg Price <price@mit.edu> Tested-by: Jiri Olsa <jolsa@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130623031720.GW22203@biohazard-cafe.mit.edu Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu Cc: Fengguang Wu <fengguang.wu@intel.com> [ remove spaces at beginning of line, reported by Fengguang Wu ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-12-07 13:48:05 +08:00
int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
#endif /* __PERF_SORT_H */