linux/tools/perf/util/sort.h

285 lines
6.5 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 <subcmd/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 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;
extern struct sort_entry sort_srcline;
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;
extern const char default_mem_sort_order[];
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;
union {
/* PERF_HPP__DELTA */
double period_ratio_delta;
/* PERF_HPP__RATIO */
double period_ratio;
/* HISTC_WEIGHTED_DIFF */
s64 wdiff;
};
};
struct hist_entry_ops {
void *(*new)(size_t size);
void (*free)(void *ptr);
};
/**
* 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 socket;
s32 cpu;
u8 cpumode;
u8 depth;
/* We are added by hists__add_dummy_entry. */
bool dummy;
bool leaf;
char level;
u8 filtered;
union {
/*
* Since perf diff only supports the stdio output, TUI
* fields are only accessed from perf report (or perf
* top). So make it an union to reduce memory usage.
*/
struct hist_entry_diff diff;
struct /* for TUI */ {
u16 row_offset;
u16 nr_rows;
bool init_have_children;
bool unfolded;
bool has_children;
bool has_no_entry;
};
};
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;
perf report: Add support for srcfile sort key In some cases it's useful to characterize samples by file. This is useful to get a higher level categorization, for example to map cost to subsystems. Add a srcfile sort key to perf report. It builds on top of the existing srcline support. Commiter notes: E.g.: # perf record -F 10000 usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (13 samples) ] [root@zoo ~]# perf report -s srcfile --stdio # Total Lost Samples: 0 # # Samples: 13 of event 'cycles' # Event count (approx.): 869878 # # Overhead Source File # ........ ........... 60.99% . 20.62% paravirt.h 14.23% rmap.c 4.04% signal.c 0.11% msr.h # The first line is collecting all the files for which srcfiles couldn't somehow get resolved to: # perf report -s srcfile,dso --stdio # Total Lost Samples: 0 # # Samples: 13 of event 'cycles' # Event count (approx.): 869878 # # Overhead Source File Shared Object # ........ ........... ................ 40.97% . ld-2.20.so 20.62% paravirt.h [kernel.vmlinux] 20.02% . libc-2.20.so 14.23% rmap.c [kernel.vmlinux] 4.04% signal.c [kernel.vmlinux] 0.11% msr.h [kernel.vmlinux] # XXX: Investigate why that is not resolving on Fedora 21, Andi says he hasn't seen this on Fedora 22. Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1438988064-21834-1-git-send-email-andi@firstfloor.org [ Added column length update, from 0e65bdb3f90f ('perf hists: Update the column width for the "srcline" sort key') ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-08 06:54:24 +08:00
char *srcfile;
struct symbol *parent;
struct branch_info *branch_info;
struct hists *hists;
struct mem_info *mem_info;
void *raw_data;
u32 raw_size;
void *trace_output;
struct perf_hpp_list *hpp_list;
struct hist_entry *parent_he;
struct hist_entry_ops *ops;
union {
/* this is for hierarchical entry structure */
struct {
struct rb_root hroot_in;
struct rb_root hroot_out;
}; /* non-leaf entries */
struct rb_root sorted_chain; /* leaf entry has callchains */
};
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;
}
static inline u64 cl_address(u64 address)
{
/* return the cacheline of the address */
return (address & ~(cacheline_size - 1));
}
static inline u64 cl_offset(u64 address)
{
/* return the cacheline of the address */
return (address & (cacheline_size - 1));
}
enum sort_mode {
SORT_MODE__NORMAL,
SORT_MODE__BRANCH,
SORT_MODE__MEMORY,
SORT_MODE__TOP,
SORT_MODE__DIFF,
SORT_MODE__TRACEPOINT,
};
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_SOCKET,
SORT_SRCLINE,
perf report: Add support for srcfile sort key In some cases it's useful to characterize samples by file. This is useful to get a higher level categorization, for example to map cost to subsystems. Add a srcfile sort key to perf report. It builds on top of the existing srcline support. Commiter notes: E.g.: # perf record -F 10000 usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (13 samples) ] [root@zoo ~]# perf report -s srcfile --stdio # Total Lost Samples: 0 # # Samples: 13 of event 'cycles' # Event count (approx.): 869878 # # Overhead Source File # ........ ........... 60.99% . 20.62% paravirt.h 14.23% rmap.c 4.04% signal.c 0.11% msr.h # The first line is collecting all the files for which srcfiles couldn't somehow get resolved to: # perf report -s srcfile,dso --stdio # Total Lost Samples: 0 # # Samples: 13 of event 'cycles' # Event count (approx.): 869878 # # Overhead Source File Shared Object # ........ ........... ................ 40.97% . ld-2.20.so 20.62% paravirt.h [kernel.vmlinux] 20.02% . libc-2.20.so 14.23% rmap.c [kernel.vmlinux] 4.04% signal.c [kernel.vmlinux] 0.11% msr.h [kernel.vmlinux] # XXX: Investigate why that is not resolving on Fedora 21, Andi says he hasn't seen this on Fedora 22. Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1438988064-21834-1-git-send-email-andi@firstfloor.org [ Added column length update, from 0e65bdb3f90f ('perf hists: Update the column width for the "srcline" sort key') ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-08 06:54:24 +08:00
SORT_SRCFILE,
SORT_LOCAL_WEIGHT,
SORT_GLOBAL_WEIGHT,
SORT_TRANSACTION,
perf tools: Add 'trace' sort key The 'trace' sort key is to show tracepoint event output using either print fmt or plugin. For example sched_switch event (using plugin) will show output like below: # perf record -e sched:sched_switch -a usleep 10 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.197 MB perf.data (69 samples) ] # $ perf report -s trace --stdio ... # Overhead Trace output # ........ ................................................... # 9.48% swapper/0:0 [120] R ==> transmission-gt:17773 [120] 9.48% transmission-gt:17773 [120] S ==> swapper/0:0 [120] 9.04% swapper/2:0 [120] R ==> transmission-gt:17773 [120] 8.92% transmission-gt:17773 [120] S ==> swapper/2:0 [120] 5.25% swapper/0:0 [120] R ==> kworker/0:1H:109 [100] 5.21% kworker/0:1H:109 [100] S ==> swapper/0:0 [120] 1.78% swapper/3:0 [120] R ==> transmission-gt:17773 [120] 1.78% transmission-gt:17773 [120] S ==> swapper/3:0 [120] 1.53% Xephyr:6524 [120] S ==> swapper/0:0 [120] 1.53% swapper/0:0 [120] R ==> Xephyr:6524 [120] 1.17% swapper/2:0 [120] R ==> irq/33-iwlwifi:233 [49] 1.13% irq/33-iwlwifi:233 [49] S ==> swapper/2:0 [120] Note that the 'trace' sort key works only for tracepoint events. If it's used to other type of events, just "N/A" will be printed. Suggested-and-acked-by: Jiri Olsa <jolsa@redhat.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1450804030-29193-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-23 01:07:04 +08:00
SORT_TRACE,
/* 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,
SORT_CYCLES,
perf report: Add srcline_from/to branch sort keys Add "srcline_from" and "srcline_to" branch sort keys that allow to show the source lines of a branch. That makes it much easier to track down where particular branches happen in the program, for example to examine branch mispredictions, or to associate it with cycle counts: % perf record -b -e cycles:p ./tcall % perf report --sort srcline_from,srcline_to,mispredict ... 15.10% tcall.c:18 tcall.c:10 N 14.83% tcall.c:11 tcall.c:5 N 14.12% tcall.c:7 tcall.c:12 N 14.04% tcall.c:12 tcall.c:5 N 12.42% tcall.c:17 tcall.c:18 N 12.39% tcall.c:7 tcall.c:13 N 12.27% tcall.c:13 tcall.c:17 N ... % perf report --sort srcline_from,srcline_to,cycles ... 17.12% tcall.c:18 tcall.c:11 1 17.01% tcall.c:12 tcall.c:6 1 16.98% tcall.c:11 tcall.c:6 1 15.91% tcall.c:17 tcall.c:18 1 6.38% tcall.c:7 tcall.c:17 7 4.80% tcall.c:7 tcall.c:12 8 4.21% tcall.c:7 tcall.c:17 8 2.67% tcall.c:7 tcall.c:12 7 2.62% tcall.c:7 tcall.c:12 10 2.10% tcall.c:7 tcall.c:17 9 1.58% tcall.c:7 tcall.c:12 6 1.44% tcall.c:7 tcall.c:12 5 1.38% tcall.c:7 tcall.c:12 9 1.06% tcall.c:7 tcall.c:17 13 1.05% tcall.c:7 tcall.c:12 4 1.01% tcall.c:7 tcall.c:17 6 Open issues: - Some kernel symbols get misresolved. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: http://lkml.kernel.org/r/1463775308-32748-1-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-21 04:15:08 +08:00
SORT_SRCLINE_FROM,
SORT_SRCLINE_TO,
/* 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: Add dcacheline sort In perf's 'mem-mode', one can get access to a whole bunch of details specific to a particular sample instruction. A bunch of those details relate to the data address. One interesting thing you can do with data addresses is to convert them into a unique cacheline they belong too. Organizing these data cachelines into similar groups and sorting them can reveal cache contention. This patch creates an alogorithm based on various sample details that can help group entries together into data cachelines and allows 'perf report' to sort on it. The algorithm relies on having proper mmap2 support in the kernel to help determine if the memory map the data address belongs to is private to a pid or globally shared. The alogortithm is as follows: o group cpumodes together o group entries with discovered maps together o sort on major, minor, inode and inode generation numbers o if userspace anon, then sort on pid o sort on cachelines based on data addresses The 'dcacheline' sort option in 'perf report' only works in 'mem-mode'. Sample output: # # Samples: 206 of event 'cpu/mem-loads/pp' # Total weight : 2534 # Sort order : dcacheline,pid # # Overhead Samples Data Cacheline Command: Pid # ........ ............ ...................................................................... .................. # 13.22% 1 [k] 0xffff88042f08ebc0 swapper: 0 9.27% 1 [k] 0xffff88082e8cea80 swapper: 0 3.59% 2 [k] 0xffffffff819ba180 swapper: 0 0.32% 1 [k] arch_trigger_all_cpu_backtrace_handler_na.23901+0xffffffffffffffe0 swapper: 0 0.32% 1 [k] timekeeper_seq+0xfffffffffffffff8 swapper: 0 Note: Added a '+1' to symlen size in hists__calc_col_len to prevent the next column from prematurely tabbing over and mis-aligning. Not sure what the problem is. Signed-off-by: Don Zickus <dzickus@redhat.com> Link: http://lkml.kernel.org/r/1401208087-181977-8-git-send-email-dzickus@redhat.com Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-06-01 21:38:29 +08:00
SORT_MEM_DCACHELINE,
SORT_MEM_IADDR_SYMBOL,
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 {
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);
int (*se_filter)(struct hist_entry *he, int type, const void *arg);
u8 se_width_idx;
};
extern struct sort_entry sort_thread;
extern struct list_head hist_entry__sort_list;
struct perf_evlist;
struct pevent;
int setup_sorting(struct perf_evlist *evlist);
int setup_output_field(void);
void reset_output_field(void);
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);
bool is_strict_order(const char *order);
int hpp_dimension__add_output(unsigned col);
void reset_dimensions(void);
int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
struct perf_evlist *evlist,
int level);
int output_field_add(struct perf_hpp_list *list, char *tok);
int64_t
sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right);
int64_t
sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right);
int64_t
sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right);
char *hist_entry__get_srcline(struct hist_entry *he);
#endif /* __PERF_SORT_H */