linux/tools/perf/util/hist.h

438 lines
13 KiB
C
Raw Normal View History

#ifndef __PERF_HIST_H
#define __PERF_HIST_H
#include <linux/types.h>
#include <pthread.h>
#include "callchain.h"
#include "evsel.h"
#include "header.h"
#include "color.h"
#include "ui/progress.h"
struct hist_entry;
struct addr_location;
struct symbol;
enum hist_filter {
HIST_FILTER__DSO,
HIST_FILTER__THREAD,
HIST_FILTER__PARENT,
HIST_FILTER__SYMBOL,
HIST_FILTER__GUEST,
HIST_FILTER__HOST,
HIST_FILTER__SOCKET,
};
enum hist_column {
HISTC_SYMBOL,
HISTC_DSO,
HISTC_THREAD,
HISTC_COMM,
HISTC_PARENT,
HISTC_CPU,
HISTC_SOCKET,
HISTC_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>
2015-08-07 22:54:24 +00:00
HISTC_SRCFILE,
HISTC_MISPREDICT,
HISTC_IN_TX,
HISTC_ABORT,
HISTC_SYMBOL_FROM,
HISTC_SYMBOL_TO,
HISTC_DSO_FROM,
HISTC_DSO_TO,
HISTC_LOCAL_WEIGHT,
HISTC_GLOBAL_WEIGHT,
HISTC_MEM_DADDR_SYMBOL,
HISTC_MEM_DADDR_DSO,
HISTC_MEM_LOCKED,
HISTC_MEM_TLB,
HISTC_MEM_LVL,
HISTC_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 13:38:29 +00:00
HISTC_MEM_DCACHELINE,
HISTC_MEM_IADDR_SYMBOL,
HISTC_TRANSACTION,
HISTC_CYCLES,
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>
2015-12-22 17:07:04 +00:00
HISTC_TRACE,
HISTC_NR_COLS, /* Last entry */
};
struct thread;
struct dso;
2010-05-10 16:04:11 +00:00
struct hists {
struct rb_root entries_in_array[2];
struct rb_root *entries_in;
2010-05-10 16:04:11 +00:00
struct rb_root entries;
struct rb_root entries_collapsed;
u64 nr_entries;
u64 nr_non_filtered_entries;
u64 callchain_period;
u64 callchain_non_filtered_period;
struct thread *thread_filter;
const struct dso *dso_filter;
const char *uid_filter_str;
const char *symbol_filter_str;
pthread_mutex_t lock;
2010-05-10 16:04:11 +00:00
struct events_stats stats;
u64 event_stream;
u16 col_len[HISTC_NR_COLS];
int socket_filter;
struct perf_hpp_list *hpp_list;
2010-05-10 16:04:11 +00:00
};
struct hist_entry_iter;
struct hist_iter_ops {
int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
};
struct hist_entry_iter {
int total;
int curr;
bool hide_unresolved;
int max_stack;
struct perf_evsel *evsel;
struct perf_sample *sample;
struct hist_entry *he;
struct symbol *parent;
void *priv;
const struct hist_iter_ops *ops;
/* user-defined callback function (optional) */
int (*add_entry_cb)(struct hist_entry_iter *iter,
struct addr_location *al, bool single, void *arg);
};
extern const struct hist_iter_ops hist_iter_normal;
extern const struct hist_iter_ops hist_iter_branch;
extern const struct hist_iter_ops hist_iter_mem;
extern const struct hist_iter_ops hist_iter_cumulative;
struct hist_entry *__hists__add_entry(struct hists *hists,
2010-05-10 16:04:11 +00:00
struct addr_location *al,
struct symbol *parent,
struct branch_info *bi,
struct mem_info *mi,
struct perf_sample *sample,
bool sample_self);
int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
int max_stack_depth, void *arg);
struct perf_hpp;
struct perf_hpp_fmt;
int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
int hist_entry__transaction_len(void);
int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
struct hists *hists);
int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
struct perf_hpp_fmt *fmt, int printed);
void hist_entry__delete(struct hist_entry *he);
void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
void hists__output_resort(struct hists *hists, struct ui_progress *prog);
int hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
void hists__delete_entries(struct hists *hists);
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> 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-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
void hists__output_recalc_col_len(struct hists *hists, int max_rows);
u64 hists__total_period(struct hists *hists);
void hists__reset_stats(struct hists *hists);
void hists__inc_stats(struct hists *hists, struct hist_entry *h);
void hists__inc_nr_events(struct hists *hists, u32 type);
void hists__inc_nr_samples(struct hists *hists, bool filtered);
void events_stats__inc(struct events_stats *stats, u32 type);
size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
int max_cols, float min_pcnt, FILE *fp);
size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
void hists__filter_by_dso(struct hists *hists);
void hists__filter_by_thread(struct hists *hists);
void hists__filter_by_symbol(struct hists *hists);
void hists__filter_by_socket(struct hists *hists);
static inline bool hists__has_filter(struct hists *hists)
{
return hists->thread_filter || hists->dso_filter ||
hists->symbol_filter_str || (hists->socket_filter > -1);
}
u16 hists__col_len(struct hists *hists, enum hist_column col);
void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len);
bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len);
void hists__reset_col_len(struct hists *hists);
void hists__calc_col_len(struct hists *hists, struct hist_entry *he);
void hists__match(struct hists *leader, struct hists *other);
int hists__link(struct hists *leader, struct hists *other);
struct hists_evsel {
struct perf_evsel evsel;
struct hists hists;
};
static inline struct perf_evsel *hists_to_evsel(struct hists *hists)
{
struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists);
return &hevsel->evsel;
}
static inline struct hists *evsel__hists(struct perf_evsel *evsel)
{
struct hists_evsel *hevsel = (struct hists_evsel *)evsel;
return &hevsel->hists;
}
int hists__init(void);
int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
int hists__collapse_insert_entry(struct hists *hists,
struct rb_root *root, struct hist_entry *he);
struct perf_hpp {
char *buf;
size_t size;
const char *sep;
void *ptr;
};
struct perf_hpp_fmt {
const char *name;
int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct perf_evsel *evsel);
int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct perf_evsel *evsel);
int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hist_entry *he);
int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hist_entry *he);
int64_t (*cmp)(struct perf_hpp_fmt *fmt,
struct hist_entry *a, struct hist_entry *b);
int64_t (*collapse)(struct perf_hpp_fmt *fmt,
struct hist_entry *a, struct hist_entry *b);
int64_t (*sort)(struct perf_hpp_fmt *fmt,
struct hist_entry *a, struct hist_entry *b);
bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
void (*free)(struct perf_hpp_fmt *fmt);
struct list_head list;
struct list_head sort_list;
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 15:15:47 +00:00
bool elide;
int len;
int user_len;
int idx;
};
struct perf_hpp_list {
struct list_head fields;
struct list_head sorts;
};
extern struct perf_hpp_list perf_hpp_list;
void perf_hpp_list__column_register(struct perf_hpp_list *list,
struct perf_hpp_fmt *format);
void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
struct perf_hpp_fmt *format);
static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
{
perf_hpp_list__column_register(&perf_hpp_list, format);
}
static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
{
perf_hpp_list__register_sort_field(&perf_hpp_list, format);
}
#define perf_hpp_list__for_each_format(_list, format) \
list_for_each_entry(format, &(_list)->fields, list)
#define perf_hpp_list__for_each_format_safe(_list, format, tmp) \
list_for_each_entry_safe(format, tmp, &(_list)->fields, list)
#define perf_hpp_list__for_each_sort_list(_list, format) \
list_for_each_entry(format, &(_list)->sorts, sort_list)
#define perf_hpp_list__for_each_sort_list_safe(_list, format, tmp) \
list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list)
#define hists__for_each_format(hists, format) \
perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
#define hists__for_each_sort_list(hists, format) \
perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
extern struct perf_hpp_fmt perf_hpp__format[];
enum {
/* Matches perf_hpp__format array. */
PERF_HPP__OVERHEAD,
PERF_HPP__OVERHEAD_SYS,
PERF_HPP__OVERHEAD_US,
PERF_HPP__OVERHEAD_GUEST_SYS,
PERF_HPP__OVERHEAD_GUEST_US,
PERF_HPP__OVERHEAD_ACC,
PERF_HPP__SAMPLES,
PERF_HPP__PERIOD,
PERF_HPP__MAX_INDEX
};
void perf_hpp__init(void);
void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
void perf_hpp__cancel_cumulate(void);
void perf_hpp__setup_output_field(struct perf_hpp_list *list);
void perf_hpp__reset_output_field(struct perf_hpp_list *list);
void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
perf tools: Skip dynamic fields not defined for current event When there are multiple events, each dynamic sort key is defined just for one event. In this case other events will always show "N/A" for those fields. But they are meaningless and consume precious screen width. Let's skip those undefined dynamic fields. $ perf record -e kmem:kmalloc,kmem:kfree -a sleep 1 $ perf report -s 'comm,kmalloc.*' --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 20K of event 'kmem:kmalloc' # Event count (approx.): 20533 # # Overhead Command call_site ptr bytes_req bytes_alloc gfp_flags # ........ ....... .................. .................. ......... ........... ................... # 99.89% perf ffffffffa01d4396 0xffff8803ffb79720 96 96 GFP_NOFS|GFP_ZERO 0.06% sleep ffffffff8114e1cd 0xffff8803d228a000 4096 4096 GFP_KERNEL 0.03% perf ffffffff811d6ae6 0xffff8803f7678f00 240 256 GFP_KERNEL|GFP_ZERO 0.00% perf ffffffff812263c1 0xffff880406172380 128 128 GFP_KERNEL 0.00% perf ffffffff812264b9 0xffff8803ffac1600 504 512 GFP_KERNEL 0.00% perf ffffffff81226634 0xffff880401dc5280 28 32 GFP_KERNEL 0.00% sleep ffffffff81226da9 0xffff8803ffac3a00 392 512 GFP_KERNEL # Samples: 20K of event 'kmem:kfree' # Event count (approx.): 20597 # # Overhead Command # ........ .............. # 99.63% perf 0.14% sleep 0.11% irq/36-iwlwifi 0.11% kworker/u16:0 0.01% Xorg 0.00% firefox Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@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: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1450804030-29193-12-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-22 17:07:08 +00:00
bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt);
bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt);
bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt);
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 15:15:47 +00:00
perf tools: Skip dynamic fields not defined for current event When there are multiple events, each dynamic sort key is defined just for one event. In this case other events will always show "N/A" for those fields. But they are meaningless and consume precious screen width. Let's skip those undefined dynamic fields. $ perf record -e kmem:kmalloc,kmem:kfree -a sleep 1 $ perf report -s 'comm,kmalloc.*' --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 20K of event 'kmem:kmalloc' # Event count (approx.): 20533 # # Overhead Command call_site ptr bytes_req bytes_alloc gfp_flags # ........ ....... .................. .................. ......... ........... ................... # 99.89% perf ffffffffa01d4396 0xffff8803ffb79720 96 96 GFP_NOFS|GFP_ZERO 0.06% sleep ffffffff8114e1cd 0xffff8803d228a000 4096 4096 GFP_KERNEL 0.03% perf ffffffff811d6ae6 0xffff8803f7678f00 240 256 GFP_KERNEL|GFP_ZERO 0.00% perf ffffffff812263c1 0xffff880406172380 128 128 GFP_KERNEL 0.00% perf ffffffff812264b9 0xffff8803ffac1600 504 512 GFP_KERNEL 0.00% perf ffffffff81226634 0xffff880401dc5280 28 32 GFP_KERNEL 0.00% sleep ffffffff81226da9 0xffff8803ffac3a00 392 512 GFP_KERNEL # Samples: 20K of event 'kmem:kfree' # Event count (approx.): 20597 # # Overhead Command # ........ .............. # 99.63% perf 0.14% sleep 0.11% irq/36-iwlwifi 0.11% kworker/u16:0 0.01% Xorg 0.00% firefox Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@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: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1450804030-29193-12-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-22 17:07:08 +00:00
static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
struct hists *hists)
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 15:15:47 +00:00
{
perf tools: Skip dynamic fields not defined for current event When there are multiple events, each dynamic sort key is defined just for one event. In this case other events will always show "N/A" for those fields. But they are meaningless and consume precious screen width. Let's skip those undefined dynamic fields. $ perf record -e kmem:kmalloc,kmem:kfree -a sleep 1 $ perf report -s 'comm,kmalloc.*' --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 20K of event 'kmem:kmalloc' # Event count (approx.): 20533 # # Overhead Command call_site ptr bytes_req bytes_alloc gfp_flags # ........ ....... .................. .................. ......... ........... ................... # 99.89% perf ffffffffa01d4396 0xffff8803ffb79720 96 96 GFP_NOFS|GFP_ZERO 0.06% sleep ffffffff8114e1cd 0xffff8803d228a000 4096 4096 GFP_KERNEL 0.03% perf ffffffff811d6ae6 0xffff8803f7678f00 240 256 GFP_KERNEL|GFP_ZERO 0.00% perf ffffffff812263c1 0xffff880406172380 128 128 GFP_KERNEL 0.00% perf ffffffff812264b9 0xffff8803ffac1600 504 512 GFP_KERNEL 0.00% perf ffffffff81226634 0xffff880401dc5280 28 32 GFP_KERNEL 0.00% sleep ffffffff81226da9 0xffff8803ffac3a00 392 512 GFP_KERNEL # Samples: 20K of event 'kmem:kfree' # Event count (approx.): 20597 # # Overhead Command # ........ .............. # 99.63% perf 0.14% sleep 0.11% irq/36-iwlwifi 0.11% kworker/u16:0 0.01% Xorg 0.00% firefox Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@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: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1450804030-29193-12-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-22 17:07:08 +00:00
if (format->elide)
return true;
if (perf_hpp__is_dynamic_entry(format) &&
!perf_hpp__defined_dynamic_entry(format, hists))
return true;
return false;
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 15:15:47 +00:00
}
void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
void perf_hpp__set_user_width(const char *width_list_str);
typedef u64 (*hpp_field_fn)(struct hist_entry *he);
typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hist_entry *he, hpp_field_fn get_field,
const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hist_entry *he, hpp_field_fn get_field,
const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
static inline void advance_hpp(struct perf_hpp *hpp, int inc)
{
hpp->buf += inc;
hpp->size -= inc;
}
static inline size_t perf_hpp__use_color(void)
{
return !symbol_conf.field_sep;
}
static inline size_t perf_hpp__color_overhead(void)
{
return perf_hpp__use_color() ?
(COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX
: 0;
}
struct perf_evlist;
struct hist_browser_timer {
void (*timer)(void *arg);
void *arg;
int refresh;
};
#ifdef HAVE_SLANG_SUPPORT
#include "../ui/keysyms.h"
int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
struct hist_browser_timer *hbt);
int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
struct hist_browser_timer *hbt);
int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
struct hist_browser_timer *hbt,
float min_pcnt,
struct perf_env *env);
int script_browse(const char *script_opt);
#else
static inline
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:03 +00:00
int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
const char *help __maybe_unused,
struct hist_browser_timer *hbt __maybe_unused,
float min_pcnt __maybe_unused,
struct perf_env *env __maybe_unused)
{
return 0;
}
static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
struct perf_evsel *evsel __maybe_unused,
struct hist_browser_timer *hbt __maybe_unused)
{
return 0;
}
static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
struct perf_evsel *evsel __maybe_unused,
struct hist_browser_timer *hbt __maybe_unused)
{
return 0;
}
static inline int script_browse(const char *script_opt __maybe_unused)
{
return 0;
}
#define K_LEFT -1000
#define K_RIGHT -2000
#define K_SWITCH_INPUT_DATA -3000
#endif
unsigned int hists__sort_list_width(struct hists *hists);
void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
struct perf_sample *sample, bool nonany_branch_mode);
struct option;
int parse_filter_percentage(const struct option *opt __maybe_unused,
const char *arg, int unset __maybe_unused);
int perf_hist_config(const char *var, const char *value);
void perf_hpp_list__init(struct perf_hpp_list *list);
enum hierarchy_move_dir {
HMD_NORMAL,
HMD_FORCE_SIBLING,
HMD_FORCE_CHILD,
};
struct rb_node *rb_hierarchy_last(struct rb_node *node);
struct rb_node *__rb_hierarchy_next(struct rb_node *node,
enum hierarchy_move_dir hmd);
struct rb_node *rb_hierarchy_prev(struct rb_node *node);
static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
{
return __rb_hierarchy_next(node, HMD_NORMAL);
}
#endif /* __PERF_HIST_H */