mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
9b32ba71ba
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>
348 lines
10 KiB
C
348 lines
10 KiB
C
#ifndef __PERF_HIST_H
|
|
#define __PERF_HIST_H
|
|
|
|
#include <linux/types.h>
|
|
#include <pthread.h>
|
|
#include "callchain.h"
|
|
#include "header.h"
|
|
#include "color.h"
|
|
#include "ui/progress.h"
|
|
|
|
extern struct callchain_param callchain_param;
|
|
|
|
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,
|
|
};
|
|
|
|
/*
|
|
* The kernel collects the number of events it couldn't send in a stretch and
|
|
* when possible sends this number in a PERF_RECORD_LOST event. The number of
|
|
* such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
|
|
* total_lost tells exactly how many events the kernel in fact lost, i.e. it is
|
|
* the sum of all struct lost_event.lost fields reported.
|
|
*
|
|
* The total_period is needed because by default auto-freq is used, so
|
|
* multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
|
|
* the total number of low level events, it is necessary to to sum all struct
|
|
* sample_event.period and stash the result in total_period.
|
|
*/
|
|
struct events_stats {
|
|
u64 total_period;
|
|
u64 total_non_filtered_period;
|
|
u64 total_lost;
|
|
u64 total_invalid_chains;
|
|
u32 nr_events[PERF_RECORD_HEADER_MAX];
|
|
u32 nr_non_filtered_samples;
|
|
u32 nr_lost_warned;
|
|
u32 nr_unknown_events;
|
|
u32 nr_invalid_chains;
|
|
u32 nr_unknown_id;
|
|
u32 nr_unprocessable_samples;
|
|
};
|
|
|
|
enum hist_column {
|
|
HISTC_SYMBOL,
|
|
HISTC_DSO,
|
|
HISTC_THREAD,
|
|
HISTC_COMM,
|
|
HISTC_PARENT,
|
|
HISTC_CPU,
|
|
HISTC_SRCLINE,
|
|
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,
|
|
HISTC_MEM_DCACHELINE,
|
|
HISTC_TRANSACTION,
|
|
HISTC_NR_COLS, /* Last entry */
|
|
};
|
|
|
|
struct thread;
|
|
struct dso;
|
|
|
|
struct hists {
|
|
struct rb_root entries_in_array[2];
|
|
struct rb_root *entries_in;
|
|
struct rb_root entries;
|
|
struct rb_root entries_collapsed;
|
|
u64 nr_entries;
|
|
u64 nr_non_filtered_entries;
|
|
const struct thread *thread_filter;
|
|
const struct dso *dso_filter;
|
|
const char *uid_filter_str;
|
|
const char *symbol_filter_str;
|
|
pthread_mutex_t lock;
|
|
struct events_stats stats;
|
|
u64 event_stream;
|
|
u16 col_len[HISTC_NR_COLS];
|
|
};
|
|
|
|
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;
|
|
|
|
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,
|
|
struct addr_location *al,
|
|
struct symbol *parent,
|
|
struct branch_info *bi,
|
|
struct mem_info *mi, u64 period,
|
|
u64 weight, u64 transaction,
|
|
bool sample_self);
|
|
int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
|
|
struct perf_evsel *evsel, struct perf_sample *sample,
|
|
int max_stack_depth, void *arg);
|
|
|
|
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);
|
|
void hist_entry__free(struct hist_entry *);
|
|
|
|
void hists__output_resort(struct hists *hists);
|
|
void 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__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);
|
|
|
|
void hists__filter_by_dso(struct hists *hists);
|
|
void hists__filter_by_thread(struct hists *hists);
|
|
void hists__filter_by_symbol(struct hists *hists);
|
|
|
|
static inline bool hists__has_filter(struct hists *hists)
|
|
{
|
|
return hists->thread_filter || hists->dso_filter ||
|
|
hists->symbol_filter_str;
|
|
}
|
|
|
|
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 perf_hpp {
|
|
char *buf;
|
|
size_t size;
|
|
const char *sep;
|
|
void *ptr;
|
|
};
|
|
|
|
struct perf_hpp_fmt {
|
|
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 hist_entry *a, struct hist_entry *b);
|
|
int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b);
|
|
int64_t (*sort)(struct hist_entry *a, struct hist_entry *b);
|
|
|
|
struct list_head list;
|
|
struct list_head sort_list;
|
|
bool elide;
|
|
};
|
|
|
|
extern struct list_head perf_hpp__list;
|
|
extern struct list_head perf_hpp__sort_list;
|
|
|
|
#define perf_hpp__for_each_format(format) \
|
|
list_for_each_entry(format, &perf_hpp__list, list)
|
|
|
|
#define perf_hpp__for_each_format_safe(format, tmp) \
|
|
list_for_each_entry_safe(format, tmp, &perf_hpp__list, list)
|
|
|
|
#define perf_hpp__for_each_sort_list(format) \
|
|
list_for_each_entry(format, &perf_hpp__sort_list, sort_list)
|
|
|
|
#define perf_hpp__for_each_sort_list_safe(format, tmp) \
|
|
list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list)
|
|
|
|
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_register(struct perf_hpp_fmt *format);
|
|
void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
|
|
void perf_hpp__column_enable(unsigned col);
|
|
void perf_hpp__column_disable(unsigned col);
|
|
void perf_hpp__cancel_cumulate(void);
|
|
|
|
void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
|
|
void perf_hpp__setup_output_field(void);
|
|
void perf_hpp__reset_output_field(void);
|
|
void perf_hpp__append_sort_keys(void);
|
|
|
|
bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
|
|
bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
|
|
|
|
static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
|
|
{
|
|
return format->elide;
|
|
}
|
|
|
|
void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
|
|
|
|
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 *hpp, struct hist_entry *he,
|
|
hpp_field_fn get_field, const char *fmt,
|
|
hpp_snprint_fn print_fn, bool fmt_percent);
|
|
int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
|
|
hpp_field_fn get_field, const char *fmt,
|
|
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 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_session_env *env);
|
|
int script_browse(const char *script_opt);
|
|
#else
|
|
static inline
|
|
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_session_env *env __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);
|
|
|
|
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);
|
|
|
|
#endif /* __PERF_HIST_H */
|