mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 11:56:45 +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>
222 lines
4.8 KiB
C
222 lines
4.8 KiB
C
#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[];
|
|
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;
|
|
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;
|
|
u8 cpumode;
|
|
|
|
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;
|
|
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,
|
|
};
|
|
|
|
enum sort_type {
|
|
/* common sort keys */
|
|
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,
|
|
SORT_MEM_DCACHELINE,
|
|
};
|
|
|
|
/*
|
|
* 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);
|
|
void perf_hpp__set_elide(int idx, bool elide);
|
|
|
|
int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
|
|
|
|
#endif /* __PERF_SORT_H */
|