diff options
Diffstat (limited to 'tools/perf/util/hist.h')
| -rw-r--r-- | tools/perf/util/hist.h | 290 |
1 files changed, 264 insertions, 26 deletions
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 4a0aea0c9e00..c64254088fc7 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -4,21 +4,23 @@ #include <linux/rbtree.h> #include <linux/types.h> -#include "evsel.h" +#include "callchain.h" #include "color.h" #include "events_stats.h" +#include "evsel.h" +#include "map_symbol.h" +#include "mem-events.h" #include "mutex.h" +#include "sample.h" +#include "spark.h" +#include "stat.h" -struct hist_entry; -struct hist_entry_ops; struct addr_location; -struct map_symbol; struct mem_info; struct kvm_info; struct branch_info; struct branch_stack; struct block_info; -struct symbol; struct ui_progress; enum hist_filter { @@ -30,17 +32,22 @@ enum hist_filter { HIST_FILTER__HOST, HIST_FILTER__SOCKET, HIST_FILTER__C2C, + HIST_FILTER__PARALLELISM, }; +typedef u16 filter_mask_t; + enum hist_column { HISTC_SYMBOL, HISTC_TIME, HISTC_DSO, HISTC_THREAD, + HISTC_TGID, HISTC_COMM, HISTC_CGROUP_ID, HISTC_CGROUP, HISTC_PARENT, + HISTC_PARALLELISM, HISTC_CPU, HISTC_SOCKET, HISTC_SRCLINE, @@ -85,12 +92,23 @@ enum hist_column { HISTC_TYPE, HISTC_TYPE_OFFSET, HISTC_SYMBOL_OFFSET, + HISTC_TYPE_CACHELINE, + HISTC_CALLCHAIN_BRANCH_PREDICTED, + HISTC_CALLCHAIN_BRANCH_ABORT, + HISTC_CALLCHAIN_BRANCH_CYCLES, HISTC_NR_COLS, /* Last entry */ }; struct thread; struct dso; +#define MEM_STAT_LEN 8 + +struct he_mem_stat { + /* meaning of entries depends on enum mem_stat_type */ + u64 entries[MEM_STAT_LEN]; +}; + struct hists { struct rb_root_cached entries_in_array[2]; struct rb_root_cached *entries_in; @@ -100,10 +118,13 @@ struct hists { u64 nr_non_filtered_entries; u64 callchain_period; u64 callchain_non_filtered_period; + u64 callchain_latency; + u64 callchain_non_filtered_latency; struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; const char *symbol_filter_str; + unsigned long *parallelism_filter; struct mutex lock; struct hists_stats stats; u64 event_stream; @@ -113,6 +134,9 @@ struct hists { struct perf_hpp_list *hpp_list; struct list_head hpp_formats; int nr_hpp_node; + int nr_mem_stats; + enum mem_stat_type *mem_stat_types; + struct he_mem_stat *mem_stat_total; }; #define hists__has(__h, __f) (__h)->hpp_list->__f @@ -131,18 +155,20 @@ struct hist_entry_iter { int total; int curr; - bool hide_unresolved; - struct evsel *evsel; struct perf_sample *sample; struct hist_entry *he; struct symbol *parent; - void *priv; + + struct mem_info *mi; + struct branch_info *bi; + struct hist_entry **he_cache; 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); + bool hide_unresolved; }; extern const struct hist_iter_ops hist_iter_normal; @@ -150,6 +176,170 @@ 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 res_sample { + u64 time; + int cpu; + int tid; +}; + +struct he_stat { + u64 period; + /* + * Period re-scaled from CPU time to wall-clock time (divided by the + * parallelism at the time of the sample). This represents effect of + * the event on latency rather than CPU consumption. + */ + u64 latency; + u64 period_sys; + u64 period_us; + u64 period_guest_sys; + u64 period_guest_us; + u64 weight1; + u64 weight2; + u64 weight3; + u32 nr_events; +}; + +struct namespace_id { + u64 dev; + u64 ino; +}; + +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; + + /* PERF_HPP_DIFF__CYCLES */ + s64 cycles; + }; + struct stats stats; + unsigned long svals[NUM_SPARKS]; +}; + +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 he_mem_stat *mem_stat; + struct map_symbol ms; + struct thread *thread; + struct comm *comm; + struct namespace_id cgroup_id; + u64 cgroup; + u64 ip; + u64 transaction; + u64 code_page_size; + u64 weight; + u64 ins_lat; + u64 p_stage_cyc; + s32 socket; + s32 cpu; + int parallelism; + int mem_type_off; + u8 cpumode; + u8 depth; + struct simd_flags simd_flags; + + /* We are added by hists__add_dummy_entry. */ + bool dummy; + bool leaf; + + char level; + filter_mask_t filtered; + + u16 callchain_size; + union { + /* + * Since perf diff only supports the stdio output, TUI + * fields are only accessed from perf report (or perf + * top). So make it a 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; + }; + }; + char *srcline; + char *srcfile; + struct symbol *parent; + struct branch_info *branch_info; + long time; + struct hists *hists; + struct mem_info *mem_info; + struct block_info *block_info; + struct kvm_info *kvm_info; + void *raw_data; + u32 raw_size; + int num_res; + struct res_sample *res_samples; + void *trace_output; + struct perf_hpp_list *hpp_list; + struct hist_entry *parent_he; + struct hist_entry_ops *ops; + struct annotated_data_type *mem_type; + union { + /* this is for hierarchical entry structure */ + struct { + struct rb_root_cached hroot_in; + struct rb_root_cached hroot_out; + }; /* non-leaf entries */ + struct rb_root sorted_chain; /* leaf entry has callchains */ + }; + struct callchain_root callchain[0]; /* must be last member */ +}; + +static __pure inline bool hist_entry__has_callchains(struct hist_entry *he) +{ + return he->callchain_size != 0; +} + +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); +} + struct hist_entry *hists__add_entry(struct hists *hists, struct addr_location *al, struct symbol *parent, @@ -179,13 +369,13 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, 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); +int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, + unsigned int width); void hist_entry__delete(struct hist_entry *he); typedef int (*hists__resort_cb_t)(struct hist_entry *he, void *arg); @@ -205,27 +395,30 @@ void hists__output_recalc_col_len(struct hists *hists, int max_rows); struct hist_entry *hists__get_entry(struct hists *hists, int idx); u64 hists__total_period(struct hists *hists); +u64 hists__total_latency(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); void hists__inc_nr_samples(struct hists *hists, bool filtered); void hists__inc_nr_lost_samples(struct hists *hists, u32 lost); +void hists__inc_nr_dropped_samples(struct hists *hists, u32 lost); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, bool ignore_callchains); -size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp, - bool skip_empty); +size_t evlist__fprintf_nr_events(struct 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); +void hists__filter_by_parallelism(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); + hists->symbol_filter_str || (hists->socket_filter > -1) || + hists->parallelism_filter; } u16 hists__col_len(struct hists *hists, enum hist_column col); @@ -238,6 +431,20 @@ void hists__match(struct hists *leader, struct hists *other); int hists__link(struct hists *leader, struct hists *other); int hists__unlink(struct hists *hists); +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; +} + struct hists_evsel { struct evsel evsel; struct hists hists; @@ -273,6 +480,9 @@ struct perf_hpp { bool skip; }; +typedef int64_t (*perf_hpp_fmt_cmp_t)( + struct perf_hpp_fmt *, struct hist_entry *, struct hist_entry *); + struct perf_hpp_fmt { const char *name; int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, @@ -284,12 +494,9 @@ struct perf_hpp_fmt { 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); + perf_hpp_fmt_cmp_t cmp; + perf_hpp_fmt_cmp_t collapse; + perf_hpp_fmt_cmp_t sort; bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); void (*free)(struct perf_hpp_fmt *fmt); @@ -370,24 +577,37 @@ extern struct perf_hpp_fmt perf_hpp__format[]; enum { /* Matches perf_hpp__format array. */ PERF_HPP__OVERHEAD, + PERF_HPP__LATENCY, PERF_HPP__OVERHEAD_SYS, PERF_HPP__OVERHEAD_US, PERF_HPP__OVERHEAD_GUEST_SYS, PERF_HPP__OVERHEAD_GUEST_US, PERF_HPP__OVERHEAD_ACC, + PERF_HPP__LATENCY_ACC, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, + PERF_HPP__WEIGHT1, + PERF_HPP__WEIGHT2, + PERF_HPP__WEIGHT3, + PERF_HPP__MEM_STAT_OP, + PERF_HPP__MEM_STAT_CACHE, + PERF_HPP__MEM_STAT_MEMORY, + PERF_HPP__MEM_STAT_SNOOP, + PERF_HPP__MEM_STAT_DTLB, PERF_HPP__MAX_INDEX }; void perf_hpp__init(void); -void perf_hpp__cancel_cumulate(void); +void perf_hpp__cancel_cumulate(struct evlist *evlist); +void perf_hpp__cancel_latency(struct evlist *evlist); 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); int perf_hpp__setup_hists_formats(struct perf_hpp_list *list, struct evlist *evlist); +int perf_hpp__alloc_mem_stats(struct perf_hpp_list *list, + struct evlist *evlist); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); @@ -400,6 +620,7 @@ bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_parallelism_entry(struct perf_hpp_fmt *fmt); struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt); @@ -423,16 +644,28 @@ 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); void hists__reset_column_width(struct hists *hists); +enum perf_hpp_fmt_type { + PERF_HPP_FMT_TYPE__RAW, + PERF_HPP_FMT_TYPE__PERCENT, + PERF_HPP_FMT_TYPE__LATENCY, + PERF_HPP_FMT_TYPE__AVERAGE, +}; + 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); + const char *fmtstr, hpp_snprint_fn print_fn, + enum perf_hpp_fmt_type fmtype); 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); + const char *fmtstr, hpp_snprint_fn print_fn, + enum perf_hpp_fmt_type fmtype); +int hpp__fmt_mem_stat(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he, enum mem_stat_type mst, + const char *fmtstr, hpp_snprint_fn print_fn); static inline void advance_hpp(struct perf_hpp *hpp, int inc) { @@ -460,15 +693,20 @@ struct hist_browser_timer { int refresh; }; -struct res_sample; - enum rstype { A_NORMAL, A_ASM, A_SOURCE }; -struct block_hist; +struct block_hist { + struct hists block_hists; + struct perf_hpp_list block_list; + struct perf_hpp_fmt block_fmt; + int block_idx; + bool valid; + struct hist_entry he; +}; #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" @@ -552,7 +790,7 @@ unsigned int hists__overhead_width(struct hists *hists); void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, struct perf_sample *sample, bool nonany_branch_mode, - u64 *total_cycles); + u64 *total_cycles, struct evsel *evsel); struct option; int parse_filter_percentage(const struct option *opt, const char *arg, int unset); |