diff options
Diffstat (limited to 'tools/perf/builtin-diff.c')
| -rw-r--r-- | tools/perf/builtin-diff.c | 769 |
1 files changed, 710 insertions, 59 deletions
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 39db2ee32d48..53d5ea4a6a4f 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -6,6 +6,7 @@ * DSOs and symbol information, sort them and produce a diff. */ #include "builtin.h" +#include "perf.h" #include "util/debug.h" #include "util/event.h" @@ -15,16 +16,37 @@ #include "util/session.h" #include "util/tool.h" #include "util/sort.h" +#include "util/srcline.h" #include "util/symbol.h" -#include "util/util.h" #include "util/data.h" #include "util/config.h" +#include "util/time-utils.h" +#include "util/annotate.h" +#include "util/map.h" +#include "util/spark.h" +#include "util/block-info.h" +#include "util/stream.h" +#include "util/util.h" +#include <linux/err.h> +#include <linux/zalloc.h> +#include <subcmd/pager.h> +#include <subcmd/parse-options.h> #include <errno.h> #include <inttypes.h> #include <stdlib.h> #include <math.h> +struct perf_diff { + struct perf_tool tool; + const char *time_str; + struct perf_time_interval *ptime_range; + int range_size; + int range_num; + bool has_br_stack; + bool stream; +}; + /* Diff command specific HPP columns. */ enum { PERF_HPP_DIFF__BASELINE, @@ -35,6 +57,8 @@ enum { PERF_HPP_DIFF__WEIGHTED_DIFF, PERF_HPP_DIFF__FORMULA, PERF_HPP_DIFF__DELTA_ABS, + PERF_HPP_DIFF__CYCLES, + PERF_HPP_DIFF__CYCLES_HIST, PERF_HPP_DIFF__MAX_INDEX }; @@ -51,6 +75,7 @@ struct data__file { struct perf_data data; int idx; struct hists *hists; + struct evlist_streams *evlist_streams; struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX]; }; @@ -69,17 +94,23 @@ static bool force; static bool show_period; static bool show_formula; static bool show_baseline_only; +static bool cycles_hist; static unsigned int sort_compute = 1; static s64 compute_wdiff_w1; static s64 compute_wdiff_w2; +static const char *cpu_list; +static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); + enum { COMPUTE_DELTA, COMPUTE_RATIO, COMPUTE_WEIGHTED_DIFF, COMPUTE_DELTA_ABS, + COMPUTE_CYCLES, COMPUTE_MAX, + COMPUTE_STREAM, /* After COMPUTE_MAX to avoid use current compute arrays */ }; const char *compute_names[COMPUTE_MAX] = { @@ -87,6 +118,7 @@ const char *compute_names[COMPUTE_MAX] = { [COMPUTE_DELTA_ABS] = "delta-abs", [COMPUTE_RATIO] = "ratio", [COMPUTE_WEIGHTED_DIFF] = "wdiff", + [COMPUTE_CYCLES] = "cycles", }; static int compute = COMPUTE_DELTA_ABS; @@ -96,6 +128,7 @@ static int compute_2_hpp[COMPUTE_MAX] = { [COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS, [COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO, [COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF, + [COMPUTE_CYCLES] = PERF_HPP_DIFF__CYCLES, }; #define MAX_COL_WIDTH 70 @@ -134,6 +167,14 @@ static struct header_column { [PERF_HPP_DIFF__FORMULA] = { .name = "Formula", .width = MAX_COL_WIDTH, + }, + [PERF_HPP_DIFF__CYCLES] = { + .name = "[Program Block Range] Cycles Diff", + .width = 70, + }, + [PERF_HPP_DIFF__CYCLES_HIST] = { + .name = "stddev/Hist", + .width = NUM_SPARKS + 9, } }; @@ -323,25 +364,93 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair, return -1; } -static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, +static void *block_hist_zalloc(size_t size) +{ + struct block_hist *bh; + + bh = zalloc(size + sizeof(*bh)); + if (!bh) + return NULL; + + return &bh->he; +} + +static void block_hist_free(void *he) +{ + struct block_hist *bh; + + bh = container_of(he, struct block_hist, he); + hists__delete_entries(&bh->block_hists); + free(bh); +} + +struct hist_entry_ops block_hist_ops = { + .new = block_hist_zalloc, + .free = block_hist_free, +}; + +static int diff__process_sample_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { + struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool); struct addr_location al; struct hists *hists = evsel__hists(evsel); + struct hist_entry_iter iter = { + .evsel = evsel, + .sample = sample, + .ops = &hist_iter_normal, + }; int ret = -1; + if (perf_time__ranges_skip_sample(pdiff->ptime_range, pdiff->range_num, + sample->time)) { + return 0; + } + + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); - return -1; + ret = -1; + goto out; } - if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, true)) { - pr_warning("problem incrementing symbol period, skipping event\n"); - goto out_put; + if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) { + ret = 0; + goto out; + } + + switch (compute) { + case COMPUTE_CYCLES: + if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL, + NULL, NULL, NULL, sample, true)) { + pr_warning("problem incrementing symbol period, " + "skipping event\n"); + goto out; + } + + hist__account_cycles(sample->branch_stack, &al, sample, + false, NULL, evsel); + break; + + case COMPUTE_STREAM: + if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH, + NULL)) { + pr_debug("problem adding hist entry, skipping event\n"); + goto out; + } + break; + + default: + if (!hists__add_entry(hists, &al, NULL, NULL, NULL, NULL, sample, + true)) { + pr_warning("problem incrementing symbol period, " + "skipping event\n"); + goto out; + } } /* @@ -354,40 +463,29 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, if (!al.filtered) hists->stats.total_non_filtered_period += sample->period; ret = 0; -out_put: - addr_location__put(&al); +out: + addr_location__exit(&al); return ret; } -static struct perf_tool tool = { - .sample = diff__process_sample_event, - .mmap = perf_event__process_mmap, - .mmap2 = perf_event__process_mmap2, - .comm = perf_event__process_comm, - .exit = perf_event__process_exit, - .fork = perf_event__process_fork, - .lost = perf_event__process_lost, - .namespaces = perf_event__process_namespaces, - .ordered_events = true, - .ordering_requires_timestamps = true, -}; +static struct perf_diff pdiff; -static struct perf_evsel *evsel_match(struct perf_evsel *evsel, - struct perf_evlist *evlist) +static struct evsel *evsel_match(struct evsel *evsel, struct evlist *evlist) { - struct perf_evsel *e; + struct evsel *e; evlist__for_each_entry(evlist, e) { - if (perf_evsel__match2(evsel, e)) + if ((evsel->core.attr.type == e->core.attr.type) && + (evsel->core.attr.config == e->core.attr.config)) return e; } return NULL; } -static void perf_evlist__collapse_resort(struct perf_evlist *evlist) +static void evlist__collapse_resort(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { struct hists *hists = evsel__hists(evsel); @@ -429,7 +527,7 @@ get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt) static void hists__baseline_only(struct hists *hists) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *next; if (hists__has(hists, need_collapse)) @@ -437,21 +535,143 @@ static void hists__baseline_only(struct hists *hists) else root = hists->entries_in; - next = rb_first(root); + next = rb_first_cached(root); while (next != NULL) { struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&he->rb_node_in); if (!hist_entry__next_pair(he)) { - rb_erase(&he->rb_node_in, root); + rb_erase_cached(&he->rb_node_in, root); hist_entry__delete(he); } } } +static int64_t block_cycles_diff_cmp(struct hist_entry *left, + struct hist_entry *right) +{ + bool pairs_left = hist_entry__has_pairs(left); + bool pairs_right = hist_entry__has_pairs(right); + s64 l, r; + + if (!pairs_left && !pairs_right) + return 0; + + l = llabs(left->diff.cycles); + r = llabs(right->diff.cycles); + return r - l; +} + +static int64_t block_sort(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + return block_cycles_diff_cmp(right, left); +} + +static void init_block_hist(struct block_hist *bh) +{ + __hists__init(&bh->block_hists, &bh->block_list); + perf_hpp_list__init(&bh->block_list); + + INIT_LIST_HEAD(&bh->block_fmt.list); + INIT_LIST_HEAD(&bh->block_fmt.sort_list); + bh->block_fmt.cmp = block_info__cmp; + bh->block_fmt.sort = block_sort; + perf_hpp_list__register_sort_field(&bh->block_list, + &bh->block_fmt); + bh->valid = true; +} + +static struct hist_entry *get_block_pair(struct hist_entry *he, + struct hists *hists_pair) +{ + struct rb_root_cached *root = hists_pair->entries_in; + struct rb_node *next = rb_first_cached(root); + int64_t cmp; + + while (next != NULL) { + struct hist_entry *he_pair = rb_entry(next, struct hist_entry, + rb_node_in); + + next = rb_next(&he_pair->rb_node_in); + + cmp = __block_info__cmp(he_pair, he); + if (!cmp) + return he_pair; + } + + return NULL; +} + +static void init_spark_values(unsigned long *svals, int num) +{ + for (int i = 0; i < num; i++) + svals[i] = 0; +} + +static void update_spark_value(unsigned long *svals, int num, + struct stats *stats, u64 val) +{ + int n = stats->n; + + if (n < num) + svals[n] = val; +} + +static void compute_cycles_diff(struct hist_entry *he, + struct hist_entry *pair) +{ + pair->diff.computed = true; + if (pair->block_info->num && he->block_info->num) { + pair->diff.cycles = + pair->block_info->cycles_aggr / pair->block_info->num_aggr - + he->block_info->cycles_aggr / he->block_info->num_aggr; + + if (!cycles_hist) + return; + + init_stats(&pair->diff.stats); + init_spark_values(pair->diff.svals, NUM_SPARKS); + + for (int i = 0; i < pair->block_info->num; i++) { + u64 val; + + if (i >= he->block_info->num || i >= NUM_SPARKS) + break; + + val = llabs(pair->block_info->cycles_spark[i] - + he->block_info->cycles_spark[i]); + + update_spark_value(pair->diff.svals, NUM_SPARKS, + &pair->diff.stats, val); + update_stats(&pair->diff.stats, val); + } + } +} + +static void block_hists_match(struct hists *hists_base, + struct hists *hists_pair) +{ + struct rb_root_cached *root = hists_base->entries_in; + struct rb_node *next = rb_first_cached(root); + + while (next != NULL) { + struct hist_entry *he = rb_entry(next, struct hist_entry, + rb_node_in); + struct hist_entry *pair = get_block_pair(he, hists_pair); + + next = rb_next(&he->rb_node_in); + + if (pair) { + hist_entry__add_pair(pair, he); + compute_cycles_diff(he, pair); + } + } +} + static void hists__precompute(struct hists *hists) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *next; if (hists__has(hists, need_collapse)) @@ -459,8 +679,9 @@ static void hists__precompute(struct hists *hists) else root = hists->entries_in; - next = rb_first(root); + next = rb_first_cached(root); while (next != NULL) { + struct block_hist *bh, *pair_bh; struct hist_entry *he, *pair; struct data__file *d; int i; @@ -468,6 +689,12 @@ static void hists__precompute(struct hists *hists) he = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&he->rb_node_in); + if (compute == COMPUTE_CYCLES) { + bh = container_of(he, struct block_hist, he); + init_block_hist(bh); + block_info__process_sym(he, bh, NULL, 0, 0); + } + data__for_each_file_new(i, d) { pair = get_pair_data(he, d); if (!pair) @@ -484,6 +711,21 @@ static void hists__precompute(struct hists *hists) case COMPUTE_WEIGHTED_DIFF: compute_wdiff(he, pair); break; + case COMPUTE_CYCLES: + pair_bh = container_of(pair, struct block_hist, + he); + init_block_hist(pair_bh); + block_info__process_sym(pair, pair_bh, NULL, 0, 0); + + bh = container_of(he, struct block_hist, he); + + if (bh->valid && pair_bh->valid) { + block_hists_match(&bh->block_hists, + &pair_bh->block_hists); + hists__output_resort(&pair_bh->block_hists, + NULL); + } + break; default: BUG_ON(1); } @@ -695,6 +937,9 @@ static void hists__process(struct hists *hists) hists__precompute(hists); hists__output_resort(hists, NULL); + if (compute == COMPUTE_CYCLES) + symbol_conf.report_block = true; + hists__fprintf(hists, !quiet, 0, 0, 0, stdout, !symbol_conf.use_callchain); } @@ -708,7 +953,7 @@ static void data__fprintf(void) data__for_each_file(i, d) fprintf(stdout, "# [%d] %s %s\n", - d->idx, d->data.file.path, + d->idx, d->data.path, !d->idx ? "(Baseline)" : ""); fprintf(stdout, "#\n"); @@ -716,8 +961,8 @@ static void data__fprintf(void) static void data_process(void) { - struct perf_evlist *evlist_base = data__files[0].session->evlist; - struct perf_evsel *evsel_base; + struct evlist *evlist_base = data__files[0].session->evlist; + struct evsel *evsel_base; bool first = true; evlist__for_each_entry(evlist_base, evsel_base) { @@ -726,8 +971,8 @@ static void data_process(void) int i; data__for_each_file_new(i, d) { - struct perf_evlist *evlist = d->session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = d->session->evlist; + struct evsel *evsel; struct hists *hists; evsel = evsel_match(evsel_base, evlist); @@ -745,7 +990,7 @@ static void data_process(void) if (!quiet) { fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n", - perf_evsel__name(evsel_base)); + evsel__name(evsel_base)); } first = false; @@ -754,16 +999,61 @@ static void data_process(void) data__fprintf(); /* Don't sort callchain for perf diff */ - perf_evsel__reset_sample_bit(evsel_base, CALLCHAIN); + evsel__reset_sample_bit(evsel_base, CALLCHAIN); hists__process(hists_base); } } +static int process_base_stream(struct data__file *data_base, + struct data__file *data_pair, + const char *title __maybe_unused) +{ + struct evlist *evlist_base = data_base->session->evlist; + struct evlist *evlist_pair = data_pair->session->evlist; + struct evsel *evsel_base, *evsel_pair; + struct evsel_streams *es_base, *es_pair; + + evlist__for_each_entry(evlist_base, evsel_base) { + evsel_pair = evsel_match(evsel_base, evlist_pair); + if (!evsel_pair) + continue; + + es_base = evsel_streams__entry(data_base->evlist_streams, + evsel_base); + if (!es_base) + return -1; + + es_pair = evsel_streams__entry(data_pair->evlist_streams, + evsel_pair); + if (!es_pair) + return -1; + + evsel_streams__match(es_base, es_pair); + evsel_streams__report(es_base, es_pair); + } + + return 0; +} + +static void stream_process(void) +{ + /* + * Stream comparison only supports two data files. + * perf.data.old and perf.data. data__files[0] is perf.data.old, + * data__files[1] is perf.data. + */ + process_base_stream(&data__files[0], &data__files[1], + "# Output based on old perf data:\n#\n"); +} + static void data__free(struct data__file *d) { int col; + if (d->evlist_streams) + evlist_streams__delete(d->evlist_streams); + for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) { struct diff_hpp_fmt *fmt = &d->fmt[col]; @@ -771,37 +1061,183 @@ static void data__free(struct data__file *d) } } +static int abstime_str_dup(char **pstr) +{ + char *str = NULL; + + if (pdiff.time_str && strchr(pdiff.time_str, ':')) { + str = strdup(pdiff.time_str); + if (!str) + return -ENOMEM; + } + + *pstr = str; + return 0; +} + +static int parse_absolute_time(struct data__file *d, char **pstr) +{ + char *p = *pstr; + int ret; + + /* + * Absolute timestamp for one file has the format: a.b,c.d + * For multiple files, the format is: a.b,c.d:a.b,c.d + */ + p = strchr(*pstr, ':'); + if (p) { + if (p == *pstr) { + pr_err("Invalid time string\n"); + return -EINVAL; + } + + *p = 0; + p++; + if (*p == 0) { + pr_err("Invalid time string\n"); + return -EINVAL; + } + } + + ret = perf_time__parse_for_ranges(*pstr, d->session, + &pdiff.ptime_range, + &pdiff.range_size, + &pdiff.range_num); + if (ret < 0) + return ret; + + if (!p || *p == 0) + *pstr = NULL; + else + *pstr = p; + + return ret; +} + +static int parse_percent_time(struct data__file *d) +{ + int ret; + + ret = perf_time__parse_for_ranges(pdiff.time_str, d->session, + &pdiff.ptime_range, + &pdiff.range_size, + &pdiff.range_num); + return ret; +} + +static int parse_time_str(struct data__file *d, char *abstime_ostr, + char **pabstime_tmp) +{ + int ret = 0; + + if (abstime_ostr) + ret = parse_absolute_time(d, pabstime_tmp); + else if (pdiff.time_str) + ret = parse_percent_time(d); + + return ret; +} + +static int check_file_brstack(void) +{ + struct data__file *d; + bool has_br_stack; + int i; + + data__for_each_file(i, d) { + d->session = perf_session__new(&d->data, &pdiff.tool); + if (IS_ERR(d->session)) { + pr_err("Failed to open %s\n", d->data.path); + return PTR_ERR(d->session); + } + + has_br_stack = perf_header__has_feat(&d->session->header, + HEADER_BRANCH_STACK); + perf_session__delete(d->session); + if (!has_br_stack) + return 0; + } + + /* Set only all files having branch stacks */ + pdiff.has_br_stack = true; + return 0; +} + static int __cmd_diff(void) { struct data__file *d; - int ret = -EINVAL, i; + int ret, i; + char *abstime_ostr, *abstime_tmp; + + ret = abstime_str_dup(&abstime_ostr); + if (ret) + return ret; + + abstime_tmp = abstime_ostr; + ret = -EINVAL; data__for_each_file(i, d) { - d->session = perf_session__new(&d->data, false, &tool); - if (!d->session) { - pr_err("Failed to open %s\n", d->data.file.path); - ret = -1; + d->session = perf_session__new(&d->data, &pdiff.tool); + if (IS_ERR(d->session)) { + ret = PTR_ERR(d->session); + pr_err("Failed to open %s\n", d->data.path); goto out_delete; } + if (pdiff.time_str) { + ret = parse_time_str(d, abstime_ostr, &abstime_tmp); + if (ret < 0) + goto out_delete; + } + + if (cpu_list) { + ret = perf_session__cpu_bitmap(d->session, cpu_list, + cpu_bitmap); + if (ret < 0) + goto out_delete; + } + ret = perf_session__process_events(d->session); if (ret) { - pr_err("Failed to process %s\n", d->data.file.path); + pr_err("Failed to process %s\n", d->data.path); goto out_delete; } - perf_evlist__collapse_resort(d->session->evlist); + evlist__collapse_resort(d->session->evlist); + + if (pdiff.ptime_range) + zfree(&pdiff.ptime_range); + + if (compute == COMPUTE_STREAM) { + d->evlist_streams = evlist__create_streams( + d->session->evlist, 5); + if (!d->evlist_streams) { + ret = -ENOMEM; + goto out_delete; + } + } } - data_process(); + if (compute == COMPUTE_STREAM) + stream_process(); + else + data_process(); out_delete: data__for_each_file(i, d) { - perf_session__delete(d->session); + if (!IS_ERR(d->session)) + perf_session__delete(d->session); data__free(d); } free(data__files); + + if (pdiff.ptime_range) + zfree(&pdiff.ptime_range); + + if (abstime_ostr) + free(abstime_ostr); + return ret; } @@ -813,17 +1249,20 @@ static const char * const diff_usage[] = { static const struct option options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"), + OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any warnings or messages"), OPT_BOOLEAN('b', "baseline-only", &show_baseline_only, "Show only items with match in baseline"), OPT_CALLBACK('c', "compute", &compute, - "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)", + "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs),cycles", "Entries differential computation selection", setup_compute), OPT_BOOLEAN('p', "period", &show_period, "Show period values."), OPT_BOOLEAN('F', "formula", &show_formula, "Show formula."), + OPT_BOOLEAN(0, "cycles-hist", &cycles_hist, + "Show cycles histogram and standard deviation " + "- WARNING: use only with -c cycles."), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), @@ -849,6 +1288,15 @@ static const struct option options[] = { OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."), OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", "How to display percentage of filtered entries", parse_filter_percentage), + OPT_STRING(0, "time", &pdiff.time_str, "str", + "Time span (time percent or absolute timestamp)"), + OPT_STRING(0, "cpu", &cpu_list, "cpu", "list of cpus to profile"), + OPT_STRING(0, "pid", &symbol_conf.pid_list_str, "pid[,pid...]", + "only consider symbols in these pids"), + OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]", + "only consider symbols in these tids"), + OPT_BOOLEAN(0, "stream", &pdiff.stream, + "Enable hot streams comparison."), OPT_END() }; @@ -888,6 +1336,50 @@ static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size) return ret; } +static int cycles_printf(struct hist_entry *he, struct hist_entry *pair, + struct perf_hpp *hpp, int width) +{ + struct block_hist *bh = container_of(he, struct block_hist, he); + struct block_hist *bh_pair = container_of(pair, struct block_hist, he); + struct hist_entry *block_he; + struct block_info *bi; + char buf[128]; + char *start_line, *end_line; + + block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx); + if (!block_he) { + hpp->skip = true; + return 0; + } + + /* + * Avoid printing the warning "addr2line_init failed for ..." + */ + symbol_conf.disable_add2line_warn = true; + + bi = block_he->block_info; + + start_line = map__srcline(he->ms.map, bi->sym->start + bi->start, + he->ms.sym); + + end_line = map__srcline(he->ms.map, bi->sym->start + bi->end, + he->ms.sym); + + if (start_line != SRCLINE_UNKNOWN && + end_line != SRCLINE_UNKNOWN) { + scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld", + start_line, end_line, block_he->diff.cycles); + } else { + scnprintf(buf, sizeof(buf), "[%7lx -> %7lx] %4ld", + bi->start, bi->end, block_he->diff.cycles); + } + + zfree_srcline(&start_line); + zfree_srcline(&end_line); + + return scnprintf(hpp->buf, hpp->size, "%*s", width, buf); +} + static int __hpp__color_compare(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he, int comparison_method) @@ -899,8 +1391,17 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt, s64 wdiff; char pfmt[20] = " "; - if (!pair) + if (!pair) { + if (comparison_method == COMPUTE_CYCLES) { + struct block_hist *bh; + + bh = container_of(he, struct block_hist, he); + if (bh->block_idx) + hpp->skip = true; + } + goto no_print; + } switch (comparison_method) { case COMPUTE_DELTA: @@ -935,6 +1436,8 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt, return color_snprintf(hpp->buf, hpp->size, get_percent_color(wdiff), pfmt, wdiff); + case COMPUTE_CYCLES: + return cycles_printf(he, pair, hpp, dfmt->header_width); default: BUG_ON(1); } @@ -964,6 +1467,96 @@ static int hpp__color_wdiff(struct perf_hpp_fmt *fmt, return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF); } +static int hpp__color_cycles(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, struct hist_entry *he) +{ + return __hpp__color_compare(fmt, hpp, he, COMPUTE_CYCLES); +} + +static int all_zero(unsigned long *vals, int len) +{ + int i; + + for (i = 0; i < len; i++) + if (vals[i] != 0) + return 0; + return 1; +} + +static int print_cycles_spark(char *bf, int size, unsigned long *svals, u64 n) +{ + int printed; + + if (n <= 1) + return 0; + + if (n > NUM_SPARKS) + n = NUM_SPARKS; + if (all_zero(svals, n)) + return 0; + + printed = print_spark(bf, size, svals, n); + printed += scnprintf(bf + printed, size - printed, " "); + return printed; +} + +static int hpp__color_cycles_hist(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, struct hist_entry *he) +{ + struct diff_hpp_fmt *dfmt = + container_of(fmt, struct diff_hpp_fmt, fmt); + struct hist_entry *pair = get_pair_fmt(he, dfmt); + struct block_hist *bh = container_of(he, struct block_hist, he); + struct block_hist *bh_pair; + struct hist_entry *block_he; + char spark[32], buf[128]; + double r; + int ret, pad; + + if (!pair) { + if (bh->block_idx) + hpp->skip = true; + + goto no_print; + } + + bh_pair = container_of(pair, struct block_hist, he); + + block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx); + if (!block_he) { + hpp->skip = true; + goto no_print; + } + + ret = print_cycles_spark(spark, sizeof(spark), block_he->diff.svals, + block_he->diff.stats.n); + + r = rel_stddev_stats(stddev_stats(&block_he->diff.stats), + avg_stats(&block_he->diff.stats)); + + if (ret) { + /* + * Padding spaces if number of sparks less than NUM_SPARKS + * otherwise the output is not aligned. + */ + pad = NUM_SPARKS - ((ret - 1) / 3); + scnprintf(buf, sizeof(buf), "%s%5.1f%% %s", "\u00B1", r, spark); + ret = scnprintf(hpp->buf, hpp->size, "%*s", + dfmt->header_width, buf); + + if (pad) { + ret += scnprintf(hpp->buf + ret, hpp->size - ret, + "%-*s", pad, " "); + } + + return ret; + } + +no_print: + return scnprintf(hpp->buf, hpp->size, "%*s", + dfmt->header_width, " "); +} + static void hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size) { @@ -1038,7 +1631,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, default: BUG_ON(1); - }; + } } static void @@ -1165,6 +1758,14 @@ static void data__hpp_register(struct data__file *d, int idx) fmt->color = hpp__color_delta; fmt->sort = hist_entry__cmp_delta_abs; break; + case PERF_HPP_DIFF__CYCLES: + fmt->color = hpp__color_cycles; + fmt->sort = hist_entry__cmp_nop; + break; + case PERF_HPP_DIFF__CYCLES_HIST: + fmt->color = hpp__color_cycles_hist; + fmt->sort = hist_entry__cmp_nop; + break; default: fmt->sort = hist_entry__cmp_nop; break; @@ -1184,16 +1785,20 @@ static int ui_init(void) data__for_each_file(i, d) { /* - * Baseline or compute realted columns: + * Baseline or compute related columns: * * PERF_HPP_DIFF__BASELINE * PERF_HPP_DIFF__DELTA * PERF_HPP_DIFF__RATIO * PERF_HPP_DIFF__WEIGHTED_DIFF + * PERF_HPP_DIFF__CYCLES */ data__hpp_register(d, i ? compute_2_hpp[compute] : PERF_HPP_DIFF__BASELINE); + if (cycles_hist && i) + data__hpp_register(d, PERF_HPP_DIFF__CYCLES_HIST); + /* * And the rest: * @@ -1245,6 +1850,13 @@ static int ui_init(void) case COMPUTE_DELTA_ABS: fmt->sort = hist_entry__cmp_delta_abs_idx; break; + case COMPUTE_CYCLES: + /* + * Should set since 'fmt->sort' is called without + * checking valid during sorting + */ + fmt->sort = hist_entry__cmp_nop; + break; default: BUG_ON(1); } @@ -1289,9 +1901,9 @@ static int data_init(int argc, const char **argv) data__for_each_file(i, d) { struct perf_data *data = &d->data; - data->file.path = use_default ? defaults[i] : argv[i]; - data->mode = PERF_DATA_MODE_READ, - data->force = force, + data->path = use_default ? defaults[i] : argv[i]; + data->mode = PERF_DATA_MODE_READ; + data->force = force; d->idx = i; } @@ -1334,6 +1946,18 @@ int cmd_diff(int argc, const char **argv) if (ret < 0) return ret; + perf_tool__init(&pdiff.tool, /*ordered_events=*/true); + pdiff.tool.sample = diff__process_sample_event; + pdiff.tool.mmap = perf_event__process_mmap; + pdiff.tool.mmap2 = perf_event__process_mmap2; + pdiff.tool.comm = perf_event__process_comm; + pdiff.tool.exit = perf_event__process_exit; + pdiff.tool.fork = perf_event__process_fork; + pdiff.tool.lost = perf_event__process_lost; + pdiff.tool.namespaces = perf_event__process_namespaces; + pdiff.tool.cgroup = perf_event__process_cgroup; + pdiff.tool.ordering_requires_timestamps = true; + perf_config(diff__config, NULL); argc = parse_options(argc, argv, options, diff_usage, 0); @@ -1341,18 +1965,45 @@ int cmd_diff(int argc, const char **argv) if (quiet) perf_quiet_option(); + if (cycles_hist && (compute != COMPUTE_CYCLES)) + usage_with_options(diff_usage, options); + + if (pdiff.stream) + compute = COMPUTE_STREAM; + + symbol__annotation_init(); + if (symbol__init(NULL) < 0) return -1; if (data_init(argc, argv) < 0) return -1; - if (ui_init() < 0) + if (check_file_brstack() < 0) + return -1; + + if ((compute == COMPUTE_CYCLES || compute == COMPUTE_STREAM) + && !pdiff.has_br_stack) { return -1; + } + + if (compute == COMPUTE_STREAM) { + symbol_conf.show_branchflag_count = true; + symbol_conf.disable_add2line_warn = true; + callchain_param.mode = CHAIN_FLAT; + callchain_param.key = CCKEY_SRCLINE; + callchain_param.branch_callstack = 1; + symbol_conf.use_callchain = true; + callchain_register_param(&callchain_param); + sort_order = "srcline,symbol,dso"; + } else { + if (ui_init() < 0) + return -1; - sort__mode = SORT_MODE__DIFF; + sort__mode = SORT_MODE__DIFF; + } - if (setup_sorting(NULL) < 0) + if (setup_sorting(/*evlist=*/NULL, perf_session__env(data__files[0].session)) < 0) usage_with_options(diff_usage, options); setup_pager(); |