diff options
author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2009-12-14 20:09:31 -0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2009-12-15 08:50:29 +0100 |
commit | 86a9eee047ba09a714c3b8e27c9df2bbf715393a (patch) | |
tree | 09c096e92b583f42480ac1dbe7dfa45eae1a7f31 /tools/perf/builtin-diff.c | |
parent | b38d34645cc52136b6c99623fef7ded26742e573 (diff) | |
download | linux-86a9eee047ba09a714c3b8e27c9df2bbf715393a.tar.gz linux-86a9eee047ba09a714c3b8e27c9df2bbf715393a.tar.bz2 linux-86a9eee047ba09a714c3b8e27c9df2bbf715393a.zip |
perf diff: Introduce tool to show performance difference
I guess it is enough to show some examples:
[root@doppio linux-2.6-tip]# rm -f perf.data*
[root@doppio linux-2.6-tip]# ls -la perf.data*
ls: cannot access perf.data*: No such file or directory
[root@doppio linux-2.6-tip]# perf record -f find / > /dev/null
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ]
[root@doppio linux-2.6-tip]# ls -la perf.data*
-rw------- 1 root root 74440 2009-12-14 20:03 perf.data
[root@doppio linux-2.6-tip]# perf record -f find / > /dev/null
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ]
[root@doppio linux-2.6-tip]# ls -la perf.data*
-rw------- 1 root root 74280 2009-12-14 20:03 perf.data
-rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old
[root@doppio linux-2.6-tip]# perf diff | head -5
1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal
2 -15307806 [kernel.kallsyms] __kmalloc
3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove
4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc
5 +7 +38538813 [kernel.kallsyms] __d_lookup
[root@doppio linux-2.6-tip]# perf diff -p | head -5
1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal
2 [kernel.kallsyms] __kmalloc
3 +1 /lib64/libc-2.10.1.so __GI_memmove
4 +4 /lib64/libc-2.10.1.so _int_malloc
5 +7 -1.00% [kernel.kallsyms] __d_lookup
[root@doppio linux-2.6-tip]# perf diff -v | head -5
1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal
2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc
3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove
4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc
5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup
[root@doppio linux-2.6-tip]# perf diff -vp | head -5
1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal
2 3.00% 3.00% [kernel.kallsyms] __kmalloc
3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove
4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc
5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup
[root@doppio linux-2.6-tip]#
This should be enough for diffs where the system is non
volatile, i.e. when one doesn't updates binaries.
For volatile environments, stay tuned for the next perf tool
feature: a buildid cache populated by 'perf record', managed by
'perf buildid-cache' a-la ccache, and used by all the report
tools.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'tools/perf/builtin-diff.c')
-rw-r--r-- | tools/perf/builtin-diff.c | 288 |
1 files changed, 288 insertions, 0 deletions
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c new file mode 100644 index 000000000000..0d528018ffb8 --- /dev/null +++ b/tools/perf/builtin-diff.c @@ -0,0 +1,288 @@ +/* + * builtin-diff.c + * + * Builtin diff command: Analyze two perf.data input files, look up and read + * DSOs and symbol information, sort them and produce a diff. + */ +#include "builtin.h" + +#include "util/debug.h" +#include "util/event.h" +#include "util/hist.h" +#include "util/session.h" +#include "util/sort.h" +#include "util/symbol.h" +#include "util/util.h" + +#include <stdlib.h> + +static char const *input_old = "perf.data.old", + *input_new = "perf.data"; +static int force; +static bool show_percent; + +struct symbol_conf symbol_conf; + +static int perf_session__add_hist_entry(struct perf_session *self, + struct addr_location *al, u64 count) +{ + bool hit; + struct hist_entry *he = __perf_session__add_hist_entry(self, al, NULL, + count, &hit); + if (he == NULL) + return -ENOMEM; + + if (hit) + he->count += count; + + return 0; +} + +static int diff__process_sample_event(event_t *event, struct perf_session *session) +{ + struct addr_location al; + struct sample_data data = { .period = 1, }; + + dump_printf("(IP, %d): %d: %p\n", event->header.misc, + event->ip.pid, (void *)(long)event->ip.ip); + + if (event__preprocess_sample(event, session, &al, NULL) < 0) { + pr_warning("problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + event__parse_sample(event, session->sample_type, &data); + + if (al.sym && perf_session__add_hist_entry(session, &al, data.period)) { + pr_warning("problem incrementing symbol count, skipping event\n"); + return -1; + } + + session->events_stats.total += data.period; + return 0; +} + +static struct perf_event_ops event_ops = { + .process_sample_event = diff__process_sample_event, + .process_mmap_event = event__process_mmap, + .process_comm_event = event__process_comm, + .process_exit_event = event__process_task, + .process_fork_event = event__process_task, + .process_lost_event = event__process_lost, +}; + +static void perf_session__insert_hist_entry_by_name(struct rb_root *root, + struct hist_entry *he) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + + while (*p != NULL) { + int cmp; + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + cmp = strcmp(he->map->dso->name, iter->map->dso->name); + if (cmp > 0) + p = &(*p)->rb_left; + else if (cmp < 0) + p = &(*p)->rb_right; + else { + cmp = strcmp(he->sym->name, iter->sym->name); + if (cmp > 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, root); +} + +static void perf_session__resort_by_name(struct perf_session *self) +{ + unsigned long position = 1; + struct rb_root tmp = RB_ROOT; + struct rb_node *next = rb_first(&self->hists); + + while (next != NULL) { + struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node); + + next = rb_next(&n->rb_node); + rb_erase(&n->rb_node, &self->hists); + n->position = position++; + perf_session__insert_hist_entry_by_name(&tmp, n); + } + + self->hists = tmp; +} + +static struct hist_entry * +perf_session__find_hist_entry_by_name(struct perf_session *self, + struct hist_entry *he) +{ + struct rb_node *n = self->hists.rb_node; + + while (n) { + struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node); + int cmp = strcmp(he->map->dso->name, iter->map->dso->name); + + if (cmp > 0) + n = n->rb_left; + else if (cmp < 0) + n = n->rb_right; + else { + cmp = strcmp(he->sym->name, iter->sym->name); + if (cmp > 0) + n = n->rb_left; + else if (cmp < 0) + n = n->rb_right; + else + return iter; + } + } + + return NULL; +} + +static void perf_session__match_hists(struct perf_session *old_session, + struct perf_session *new_session) +{ + struct rb_node *nd; + + perf_session__resort_by_name(old_session); + + for (nd = rb_first(&new_session->hists); nd; nd = rb_next(nd)) { + struct hist_entry *pos = rb_entry(nd, struct hist_entry, rb_node); + pos->pair = perf_session__find_hist_entry_by_name(old_session, pos); + } +} + +static size_t hist_entry__fprintf_matched(struct hist_entry *self, + unsigned long pos, + struct perf_session *session, + struct perf_session *pair_session, + FILE *fp) +{ + u64 old_count = 0; + char displacement[16]; + size_t printed; + + if (self->pair != NULL) { + long pdiff = (long)self->pair->position - (long)pos; + old_count = self->pair->count; + if (pdiff == 0) + goto blank; + snprintf(displacement, sizeof(displacement), "%+4ld", pdiff); + } else { +blank: memset(displacement, ' ', sizeof(displacement)); + } + + printed = fprintf(fp, "%4lu %5.5s ", pos, displacement); + + if (show_percent) { + double old_percent = (old_count * 100) / pair_session->events_stats.total, + new_percent = (self->count * 100) / session->events_stats.total; + double diff = old_percent - new_percent; + + if (verbose) + printed += fprintf(fp, " %3.2f%% %3.2f%%", old_percent, new_percent); + + if ((u64)diff != 0) + printed += fprintf(fp, " %+4.2F%%", diff); + else + printed += fprintf(fp, " "); + } else { + if (verbose) + printed += fprintf(fp, " %9Lu %9Lu", old_count, self->count); + printed += fprintf(fp, " %+9Ld", (s64)self->count - (s64)old_count); + } + + return printed + fprintf(fp, " %25.25s %s\n", + self->map->dso->name, self->sym->name); +} + +static size_t perf_session__fprintf_matched_hists(struct perf_session *self, + struct perf_session *pair, + FILE *fp) +{ + struct rb_node *nd; + size_t printed = 0; + unsigned long pos = 1; + + for (nd = rb_first(&self->hists); nd; nd = rb_next(nd)) { + struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); + printed += hist_entry__fprintf_matched(he, pos++, self, pair, fp); + } + + return printed; +} + +static int __cmd_diff(void) +{ + int ret, i; + struct perf_session *session[2]; + + session[0] = perf_session__new(input_old, O_RDONLY, force, &symbol_conf); + session[1] = perf_session__new(input_new, O_RDONLY, force, &symbol_conf); + if (session[0] == NULL || session[1] == NULL) + return -ENOMEM; + + for (i = 0; i < 2; ++i) { + ret = perf_session__process_events(session[i], &event_ops); + if (ret) + goto out_delete; + perf_session__output_resort(session[i], session[i]->events_stats.total); + } + + perf_session__match_hists(session[0], session[1]); + perf_session__fprintf_matched_hists(session[1], session[0], stdout); +out_delete: + for (i = 0; i < 2; ++i) + perf_session__delete(session[i]); + return ret; +} + +static const char *const diff_usage[] = { + "perf diff [<options>] [old_file] [new_file]", +}; + +static const struct option options[] = { + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, + "dump raw trace in ASCII"), + OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), + OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, + "load module symbols - WARNING: use only with -k and LIVE kernel"), + OPT_BOOLEAN('p', "percentages", &show_percent, + "Don't shorten the pathnames taking into account the cwd"), + OPT_BOOLEAN('P', "full-paths", &event_ops.full_paths, + "Don't shorten the pathnames taking into account the cwd"), + OPT_END() +}; + +int cmd_diff(int argc, const char **argv, const char *prefix __used) +{ + if (symbol__init(&symbol_conf) < 0) + return -1; + + setup_sorting(diff_usage, options); + + argc = parse_options(argc, argv, options, diff_usage, 0); + if (argc) { + if (argc > 2) + usage_with_options(diff_usage, options); + if (argc == 2) { + input_old = argv[0]; + input_new = argv[1]; + } else + input_new = argv[0]; + } + + setup_pager(); + return __cmd_diff(); +} |