perf/urgent fixes:

. Fix parsing with no sample_id_all bit set, this regression prevents perf
   from reading old perf.data files generated in systems where
   perf_event_attr.sample_id_all isn't available, from Adrian Hunter.
 
 . Add signal checking to the inner 'perf trace' event processing loop, allowing
   faster response to control+C.
 
 . Fix formatting of long symbol names removing the hardcoding of a buffer
   size used to format histogram entries, which was truncating the lines.
 
 . Separate progress bar update when processing events, reducing potentially big
   overhead in not needed TUI progress bar screen updates, from Jiri Olsa.
 
 . Fix 'perf trace' build in architectures where MAP_32BIT is not defined, from
   Kyle McMartin.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.14 (GNU/Linux)
 
 iQIcBAABAgAGBQJSKN3vAAoJENZQFvNTUqpAHRIQAJnS3nUqxwsoaqKB2IJZjhTK
 eZhplHS3kxoMuP0ZNIR6cDT/gHfILak2jiTYLpuDpp8MfXBVDKUfV73UwKunIO7w
 CYD+WstJw6zH2HhXkL1a+Tk6R06G+fls6tErFlg4J4wuFo3wWTwUYfWi7QYyUdf6
 FaU8YF+xQT08XR/f1dBxv6fK/2ibblBxuh1puhbnoJd2VCRtaeIO+7XbOEGNnDqN
 rkLgSlBxzEfIyHvm4yo1TsKfZMKH9PrJZ3OY6/Ga6MAlC1uZ7b0eHrNpd5SeWjKL
 z+QPpoFKdW+7hDHEffml/3+xyhHOGc3Dr1BfEEn0ue30GfeLV1mRFu9qofN9agJO
 5HuimdrA49BTsx3bjuiaQLy4vfUVSxPOmgAUKVXMRjf8WVXlsy5ygBWeX5/DP4NK
 zMexGE+IKVFv33cJFVp6HBwmLB68q0YOZ9SHCTXtKQKvIFzC+W0JQ3wHX+7YeI7f
 u02zezxdmdcH0H+QVztwM1k9rnkwR02lN17SOcRNj0NNgyzb4UD2Xqijn/PJVN/k
 SnikNdi4w3v/I02NjAun7KBdzlZlglsoU96FrdifwXrj6q8ZR2yjx/v8cUfSeebu
 GeYUteR4Me00p1s7FGyTd9yVAuJ2/mOZzD4BFz8Q0LxdCBaMf2aMCA9jUqmQBsz4
 m6/bpt2YdC8t+KzDEHDW
 =akcD
 -----END PGP SIGNATURE-----

Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes from Arnaldo Carvalho de Melo:

 * Fix parsing with no sample_id_all bit set, this regression prevents perf
   from reading old perf.data files generated in systems where
   perf_event_attr.sample_id_all isn't available, from Adrian Hunter.

 * Add signal checking to the inner 'perf trace' event processing loop, allowing
   faster response to control+C.

 * Fix formatting of long symbol names removing the hardcoding of a buffer
   size used to format histogram entries, which was truncating the lines.

 * Separate progress bar update when processing events, reducing potentially big
   overhead in not needed TUI progress bar screen updates, from Jiri Olsa.

 * Fix 'perf trace' build in architectures where MAP_32BIT is not defined, from
   Kyle McMartin.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar 2013-09-06 14:08:08 +02:00
commit 72f4a11d2f
8 changed files with 146 additions and 10 deletions

View File

@ -394,6 +394,8 @@ ifeq ($(ARCH),x86)
LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o
endif
LIB_OBJS += $(OUTPUT)tests/code-reading.o
LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@ -439,7 +441,6 @@ PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
ifneq ($(OUTPUT),)
CFLAGS += -I$(OUTPUT)
endif
LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
ifdef NO_LIBELF
EXTLIBS := $(filter-out -lelf,$(EXTLIBS))

View File

@ -100,7 +100,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
P_MMAP_FLAG(SHARED);
P_MMAP_FLAG(PRIVATE);
#ifdef MAP_32BIT
P_MMAP_FLAG(32BIT);
#endif
P_MMAP_FLAG(ANONYMOUS);
P_MMAP_FLAG(DENYWRITE);
P_MMAP_FLAG(EXECUTABLE);
@ -994,6 +996,9 @@ again:
handler = evsel->handler.func;
handler(trace, evsel, &sample);
if (done)
goto out_unmap_evlist;
}
}

View File

@ -111,6 +111,10 @@ static struct test {
.desc = "Test using a dummy software event to keep tracking",
.func = test__keep_tracking,
},
{
.desc = "Test parsing with no sample_id_all bit set",
.func = test__parse_no_sample_id_all,
},
{
.func = NULL,
},

View File

@ -0,0 +1,108 @@
#include <sys/types.h>
#include <stddef.h>
#include "tests.h"
#include "event.h"
#include "evlist.h"
#include "header.h"
#include "util.h"
static int process_event(struct perf_evlist **pevlist, union perf_event *event)
{
struct perf_sample sample;
if (event->header.type == PERF_RECORD_HEADER_ATTR) {
if (perf_event__process_attr(NULL, event, pevlist)) {
pr_debug("perf_event__process_attr failed\n");
return -1;
}
return 0;
}
if (event->header.type >= PERF_RECORD_USER_TYPE_START)
return -1;
if (!*pevlist)
return -1;
if (perf_evlist__parse_sample(*pevlist, event, &sample)) {
pr_debug("perf_evlist__parse_sample failed\n");
return -1;
}
return 0;
}
static int process_events(union perf_event **events, size_t count)
{
struct perf_evlist *evlist = NULL;
int err = 0;
size_t i;
for (i = 0; i < count && !err; i++)
err = process_event(&evlist, events[i]);
if (evlist)
perf_evlist__delete(evlist);
return err;
}
struct test_attr_event {
struct attr_event attr;
u64 id;
};
/**
* test__parse_no_sample_id_all - test parsing with no sample_id_all bit set.
*
* This function tests parsing data produced on kernel's that do not support the
* sample_id_all bit. Without the sample_id_all bit, non-sample events (such as
* mmap events) do not have an id sample appended, and consequently logic
* designed to determine the id will not work. That case happens when there is
* more than one selected event, so this test processes three events: 2
* attributes representing the selected events and one mmap event.
*
* Return: %0 on success, %-1 if the test fails.
*/
int test__parse_no_sample_id_all(void)
{
int err;
struct test_attr_event event1 = {
.attr = {
.header = {
.type = PERF_RECORD_HEADER_ATTR,
.size = sizeof(struct test_attr_event),
},
},
.id = 1,
};
struct test_attr_event event2 = {
.attr = {
.header = {
.type = PERF_RECORD_HEADER_ATTR,
.size = sizeof(struct test_attr_event),
},
},
.id = 2,
};
struct mmap_event event3 = {
.header = {
.type = PERF_RECORD_MMAP,
.size = sizeof(struct mmap_event),
},
};
union perf_event *events[] = {
(union perf_event *)&event1,
(union perf_event *)&event2,
(union perf_event *)&event3,
};
err = process_events(events, ARRAY_SIZE(events));
if (err)
return -1;
return 0;
}

View File

@ -39,5 +39,6 @@ int test__perf_time_to_tsc(void);
int test__code_reading(void);
int test__sample_parsing(void);
int test__keep_tracking(void);
int test__parse_no_sample_id_all(void);
#endif /* TESTS_H */

View File

@ -350,9 +350,9 @@ static int hist_entry__period_snprintf(struct perf_hpp *hpp,
}
static int hist_entry__fprintf(struct hist_entry *he, size_t size,
struct hists *hists, FILE *fp)
struct hists *hists,
char *bf, size_t bfsz, FILE *fp)
{
char bf[512];
int ret;
struct perf_hpp hpp = {
.buf = bf,
@ -360,8 +360,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
};
bool color = !symbol_conf.field_sep;
if (size == 0 || size > sizeof(bf))
size = hpp.size = sizeof(bf);
if (size == 0 || size > bfsz)
size = hpp.size = bfsz;
ret = hist_entry__period_snprintf(&hpp, he, color);
hist_entry__sort_snprintf(he, bf + ret, size - ret, hists);
@ -392,6 +392,8 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
.ptr = hists_to_evsel(hists),
};
bool first = true;
size_t linesz;
char *line = NULL;
init_rem_hits();
@ -479,6 +481,13 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
goto out;
print_entries:
linesz = hists__sort_list_width(hists) + 3 + 1;
line = malloc(linesz);
if (line == NULL) {
ret = -1;
goto out;
}
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
float percent = h->stat.period * 100.0 /
@ -490,10 +499,10 @@ print_entries:
if (percent < min_pcnt)
continue;
ret += hist_entry__fprintf(h, max_cols, hists, fp);
ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp);
if (max_rows && ++nr_rows >= max_rows)
goto out;
break;
if (h->ms.map == NULL && verbose > 1) {
__map_groups__fprintf_maps(&h->thread->mg,
@ -501,6 +510,8 @@ print_entries:
fprintf(fp, "%.10s end\n", graph_dotted_line);
}
}
free(line);
out:
free(rem_sq_bracket);

View File

@ -446,20 +446,25 @@ static int perf_evlist__event2id(struct perf_evlist *evlist,
static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
union perf_event *event)
{
struct perf_evsel *first = perf_evlist__first(evlist);
struct hlist_head *head;
struct perf_sample_id *sid;
int hash;
u64 id;
if (evlist->nr_entries == 1)
return perf_evlist__first(evlist);
return first;
if (!first->attr.sample_id_all &&
event->header.type != PERF_RECORD_SAMPLE)
return first;
if (perf_evlist__event2id(evlist, event, &id))
return NULL;
/* Synthesized events have an id of zero */
if (!id)
return perf_evlist__first(evlist);
return first;
hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
head = &evlist->heads[hash];

View File

@ -504,6 +504,7 @@ static int flush_sample_queue(struct perf_session *s,
u64 limit = os->next_flush;
u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
unsigned idx = 0, progress_next = os->nr_samples / 16;
bool show_progress = limit == ULLONG_MAX;
int ret;
if (!tool->ordered_samples || !limit)
@ -526,7 +527,7 @@ static int flush_sample_queue(struct perf_session *s,
os->last_flush = iter->timestamp;
list_del(&iter->list);
list_add(&iter->list, &os->sample_cache);
if (++idx >= progress_next) {
if (show_progress && (++idx >= progress_next)) {
progress_next += os->nr_samples / 16;
ui_progress__update(idx, os->nr_samples,
"Processing time ordered events...");