[PATCH 05/32] perf tests: Move test__PERF_RECORD into separate object
From: Arnaldo Carvalho de Melo
Date: Sun Nov 18 2012 - 09:34:01 EST
From: Jiri Olsa <jolsa@xxxxxxxxxx>
Separating test__PERF_RECORD test from the builtin-test into perf-record
object.
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Corey Ashford <cjashfor@xxxxxxxxxxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Link: http://lkml.kernel.org/r/1352508412-16914-6-git-send-email-jolsa@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/Makefile | 1 +
tools/perf/tests/builtin-test.c | 307 --------------------------------------
tools/perf/tests/perf-record.c | 312 +++++++++++++++++++++++++++++++++++++++
tools/perf/tests/tests.h | 1 +
4 files changed, 314 insertions(+), 307 deletions(-)
create mode 100644 tools/perf/tests/perf-record.c
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 337489e..a2d6153 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -435,6 +435,7 @@ LIB_OBJS += $(OUTPUT)tests/vmlinux-kallsyms.o
LIB_OBJS += $(OUTPUT)tests/open-syscall.o
LIB_OBJS += $(OUTPUT)tests/open-syscall-all-cpus.o
LIB_OBJS += $(OUTPUT)tests/mmap-basic.o
+LIB_OBJS += $(OUTPUT)tests/perf-record.o
LIB_OBJS += $(OUTPUT)tests/util.o
BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 609f592..7cb3928 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -31,313 +31,6 @@
-static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp)
-{
- int i, cpu = -1, nrcpus = 1024;
-realloc:
- CPU_ZERO(maskp);
-
- if (sched_getaffinity(pid, sizeof(*maskp), maskp) == -1) {
- if (errno == EINVAL && nrcpus < (1024 << 8)) {
- nrcpus = nrcpus << 2;
- goto realloc;
- }
- perror("sched_getaffinity");
- return -1;
- }
-
- for (i = 0; i < nrcpus; i++) {
- if (CPU_ISSET(i, maskp)) {
- if (cpu == -1)
- cpu = i;
- else
- CPU_CLR(i, maskp);
- }
- }
-
- return cpu;
-}
-
-static int test__PERF_RECORD(void)
-{
- struct perf_record_opts opts = {
- .target = {
- .uid = UINT_MAX,
- .uses_mmap = true,
- },
- .no_delay = true,
- .freq = 10,
- .mmap_pages = 256,
- };
- cpu_set_t cpu_mask;
- size_t cpu_mask_size = sizeof(cpu_mask);
- struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
- struct perf_evsel *evsel;
- struct perf_sample sample;
- const char *cmd = "sleep";
- const char *argv[] = { cmd, "1", NULL, };
- char *bname;
- u64 prev_time = 0;
- bool found_cmd_mmap = false,
- found_libc_mmap = false,
- found_vdso_mmap = false,
- found_ld_mmap = false;
- int err = -1, errs = 0, i, wakeups = 0;
- u32 cpu;
- int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
-
- if (evlist == NULL || argv == NULL) {
- pr_debug("Not enough memory to create evlist\n");
- goto out;
- }
-
- /*
- * We need at least one evsel in the evlist, use the default
- * one: "cycles".
- */
- err = perf_evlist__add_default(evlist);
- if (err < 0) {
- pr_debug("Not enough memory to create evsel\n");
- goto out_delete_evlist;
- }
-
- /*
- * Create maps of threads and cpus to monitor. In this case
- * we start with all threads and cpus (-1, -1) but then in
- * perf_evlist__prepare_workload we'll fill in the only thread
- * we're monitoring, the one forked there.
- */
- err = perf_evlist__create_maps(evlist, &opts.target);
- if (err < 0) {
- pr_debug("Not enough memory to create thread/cpu maps\n");
- goto out_delete_evlist;
- }
-
- /*
- * Prepare the workload in argv[] to run, it'll fork it, and then wait
- * for perf_evlist__start_workload() to exec it. This is done this way
- * so that we have time to open the evlist (calling sys_perf_event_open
- * on all the fds) and then mmap them.
- */
- err = perf_evlist__prepare_workload(evlist, &opts, argv);
- if (err < 0) {
- pr_debug("Couldn't run the workload!\n");
- goto out_delete_evlist;
- }
-
- /*
- * Config the evsels, setting attr->comm on the first one, etc.
- */
- evsel = perf_evlist__first(evlist);
- evsel->attr.sample_type |= PERF_SAMPLE_CPU;
- evsel->attr.sample_type |= PERF_SAMPLE_TID;
- evsel->attr.sample_type |= PERF_SAMPLE_TIME;
- perf_evlist__config_attrs(evlist, &opts);
-
- err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
- if (err < 0) {
- pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
- goto out_delete_evlist;
- }
-
- cpu = err;
-
- /*
- * So that we can check perf_sample.cpu on all the samples.
- */
- if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
- pr_debug("sched_setaffinity: %s\n", strerror(errno));
- goto out_delete_evlist;
- }
-
- /*
- * Call sys_perf_event_open on all the fds on all the evsels,
- * grouping them if asked to.
- */
- err = perf_evlist__open(evlist);
- if (err < 0) {
- pr_debug("perf_evlist__open: %s\n", strerror(errno));
- goto out_delete_evlist;
- }
-
- /*
- * mmap the first fd on a given CPU and ask for events for the other
- * fds in the same CPU to be injected in the same mmap ring buffer
- * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)).
- */
- err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
- if (err < 0) {
- pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
- goto out_delete_evlist;
- }
-
- /*
- * Now that all is properly set up, enable the events, they will
- * count just on workload.pid, which will start...
- */
- perf_evlist__enable(evlist);
-
- /*
- * Now!
- */
- perf_evlist__start_workload(evlist);
-
- while (1) {
- int before = total_events;
-
- for (i = 0; i < evlist->nr_mmaps; i++) {
- union perf_event *event;
-
- while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
- const u32 type = event->header.type;
- const char *name = perf_event__name(type);
-
- ++total_events;
- if (type < PERF_RECORD_MAX)
- nr_events[type]++;
-
- err = perf_evlist__parse_sample(evlist, event, &sample);
- if (err < 0) {
- if (verbose)
- perf_event__fprintf(event, stderr);
- pr_debug("Couldn't parse sample\n");
- goto out_err;
- }
-
- if (verbose) {
- pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
- perf_event__fprintf(event, stderr);
- }
-
- if (prev_time > sample.time) {
- pr_debug("%s going backwards in time, prev=%" PRIu64 ", curr=%" PRIu64 "\n",
- name, prev_time, sample.time);
- ++errs;
- }
-
- prev_time = sample.time;
-
- if (sample.cpu != cpu) {
- pr_debug("%s with unexpected cpu, expected %d, got %d\n",
- name, cpu, sample.cpu);
- ++errs;
- }
-
- if ((pid_t)sample.pid != evlist->workload.pid) {
- pr_debug("%s with unexpected pid, expected %d, got %d\n",
- name, evlist->workload.pid, sample.pid);
- ++errs;
- }
-
- if ((pid_t)sample.tid != evlist->workload.pid) {
- pr_debug("%s with unexpected tid, expected %d, got %d\n",
- name, evlist->workload.pid, sample.tid);
- ++errs;
- }
-
- if ((type == PERF_RECORD_COMM ||
- type == PERF_RECORD_MMAP ||
- type == PERF_RECORD_FORK ||
- type == PERF_RECORD_EXIT) &&
- (pid_t)event->comm.pid != evlist->workload.pid) {
- pr_debug("%s with unexpected pid/tid\n", name);
- ++errs;
- }
-
- if ((type == PERF_RECORD_COMM ||
- type == PERF_RECORD_MMAP) &&
- event->comm.pid != event->comm.tid) {
- pr_debug("%s with different pid/tid!\n", name);
- ++errs;
- }
-
- switch (type) {
- case PERF_RECORD_COMM:
- if (strcmp(event->comm.comm, cmd)) {
- pr_debug("%s with unexpected comm!\n", name);
- ++errs;
- }
- break;
- case PERF_RECORD_EXIT:
- goto found_exit;
- case PERF_RECORD_MMAP:
- bname = strrchr(event->mmap.filename, '/');
- if (bname != NULL) {
- if (!found_cmd_mmap)
- found_cmd_mmap = !strcmp(bname + 1, cmd);
- if (!found_libc_mmap)
- found_libc_mmap = !strncmp(bname + 1, "libc", 4);
- if (!found_ld_mmap)
- found_ld_mmap = !strncmp(bname + 1, "ld", 2);
- } else if (!found_vdso_mmap)
- found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]");
- break;
-
- case PERF_RECORD_SAMPLE:
- /* Just ignore samples for now */
- break;
- default:
- pr_debug("Unexpected perf_event->header.type %d!\n",
- type);
- ++errs;
- }
- }
- }
-
- /*
- * We don't use poll here because at least at 3.1 times the
- * PERF_RECORD_{!SAMPLE} events don't honour
- * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
- */
- if (total_events == before && false)
- poll(evlist->pollfd, evlist->nr_fds, -1);
-
- sleep(1);
- if (++wakeups > 5) {
- pr_debug("No PERF_RECORD_EXIT event!\n");
- break;
- }
- }
-
-found_exit:
- if (nr_events[PERF_RECORD_COMM] > 1) {
- pr_debug("Excessive number of PERF_RECORD_COMM events!\n");
- ++errs;
- }
-
- if (nr_events[PERF_RECORD_COMM] == 0) {
- pr_debug("Missing PERF_RECORD_COMM for %s!\n", cmd);
- ++errs;
- }
-
- if (!found_cmd_mmap) {
- pr_debug("PERF_RECORD_MMAP for %s missing!\n", cmd);
- ++errs;
- }
-
- if (!found_libc_mmap) {
- pr_debug("PERF_RECORD_MMAP for %s missing!\n", "libc");
- ++errs;
- }
-
- if (!found_ld_mmap) {
- pr_debug("PERF_RECORD_MMAP for %s missing!\n", "ld");
- ++errs;
- }
-
- if (!found_vdso_mmap) {
- pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
- ++errs;
- }
-out_err:
- perf_evlist__munmap(evlist);
-out_delete_evlist:
- perf_evlist__delete(evlist);
-out:
- return (err < 0 || errs > 0) ? -1 : 0;
-}
-
-
#if defined(__x86_64__) || defined(__i386__)
#define barrier() asm volatile("" ::: "memory")
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
new file mode 100644
index 0000000..70e0d44
--- /dev/null
+++ b/tools/perf/tests/perf-record.c
@@ -0,0 +1,312 @@
+#include <sched.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "perf.h"
+#include "debug.h"
+#include "tests.h"
+
+static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp)
+{
+ int i, cpu = -1, nrcpus = 1024;
+realloc:
+ CPU_ZERO(maskp);
+
+ if (sched_getaffinity(pid, sizeof(*maskp), maskp) == -1) {
+ if (errno == EINVAL && nrcpus < (1024 << 8)) {
+ nrcpus = nrcpus << 2;
+ goto realloc;
+ }
+ perror("sched_getaffinity");
+ return -1;
+ }
+
+ for (i = 0; i < nrcpus; i++) {
+ if (CPU_ISSET(i, maskp)) {
+ if (cpu == -1)
+ cpu = i;
+ else
+ CPU_CLR(i, maskp);
+ }
+ }
+
+ return cpu;
+}
+
+int test__PERF_RECORD(void)
+{
+ struct perf_record_opts opts = {
+ .target = {
+ .uid = UINT_MAX,
+ .uses_mmap = true,
+ },
+ .no_delay = true,
+ .freq = 10,
+ .mmap_pages = 256,
+ };
+ cpu_set_t cpu_mask;
+ size_t cpu_mask_size = sizeof(cpu_mask);
+ struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+ struct perf_evsel *evsel;
+ struct perf_sample sample;
+ const char *cmd = "sleep";
+ const char *argv[] = { cmd, "1", NULL, };
+ char *bname;
+ u64 prev_time = 0;
+ bool found_cmd_mmap = false,
+ found_libc_mmap = false,
+ found_vdso_mmap = false,
+ found_ld_mmap = false;
+ int err = -1, errs = 0, i, wakeups = 0;
+ u32 cpu;
+ int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
+
+ if (evlist == NULL || argv == NULL) {
+ pr_debug("Not enough memory to create evlist\n");
+ goto out;
+ }
+
+ /*
+ * We need at least one evsel in the evlist, use the default
+ * one: "cycles".
+ */
+ err = perf_evlist__add_default(evlist);
+ if (err < 0) {
+ pr_debug("Not enough memory to create evsel\n");
+ goto out_delete_evlist;
+ }
+
+ /*
+ * Create maps of threads and cpus to monitor. In this case
+ * we start with all threads and cpus (-1, -1) but then in
+ * perf_evlist__prepare_workload we'll fill in the only thread
+ * we're monitoring, the one forked there.
+ */
+ err = perf_evlist__create_maps(evlist, &opts.target);
+ if (err < 0) {
+ pr_debug("Not enough memory to create thread/cpu maps\n");
+ goto out_delete_evlist;
+ }
+
+ /*
+ * Prepare the workload in argv[] to run, it'll fork it, and then wait
+ * for perf_evlist__start_workload() to exec it. This is done this way
+ * so that we have time to open the evlist (calling sys_perf_event_open
+ * on all the fds) and then mmap them.
+ */
+ err = perf_evlist__prepare_workload(evlist, &opts, argv);
+ if (err < 0) {
+ pr_debug("Couldn't run the workload!\n");
+ goto out_delete_evlist;
+ }
+
+ /*
+ * Config the evsels, setting attr->comm on the first one, etc.
+ */
+ evsel = perf_evlist__first(evlist);
+ evsel->attr.sample_type |= PERF_SAMPLE_CPU;
+ evsel->attr.sample_type |= PERF_SAMPLE_TID;
+ evsel->attr.sample_type |= PERF_SAMPLE_TIME;
+ perf_evlist__config_attrs(evlist, &opts);
+
+ err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
+ if (err < 0) {
+ pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
+ goto out_delete_evlist;
+ }
+
+ cpu = err;
+
+ /*
+ * So that we can check perf_sample.cpu on all the samples.
+ */
+ if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
+ pr_debug("sched_setaffinity: %s\n", strerror(errno));
+ goto out_delete_evlist;
+ }
+
+ /*
+ * Call sys_perf_event_open on all the fds on all the evsels,
+ * grouping them if asked to.
+ */
+ err = perf_evlist__open(evlist);
+ if (err < 0) {
+ pr_debug("perf_evlist__open: %s\n", strerror(errno));
+ goto out_delete_evlist;
+ }
+
+ /*
+ * mmap the first fd on a given CPU and ask for events for the other
+ * fds in the same CPU to be injected in the same mmap ring buffer
+ * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)).
+ */
+ err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+ if (err < 0) {
+ pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+ goto out_delete_evlist;
+ }
+
+ /*
+ * Now that all is properly set up, enable the events, they will
+ * count just on workload.pid, which will start...
+ */
+ perf_evlist__enable(evlist);
+
+ /*
+ * Now!
+ */
+ perf_evlist__start_workload(evlist);
+
+ while (1) {
+ int before = total_events;
+
+ for (i = 0; i < evlist->nr_mmaps; i++) {
+ union perf_event *event;
+
+ while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+ const u32 type = event->header.type;
+ const char *name = perf_event__name(type);
+
+ ++total_events;
+ if (type < PERF_RECORD_MAX)
+ nr_events[type]++;
+
+ err = perf_evlist__parse_sample(evlist, event, &sample);
+ if (err < 0) {
+ if (verbose)
+ perf_event__fprintf(event, stderr);
+ pr_debug("Couldn't parse sample\n");
+ goto out_err;
+ }
+
+ if (verbose) {
+ pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
+ perf_event__fprintf(event, stderr);
+ }
+
+ if (prev_time > sample.time) {
+ pr_debug("%s going backwards in time, prev=%" PRIu64 ", curr=%" PRIu64 "\n",
+ name, prev_time, sample.time);
+ ++errs;
+ }
+
+ prev_time = sample.time;
+
+ if (sample.cpu != cpu) {
+ pr_debug("%s with unexpected cpu, expected %d, got %d\n",
+ name, cpu, sample.cpu);
+ ++errs;
+ }
+
+ if ((pid_t)sample.pid != evlist->workload.pid) {
+ pr_debug("%s with unexpected pid, expected %d, got %d\n",
+ name, evlist->workload.pid, sample.pid);
+ ++errs;
+ }
+
+ if ((pid_t)sample.tid != evlist->workload.pid) {
+ pr_debug("%s with unexpected tid, expected %d, got %d\n",
+ name, evlist->workload.pid, sample.tid);
+ ++errs;
+ }
+
+ if ((type == PERF_RECORD_COMM ||
+ type == PERF_RECORD_MMAP ||
+ type == PERF_RECORD_FORK ||
+ type == PERF_RECORD_EXIT) &&
+ (pid_t)event->comm.pid != evlist->workload.pid) {
+ pr_debug("%s with unexpected pid/tid\n", name);
+ ++errs;
+ }
+
+ if ((type == PERF_RECORD_COMM ||
+ type == PERF_RECORD_MMAP) &&
+ event->comm.pid != event->comm.tid) {
+ pr_debug("%s with different pid/tid!\n", name);
+ ++errs;
+ }
+
+ switch (type) {
+ case PERF_RECORD_COMM:
+ if (strcmp(event->comm.comm, cmd)) {
+ pr_debug("%s with unexpected comm!\n", name);
+ ++errs;
+ }
+ break;
+ case PERF_RECORD_EXIT:
+ goto found_exit;
+ case PERF_RECORD_MMAP:
+ bname = strrchr(event->mmap.filename, '/');
+ if (bname != NULL) {
+ if (!found_cmd_mmap)
+ found_cmd_mmap = !strcmp(bname + 1, cmd);
+ if (!found_libc_mmap)
+ found_libc_mmap = !strncmp(bname + 1, "libc", 4);
+ if (!found_ld_mmap)
+ found_ld_mmap = !strncmp(bname + 1, "ld", 2);
+ } else if (!found_vdso_mmap)
+ found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]");
+ break;
+
+ case PERF_RECORD_SAMPLE:
+ /* Just ignore samples for now */
+ break;
+ default:
+ pr_debug("Unexpected perf_event->header.type %d!\n",
+ type);
+ ++errs;
+ }
+ }
+ }
+
+ /*
+ * We don't use poll here because at least at 3.1 times the
+ * PERF_RECORD_{!SAMPLE} events don't honour
+ * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
+ */
+ if (total_events == before && false)
+ poll(evlist->pollfd, evlist->nr_fds, -1);
+
+ sleep(1);
+ if (++wakeups > 5) {
+ pr_debug("No PERF_RECORD_EXIT event!\n");
+ break;
+ }
+ }
+
+found_exit:
+ if (nr_events[PERF_RECORD_COMM] > 1) {
+ pr_debug("Excessive number of PERF_RECORD_COMM events!\n");
+ ++errs;
+ }
+
+ if (nr_events[PERF_RECORD_COMM] == 0) {
+ pr_debug("Missing PERF_RECORD_COMM for %s!\n", cmd);
+ ++errs;
+ }
+
+ if (!found_cmd_mmap) {
+ pr_debug("PERF_RECORD_MMAP for %s missing!\n", cmd);
+ ++errs;
+ }
+
+ if (!found_libc_mmap) {
+ pr_debug("PERF_RECORD_MMAP for %s missing!\n", "libc");
+ ++errs;
+ }
+
+ if (!found_ld_mmap) {
+ pr_debug("PERF_RECORD_MMAP for %s missing!\n", "ld");
+ ++errs;
+ }
+
+ if (!found_vdso_mmap) {
+ pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
+ ++errs;
+ }
+out_err:
+ perf_evlist__munmap(evlist);
+out_delete_evlist:
+ perf_evlist__delete(evlist);
+out:
+ return (err < 0 || errs > 0) ? -1 : 0;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 1a925dd..374b039 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -6,6 +6,7 @@ int test__vmlinux_matches_kallsyms(void);
int test__open_syscall_event(void);
int test__open_syscall_event_on_all_cpus(void);
int test__basic_mmap(void);
+int test__PERF_RECORD(void);
/* Util */
int trace_event__id(const char *evname);
--
1.7.9.2.358.g22243
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/