linux/tools/perf/builtin-record.c

1201 lines
31 KiB
C
Raw Normal View History

/*
* builtin-record.c
*
* Builtin record command: Record the profile of a workload
* (or a CPU, or a PID) into the perf.data output file - for
* later analysis via perf report.
*/
#include "builtin.h"
#include "perf.h"
#include "util/build-id.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/callchain.h"
#include "util/cgroup.h"
#include "util/header.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/session.h"
#include "util/tool.h"
perf symbols: Use the buildids if present With this change 'perf record' will intercept PERF_RECORD_MMAP calls, creating a linked list of DSOs, then when the session finishes, it will traverse this list and read the buildids, stashing them at the end of the file and will set up a new feature bit in the header bitmask. 'perf report' will then notice this feature and populate the 'dsos' list and set the build ids. When reading the symtabs it will refuse to load from a file that doesn't have the same build id. This improves the reliability of the profiler output, as symbols and profiling data is more guaranteed to match. Example: [root@doppio ~]# perf report | head /home/acme/bin/perf with build id b1ea544ac3746e7538972548a09aadecc5753868 not found, continuing without symbols # Samples: 2621434559 # # Overhead Command Shared Object Symbol # ........ ............... ............................. ...... # 7.91% init [kernel] [k] read_hpet 7.64% init [kernel] [k] mwait_idle_with_hints 7.60% swapper [kernel] [k] read_hpet 7.60% swapper [kernel] [k] mwait_idle_with_hints 3.65% init [kernel] [k] 0xffffffffa02339d9 [root@doppio ~]# In this case the 'perf' binary was an older one, vanished, so its symbols probably wouldn't match or would cause subtly different (and misleading) output. Next patches will support the kernel as well, reading the build id notes for it and the modules from /sys. Another patch should also introduce a new plumbing command: 'perf list-buildids' that will then be used in porcelain that is distro specific to fetch -debuginfo packages where such buildids are present. This will in turn allow for one to run 'perf record' in one machine and 'perf report' in another. Future work on having the buildid sent directly from the kernel in the PERF_RECORD_MMAP event is needed to close races, as the DSO can be changed during a 'perf record' session, but this patch at least helps with non-corner cases and current/older kernels. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: K. Prasad <prasad@linux.vnet.ibm.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roland McGrath <roland@redhat.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1257367843-26224-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-05 04:50:43 +08:00
#include "util/symbol.h"
perf tools: Fix sparse CPU numbering related bugs At present, the perf subcommands that do system-wide monitoring (perf stat, perf record and perf top) don't work properly unless the online cpus are numbered 0, 1, ..., N-1. These tools ask for the number of online cpus with sysconf(_SC_NPROCESSORS_ONLN) and then try to create events for cpus 0, 1, ..., N-1. This creates problems for systems where the online cpus are numbered sparsely. For example, a POWER6 system in single-threaded mode (i.e. only running 1 hardware thread per core) will have only even-numbered cpus online. This fixes the problem by reading the /sys/devices/system/cpu/online file to find out which cpus are online. The code that does that is in tools/perf/util/cpumap.[ch], and consists of a read_cpu_map() function that sets up a cpumap[] array and returns the number of online cpus. If /sys/devices/system/cpu/online can't be read or can't be parsed successfully, it falls back to using sysconf to ask how many cpus are online and sets up an identity map in cpumap[]. The perf record, perf stat and perf top code then calls read_cpu_map() in the system-wide monitoring case (instead of sysconf) and uses cpumap[] to get the cpu numbers to pass to perf_event_open. Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> LKML-Reference: <20100310093609.GA3959@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 17:36:09 +08:00
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/data.h"
#include "util/auxtrace.h"
#include "util/parse-branch-options.h"
#include <unistd.h>
#include <sched.h>
#include <sys/mman.h>
struct record {
struct perf_tool tool;
struct record_opts opts;
u64 bytes_written;
struct perf_data_file file;
struct auxtrace_record *itr;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
int realtime_prio;
bool no_buildid;
bool no_buildid_cache;
long samples;
};
static int record__write(struct record *rec, void *bf, size_t size)
{
if (perf_data_file__write(rec->session->file, bf, size) < 0) {
pr_err("failed to write perf data, error: %m\n");
return -1;
}
rec->bytes_written += size;
return 0;
}
static int process_synthesized_event(struct perf_tool *tool,
union perf_event *event,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct record *rec = container_of(tool, struct record, tool);
return record__write(rec, event, event->header.size);
}
static int record__mmap_read(struct record *rec, int idx)
{
struct perf_mmap *md = &rec->evlist->mmap[idx];
u64 head = perf_mmap__read_head(md);
u64 old = md->prev;
unsigned char *data = md->base + page_size;
unsigned long size;
void *buf;
int rc = 0;
if (old == head)
return 0;
rec->samples++;
size = head - old;
if ((old & md->mask) + size != (head & md->mask)) {
buf = &data[old & md->mask];
size = md->mask + 1 - (old & md->mask);
old += size;
if (record__write(rec, buf, size) < 0) {
rc = -1;
goto out;
}
}
buf = &data[old & md->mask];
size = head - old;
old += size;
if (record__write(rec, buf, size) < 0) {
rc = -1;
goto out;
}
md->prev = old;
perf_evlist__mmap_consume(rec->evlist, idx);
out:
return rc;
}
static volatile int done;
static volatile int signr = -1;
static volatile int child_finished;
static volatile int auxtrace_snapshot_enabled;
static volatile int auxtrace_snapshot_err;
static volatile int auxtrace_record__snapshot_started;
static void sig_handler(int sig)
{
if (sig == SIGCHLD)
child_finished = 1;
else
signr = sig;
done = 1;
}
static void record__sig_exit(void)
{
if (signr == -1)
return;
signal(signr, SIG_DFL);
raise(signr);
}
#ifdef HAVE_AUXTRACE_SUPPORT
static int record__process_auxtrace(struct perf_tool *tool,
union perf_event *event, void *data1,
size_t len1, void *data2, size_t len2)
{
struct record *rec = container_of(tool, struct record, tool);
struct perf_data_file *file = &rec->file;
size_t padding;
u8 pad[8] = {0};
if (!perf_data_file__is_pipe(file)) {
off_t file_offset;
int fd = perf_data_file__fd(file);
int err;
file_offset = lseek(fd, 0, SEEK_CUR);
if (file_offset == -1)
return -1;
err = auxtrace_index__auxtrace_event(&rec->session->auxtrace_index,
event, file_offset);
if (err)
return err;
}
/* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
padding = (len1 + len2) & 7;
if (padding)
padding = 8 - padding;
record__write(rec, event, event->header.size);
record__write(rec, data1, len1);
if (len2)
record__write(rec, data2, len2);
record__write(rec, &pad, padding);
return 0;
}
static int record__auxtrace_mmap_read(struct record *rec,
struct auxtrace_mmap *mm)
{
int ret;
ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
record__process_auxtrace);
if (ret < 0)
return ret;
if (ret)
rec->samples++;
return 0;
}
static int record__auxtrace_mmap_read_snapshot(struct record *rec,
struct auxtrace_mmap *mm)
{
int ret;
ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
record__process_auxtrace,
rec->opts.auxtrace_snapshot_size);
if (ret < 0)
return ret;
if (ret)
rec->samples++;
return 0;
}
static int record__auxtrace_read_snapshot_all(struct record *rec)
{
int i;
int rc = 0;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
struct auxtrace_mmap *mm =
&rec->evlist->mmap[i].auxtrace_mmap;
if (!mm->base)
continue;
if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
rc = -1;
goto out;
}
}
out:
return rc;
}
static void record__read_auxtrace_snapshot(struct record *rec)
{
pr_debug("Recording AUX area tracing snapshot\n");
if (record__auxtrace_read_snapshot_all(rec) < 0) {
auxtrace_snapshot_err = -1;
} else {
auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr);
if (!auxtrace_snapshot_err)
auxtrace_snapshot_enabled = 1;
}
}
#else
static inline
int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
struct auxtrace_mmap *mm __maybe_unused)
{
return 0;
}
static inline
void record__read_auxtrace_snapshot(struct record *rec __maybe_unused)
{
}
static inline
int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
{
return 0;
}
#endif
static int record__open(struct record *rec)
{
char msg[512];
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 18:22:36 +08:00
struct perf_evsel *pos;
struct perf_evlist *evlist = rec->evlist;
struct perf_session *session = rec->session;
struct record_opts *opts = &rec->opts;
int rc = 0;
perf_evlist__config(evlist, opts);
evlist__for_each(evlist, pos) {
try_again:
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 18:22:36 +08:00
if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
if (verbose)
ui__warning("%s\n", msg);
goto try_again;
}
rc = -errno;
perf_evsel__open_strerror(pos, &opts->target,
errno, msg, sizeof(msg));
ui__error("%s\n", msg);
goto out;
}
}
if (perf_evlist__apply_filters(evlist, &pos)) {
error("failed to set filter \"%s\" on event %s with %d (%s)\n",
pos->filter, perf_evsel__name(pos), errno,
strerror_r(errno, msg, sizeof(msg)));
rc = -1;
goto out;
}
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
opts->auxtrace_mmap_pages,
opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
"/proc/sys/kernel/perf_event_mlock_kb,\n"
"or try again with a smaller value of -m/--mmap_pages.\n"
"(current value: %u,%u)\n",
opts->mmap_pages, opts->auxtrace_mmap_pages);
rc = -errno;
} else {
pr_err("failed to mmap with %d (%s)\n", errno,
strerror_r(errno, msg, sizeof(msg)));
rc = -errno;
}
goto out;
}
session->evlist = evlist;
perf_session__set_id_hdr_size(session);
out:
return rc;
}
perf record: Show precise number of samples After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value. However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples. $ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ] $ perf report --stdio -n # To display the perf.data header info, please use --header/--header-only options. # # Samples: 3K of event 'cycles' # Event count (approx.): 3771330663 # # Overhead Samples Command Shared Object Symbol # ........ ............ ....... ................ .......................... # 99.90% 3982 noploop noploop [.] main 0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions 0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages 0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all Reported-by: Milian Wolff <mail@milianw.de> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1422518843-25818-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-29 16:06:44 +08:00
static int process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
struct record *rec = container_of(tool, struct record, tool);
rec->samples++;
return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
}
static int process_buildids(struct record *rec)
{
struct perf_data_file *file = &rec->file;
struct perf_session *session = rec->session;
if (file->size == 0)
return 0;
perf record: Do not save pathname in ./debug/.build-id directory for vmlinux When perf record finishes a session, it pre-processes samples in order to write build-id info from DSOs that had samples. During this process it'll call map__load() for the kernel map, and it ends up calling dso__load_vmlinux_path() which replaces dso->long_name. But this function checks kernel's build-id before searching vmlinux path so it'll end up with a cryptic name, the pathname for the entry in the ~/.debug cache, which can be confusing to users. This patch adds a flag to skip the build-id check during record, so that it'll have the original vmlinux path for the kernel dso->long_name, not the entry in the ~/.debug cache. Before: # perf record -va sleep 3 mmap size 528384B [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.196 MB perf.data (~8545 samples) ] Looking at the vmlinux_path (7 entries long) Using /home/namhyung/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551 for symbols After: # perf record -va sleep 3 mmap size 528384B [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.193 MB perf.data (~8432 samples) ] Looking at the vmlinux_path (7 entries long) Using /lib/modules/3.16.4-1-ARCH/build/vmlinux for symbols Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1415063674-17206-7-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-11-04 09:14:32 +08:00
/*
* During this process, it'll load kernel map and replace the
* dso->long_name to a real pathname it found. In this case
* we prefer the vmlinux path like
* /lib/modules/3.16.4/build/vmlinux
*
* rather than build-id path (in debug directory).
* $HOME/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551
*/
symbol_conf.ignore_vmlinux_buildid = true;
return perf_session__process_events(session);
}
static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
{
int err;
struct perf_tool *tool = data;
/*
*As for guest kernel when processing subcommand record&report,
*we arrange module mmap prior to guest kernel mmap and trigger
*a preload dso because default guest module symbols are loaded
*from guest kallsyms instead of /lib/modules/XXX/XXX. This
*method is used to avoid symbol missing when the first addr is
*in module instead of in guest kernel.
*/
err = perf_event__synthesize_modules(tool, process_synthesized_event,
machine);
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
/*
* We use _stext for guest kernel because guest kernel's /proc/kallsyms
* have no _text sometimes.
*/
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine);
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
}
static struct perf_event_header finished_round_event = {
.size = sizeof(struct perf_event_header),
.type = PERF_RECORD_FINISHED_ROUND,
};
static int record__mmap_read_all(struct record *rec)
{
u64 bytes_written = rec->bytes_written;
int i;
int rc = 0;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
if (rec->evlist->mmap[i].base) {
if (record__mmap_read(rec, i) != 0) {
rc = -1;
goto out;
}
}
if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
record__auxtrace_mmap_read(rec, mm) != 0) {
rc = -1;
goto out;
}
}
/*
* Mark the round finished in case we wrote
* at least one event.
*/
if (bytes_written != rec->bytes_written)
rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
out:
return rc;
}
static void record__init_features(struct record *rec)
{
struct perf_session *session = rec->session;
int feat;
for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
perf_header__set_feat(&session->header, feat);
if (rec->no_buildid)
perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
if (!have_tracepoints(&rec->evlist->entries))
perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
if (!rec->opts.branch_stack)
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
if (!rec->opts.full_auxtrace)
perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
}
static volatile int workload_exec_errno;
/*
* perf_evlist__prepare_workload will send a SIGUSR1
* if the fork fails, since we asked by setting its
* want_signal to true.
*/
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
static void workload_exec_failed_signal(int signo __maybe_unused,
siginfo_t *info,
void *ucontext __maybe_unused)
{
workload_exec_errno = info->si_value.sival_int;
done = 1;
child_finished = 1;
}
static void snapshot_sig_handler(int sig);
static int __cmd_record(struct record *rec, int argc, const char **argv)
{
int err;
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
int status = 0;
unsigned long waking = 0;
const bool forks = argc > 0;
struct machine *machine;
struct perf_tool *tool = &rec->tool;
struct record_opts *opts = &rec->opts;
struct perf_data_file *file = &rec->file;
struct perf_session *session;
bool disabled = false, draining = false;
int fd;
rec->progname = argv[0];
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
atexit(record__sig_exit);
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGTERM, sig_handler);
if (rec->opts.auxtrace_snapshot_mode)
signal(SIGUSR2, snapshot_sig_handler);
else
signal(SIGUSR2, SIG_IGN);
session = perf_session__new(file, false, tool);
if (session == NULL) {
pr_err("Perf session creation failed.\n");
return -1;
}
fd = perf_data_file__fd(file);
rec->session = session;
record__init_features(rec);
if (forks) {
err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
argv, file->is_pipe,
workload_exec_failed_signal);
if (err < 0) {
pr_err("Couldn't run the workload!\n");
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
status = err;
goto out_delete_session;
}
}
if (record__open(rec) != 0) {
err = -1;
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
}
if (!rec->evlist->nr_groups)
perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
if (file->is_pipe) {
err = perf_header__write_pipe(fd);
if (err < 0)
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
} else {
err = perf_session__write_header(session, rec->evlist, fd, false);
if (err < 0)
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
perf tools: Handle relocatable kernels DSOs don't have this problem because the kernel emits a PERF_MMAP for each new executable mapping it performs on monitored threads. To fix the kernel case we simulate the same behaviour, by having 'perf record' to synthesize a PERF_MMAP for the kernel, encoded like this: [root@doppio ~]# perf record -a -f sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.344 MB perf.data (~15038 samples) ] [root@doppio ~]# perf report -D | head -10 0xd0 [0x40]: event: 1 . . ... raw event: size 64 bytes . 0000: 01 00 00 00 00 00 40 00 00 00 00 00 00 00 00 00 ......@........ . 0010: 00 00 00 81 ff ff ff ff 00 00 00 00 00 00 00 00 ............... . 0020: 00 00 00 00 00 00 00 00 5b 6b 65 72 6e 65 6c 2e ........ [kernel . 0030: 6b 61 6c 6c 73 79 6d 73 2e 5f 74 65 78 74 5d 00 kallsyms._text] . 0xd0 [0x40]: PERF_RECORD_MMAP 0/0: [0xffffffff81000000((nil)) @ (nil)]: [kernel.kallsyms._text] I.e. we identify such event as having: .pid = 0 .filename = [kernel.kallsyms.REFNAME] .start = REFNAME addr in /proc/kallsyms at 'perf record' time and use now a hardcoded value of '.text' for REFNAME. Then, later, in 'perf report', if there are any kernel hits and thus we need to resolve kernel symbols, we search for REFNAME and if its address changed, relocation happened and we thus must change the kernel mapping routines to one that uses .pgoff as the relocation to apply. This way we use the same mechanism used for the other DSOs and don't have to do a two pass in all the kernel symbols. Reported-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> LKML-Reference: <1262717431-1246-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 02:50:31 +08:00
}
if (!rec->no_buildid
&& !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
pr_err("Couldn't generate buildids. "
"Use --no-buildid to profile anyway.\n");
err = -1;
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
}
machine = &session->machines.host;
if (file->is_pipe) {
err = perf_event__synthesize_attrs(tool, session,
process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
}
if (have_tracepoints(&rec->evlist->entries)) {
/*
* FIXME err <= 0 here actually means that
* there were no tracepoints so its not really
* an error, just that we don't need to
* synthesize anything. We really have to
* return this more properly and also
* propagate errors that now are calling die()
*/
err = perf_event__synthesize_tracing_data(tool, fd, rec->evlist,
process_synthesized_event);
if (err <= 0) {
pr_err("Couldn't record tracing data.\n");
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
}
rec->bytes_written += err;
}
}
if (rec->opts.full_auxtrace) {
err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
session, process_synthesized_event);
if (err)
goto out_delete_session;
}
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine);
perf record: Handle restrictive permissions in /proc/{kallsyms,modules} The 59365d1 commit, even being reverted by 33e0d57, showed a non robust behavior in 'perf record': it really should just warn the user that some functionality will not be available. The new behavior then becomes: [acme@felicio linux]$ ls -la /proc/{kallsyms,modules} -r-------- 1 root root 0 Nov 22 12:19 /proc/kallsyms -r-------- 1 root root 0 Nov 22 12:19 /proc/modules [acme@felicio linux]$ perf record ls -R > /dev/null Couldn't record kernel reference relocation symbol Symbol resolution may be skewed if relocation was used (e.g. kexec). Check /proc/kallsyms permission or run as root. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.004 MB perf.data (~161 samples) ] [acme@felicio linux]$ perf report --stdio [kernel.kallsyms] with build id 77b05e00e64e4de1c9347d83879779b540d69f00 not found, continuing without symbols # Events: 98 cycles # # Overhead Command Shared Object Symbol # ........ ....... ............... .................... # 48.26% ls [kernel] [k] ffffffff8102b92b 22.49% ls libc-2.12.90.so [.] __strlen_sse2 8.35% ls libc-2.12.90.so [.] __GI___strcoll_l 8.17% ls ls [.] 11580 3.35% ls libc-2.12.90.so [.] _IO_new_file_xsputn 3.33% ls libc-2.12.90.so [.] _int_malloc 1.88% ls libc-2.12.90.so [.] _int_free 0.84% ls libc-2.12.90.so [.] malloc_consolidate 0.84% ls libc-2.12.90.so [.] __readdir64 0.83% ls ls [.] strlen@plt 0.83% ls libc-2.12.90.so [.] __GI_fwrite_unlocked 0.83% ls libc-2.12.90.so [.] __memcpy_sse2 # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@felicio linux]$ It still has the build-ids for DSOs in the maps with hits: [acme@felicio linux]$ perf buildid-list 77b05e00e64e4de1c9347d83879779b540d69f00 [kernel.kallsyms] 09c4a431a4a8b648fcfc2c2bdda70f56050ddff1 /bin/ls af75ea9ad951d25e0f038901a11b3846dccb29a4 /lib64/libc-2.12.90.so [acme@felicio linux]$ That can be used in another machine to resolve kernel symbols. Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jesper Juhl <jj@chaosbits.net> Cc: Marcus Meissner <meissner@suse.de> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-23 00:01:55 +08:00
if (err < 0)
pr_err("Couldn't record kernel reference relocation symbol\n"
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
"Check /proc/kallsyms permission or run as root.\n");
err = perf_event__synthesize_modules(tool, process_synthesized_event,
machine);
perf record: Handle restrictive permissions in /proc/{kallsyms,modules} The 59365d1 commit, even being reverted by 33e0d57, showed a non robust behavior in 'perf record': it really should just warn the user that some functionality will not be available. The new behavior then becomes: [acme@felicio linux]$ ls -la /proc/{kallsyms,modules} -r-------- 1 root root 0 Nov 22 12:19 /proc/kallsyms -r-------- 1 root root 0 Nov 22 12:19 /proc/modules [acme@felicio linux]$ perf record ls -R > /dev/null Couldn't record kernel reference relocation symbol Symbol resolution may be skewed if relocation was used (e.g. kexec). Check /proc/kallsyms permission or run as root. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.004 MB perf.data (~161 samples) ] [acme@felicio linux]$ perf report --stdio [kernel.kallsyms] with build id 77b05e00e64e4de1c9347d83879779b540d69f00 not found, continuing without symbols # Events: 98 cycles # # Overhead Command Shared Object Symbol # ........ ....... ............... .................... # 48.26% ls [kernel] [k] ffffffff8102b92b 22.49% ls libc-2.12.90.so [.] __strlen_sse2 8.35% ls libc-2.12.90.so [.] __GI___strcoll_l 8.17% ls ls [.] 11580 3.35% ls libc-2.12.90.so [.] _IO_new_file_xsputn 3.33% ls libc-2.12.90.so [.] _int_malloc 1.88% ls libc-2.12.90.so [.] _int_free 0.84% ls libc-2.12.90.so [.] malloc_consolidate 0.84% ls libc-2.12.90.so [.] __readdir64 0.83% ls ls [.] strlen@plt 0.83% ls libc-2.12.90.so [.] __GI_fwrite_unlocked 0.83% ls libc-2.12.90.so [.] __memcpy_sse2 # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@felicio linux]$ It still has the build-ids for DSOs in the maps with hits: [acme@felicio linux]$ perf buildid-list 77b05e00e64e4de1c9347d83879779b540d69f00 [kernel.kallsyms] 09c4a431a4a8b648fcfc2c2bdda70f56050ddff1 /bin/ls af75ea9ad951d25e0f038901a11b3846dccb29a4 /lib64/libc-2.12.90.so [acme@felicio linux]$ That can be used in another machine to resolve kernel symbols. Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jesper Juhl <jj@chaosbits.net> Cc: Marcus Meissner <meissner@suse.de> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-23 00:01:55 +08:00
if (err < 0)
pr_err("Couldn't record kernel module information.\n"
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
"Check /proc/modules permission or run as root.\n");
if (perf_guest) {
machines__process_guests(&session->machines,
perf_event__synthesize_guest_os, tool);
}
err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
process_synthesized_event, opts->sample_address,
opts->proc_map_timeout);
if (err != 0)
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
if (rec->realtime_prio) {
struct sched_param param;
param.sched_priority = rec->realtime_prio;
if (sched_setscheduler(0, SCHED_FIFO, &param)) {
pr_err("Could not set realtime priority.\n");
err = -1;
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
}
}
perf tools: Fix 'disabled' attribute config for record command Currently the record command sets all events initially as disabled. There's non conditional perf_evlist__enable call, that enables all events before we exec tracee program. That actually screws whole enable_on_exec logic, because the event is enabled before the traced program got executed. What we actually want is: 1) For any type of traced program: - all independent events and group leaders are disabled - all group members are enabled Group members are ruled by group leaders. They need to be enabled, because the group scheduling relies on that. 2) For traced programs executed by perf: - all independent events and group leaders have enable_on_exec set - we don't specifically enable or disable any event during the record command Independent events and group leaders are initially disabled and get enabled by exec. Group members are ruled by group leaders as stated in 1). 3) For traced programs attached by perf (pid/tid): - we specifically enable or disable all events during the record command When attaching events to already running traced we enable/disable events specifically, as there's no initial traced exec call. Fixing appropriate perf_event_attr test case to cover this change. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1352741644-16809-3-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-11-13 01:34:01 +08:00
/*
* When perf is starting the traced process, all the events
* (apart from group members) have enable_on_exec=1 set,
* so don't spoil it by prematurely enabling them.
*/
if (!target__none(&opts->target) && !opts->initial_delay)
perf_evlist__enable(rec->evlist);
/*
* Let the child rip
*/
if (forks)
perf_evlist__start_workload(rec->evlist);
if (opts->initial_delay) {
usleep(opts->initial_delay * 1000);
perf_evlist__enable(rec->evlist);
}
auxtrace_snapshot_enabled = 1;
for (;;) {
int hits = rec->samples;
if (record__mmap_read_all(rec) < 0) {
auxtrace_snapshot_enabled = 0;
err = -1;
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
}
if (auxtrace_record__snapshot_started) {
auxtrace_record__snapshot_started = 0;
if (!auxtrace_snapshot_err)
record__read_auxtrace_snapshot(rec);
if (auxtrace_snapshot_err) {
pr_err("AUX area tracing snapshot failed\n");
err = -1;
goto out_child;
}
}
if (hits == rec->samples) {
if (done || draining)
break;
err = perf_evlist__poll(rec->evlist, -1);
/*
* Propagate error, only if there's any. Ignore positive
* number of returned events and interrupt error.
*/
if (err > 0 || (err < 0 && errno == EINTR))
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
err = 0;
waking++;
if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
draining = true;
}
perf tools: Fix 'disabled' attribute config for record command Currently the record command sets all events initially as disabled. There's non conditional perf_evlist__enable call, that enables all events before we exec tracee program. That actually screws whole enable_on_exec logic, because the event is enabled before the traced program got executed. What we actually want is: 1) For any type of traced program: - all independent events and group leaders are disabled - all group members are enabled Group members are ruled by group leaders. They need to be enabled, because the group scheduling relies on that. 2) For traced programs executed by perf: - all independent events and group leaders have enable_on_exec set - we don't specifically enable or disable any event during the record command Independent events and group leaders are initially disabled and get enabled by exec. Group members are ruled by group leaders as stated in 1). 3) For traced programs attached by perf (pid/tid): - we specifically enable or disable all events during the record command When attaching events to already running traced we enable/disable events specifically, as there's no initial traced exec call. Fixing appropriate perf_event_attr test case to cover this change. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1352741644-16809-3-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-11-13 01:34:01 +08:00
/*
* When perf is starting the traced process, at the end events
* die with the process and we wait for that. Thus no need to
* disable events in this case.
*/
if (done && !disabled && !target__none(&opts->target)) {
auxtrace_snapshot_enabled = 0;
perf_evlist__disable(rec->evlist);
disabled = true;
}
}
auxtrace_snapshot_enabled = 0;
if (forks && workload_exec_errno) {
char msg[STRERR_BUFSIZE];
const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
pr_err("Workload failed: %s\n", emsg);
err = -1;
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
goto out_child;
}
perf record: Show precise number of samples After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value. However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples. $ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ] $ perf report --stdio -n # To display the perf.data header info, please use --header/--header-only options. # # Samples: 3K of event 'cycles' # Event count (approx.): 3771330663 # # Overhead Samples Command Shared Object Symbol # ........ ............ ....... ................ .......................... # 99.90% 3982 noploop noploop [.] main 0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions 0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages 0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all Reported-by: Milian Wolff <mail@milianw.de> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1422518843-25818-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-29 16:06:44 +08:00
if (!quiet)
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
out_child:
if (forks) {
int exit_status;
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
if (!child_finished)
kill(rec->evlist->workload.pid, SIGTERM);
wait(&exit_status);
if (err < 0)
status = err;
else if (WIFEXITED(exit_status))
status = WEXITSTATUS(exit_status);
else if (WIFSIGNALED(exit_status))
signr = WTERMSIG(exit_status);
} else
status = err;
perf record: Show precise number of samples After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value. However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples. $ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ] $ perf report --stdio -n # To display the perf.data header info, please use --header/--header-only options. # # Samples: 3K of event 'cycles' # Event count (approx.): 3771330663 # # Overhead Samples Command Shared Object Symbol # ........ ............ ....... ................ .......................... # 99.90% 3982 noploop noploop [.] main 0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions 0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages 0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all Reported-by: Milian Wolff <mail@milianw.de> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1422518843-25818-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-29 16:06:44 +08:00
/* this will be recalculated during process_buildids() */
rec->samples = 0;
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
if (!err && !file->is_pipe) {
rec->session->header.data_size += rec->bytes_written;
file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
if (!rec->no_buildid) {
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
process_buildids(rec);
/*
* We take all buildids when the file contains
* AUX area tracing data because we do not decode the
* trace because it would take too long.
*/
if (rec->opts.full_auxtrace)
dsos__hit_all(rec->session);
}
perf_session__write_header(rec->session, rec->evlist, fd, true);
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
}
perf record: Show precise number of samples After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value. However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples. $ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ] $ perf report --stdio -n # To display the perf.data header info, please use --header/--header-only options. # # Samples: 3K of event 'cycles' # Event count (approx.): 3771330663 # # Overhead Samples Command Shared Object Symbol # ........ ............ ....... ................ .......................... # 99.90% 3982 noploop noploop [.] main 0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions 0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages 0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all Reported-by: Milian Wolff <mail@milianw.de> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1422518843-25818-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-29 16:06:44 +08:00
if (!err && !quiet) {
char samples[128];
if (rec->samples && !rec->opts.full_auxtrace)
perf record: Show precise number of samples After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value. However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples. $ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ] $ perf report --stdio -n # To display the perf.data header info, please use --header/--header-only options. # # Samples: 3K of event 'cycles' # Event count (approx.): 3771330663 # # Overhead Samples Command Shared Object Symbol # ........ ............ ....... ................ .......................... # 99.90% 3982 noploop noploop [.] main 0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions 0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages 0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all Reported-by: Milian Wolff <mail@milianw.de> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1422518843-25818-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-29 16:06:44 +08:00
scnprintf(samples, sizeof(samples),
" (%" PRIu64 " samples)", rec->samples);
else
samples[0] = '\0';
fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s ]\n",
perf_data_file__size(file) / 1024.0 / 1024.0,
file->path, samples);
}
out_delete_session:
perf_session__delete(session);
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
return status;
}
static void callchain_debug(void)
{
perf tools: Enable LBR call stack support Currently, there are two call chain recording options, fp and dwarf. Haswell has a new feature that utilizes the existing LBR facility to record call chains. Kernel side LBR support code provides this as a third option to record call chains. This patch enables the lbr call stack support on the tooling side. LBR call stack has some limitations: - It reuses current LBR facility, so LBR call stack and branch record can not be enabled at the same time. - It is only available for user-space callchains. However, it also offers some advantages: - LBR call stack can work on user apps which don't have frame-pointers or dwarf debug info compiled. It is a good alternative when nothing else works. Tested-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Cody P Schafer <cody@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Jacob Shin <jacob.w.shin@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masanari Iida <standby24x7@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Rodrigo Campos <rodrigo@sdfg.com.ar> Cc: Stephane Eranian <eranian@google.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1420482185-29830-2-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-06 02:23:04 +08:00
static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" };
pr_debug("callchain: type %s\n", str[callchain_param.record_mode]);
perf tools: Support for DWARF mode callchain This patch enables perf to use the DWARF unwind code. It extends the perf record '-g' option with following arguments: 'fp' - provides framepointer based user stack backtrace 'dwarf[,size]' - provides DWARF (libunwind) based user stack backtrace. The size specifies the size of the user stack dump. If omitted it is 8192 by default. If libunwind is found during the perf build, then the 'dwarf' argument becomes available for record command. The 'fp' stays as default option in any case. Examples: (perf compiled with libunwind) perf record -g dwarf ls - provides dwarf unwind with 8192 as stack dump size perf record -g dwarf,4096 ls - provides dwarf unwind with 4096 as stack dump size perf record -g -- ls perf record -g fp ls - provides frame pointer unwind Signed-off-by: Jiri Olsa <jolsa@redhat.com> Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1344345647-11536-13-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-07 21:20:47 +08:00
if (callchain_param.record_mode == CALLCHAIN_DWARF)
pr_debug("callchain: stack dump size %d\n",
callchain_param.dump_size);
}
int record_parse_callchain_opt(const struct option *opt,
const char *arg,
int unset)
{
int ret;
struct record_opts *record = (struct record_opts *)opt->value;
record->callgraph_set = true;
callchain_param.enabled = !unset;
/* --no-call-graph */
if (unset) {
callchain_param.record_mode = CALLCHAIN_NONE;
pr_debug("callchain: disabled\n");
return 0;
}
ret = parse_callchain_record_opt(arg);
perf tools: Support for DWARF mode callchain This patch enables perf to use the DWARF unwind code. It extends the perf record '-g' option with following arguments: 'fp' - provides framepointer based user stack backtrace 'dwarf[,size]' - provides DWARF (libunwind) based user stack backtrace. The size specifies the size of the user stack dump. If omitted it is 8192 by default. If libunwind is found during the perf build, then the 'dwarf' argument becomes available for record command. The 'fp' stays as default option in any case. Examples: (perf compiled with libunwind) perf record -g dwarf ls - provides dwarf unwind with 8192 as stack dump size perf record -g dwarf,4096 ls - provides dwarf unwind with 4096 as stack dump size perf record -g -- ls perf record -g fp ls - provides frame pointer unwind Signed-off-by: Jiri Olsa <jolsa@redhat.com> Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1344345647-11536-13-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-07 21:20:47 +08:00
if (!ret)
callchain_debug();
perf tools: Support for DWARF mode callchain This patch enables perf to use the DWARF unwind code. It extends the perf record '-g' option with following arguments: 'fp' - provides framepointer based user stack backtrace 'dwarf[,size]' - provides DWARF (libunwind) based user stack backtrace. The size specifies the size of the user stack dump. If omitted it is 8192 by default. If libunwind is found during the perf build, then the 'dwarf' argument becomes available for record command. The 'fp' stays as default option in any case. Examples: (perf compiled with libunwind) perf record -g dwarf ls - provides dwarf unwind with 8192 as stack dump size perf record -g dwarf,4096 ls - provides dwarf unwind with 4096 as stack dump size perf record -g -- ls perf record -g fp ls - provides frame pointer unwind Signed-off-by: Jiri Olsa <jolsa@redhat.com> Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1344345647-11536-13-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-07 21:20:47 +08:00
return ret;
}
int record_callchain_opt(const struct option *opt,
const char *arg __maybe_unused,
int unset __maybe_unused)
{
struct record_opts *record = (struct record_opts *)opt->value;
record->callgraph_set = true;
callchain_param.enabled = true;
if (callchain_param.record_mode == CALLCHAIN_NONE)
callchain_param.record_mode = CALLCHAIN_FP;
callchain_debug();
return 0;
}
static int perf_record_config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "record.call-graph"))
var = "call-graph.record-mode"; /* fall-through */
return perf_default_config(var, value, cb);
}
struct clockid_map {
const char *name;
int clockid;
};
#define CLOCKID_MAP(n, c) \
{ .name = n, .clockid = (c), }
#define CLOCKID_END { .name = NULL, }
/*
* Add the missing ones, we need to build on many distros...
*/
#ifndef CLOCK_MONOTONIC_RAW
#define CLOCK_MONOTONIC_RAW 4
#endif
#ifndef CLOCK_BOOTTIME
#define CLOCK_BOOTTIME 7
#endif
#ifndef CLOCK_TAI
#define CLOCK_TAI 11
#endif
static const struct clockid_map clockids[] = {
/* available for all events, NMI safe */
CLOCKID_MAP("monotonic", CLOCK_MONOTONIC),
CLOCKID_MAP("monotonic_raw", CLOCK_MONOTONIC_RAW),
/* available for some events */
CLOCKID_MAP("realtime", CLOCK_REALTIME),
CLOCKID_MAP("boottime", CLOCK_BOOTTIME),
CLOCKID_MAP("tai", CLOCK_TAI),
/* available for the lazy */
CLOCKID_MAP("mono", CLOCK_MONOTONIC),
CLOCKID_MAP("raw", CLOCK_MONOTONIC_RAW),
CLOCKID_MAP("real", CLOCK_REALTIME),
CLOCKID_MAP("boot", CLOCK_BOOTTIME),
CLOCKID_END,
};
static int parse_clockid(const struct option *opt, const char *str, int unset)
{
struct record_opts *opts = (struct record_opts *)opt->value;
const struct clockid_map *cm;
const char *ostr = str;
if (unset) {
opts->use_clockid = 0;
return 0;
}
/* no arg passed */
if (!str)
return 0;
/* no setting it twice */
if (opts->use_clockid)
return -1;
opts->use_clockid = true;
/* if its a number, we're done */
if (sscanf(str, "%d", &opts->clockid) == 1)
return 0;
/* allow a "CLOCK_" prefix to the name */
if (!strncasecmp(str, "CLOCK_", 6))
str += 6;
for (cm = clockids; cm->name; cm++) {
if (!strcasecmp(str, cm->name)) {
opts->clockid = cm->clockid;
return 0;
}
}
opts->use_clockid = false;
ui__warning("unknown clockid %s, check man page\n", ostr);
return -1;
}
static int record__parse_mmap_pages(const struct option *opt,
const char *str,
int unset __maybe_unused)
{
struct record_opts *opts = opt->value;
char *s, *p;
unsigned int mmap_pages;
int ret;
if (!str)
return -EINVAL;
s = strdup(str);
if (!s)
return -ENOMEM;
p = strchr(s, ',');
if (p)
*p = '\0';
if (*s) {
ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
if (ret)
goto out_free;
opts->mmap_pages = mmap_pages;
}
if (!p) {
ret = 0;
goto out_free;
}
ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
if (ret)
goto out_free;
opts->auxtrace_mmap_pages = mmap_pages;
out_free:
free(s);
return ret;
}
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
NULL
};
const char * const *record_usage = __record_usage;
/*
* XXX Ideally would be local to cmd_record() and passed to a record__new
* because we need to have access to it in record__exit, that is called
* after cmd_record() exits, but since record_options need to be accessible to
* builtin-script, leave it here.
*
* At least we don't ouch it in all the other functions here directly.
*
* Just say no to tons of global variables, sigh.
*/
static struct record record = {
.opts = {
.sample_time = true,
.mmap_pages = UINT_MAX,
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.freq = 4000,
.target = {
.uses_mmap = true,
.default_per_cpu = true,
},
.proc_map_timeout = 500,
},
perf record: Show precise number of samples After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value. However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples. $ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ] $ perf report --stdio -n # To display the perf.data header info, please use --header/--header-only options. # # Samples: 3K of event 'cycles' # Event count (approx.): 3771330663 # # Overhead Samples Command Shared Object Symbol # ........ ............ ....... ................ .......................... # 99.90% 3982 noploop noploop [.] main 0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions 0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages 0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all Reported-by: Milian Wolff <mail@milianw.de> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1422518843-25818-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-29 16:06:44 +08:00
.tool = {
.sample = process_sample_event,
.fork = perf_event__process_fork,
.comm = perf_event__process_comm,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
},
};
#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
#ifdef HAVE_DWARF_UNWIND_SUPPORT
perf tools: Enable LBR call stack support Currently, there are two call chain recording options, fp and dwarf. Haswell has a new feature that utilizes the existing LBR facility to record call chains. Kernel side LBR support code provides this as a third option to record call chains. This patch enables the lbr call stack support on the tooling side. LBR call stack has some limitations: - It reuses current LBR facility, so LBR call stack and branch record can not be enabled at the same time. - It is only available for user-space callchains. However, it also offers some advantages: - LBR call stack can work on user apps which don't have frame-pointers or dwarf debug info compiled. It is a good alternative when nothing else works. Tested-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Cody P Schafer <cody@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Jacob Shin <jacob.w.shin@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masanari Iida <standby24x7@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Rodrigo Campos <rodrigo@sdfg.com.ar> Cc: Stephane Eranian <eranian@google.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1420482185-29830-2-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-06 02:23:04 +08:00
const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf lbr";
#else
perf tools: Enable LBR call stack support Currently, there are two call chain recording options, fp and dwarf. Haswell has a new feature that utilizes the existing LBR facility to record call chains. Kernel side LBR support code provides this as a third option to record call chains. This patch enables the lbr call stack support on the tooling side. LBR call stack has some limitations: - It reuses current LBR facility, so LBR call stack and branch record can not be enabled at the same time. - It is only available for user-space callchains. However, it also offers some advantages: - LBR call stack can work on user apps which don't have frame-pointers or dwarf debug info compiled. It is a good alternative when nothing else works. Tested-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Cody P Schafer <cody@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Jacob Shin <jacob.w.shin@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masanari Iida <standby24x7@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Rodrigo Campos <rodrigo@sdfg.com.ar> Cc: Stephane Eranian <eranian@google.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1420482185-29830-2-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-06 02:23:04 +08:00
const char record_callchain_help[] = CALLCHAIN_HELP "fp lbr";
#endif
/*
* XXX Will stay a global variable till we fix builtin-script.c to stop messing
* with it and switch to use the library functions in perf_evlist that came
* from builtin-record.c, i.e. use record_opts,
* perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
* using pipes, etc.
*/
struct option __record_options[] = {
OPT_CALLBACK('e', "event", &record.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
OPT_CALLBACK(0, "filter", &record.evlist, "filter",
"event filter", parse_filter),
perf record: Allow filtering perf's pid via --exclude-perf This patch allows 'perf record' to exclude events issued by perf itself by '--exclude-perf' option. Before this patch, when doing something like: # perf record -a -e syscalls:sys_enter_write <cmd> One could easily get result like this: # /tmp/perf report --stdio ... # Overhead Command Shared Object Symbol # ........ ....... .................. .................... # 99.99% perf libpthread-2.18.so [.] __write_nocancel 0.01% ls libc-2.18.so [.] write 0.01% sshd libc-2.18.so [.] write ... Where most events are generated by perf itself. A shell trick can be done to filter perf itself out: # cat << EOF > ./tmp > #!/bin/sh > exec perf record -e ... --filter="common_pid != \$\$" -a sleep 10 > EOF # chmod a+x ./tmp # ./tmp However, doing so is user unfriendly. This patch extracts evsel iteration framework introduced by patch 'perf record: Apply filter to all events in a glob matching' into foreach_evsel_in_last_glob(), and makes exclude_perf() function append new filter expression to each evsel selected by a '-e' selector. To avoid losing filters if user pass '--filter' after '--exclude-perf', this patch uses perf_evsel__append_filter() in both case, instead of perf_evsel__set_filter() which removes old filter. As a side effect, now it is possible to use multiple '--filter' option for one selector. They are combinded with '&&'. Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1436513770-8896-2-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-10 15:36:10 +08:00
OPT_CALLBACK_NOOPT(0, "exclude-perf", &record.evlist,
NULL, "don't record events from perf itself",
exclude_perf),
OPT_STRING('p', "pid", &record.opts.target.pid, "pid",
"record events on existing process id"),
OPT_STRING('t', "tid", &record.opts.target.tid, "tid",
"record events on existing thread id"),
OPT_INTEGER('r', "realtime", &record.realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
OPT_BOOLEAN(0, "no-buffering", &record.opts.no_buffering,
perf record: Add "nodelay" mode, disabled by default Sometimes there is a need to use perf in "live-log" mode. The problem is, for seldom events, actual info output is largely delayed because perf-record reads sample data in whole pages. So for such scenarious, add flag for perf-record to go in "nodelay" mode. To track e.g. what's going on in icmp_rcv while ping is running Use it with something like this: (1) $ perf probe -L icmp_rcv | grep -U8 '^ *43\>' goto error; } 38 if (!pskb_pull(skb, sizeof(*icmph))) goto error; icmph = icmp_hdr(skb); 43 ICMPMSGIN_INC_STATS_BH(net, icmph->type); /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ 50 if (icmph->type > NR_ICMP_TYPES) goto error; $ perf probe icmp_rcv:43 'type=icmph->type' (2) $ cat trace-icmp.py [...] def trace_begin(): print "in trace_begin" def trace_end(): print "in trace_end" def probe__icmp_rcv(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, __probe_ip, type): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) print "__probe_ip=%u, type=%u\n" % \ (__probe_ip, type), [...] (3) $ perf record -a -D -e probe:icmp_rcv -o - | \ perf script -i - -s trace-icmp.py Thanks to Peter Zijlstra for pointing how to do it. Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu>, Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <20110112140613.GA11698@tugrik.mns.mnsspb.ru> Signed-off-by: Kirill Smelkov <kirr@mns.spb.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-12 22:59:36 +08:00
"collect data without buffering"),
OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
"collect raw sample records from all opened counters"),
OPT_BOOLEAN('a', "all-cpus", &record.opts.target.system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
OPT_STRING('o', "output", &record.file.path, "file",
"output file name"),
OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
&record.opts.no_inherit_set,
"child tasks do not inherit counters"),
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
"number of mmap data pages and AUX area tracing mmap pages",
record__parse_mmap_pages),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
NULL, "enables call-graph recording" ,
&record_callchain_opt),
OPT_CALLBACK(0, "call-graph", &record.opts,
"mode[,dump_size]", record_callchain_help,
&record_parse_callchain_opt),
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
"per thread counts"),
OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
&record.opts.sample_time_set,
"Record the sample timestamps"),
OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
"don't sample"),
OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
"do not update the buildid cache"),
OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
"do not collect buildids in perf.data"),
OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
"monitor event in cgroup name only",
parse_cgroups),
OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
"ms to wait before starting measurement after program start"),
OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
"user to profile"),
OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
"branch any", "sample any taken branches",
parse_branch_stack),
OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
"branch filter mask", "branch stack filter modes",
parse_branch_stack),
OPT_BOOLEAN('W', "weight", &record.opts.sample_weight,
"sample by weight (on special events only)"),
OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
"sample transaction flags (special events only)"),
OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
"use per-thread mmaps"),
OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs,
"Sample machine registers on interrupt"),
OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
"Record running/enabled time of read (:S) events"),
OPT_CALLBACK('k', "clockid", &record.opts,
"clockid", "clockid to use for events, see clock_gettime()",
parse_clockid),
OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
"opts", "AUX area tracing Snapshot Mode", ""),
OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
"per thread proc mmap processing timeout in ms"),
OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
"Record context switch events"),
OPT_END()
};
struct option *record_options = __record_options;
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
{
int err;
struct record *rec = &record;
char errbuf[BUFSIZ];
rec->evlist = perf_evlist__new();
if (rec->evlist == NULL)
return -ENOMEM;
perf_config(perf_record_config, rec);
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && target__none(&rec->opts.target))
usage_with_options(record_usage, record_options);
if (nr_cgroups && !rec->opts.target.system_wide) {
ui__error("cgroup monitoring only available in"
" system-wide mode\n");
usage_with_options(record_usage, record_options);
}
if (rec->opts.record_switch_events &&
!perf_can_record_switch_events()) {
ui__error("kernel does not support recording context switch events (--switch-events option)\n");
usage_with_options(record_usage, record_options);
}
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
if (err)
return err;
}
err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
rec->opts.auxtrace_snapshot_opts);
if (err)
return err;
err = -ENOMEM;
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 14:40:45 +08:00
symbol__init(NULL);
perf symbols: Handle /proc/sys/kernel/kptr_restrict Perf uses /proc/modules to figure out where kernel modules are loaded. With the advent of kptr_restrict, non root users get zeroes for all module start addresses. So check if kptr_restrict is non zero and don't generate the syntethic PERF_RECORD_MMAP events for them. Warn the user about it in perf record and in perf report. In perf report the reference relocation symbol being zero means that kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't use it to fixup symbol addresses when using a valid kallsyms (in the buildid cache) or vmlinux (in the vmlinux path) build-id located automatically or specified by the user. Provide an explanation about it in 'perf report' if kernel samples were taken, checking if a suitable vmlinux or kallsyms was found/specified. Restricted /proc/kallsyms don't go to the buildid cache anymore. Example: [acme@emilia ~]$ perf record -F 100000 sleep 1 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check /proc/sys/kernel/kptr_restrict. Samples in kernel functions may not be resolved if a suitable vmlinux file is not found in the buildid cache or in the vmlinux path. Samples in kernel modules won't be resolved at all. If some relocation was applied (e.g. kexec) symbols may be misresolved even with a suitable vmlinux or kallsyms file. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ] [acme@emilia ~]$ [acme@emilia ~]$ perf report --stdio Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. If some relocation was applied (e.g. kexec) symbols may be misresolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ..................... # 20.24% sleep [kernel.kallsyms] [k] page_fault 20.04% sleep [kernel.kallsyms] [k] filemap_fault 19.78% sleep [kernel.kallsyms] [k] __lru_cache_add 19.69% sleep ld-2.12.so [.] memcpy 14.71% sleep [kernel.kallsyms] [k] dput 4.70% sleep [kernel.kallsyms] [k] flush_signal_handlers 0.73% sleep [kernel.kallsyms] [k] perf_event_comm 0.11% sleep [kernel.kallsyms] [k] native_write_msr_safe # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ This is because it found a suitable vmlinux (build-id checked) in /lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long file name). If we remove that file from the vmlinux path: [root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \ /lib/modules/2.6.39-rc7+/build/vmlinux.OFF [acme@emilia ~]$ perf report --stdio [kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562 not found, continuing without symbols Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. As no suitable kallsyms nor vmlinux was found, kernel samples can't be resolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ...... # 80.31% sleep [kernel.kallsyms] [k] 0xffffffff8103425a 19.69% sleep ld-2.12.so [.] memcpy # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ Reported-by: Stephane Eranian <eranian@google.com> Suggested-by: David Miller <davem@davemloft.net> Cc: Dave Jones <davej@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-26 20:53:51 +08:00
if (symbol_conf.kptr_restrict)
pr_warning(
"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
"check /proc/sys/kernel/kptr_restrict.\n\n"
"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
"file is not found in the buildid cache or in the vmlinux path.\n\n"
"Samples in kernel modules won't be resolved at all.\n\n"
"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
"even with a suitable vmlinux or kallsyms file.\n\n");
perf symbols: Handle /proc/sys/kernel/kptr_restrict Perf uses /proc/modules to figure out where kernel modules are loaded. With the advent of kptr_restrict, non root users get zeroes for all module start addresses. So check if kptr_restrict is non zero and don't generate the syntethic PERF_RECORD_MMAP events for them. Warn the user about it in perf record and in perf report. In perf report the reference relocation symbol being zero means that kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't use it to fixup symbol addresses when using a valid kallsyms (in the buildid cache) or vmlinux (in the vmlinux path) build-id located automatically or specified by the user. Provide an explanation about it in 'perf report' if kernel samples were taken, checking if a suitable vmlinux or kallsyms was found/specified. Restricted /proc/kallsyms don't go to the buildid cache anymore. Example: [acme@emilia ~]$ perf record -F 100000 sleep 1 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check /proc/sys/kernel/kptr_restrict. Samples in kernel functions may not be resolved if a suitable vmlinux file is not found in the buildid cache or in the vmlinux path. Samples in kernel modules won't be resolved at all. If some relocation was applied (e.g. kexec) symbols may be misresolved even with a suitable vmlinux or kallsyms file. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ] [acme@emilia ~]$ [acme@emilia ~]$ perf report --stdio Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. If some relocation was applied (e.g. kexec) symbols may be misresolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ..................... # 20.24% sleep [kernel.kallsyms] [k] page_fault 20.04% sleep [kernel.kallsyms] [k] filemap_fault 19.78% sleep [kernel.kallsyms] [k] __lru_cache_add 19.69% sleep ld-2.12.so [.] memcpy 14.71% sleep [kernel.kallsyms] [k] dput 4.70% sleep [kernel.kallsyms] [k] flush_signal_handlers 0.73% sleep [kernel.kallsyms] [k] perf_event_comm 0.11% sleep [kernel.kallsyms] [k] native_write_msr_safe # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ This is because it found a suitable vmlinux (build-id checked) in /lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long file name). If we remove that file from the vmlinux path: [root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \ /lib/modules/2.6.39-rc7+/build/vmlinux.OFF [acme@emilia ~]$ perf report --stdio [kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562 not found, continuing without symbols Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. As no suitable kallsyms nor vmlinux was found, kernel samples can't be resolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ...... # 80.31% sleep [kernel.kallsyms] [k] 0xffffffff8103425a 19.69% sleep ld-2.12.so [.] memcpy # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ Reported-by: Stephane Eranian <eranian@google.com> Suggested-by: David Miller <davem@davemloft.net> Cc: Dave Jones <davej@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-26 20:53:51 +08:00
if (rec->no_buildid_cache || rec->no_buildid)
disable_buildid_cache();
if (rec->evlist->nr_entries == 0 &&
perf_evlist__add_default(rec->evlist) < 0) {
pr_err("Not enough memory for event selector list\n");
goto out_symbol_exit;
}
if (rec->opts.target.tid && !rec->opts.no_inherit_set)
rec->opts.no_inherit = true;
err = target__validate(&rec->opts.target);
if (err) {
target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
ui__warning("%s", errbuf);
}
err = target__parse_uid(&rec->opts.target);
if (err) {
int saved_errno = errno;
target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
ui__error("%s", errbuf);
err = -saved_errno;
goto out_symbol_exit;
}
err = -ENOMEM;
if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
if (err)
goto out_symbol_exit;
if (record_opts__config(&rec->opts)) {
err = -EINVAL;
goto out_symbol_exit;
}
err = __cmd_record(&record, argc, argv);
out_symbol_exit:
perf record: Propagate exit status of a command line workload Currently perf record doesn't propagate the exit status of a workload given by the command line. But sometimes it'd useful if it's propagated so that a monitoring script can handle errors appropriately. To do that, it moves most of logic out of the exit handlers and run them directly in the __cmd_record(). The only thing needs to be done in the handler is propagating terminating signal so that the shell can terminate its loop properly when Ctrl-C was pressed. Also it cleaned up the resource management code in record__exit(). With this change, perf record returns the child exit status in case of normal termination and send signal to itself when terminated by signal. Example run of Stephane's case: $ perf record true && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] yes $ perf record false && echo yes || echo no [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (~589 samples) ] no Jiri's case (error in parent): $ perf record -m 10G true && echo yes || echo no rounding mmap pages size to 17179869184 bytes (4194304 pages) failed to mmap with 12 (Cannot allocate memory) no $ ulimit -n 6 $ perf record sleep 1 && echo yes || echo no failed to create 'go' pipe: Too many open files Couldn't run the workload! no And Peter's case (interrupted by signal): $ while :; do perf record sleep 1; done ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB perf.data (~593 samples) ] Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/1399855645-25815-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-05-12 08:47:24 +08:00
perf_evlist__delete(rec->evlist);
symbol__exit();
auxtrace_record__free(rec->itr);
return err;
}
static void snapshot_sig_handler(int sig __maybe_unused)
{
if (!auxtrace_snapshot_enabled)
return;
auxtrace_snapshot_enabled = 0;
auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr);
auxtrace_record__snapshot_started = 1;
}