perf trace: Implement --delay

In the perf wiki todo-list[1], there is an entry regarding initial-delay
and 'perf trace'; the following small patch tries to fulfill this point.
It has been generated against the branch tip/perf/core.

It has only been implemented in the "trace__run" case.

Ex.:

  $ sudo strace -- ./perf trace --delay 5 sleep 1 2>&1
  ...
  fcntl(7, F_SETFL, O_RDONLY|O_NONBLOCK)  = 0
  ioctl(7, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0
  ioctl(11, PERF_EVENT_IOC_SET_OUTPUT, 0x7) = 0
  fcntl(11, F_SETFL, O_RDONLY|O_NONBLOCK) = 0
  ioctl(11, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0
  write(6, "\0", 1)                       = 1
  close(6)                                = 0
  nanosleep({0, 5000000}, NULL)           = 0  # DELAY OF 5 MS BEFORE ENABLING THE EVENTS
  ioctl(3, PERF_EVENT_IOC_ENABLE, 0)      = 0
  ioctl(4, PERF_EVENT_IOC_ENABLE, 0)      = 0
  ioctl(5, PERF_EVENT_IOC_ENABLE, 0)      = 0
  ioctl(7, PERF_EVENT_IOC_ENABLE, 0)      = 0
  ...

[1]: https://perf.wiki.kernel.org/index.php/Todo

Signed-off-by: Alexis Berlemont <alexis.berlemont@gmail.com>
Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20161010054328.4028-2-alexis.berlemont@gmail.com
[ Add entry to the manpage, cut'n'pasted from stat's and record's ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 1ab0782369b1faa9bbe6758ed0e3439c414eb7e1..781b019751a4cb8bafeb70afc467aca54c410177 100644 (file)
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -39,6 +39,11 @@ OPTIONS
        Prefixing with ! shows all syscalls but the ones specified.  You may
        need to escape it.
 
+-D msecs::
+--delay msecs::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
 -o::
 --output=::
        Output file name.

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c298bd3e1d909cfd808f911af1df053e608f55fe..0bae454e8efac89cc600477eabd215f16da75c1b 100644 (file)
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2310,12 +2310,17 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
        if (err < 0)
                goto out_error_mmap;
 
-       if (!target__none(&trace->opts.target))
+       if (!target__none(&trace->opts.target) && !trace->opts.initial_delay)
                perf_evlist__enable(evlist);
 
        if (forks)
                perf_evlist__start_workload(evlist);
 
+       if (trace->opts.initial_delay) {
+               usleep(trace->opts.initial_delay * 1000);
+               perf_evlist__enable(evlist);
+       }
+
        trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
                                  evlist->threads->nr > 1 ||
                                  perf_evlist__first(evlist)->attr.inherit;
@@ -2816,6 +2821,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
        OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
                        "per thread proc mmap processing timeout in ms"),
+       OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
+                    "ms to wait before starting measurement after program "
+                    "start"),
        OPT_END()
        };
        bool __maybe_unused max_stack_user_set = true;