Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1731675
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH RFC V2 02/10] perf tools: using scandir to replace readdir |
| Date | 2017-09-13 17:30 +0200 |
| Message-ID | <uphLY-DH-7@gated-at.bofh.it> (permalink) |
| References | <uomE1-4Gu-1@gated-at.bofh.it> <uomE1-4Gu-13@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
Em Sun, Sep 10, 2017 at 07:23:15PM -0700, kan.liang@intel.com escreveu:
> From: Kan Liang <kan.liang@intel.com>
>
> For perf_event__synthesize_threads, perf goes through all proc files
> serially by readdir.
> scandir did a snapshoot of proc, which is multithreading friendly.
>
> It's possible that some threads which are added during event synthesize.
> But the number of lost threads should be small.
> They should not impact the final analysis.
This one I had already merged into my perf/core branch,
- Arnaldo
> Signed-off-by: Kan Liang <kan.liang@intel.com>
> ---
> tools/perf/util/event.c | 46 ++++++++++++++++++++++++++--------------------
> 1 file changed, 26 insertions(+), 20 deletions(-)
>
> diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
> index 1c905ba..c31f678 100644
> --- a/tools/perf/util/event.c
> +++ b/tools/perf/util/event.c
> @@ -683,12 +683,14 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
> bool mmap_data,
> unsigned int proc_map_timeout)
> {
> - DIR *proc;
> - char proc_path[PATH_MAX];
> - struct dirent *dirent;
> union perf_event *comm_event, *mmap_event, *fork_event;
> union perf_event *namespaces_event;
> + char proc_path[PATH_MAX];
> + struct dirent **dirent;
> int err = -1;
> + char *end;
> + pid_t pid;
> + int n, i;
>
> if (machine__is_default_guest(machine))
> return 0;
> @@ -712,29 +714,33 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
> goto out_free_fork;
>
> snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
> - proc = opendir(proc_path);
> + n = scandir(proc_path, &dirent, 0, alphasort);
>
> - if (proc == NULL)
> + if (n < 0)
> goto out_free_namespaces;
>
> - while ((dirent = readdir(proc)) != NULL) {
> - char *end;
> - pid_t pid = strtol(dirent->d_name, &end, 10);
> -
> - if (*end) /* only interested in proper numerical dirents */
> + for (i = 0; i < n; i++) {
> + if (!isdigit(dirent[i]->d_name[0]))
> continue;
> - /*
> - * We may race with exiting thread, so don't stop just because
> - * one thread couldn't be synthesized.
> - */
> - __event__synthesize_thread(comm_event, mmap_event, fork_event,
> - namespaces_event, pid, 1, process,
> - tool, machine, mmap_data,
> - proc_map_timeout);
> - }
>
> + pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
> + /* only interested in proper numerical dirents */
> + if (!*end) {
> + /*
> + * We may race with exiting thread, so don't stop
> + * just because one thread couldn't be synthesized.
> + */
> + __event__synthesize_thread(comm_event, mmap_event,
> + fork_event, namespaces_event,
> + pid, 1, process, tool,
> + machine, mmap_data,
> + proc_map_timeout);
> + }
> + free(dirent[i]);
> + }
> + free(dirent);
> err = 0;
> - closedir(proc);
> +
> out_free_namespaces:
> free(namespaces_event);
> out_free_fork:
> --
> 2.5.5
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH RFC V2 00/10] perf top optimization kan.liang@intel.com - 2017-09-11 04:30 +0200
[PATCH RFC V2 10/10] perf top: switch back to overwrite mode kan.liang@intel.com - 2017-09-11 04:30 +0200
[PATCH RFC V2 04/10] petf tools: introduce a new function to set namespaces id kan.liang@intel.com - 2017-09-11 04:30 +0200
[PATCH RFC V2 06/10] perf tools: lock to protect comm_str rb tree kan.liang@intel.com - 2017-09-11 04:30 +0200
[PATCH RFC V2 02/10] perf tools: using scandir to replace readdir kan.liang@intel.com - 2017-09-11 04:30 +0200
Re: [PATCH RFC V2 02/10] perf tools: using scandir to replace readdir Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-13 17:30 +0200
[PATCH RFC V2 03/10] petf tools: using comm_str to replace comm in hist_entry kan.liang@intel.com - 2017-09-11 04:30 +0200
Re: [PATCH RFC V2 03/10] petf tools: using comm_str to replace comm in hist_entry Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-13 17:30 +0200
Re: [PATCH RFC V2 03/10] petf tools: using comm_str to replace comm in hist_entry Jiri Olsa <jolsa@redhat.com> - 2017-09-18 10:40 +0200
[PATCH RFC V2 01/10] perf tools: hashtable for machine threads kan.liang@intel.com - 2017-09-11 04:30 +0200
Re: [PATCH RFC V2 01/10] perf tools: hashtable for machine threads Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-13 15:30 +0200
[tip:perf/core] perf machine: Use hashtable for machine threads tip-bot for Kan Liang <tipbot@zytor.com> - 2017-09-22 18:50 +0200
[PATCH RFC V2 08/10] perf top: implement multithreading for perf_event__synthesize_threads kan.liang@intel.com - 2017-09-11 04:30 +0200
Re: [PATCH RFC V2 08/10] perf top: implement multithreading for perf_event__synthesize_threads Jiri Olsa <jolsa@redhat.com> - 2017-09-18 13:30 +0200
[PATCH RFC V2 07/10] perf tools: change machine comm_exec type to atomic kan.liang@intel.com - 2017-09-11 04:30 +0200
Re: [PATCH RFC V2 07/10] perf tools: change machine comm_exec type to atomic Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-13 17:30 +0200
RE: [PATCH RFC V2 07/10] perf tools: change machine comm_exec type to atomic "Liang, Kan" <kan.liang@intel.com> - 2017-09-15 22:10 +0200
Re: [PATCH RFC V2 07/10] perf tools: change machine comm_exec type to atomic Jiri Olsa <jolsa@redhat.com> - 2017-09-18 13:40 +0200
[PATCH RFC V2 05/10] perf tools: lock to protect thread list kan.liang@intel.com - 2017-09-11 04:30 +0200
Re: [PATCH RFC V2 05/10] perf tools: lock to protect thread list Jiri Olsa <jolsa@redhat.com> - 2017-09-18 11:00 +0200
RE: [PATCH RFC V2 05/10] perf tools: lock to protect thread list "Liang, Kan" <kan.liang@intel.com> - 2017-09-18 18:20 +0200
[PATCH RFC V2 09/10] perf top: add option to set the number of thread for event synthesize kan.liang@intel.com - 2017-09-11 04:30 +0200
RE: [PATCH RFC V2 00/10] perf top optimization "Liang, Kan" <kan.liang@intel.com> - 2017-09-13 17:30 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-13 17:40 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-14 23:20 +0200
RE: [PATCH RFC V2 00/10] perf top optimization "Liang, Kan" <kan.liang@intel.com> - 2017-09-15 17:20 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-15 19:30 +0200
RE: [PATCH RFC V2 00/10] perf top optimization "Liang, Kan" <kan.liang@intel.com> - 2017-09-15 19:30 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-15 20:30 +0200
RE: [PATCH RFC V2 00/10] perf top optimization "Liang, Kan" <kan.liang@intel.com> - 2017-09-15 20:30 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-13 17:30 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Jiri Olsa <jolsa@redhat.com> - 2017-09-18 11:00 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-18 15:10 +0200
RE: [PATCH RFC V2 00/10] perf top optimization "Liang, Kan" <kan.liang@intel.com> - 2017-09-18 18:30 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Jiri Olsa <jolsa@redhat.com> - 2017-09-19 10:20 +0200
RE: [PATCH RFC V2 00/10] perf top optimization "Liang, Kan" <kan.liang@intel.com> - 2017-09-19 14:50 +0200
Re: [PATCH RFC V2 00/10] perf top optimization Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-09-19 16:30 +0200
csiph-web