Messages in this thread | | | Subject | Re: [PATCH v2] perf record: Add support for limit perf output file size | From | Jiwei Sun <> | Date | Mon, 25 Feb 2019 10:39:49 +0800 |
| |
Hi Arnaldo,
On 02/22/2019 10:53 PM, Arnaldo Carvalho de Melo wrote: > Em Fri, Feb 22, 2019 at 03:19:04PM +0800, Jiwei Sun escreveu: >> The patch adds a new option to limit the output file size, then based >> on it, we can create a wrapper of the perf command that uses the option >> to avoid exhausting the disk space by the unconscious user. >> >> Signed-off-by: Jiwei Sun <jiwei.sun@windriver.com> >> --- >> v2 changes: > > Please do a v3 adding this new option to > tools/perf/Documentation/perf-record.txt > > Please also rename it to --max-size-output, because then we coudl use: > > perf record --max-size-output > > or: > > perf record --max-size > > or even: > > perf record --max saving typing :-) > > Also please show it in use, i.e. the output of it working.
Thanks for your advice, I will modify the patch and send a v3.
Thanks, Regards, Jiwei
> > > - Arnaldo > >> - make patch based on latest Arnaldo's perf/core, >> - display warning message when reached the limit. >> --- >> tools/perf/builtin-record.c | 42 +++++++++++++++++++++++++++++++++++++ >> 1 file changed, 42 insertions(+) >> >> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c >> index 6c3719ac901d..dc3648c0816d 100644 >> --- a/tools/perf/builtin-record.c >> +++ b/tools/perf/builtin-record.c >> @@ -83,6 +83,7 @@ struct record { >> struct switch_output switch_output; >> unsigned long long samples; >> cpu_set_t affinity_mask; >> + unsigned long output_max_size; /* = 0: unlimited */ >> }; >> >> static volatile int auxtrace_record__snapshot_started; >> @@ -112,6 +113,12 @@ static bool switch_output_time(struct record *rec) >> trigger_is_ready(&switch_output_trigger); >> } >> >> +static bool record__output_max_size_exceeded(struct record *rec) >> +{ >> + return (rec->output_max_size && >> + rec->bytes_written >= rec->output_max_size); >> +} >> + >> static int record__write(struct record *rec, struct perf_mmap *map __maybe_unused, >> void *bf, size_t size) >> { >> @@ -124,6 +131,12 @@ static int record__write(struct record *rec, struct perf_mmap *map __maybe_unuse >> >> rec->bytes_written += size; >> >> + if (record__output_max_size_exceeded(rec)) { >> + pr_warning("WARNING: The perf data has already reached " >> + "the limit, stop recording!\n"); >> + raise(SIGTERM); >> + } >> + >> if (switch_output_size(rec)) >> trigger_hit(&switch_output_trigger); >> >> @@ -1671,6 +1684,33 @@ static int record__parse_affinity(const struct option *opt, const char *str, int >> return 0; >> } >> >> +static int parse_output_max_size(const struct option *opt, >> + const char *str, int unset) >> +{ >> + unsigned long *s = (unsigned long *)opt->value; >> + static struct parse_tag tags_size[] = { >> + { .tag = 'B', .mult = 1 }, >> + { .tag = 'K', .mult = 1 << 10 }, >> + { .tag = 'M', .mult = 1 << 20 }, >> + { .tag = 'G', .mult = 1 << 30 }, >> + { .tag = 0 }, >> + }; >> + unsigned long val; >> + >> + if (unset) { >> + *s = 0; >> + return 0; >> + } >> + >> + val = parse_tag_value(str, tags_size); >> + if (val != (unsigned long) -1) { >> + *s = val; >> + return 0; >> + } >> + >> + return -1; >> +} >> + >> static int record__parse_mmap_pages(const struct option *opt, >> const char *str, >> int unset __maybe_unused) >> @@ -1982,6 +2022,8 @@ static struct option __record_options[] = { >> OPT_CALLBACK(0, "affinity", &record.opts, "node|cpu", >> "Set affinity mask of trace reading thread to NUMA node cpu mask or cpu of processed mmap buffer", >> record__parse_affinity), >> + OPT_CALLBACK(0, "output-max-size", &record.output_max_size, >> + "size", "Output file maximum size", parse_output_max_size), >> OPT_END() >> }; >> >> -- >> 2.20.1 >
| |