From: "Rafael J. Wysocki" <rjw@rjwysocki.net>
To: Yu Chen <yu.c.chen@intel.com>
Cc: Len Brown <lenb@kernel.org>,
Artem Bityutskiy <artem.bityutskiy@intel.com>,
Doug Smythies <dsmythies@telus.net>,
linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH][v4] tools/power turbostat: if --iterations, print for specific time of iterations
Date: Fri, 13 Apr 2018 09:38:18 +0200 [thread overview]
Message-ID: <6001773.M4ClJSFhmh@aspire.rjw.lan> (raw)
In-Reply-To: <20180413034047.1240-1-yu.c.chen@intel.com>
On Friday, April 13, 2018 5:40:47 AM CEST Yu Chen wrote:
> From: Chen Yu <yu.c.chen@intel.com>
>
> There's a use case during test to only print specific round of iterations
> if --iterations is specified, for example, with this patch applied:
>
> turbostat -i 5 -I 4
> will capture 4 samples with 5 seconds interval.
>
> Cc: Len Brown <lenb@kernel.org>
> Cc: Rafael J Wysocki <rjw@rjwysocki.net>
> Cc: Artem Bityutskiy <artem.bityutskiy@intel.com>
> Cc: Doug Smythies <dsmythies@telus.net>
> Cc: linux-pm@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> Signed-off-by: Chen Yu <yu.c.chen@intel.com>
> ---
> tools/power/x86/turbostat/turbostat.c | 23 ++++++++++++++++++++++-
> 1 file changed, 22 insertions(+), 1 deletion(-)
>
> diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
> index bd9c6b31a504..a2fe96f038f0 100644
> --- a/tools/power/x86/turbostat/turbostat.c
> +++ b/tools/power/x86/turbostat/turbostat.c
> @@ -48,6 +48,7 @@ char *proc_stat = "/proc/stat";
> FILE *outf;
> int *fd_percpu;
> struct timespec interval_ts = {5, 0};
> +int iterations;
> unsigned int debug;
> unsigned int quiet;
> unsigned int sums_need_wide_columns;
> @@ -470,6 +471,7 @@ void help(void)
> " {core | package | j,k,l..m,n-p }\n"
> "--quiet skip decoding system configuration header\n"
> "--interval sec Override default 5-second measurement interval\n"
> + "--iterations count Number of measurement iterations(requires '--interval'\n"
Why does it require --interval? Surely it should work with the default interval too?
> "--help print this help message\n"
> "--list list column headers only\n"
> "--out file create or truncate \"file\" for all output\n"
> @@ -2565,6 +2567,7 @@ void turbostat_loop()
> {
> int retval;
> int restarted = 0;
> + int done_iters = 0;
>
> restart:
> restarted++;
> @@ -2581,6 +2584,7 @@ void turbostat_loop()
> goto restart;
> }
> restarted = 0;
> + done_iters = 0;
> gettimeofday(&tv_even, (struct timezone *)NULL);
>
> while (1) {
> @@ -2607,6 +2611,10 @@ void turbostat_loop()
> compute_average(EVEN_COUNTERS);
> format_all_counters(EVEN_COUNTERS);
> flush_output_stdout();
> +
> + if (iterations && (++done_iters >= iterations))
> + break;
> +
> nanosleep(&interval_ts, NULL);
> if (snapshot_proc_sysfs_files())
> goto restart;
> @@ -2626,6 +2634,9 @@ void turbostat_loop()
> compute_average(ODD_COUNTERS);
> format_all_counters(ODD_COUNTERS);
> flush_output_stdout();
> +
> + if (iterations && (++done_iters >= iterations))
> + break;
> }
> }
>
> @@ -4999,6 +5010,7 @@ void cmdline(int argc, char **argv)
> {"Dump", no_argument, 0, 'D'},
> {"debug", no_argument, 0, 'd'}, /* internal, not documented */
> {"interval", required_argument, 0, 'i'},
> + {"iterations", required_argument, 0, 'I'},
I would use "-r" rather (unless assigned already). It may be interpreted as
"repetitions" and there's no confusion with "-i".
> {"help", no_argument, 0, 'h'},
> {"hide", required_argument, 0, 'H'}, // meh, -h taken by --help
> {"Joules", no_argument, 0, 'J'},
> @@ -5014,7 +5026,7 @@ void cmdline(int argc, char **argv)
>
> progname = argv[0];
>
> - while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
> + while ((opt = getopt_long_only(argc, argv, "+C:c:DdhI:i:JM:m:o:qST:v",
> long_options, &option_index)) != -1) {
> switch (opt) {
> case 'a':
> @@ -5036,6 +5048,15 @@ void cmdline(int argc, char **argv)
> default:
> help();
> exit(1);
> + case 'I':
> + iterations = strtod(optarg, NULL);
> +
> + if (iterations <= 0) {
> + fprintf(outf, "iterations %d should be positive number\n",
> + iterations);
> + exit(2);
> + }
> + break;
> case 'i':
> {
> double interval = strtod(optarg, NULL);
>
What about the man page?
prev parent reply other threads:[~2018-04-13 7:38 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-13 3:40 [PATCH][v4] tools/power turbostat: if --iterations, print for specific time of iterations Yu Chen
2018-04-13 6:48 ` Artem Bityutskiy
2018-04-13 7:38 ` Rafael J. Wysocki [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6001773.M4ClJSFhmh@aspire.rjw.lan \
--to=rjw@rjwysocki.net \
--cc=artem.bityutskiy@intel.com \
--cc=dsmythies@telus.net \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=yu.c.chen@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).