linux-kernel - Re: [PATCH 6/8] perf sched: Introduce timehist command

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Thu, 28 Nov 2013 09:01:00 -0700
From:	David Ahern <dsahern@...il.com>
To:	Namhyung Kim <namhyung@...nel.org>
CC:	acme@...stprotocols.net, linux-kernel@...r.kernel.org,
	Ingo Molnar <mingo@...nel.org>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Mike Galbraith <efault@....de>, Jiri Olsa <jolsa@...hat.com>,
	Stephane Eranian <eranian@...gle.com>,
	Pekka Enberg <penberg@...nel.org>
Subject: Re: [PATCH 6/8] perf sched: Introduce timehist command

On 11/28/13, 2:50 AM, Namhyung Kim wrote:
>> +static inline void printf_nsecs(unsigned long long nsecs, int width_sec)
>> >+{
>> >+	unsigned long secs;
>> >+	unsigned long usecs;
>> >+
>> >+	secs = nsecs / NSECS_PER_SEC;
>> >+	nsecs -= secs * NSECS_PER_SEC;
>> >+	usecs = nsecs / NSECS_PER_USEC;
>> >+	printf("%*lu.%06lu ", width_sec, secs, usecs);
>> >+}
> It seems very similar to what timehist_time_str() does.  Better to
> factor out?

yes and no. The above is used to dump time-based stats (time between 
sched-in events, scheduling delay, and run time).

What I really want for timehist_time_str is time-of-day. And in local 
variants of this code I have that. Until I can convince Peter, et al. 
about the real need to pull perf_clock into userspace this is a bit of a 
place holder so that local code and this version do not differ too much.

>
>
> [SNIP]
>> >+static unsigned int comm_width = 20;
>> >+
>> >+static char *timehist_get_commstr(struct thread *thread)
>> >+{
>> >+	static char str[32];
>> >+	const char *comm = thread__comm_str(thread);
>> >+	pid_t tid = thread->tid;
>> >+	pid_t pid = thread->pid_;
>> >+	unsigned int n;
>> >+
>> >+	if (pid == 0)
>> >+		scnprintf(str, sizeof(str), "%s", comm);
>> >+
>> >+	else if (tid != pid)
>> >+		scnprintf(str, sizeof(str), "%s[%d/%d]", comm, tid, pid);
>> >+
>> >+	else
>> >+		scnprintf(str, sizeof(str), "%s[%d]", comm, tid);
>> >+
>> >+	n = strlen(str);
> Why not just using return value of scnprintf()?

right. will do.

>
>
>> >+	if (n > comm_width)
>> >+		comm_width = n;
>> >+
>> >+	return str;
>> >+}
>> >+
>> >+static void timehist_header(struct perf_sched *sched)
>> >+{
>> >+	u32 max_cpus = sched->max_cpu;
>> >+	u32 i, j;
>> >+
>> >+	printf("%15s %-4s", "time", "cpu");
>> >+
>> >+	if (sched->show_cpu_visual && max_cpus) {
>> >+		printf(" ");
>> >+		for (i = 0, j = 0; i < max_cpus; ++i) {
>> >+			printf("%x", j++);
>> >+			if (j > 15)
>> >+				j = 0;
>> >+		}
>> >+		printf(" ");
>> >+	}
>> >+
>> >+	printf(" %-20s %9s %9s %9s",
>> >+		"task name[tid/pid]", "b/n time", "sch delay", "run time");
>> >+
>> >+	if (sched->show_wakeups)
>> >+		printf("  %-20s", "wakeup");
>> >+
>> >+	printf("\n");
>> >+
>> >+	printf("%15s %4s", "---------------", "----");
> You might want to use "%.15s" and graph_dotted_line.

did not know about that. will update.


>> >+static void timehist_print_sample(struct perf_sched *sched,
>> >+				  union perf_event *event,
>> >+				  struct perf_evsel *evsel,
>> >+				  struct perf_sample *sample,
>> >+				  struct thread *thread,
>> >+				  struct machine *machine)
>> >+{
>> >+	struct thread_runtime *tr = thread__priv(thread);
>> >+	char tstr[64];
>> >+	u32 max_cpus = sched->max_cpu;
>> >+
>> >+	printf("%15s ", timehist_time_str(tstr, sizeof(tstr), sample->time));
>> >+
>> >+	printf("[%02d] ", sample->cpu);
>> >+
>> >+	if (sched->show_cpu_visual && max_cpus) {
>> >+		u32 i;
>> >+		char c;
>> >+		for (i = 0; i < max_cpus; ++i) {
>> >+			if (i == sample->cpu)
>> >+				c = (thread->tid == 0) ? 'i' : 's';
> It'd better explaining what the 'i' and 's' mean..

visual aid: i = idle, s = sched-event. will add a comment.

>> >+static void free_idle_threads(void)
>> >+{
>> >+	int i;
>> >+
>> >+	if (idle_threads == NULL)
>> >+		return;
>> >+
>> >+	for (i = 0; i <= idle_max_cpu; ++i)
>> >+		free(idle_threads[i]);
> Doesn't it need to be thread__delete(idle_threads[i]) ?

yes. forgot to update this to the new api.

David

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/