linux/tools/lib/traceevent/plugin_sched_switch.c

161 lines
4.3 KiB
C
Raw Normal View History

/*
* Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation;
* version 2.1 of the License (not later!)
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses>
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "event-parse.h"
static void write_state(struct trace_seq *s, int val)
{
const char states[] = "SDTtZXxW";
int found = 0;
int i;
for (i = 0; i < (sizeof(states) - 1); i++) {
if (!(val & (1 << i)))
continue;
if (found)
trace_seq_putc(s, '|');
found = 1;
trace_seq_putc(s, states[i]);
}
if (!found)
trace_seq_putc(s, 'R');
}
static void write_and_save_comm(struct format_field *field,
struct tep_record *record,
struct trace_seq *s, int pid)
{
const char *comm;
int len;
comm = (char *)(record->data + field->offset);
len = s->len;
trace_seq_printf(s, "%.*s",
field->size, comm);
/* make sure the comm has a \0 at the end. */
trace_seq_terminate(s);
comm = &s->buffer[len];
/* Help out the comm to ids. This will handle dups */
tep_register_comm(field->event->pevent, comm, pid);
}
static int sched_wakeup_handler(struct trace_seq *s,
struct tep_record *record,
struct event_format *event, void *context)
{
struct format_field *field;
unsigned long long val;
if (tep_get_field_val(s, event, "pid", record, &val, 1))
return trace_seq_putc(s, '!');
field = tep_find_any_field(event, "comm");
if (field) {
write_and_save_comm(field, record, s, val);
trace_seq_putc(s, ':');
}
trace_seq_printf(s, "%lld", val);
if (tep_get_field_val(s, event, "prio", record, &val, 0) == 0)
trace_seq_printf(s, " [%lld]", val);
if (tep_get_field_val(s, event, "success", record, &val, 1) == 0)
trace_seq_printf(s, " success=%lld", val);
if (tep_get_field_val(s, event, "target_cpu", record, &val, 0) == 0)
trace_seq_printf(s, " CPU:%03llu", val);
return 0;
}
static int sched_switch_handler(struct trace_seq *s,
struct tep_record *record,
struct event_format *event, void *context)
{
struct format_field *field;
unsigned long long val;
if (tep_get_field_val(s, event, "prev_pid", record, &val, 1))
return trace_seq_putc(s, '!');
field = tep_find_any_field(event, "prev_comm");
if (field) {
write_and_save_comm(field, record, s, val);
trace_seq_putc(s, ':');
}
trace_seq_printf(s, "%lld ", val);
if (tep_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
tools lib traceevent: Fix prev/next_prio for deadline tasks Currently, the sched:sched_switch tracepoint reports deadline tasks with priority -1. But when reading the trace via perf script I've got the following output: # ./d & # (d is a deadline task, see [1]) # perf record -e sched:sched_switch -a sleep 1 # perf script ... swapper 0 [000] 2146.962441: sched:sched_switch: swapper/0:0 [120] R ==> d:2593 [4294967295] d 2593 [000] 2146.972472: sched:sched_switch: d:2593 [4294967295] R ==> g:2590 [4294967295] The task d reports the wrong priority [4294967295]. This happens because the "int prio" is stored in an unsigned long long val. Although it is set as a %lld, as int is shorter than unsigned long long, trace_seq_printf prints it as a positive number. The fix is just to cast the val as an int, and print it as a %d, as in the sched:sched_switch tracepoint's "format". The output with the fix is: # ./d & # perf record -e sched:sched_switch -a sleep 1 # perf script ... swapper 0 [000] 4306.374037: sched:sched_switch: swapper/0:0 [120] R ==> d:10941 [-1] d 10941 [000] 4306.383823: sched:sched_switch: d:10941 [-1] R ==> swapper/0:0 [120] [1] d.c --- #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #include <linux/types.h> #include <linux/sched.h> struct sched_attr { __u32 size, sched_policy; __u64 sched_flags; __s32 sched_nice; __u32 sched_priority; __u64 sched_runtime, sched_deadline, sched_period; }; int sched_setattr(pid_t pid, const struct sched_attr *attr, unsigned int flags) { return syscall(__NR_sched_setattr, pid, attr, flags); } int main(void) { struct sched_attr attr = { .size = sizeof(attr), .sched_policy = SCHED_DEADLINE, /* This creates a 10ms/30ms reservation */ .sched_runtime = 10 * 1000 * 1000, .sched_period = attr.sched_deadline = 30 * 1000 * 1000, }; if (sched_setattr(0, &attr, 0) < 0) { perror("sched_setattr"); return -1; } for(;;); } --- Committer notes: Got the program from the provided URL, http://bristot.me/lkml/d.c, trimmed it and included in the cset log above, so that we have everything needed to test it in one place. Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/866ef75bcebf670ae91c6a96daa63597ba981f0d.1483443552.git.bristot@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-03 14:42:42 +03:00
trace_seq_printf(s, "[%d] ", (int) val);
if (tep_get_field_val(s, event, "prev_state", record, &val, 0) == 0)
write_state(s, val);
trace_seq_puts(s, " ==> ");
if (tep_get_field_val(s, event, "next_pid", record, &val, 1))
return trace_seq_putc(s, '!');
field = tep_find_any_field(event, "next_comm");
if (field) {
write_and_save_comm(field, record, s, val);
trace_seq_putc(s, ':');
}
trace_seq_printf(s, "%lld", val);
if (tep_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
tools lib traceevent: Fix prev/next_prio for deadline tasks Currently, the sched:sched_switch tracepoint reports deadline tasks with priority -1. But when reading the trace via perf script I've got the following output: # ./d & # (d is a deadline task, see [1]) # perf record -e sched:sched_switch -a sleep 1 # perf script ... swapper 0 [000] 2146.962441: sched:sched_switch: swapper/0:0 [120] R ==> d:2593 [4294967295] d 2593 [000] 2146.972472: sched:sched_switch: d:2593 [4294967295] R ==> g:2590 [4294967295] The task d reports the wrong priority [4294967295]. This happens because the "int prio" is stored in an unsigned long long val. Although it is set as a %lld, as int is shorter than unsigned long long, trace_seq_printf prints it as a positive number. The fix is just to cast the val as an int, and print it as a %d, as in the sched:sched_switch tracepoint's "format". The output with the fix is: # ./d & # perf record -e sched:sched_switch -a sleep 1 # perf script ... swapper 0 [000] 4306.374037: sched:sched_switch: swapper/0:0 [120] R ==> d:10941 [-1] d 10941 [000] 4306.383823: sched:sched_switch: d:10941 [-1] R ==> swapper/0:0 [120] [1] d.c --- #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #include <linux/types.h> #include <linux/sched.h> struct sched_attr { __u32 size, sched_policy; __u64 sched_flags; __s32 sched_nice; __u32 sched_priority; __u64 sched_runtime, sched_deadline, sched_period; }; int sched_setattr(pid_t pid, const struct sched_attr *attr, unsigned int flags) { return syscall(__NR_sched_setattr, pid, attr, flags); } int main(void) { struct sched_attr attr = { .size = sizeof(attr), .sched_policy = SCHED_DEADLINE, /* This creates a 10ms/30ms reservation */ .sched_runtime = 10 * 1000 * 1000, .sched_period = attr.sched_deadline = 30 * 1000 * 1000, }; if (sched_setattr(0, &attr, 0) < 0) { perror("sched_setattr"); return -1; } for(;;); } --- Committer notes: Got the program from the provided URL, http://bristot.me/lkml/d.c, trimmed it and included in the cset log above, so that we have everything needed to test it in one place. Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/866ef75bcebf670ae91c6a96daa63597ba981f0d.1483443552.git.bristot@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-03 14:42:42 +03:00
trace_seq_printf(s, " [%d]", (int) val);
return 0;
}
int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
{
tep_register_event_handler(pevent, -1, "sched", "sched_switch",
sched_switch_handler, NULL);
tep_register_event_handler(pevent, -1, "sched", "sched_wakeup",
sched_wakeup_handler, NULL);
tep_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
sched_wakeup_handler, NULL);
return 0;
}
void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
{
tep_unregister_event_handler(pevent, -1, "sched", "sched_switch",
sched_switch_handler, NULL);
tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup",
sched_wakeup_handler, NULL);
tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new",
sched_wakeup_handler, NULL);
}