On Tue, Nov 12, 2013 at 02:21:39PM -0000, David Laight wrote:
> Shame there isn't a process flag to indicate that the process
> will sleep uninterruptibly and that it doesn't matter.
> So don't count to the load average and don't emit a warning
> if it has been sleeping for a long time.
A process flag wouldn't work, because the task could block waiting for
actual work to complete in other sleeps.
However, we could do something like the below; which would allow us
writing things like:
(void)___wait_event(*sk_sleep(sk),
sock_writeable(sk) || kthread_should_stop(),
TASK_UNINTERRUPTIBLE | TASK_IDLE, 0, 0,
schedule());
Marking the one wait-for-more-work as TASK_IDLE such that it doesn't
contribute to the load avg.
---
fs/proc/array.c | 23 ++++++++++++-----------
include/linux/sched.h | 8 +++++---
include/trace/events/sched.h | 3 ++-
3 files changed, 19 insertions(+), 15 deletions(-)
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 1bd2077187fd..da9a9c8b5bba 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -133,17 +133,18 @@ static inline void task_name(struct seq_file *m, struct
task_struct *p)
* simple bit tests.
*/
static const char * const task_state_array[] = {
- "R (running)", /* 0 */
- "S (sleeping)", /* 1 */
- "D (disk sleep)", /* 2 */
- "T (stopped)", /* 4 */
- "t (tracing stop)", /* 8 */
- "Z (zombie)", /* 16 */
- "X (dead)", /* 32 */
- "x (dead)", /* 64 */
- "K (wakekill)", /* 128 */
- "W (waking)", /* 256 */
- "P (parked)", /* 512 */
+ "R (running)", /* 0 */
+ "S (sleeping)", /* 1 */
+ "D (disk sleep)", /* 2 */
+ "T (stopped)", /* 4 */
+ "t (tracing stop)", /* 8 */
+ "Z (zombie)", /* 16 */
+ "X (dead)", /* 32 */
+ "x (dead)", /* 64 */
+ "K (wakekill)", /* 128 */
+ "W (waking)", /* 256 */
+ "P (parked)", /* 512 */
+ "I (idle)", /* 1024 */
};
static inline const char *get_task_state(struct task_struct *tsk)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 045b0d227846..a4a9e80688d8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -145,9 +145,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq
*cfs_rq);
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
#define TASK_PARKED 512
-#define TASK_STATE_MAX 1024
+#define TASK_IDLE 1024
+#define TASK_STATE_MAX 2048
-#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWPI"
extern char ___assert_task_state[1 - 2*!!(
sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -173,7 +174,8 @@ extern char ___assert_task_state[1 - 2*!!(
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
- (task->flags & PF_FROZEN) == 0)
+ (task->flags & PF_FROZEN) == 0 && \
+ (task->state & TASK_IDLE) == 0)
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 04c308413a5d..4553a2495c25 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -144,7 +144,8 @@ TRACE_EVENT(sched_switch,
__print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
{ 16, "Z" }, { 32, "X" }, { 64, "x" },
- { 128, "K" }, { 256, "W" }, { 512, "P" }) : "R",
+ { 128, "K" }, { 256, "W" }, { 512, "P" },
+ { 1024, "I" }) : "R",
__entry->prev_state & TASK_STATE_MAX ? "+" : "",
__entry->next_comm, __entry->next_pid, __entry->next_prio)
);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
