sched/wait: Introduce TASK_NOLOAD and TASK_IDLE

Currently people use TASK_INTERRUPTIBLE to idle kthreads and wait for
'work' because TASK_UNINTERRUPTIBLE contributes to the loadavg. Having
all idle kthreads contribute to the loadavg is somewhat silly.

Now mostly this works OK, because kthreads have all their signals
masked. However there's a few sites where this is causing problems and
TASK_UNINTERRUPTIBLE should be used, except for that loadavg issue.

This patch adds TASK_NOLOAD which, when combined with
TASK_UNINTERRUPTIBLE avoids the loadavg accounting.

As most of imagined usage sites are loops where a thread wants to
idle, waiting for work, a helper TASK_IDLE is introduced.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: NeilBrown <neilb@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index dd07ac03f82a8aa1294a46ce8a7cb36cebfd6839..7de815c6fa787221bc244d1be64da7dcb3c4d781 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -218,9 +218,10 @@ 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_NOLOAD            1024
+#define TASK_STATE_MAX         2048
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN"
 
 extern char ___assert_task_state[1 - 2*!!(
                sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -230,6 +231,8 @@ extern char ___assert_task_state[1 - 2*!!(
 #define TASK_STOPPED           (TASK_WAKEKILL | __TASK_STOPPED)
 #define TASK_TRACED            (TASK_WAKEKILL | __TASK_TRACED)
 
+#define TASK_IDLE              (TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
+
 /* Convenience macros for the sake of wake_up */
 #define TASK_NORMAL            (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
 #define TASK_ALL               (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
@@ -245,7 +248,8 @@ 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_NOLOAD) == 0)
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 30fedaf3e56a253175619fbef7a9f9a1f6dc15a3..d57a575fe31fc5796e9866470e3dd40a881ca12a 100644 (file)
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -147,7 +147,8 @@ 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, "N" }) : "R",
                __entry->prev_state & TASK_STATE_MAX ? "+" : "",
                __entry->next_comm, __entry->next_pid, __entry->next_prio)
 );