From 27a7a28e0d3013e6b12072f18e00faa5366ae53e Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Wed, 30 Nov 2011 15:07:20 +1100 Subject: [PATCH] hrtimers: Special-case zero length sleeps sleep(0) is a common construct used by applications that want to trigger the scheduler. sched_yield() might make more sense, but only appeared in POSIX.1-2001 and so plenty of example code still uses the sleep(0) form. This wouldn't normally be a problem, but it means that event-driven applications that are merely trying to avoid starving other processes may actually end up sleeping due to having large timer_slack values. Special- casing this seems reasonable. Signed-off-by: Matthew Garrett Cc: Thomas Gleixner Cc: Arjan van de Ven Signed-off-by: Andrew Morton --- kernel/hrtimer.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index ae34bf51682b..a53fff92fda4 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1568,6 +1568,14 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, if (rt_task(current)) slack = 0; + /* + * Applications will often sleep(0) to indicate that they wish to + * be scheduled. Special case that to avoid actually putting them + * to sleep for the duration of the slack. + */ + if (rqtp->tv_sec == 0 && rqtp->tv_nsec == 0) + slack = 0; + hrtimer_init_on_stack(&t.timer, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); if (do_nanosleep(&t, mode)) -- 2.39.5