[RFC 7/12][PATCH] SCHED_DEADLINE: signal delivery when overrunning

From: Raistlin
Date: Fri Oct 16 2009 - 11:46:19 EST

Starting from this commit, the user can ask to receive a SIGXCPU signal
every time the task runtime is overrun or a scheduling deadline is missed.
This is done by means of the sched_flags field already present in
sched_param_ex.

A runtime overrun will be quite common, e.g. due to coarse execution time
accounting, wrong parameter assignement, etc.
A deadline miss --since the deadlines the scheduler sees are ``scheduling
deadlines'' which have not necessarily to be equal to task's deadlines-- is
much more unlikely, and should only happen in an overloaded system.

Signed-off-by: Raistlin <raistlin@xxxxxxxx>
---
include/linux/sched.h | 5 ++++
kernel/posix-cpu-timers.c | 52 +++++++++++++++++++++++++++++++++++++++++++-
kernel/sched_deadline.c | 18 +++++++++++++++
3 files changed, 73 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index fac928a..16668f9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -95,6 +95,9 @@ struct sched_param {

#include <asm/processor.h>

+#define SCHED_SIG_RORUN 0x80000000
+#define SCHED_SIG_DMISS 0x40000000
+
struct sched_param_ex {
int sched_priority;
struct timespec sched_runtime;
@@ -1229,6 +1232,8 @@ struct sched_rt_entity {
#define DL_NEW 0x00000001
#define DL_THROTTLED 0x00000002
#define DL_BOOSTED 0x00000004
+#define DL_RORUN 0x00000008
+#define DL_DMISS 0x00000010

struct sched_dl_entity {
struct rb_node rb_node;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 5c9dc22..4caa5bf 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1029,8 +1029,28 @@ static void check_thread_timers(struct task_struct *tsk,
}

/*
- * Check for the special case thread timers.
+ * Check for the special case thread timers:
+ * - sched_deadline runtime/deadline overrun notification
+ * - sched_rt rlimit overrun notification
*/
+ if (deadline_task(tsk) && (tsk->dl.flags & SCHED_SIG_RORUN ||
+ tsk->dl.flags & SCHED_SIG_DMISS)) {
+ if (tsk->dl.flags & SCHED_SIG_RORUN &&
+ tsk->dl.flags & DL_RORUN) {
+ tsk->dl.flags &= ~DL_RORUN;
+ printk(KERN_INFO "runtime overrun: %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+ }
+ if (tsk->dl.flags & SCHED_SIG_DMISS &&
+ tsk->dl.flags & DL_DMISS) {
+ tsk->dl.flags &= ~DL_DMISS;
+ printk(KERN_INFO "scheduling deadline miss: %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+ }
+ }
+
if (sig->rlim[RLIMIT_RTTIME].rlim_cur != RLIM_INFINITY) {
unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max;
unsigned long *soft = &sig->rlim[RLIMIT_RTTIME].rlim_cur;
@@ -1129,6 +1149,9 @@ static void check_process_timers(struct task_struct *tsk,
if (list_empty(&timers[CPUCLOCK_PROF]) &&
cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) &&
sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
+ !(deadline_task(tsk) && ((tsk->dl.flags & SCHED_SIG_RORUN &&
+ tsk->dl.flags & DL_RORUN) || (tsk->dl.flags & SCHED_SIG_DMISS &&
+ tsk->dl.flags & DL_DMISS))) &&
list_empty(&timers[CPUCLOCK_VIRT]) &&
cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
list_empty(&timers[CPUCLOCK_SCHED])) {
@@ -1188,8 +1211,28 @@ static void check_process_timers(struct task_struct *tsk,
}

/*
- * Check for the special case process timers.
+ * Check for the special case thread timers:
+ * - sched_deadline runtime/deadline overrun notification
+ * - sched_rt rlimit overrun notification
*/
+ if (deadline_task(tsk) && (tsk->dl.flags & SCHED_SIG_RORUN ||
+ tsk->dl.flags & SCHED_SIG_DMISS)) {
+ if (tsk->dl.flags & SCHED_SIG_RORUN &&
+ tsk->dl.flags & DL_RORUN) {
+ tsk->dl.flags &= ~DL_RORUN;
+ printk(KERN_INFO "runtime overrun: %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+ }
+ if (tsk->dl.flags & SCHED_SIG_DMISS &&
+ tsk->dl.flags & DL_DMISS) {
+ tsk->dl.flags &= ~DL_DMISS;
+ printk(KERN_INFO "scheduling deadline miss: %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+ }
+ }
+
check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
SIGPROF);
check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
@@ -1383,6 +1426,11 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
return 1;
}

+ if (deadline_task(tsk) &&
+ ((tsk->dl.flags & SCHED_SIG_RORUN && tsk->dl.flags & DL_RORUN) ||
+ (tsk->dl.flags & SCHED_SIG_DMISS && tsk->dl.flags & DL_DMISS)))
+ return 1;
+
return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY;
}

diff --git a/kernel/sched_deadline.c b/kernel/sched_deadline.c
index f2c1b6e..7b57bb0 100644
--- a/kernel/sched_deadline.c
+++ b/kernel/sched_deadline.c
@@ -236,9 +236,27 @@ static void init_deadline_task(struct task_struct *p)
static
int deadline_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
{
+ /*
+ * if the user asked for that, we have to inform him about
+ * a (scheduling) deadline miss ...
+ */
+ if (unlikely(dl_se->flags & SCHED_SIG_DMISS &&
+ deadline_time_before(dl_se->deadline, rq->clock)))
+ dl_se->flags |= DL_DMISS;
+
if (dl_se->runtime >= 0 || deadline_se_boosted(dl_se))
return 0;

+ /*
+ * ... and the same appies to runtime overruns.
+ *
+ * Note that (hopefully small) runtime overruns are very likely
+ * to occur, mainly due to accounting resolution, while missing a
+ * scheduling deadline should happen only on oversubscribed systems.
+ */
+ if (dl_se->flags & SCHED_SIG_RORUN)
+ dl_se->flags |= DL_RORUN;
+
dequeue_deadline_entity(dl_se);
if (!start_deadline_timer(dl_se, dl_se->deadline)) {
replenish_deadline_entity(dl_se);
--
1.6.0.4


--
<<This happens because I choose it to happen!>> (Raistlin Majere)
----------------------------------------------------------------------
Dario Faggioli, ReTiS Lab, Scuola Superiore Sant'Anna, Pisa (Italy)

http://blog.linux.it/raistlin / raistlin@xxxxxxxxx /
dario.faggioli@xxxxxxxxxx

Attachment: signature.asc
Description: This is a digitally signed message part