Greetings,
The semaphore scalability changes have a less than wonderful trait for
-rt. The below.. makes it not do that. I originally did this to test
(and actually survive) scalability patches backported to 3.0-rt on a 64
core box, and was just rudely reminded of the problem after putting
3.10-rt onto the same box for latency comparison.
goto again loop can and does induce livelock in -rt. Remove it.
Signed-off-by: Mike Galbraith <bitbucket@xxxxxxxxx>
---
ipc/sem.c | 56 ++++++++++++++++++++++++++++++++++++++------------------
1 file changed, 38 insertions(+), 18 deletions(-)
Index: linux-2.6/ipc/sem.c
===================================================================
--- linux-2.6.orig/ipc/sem.c
+++ linux-2.6/ipc/sem.c
@@ -208,22 +208,11 @@ void __init sem_init (void)
static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
int nsops)
{
+ struct sem *sem;
int locknum;
- again:
- if (nsops == 1 && !sma->complex_count) {
- struct sem *sem = sma->sem_base + sops->sem_num;
-
- /* Lock just the semaphore we are interested in. */
- spin_lock(&sem->lock);
- /*
- * If sma->complex_count was set while we were spinning,
- * we may need to look at things we did not lock here.
- */
- if (unlikely(sma->complex_count)) {
- spin_unlock(&sem->lock);
- goto lock_array;
- }
+ if (nsops == 1 && !sma->complex_count) {
+ sem = sma->sem_base + sops->sem_num;
/*
* Another process is holding the global lock on the
@@ -231,9 +220,29 @@ static inline int sem_lock(struct sem_ar
* but have to wait for the global lock to be released.
*/
if (unlikely(spin_is_locked(&sma->sem_perm.lock))) {
- spin_unlock(&sem->lock);
- spin_unlock_wait(&sma->sem_perm.lock);
- goto again;
+ spin_lock(&sma->sem_perm.lock);
+ if (sma->complex_count)
+ goto wait_array;
+
+ /*
+ * Acquiring our sem->lock under the global lock
+ * forces new complex operations to wait for us
+ * to exit our critical section.
+ */
+ spin_lock(&sem->lock);
+ spin_unlock(&sma->sem_perm.lock);
+ } else {
+ /* Lock just the semaphore we are interested in. */
+ spin_lock(&sem->lock);
+
+ /*
+ * If sma->complex_count was set prior to acquisition,
+ * we must fall back to the global array lock.
+ */
+ if (unlikely(sma->complex_count)) {
+ spin_unlock(&sem->lock);
+ goto lock_array;
+ }
}
locknum = sops->sem_num;
@@ -247,11 +256,22 @@ static inline int sem_lock(struct sem_ar
*/
lock_array:
spin_lock(&sma->sem_perm.lock);
+ wait_array:
for (i = 0; i < sma->sem_nsems; i++) {
- struct sem *sem = sma->sem_base + i;
+ sem = sma->sem_base + i;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ if (spin_is_locked(&sem->lock))
+#endif
spin_unlock_wait(&sem->lock);
}
locknum = -1;
+
+ if (nsops == 1 && !sma->complex_count) {
+ sem = sma->sem_base + sops->sem_num;
+ spin_lock(&sem->lock);
+ spin_unlock(&sma->sem_perm.lock);
+ locknum = sops->sem_num;
+ }
}
return locknum;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
