FWIW, I think I have a kinda-sorta solution for bufmap slot allocation/waiting;
if somebody has a better idea, I would love to drop the variant below. And
I would certainly appreciate review - I hate messing with waitqueue primitives
and I know how easy it is to fuck those up ;-/
Below is a mockup of that thing:
/* Three possible states: absent, installed and shutting down.
* install(map, count, bitmap) sets it up
* get(map)/put(map, slot) allocate and free resp.
* mark_dead(map) moves to shutdown state - no new allocations succeed until
* we reinstall it.
* run_down(map) waits for all allocations to be released; in the end, we
* are in the "absent" state again.
*
* get() is not allowed to take longer than slot_timeout_secs seconds total;
* if the thing gets shut down and reinstalled during the wait, we are OK
* as long as reinstall comes within restart_timeout_secs. For orangefs
* those default to 15 minutes and 30 seconds resp...
*/
struct slot_map {
int c; // absent -> -1
// installed and full -> 0
// installed with n slots free -> n
// shutting down, with n slots in use -> -1-n
wait_queue_head_t q; // q.lock protects everything here.
int count;
unsigned long *map;
};
void install(struct slot_map *m, int count, unsigned long *map)
{
spin_lock(&m->q.lock);
m->c = m->count = count;
m->map = map;
wake_up_all_locked(&m->q);
spin_unlock(&m->q.lock);
}
void mark_killed(struct slot_map *m)
{
spin_lock(&m->q.lock);
m->c -= m->count + 1;
spin_unlock(&m->q.lock);
}
void run_down(struct slot_map *m)
{
DEFINE_WAIT(wait);
spin_lock(&m->q.lock);
#if 0
// we don't have wait_event_locked(); might be worth adding.
wait_event_locked(&m->q, m->c == -1);
#else
// or we can open-code it
if (m->c != -1) {
for (;;) {
if (likely(list_empty(&wait.task_list)))
__add_wait_queue_tail(&m->q, &wait);
set_current_state(TASK_UNINTERRUPTIBLE);
if (m->c == -1)
break;
spin_unlock(&m->q.lock);
schedule();
spin_lock(&m->q.lock);
}
__remove_wait_queue(&m->q, &wait);
__set_current_state(TASK_RUNNING);
}
#endif
m->map = NULL;
spin_unlock(&m->q.lock);
}
void put(struct slot_map *m, int slot)
{
int v;
spin_lock(&m->q.lock);
__clear_bit(slot, m->map);
v = ++m->c;
if (unlikely(v == 1)) /* no free slots -> one free slot */
wake_up_locked(&m->q);
else if (unlikely(v == -1)) /* finished dying */
wake_up_all_locked(&m->q);
spin_unlock(&m->q.lock);
}
static int wait_for_free(struct slot_map *m)
{
long left = slot_timeout_secs * HZ;
DEFINE_WAIT(wait);
#if 0
// the trouble is, there's no wait_event_interruptible_timeout_locked()
// might be worth adding...
do {
if (m->c > 0)
break;
if (m->c < 0) {
/* we are waiting for map to be installed */
/* it would better be there soon, or we go away */
long n = left, t;
if (n > restart_timeout_secs * HZ)
n = restart_timeout_secs * HZ;
t = wait_event_interruptible_timeout_locked(&m->q,
m->c > 0, n);
if (unlikely(t < 0) || (!t && m->c < 0))
left = t;
else
left = t + (left - n);
} else {
/* just waiting for a slot to come free */
left = wait_event_interruptible_timeout_locked(&m->q,
m->c > 0, left);
}
} while (left > 0);
#else
// or we can open-code it
do {
if (likely(list_empty(&wait.task_list)))
__add_wait_queue_tail_exclusive(&m->q, &wait);
set_current_state(TASK_INTERRUPTIBLE);
if (m->c > 0)
break;
if (m->c < 0) {
/* we are waiting for map to be installed */
/* it would better be there soon, or we go away */
long n = left, t;
if (n > ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS * HZ)
n = ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS * HZ;
spin_unlock(&m->q.lock);
t = schedule_timeout(n);
spin_lock(&m->q.lock);
if (unlikely(t < 0) || (!t && m->c < 0))
left = t;
else
left = t + (left - n);
} else {
/* just waiting for a slot to come free */
spin_unlock(&m->q.lock);
left = schedule_timeout(left);
spin_lock(&m->q.lock);
}
} while (left > 0);
__remove_wait_queue(&m->q, &wait);
__set_current_state(TASK_RUNNING);
#endif
if (likely(left > 0))
return 0;
return left < 0 ? -EINTR : -ETIMEDOUT;
}
int get(struct slot_map *m)
{
int res = 0;
spin_lock(&m->q.lock);
if (unlikely(m->c <= 0))
res = wait_for_free(m);
if (likely(!res)) {
m->c--;
res = find_first_zero_bit(m->map, m->count);
__set_bit(res, m->map);
}
spin_unlock(&m->q.lock);
return res;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
