drbd: Fixed a deadlock, probably only affected UP machines

After disconnect (most likely mdev->net_cnt == 0) and we are
still in an unstable state (!drbd_state_is_stable()). When we
get an IO request in drbd_get_max_buffers() (called from
__inc_ap_bio_cond(), called from inc_ap_bio()) we wake up
misc_wait. Misc_wait is also used in inc_ap_bio() to sleep
until the outcome of __inc_ap_bio_cond() changes. => Busy loop!

Solution: Have a dedicated wait queue for get_net_conf() and
put_net_conf().

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
This commit is contained in:
Philipp Reisner 2010-06-23 11:20:05 +02:00
parent 65d922c33e
commit 84dfb9f564
3 changed files with 4 additions and 2 deletions

View File

@ -947,6 +947,7 @@ struct drbd_conf {
union drbd_state state;
wait_queue_head_t misc_wait;
wait_queue_head_t state_wait; /* upon each state change. */
wait_queue_head_t net_cnt_wait;
unsigned int send_cnt;
unsigned int recv_cnt;
unsigned int read_cnt;
@ -2018,7 +2019,7 @@ static inline void inc_unacked(struct drbd_conf *mdev)
static inline void put_net_conf(struct drbd_conf *mdev)
{
if (atomic_dec_and_test(&mdev->net_cnt))
wake_up(&mdev->misc_wait);
wake_up(&mdev->net_cnt_wait);
}
/**

View File

@ -2763,6 +2763,7 @@ void drbd_init_set_defaults(struct drbd_conf *mdev)
init_waitqueue_head(&mdev->misc_wait);
init_waitqueue_head(&mdev->state_wait);
init_waitqueue_head(&mdev->net_cnt_wait);
init_waitqueue_head(&mdev->ee_wait);
init_waitqueue_head(&mdev->al_wait);
init_waitqueue_head(&mdev->seq_wait);

View File

@ -3775,7 +3775,7 @@ static void drbd_disconnect(struct drbd_conf *mdev)
if (os.conn == C_DISCONNECTING) {
struct hlist_head *h;
wait_event(mdev->misc_wait, atomic_read(&mdev->net_cnt) == 0);
wait_event(mdev->net_cnt_wait, atomic_read(&mdev->net_cnt) == 0);
/* we must not free the tl_hash
* while application io is still on the fly */