/*
* CheckDeadLock
*
* We only get to this routine, if DEADLOCK_TIMEOUT fired while waiting for a
* lock to be released by some other process. Check if there's a deadlock; if
* not, just return. (But signal ProcSleep to log a message, if
* log_lock_waits is true.) If we have a real deadlock, remove ourselves from
* the lock's wait queue and signal an error to ProcSleep.
*/
static void
CheckDeadLock(void)
{
int i;
/*
* Acquire exclusive lock on the entire shared lock data structures. Must
* grab LWLocks in partition-number order to avoid LWLock deadlock.
*
* Note that the deadlock check interrupt had better not be enabled
* anywhere that this process itself holds lock partition locks, else this
* will wait forever. Also note that LWLockAcquire creates a critical
* section, so that this routine cannot be interrupted by cancel/die
* interrupts.
*/
for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
LWLockAcquire(LockHashPartitionLockByIndex(i), LW_EXCLUSIVE);
/*
* Check to see if we've been awoken by anyone in the interim.
*
* If we have, we can return and resume our transaction -- happy day.
* Before we are awoken the process releasing the lock grants it to us so
* we know that we don't have to wait anymore.
*
* We check by looking to see if we've been unlinked from the wait queue.
* This is quicker than checking our semaphore's state, since no kernel
* call is needed, and it is safe because we hold the lock partition lock.
*/
if (MyProc->links.prev == NULL ||
MyProc->links.next == NULL)
goto check_done;
#ifdef LOCK_DEBUG
if (Debug_deadlocks)
DumpAllLocks();
#endif
/* Run the deadlock check, and set deadlock_state for use by ProcSleep */
deadlock_state = DeadLockCheck(MyProc);
if (deadlock_state == DS_HARD_DEADLOCK)
{
/*
* Oops. We have a deadlock.
*
* Get this process out of wait state. (Note: we could do this more
* efficiently by relying on lockAwaited, but use this coding to
* preserve the flexibility to kill some other transaction than the
* one detecting the deadlock.)
*
* RemoveFromWaitQueue sets MyProc->waitStatus to STATUS_ERROR, so
* ProcSleep will report an error after we return from the signal
* handler.
*/
Assert(MyProc->waitLock != NULL);
RemoveFromWaitQueue(MyProc, LockTagHashCode(&(MyProc->waitLock->tag)));
/*
* We're done here. Transaction abort caused by the error that
* ProcSleep will raise will cause any other locks we hold to be
* released, thus allowing other processes to wake up; we don't need
* to do that here. NOTE: an exception is that releasing locks we
* hold doesn't consider the possibility of waiters that were blocked
* behind us on the lock we just failed to get, and might now be
* wakable because we're not in front of them anymore. However,
* RemoveFromWaitQueue took care of waking up any such processes.
*/
}
/*
* And release locks. We do this in reverse order for two reasons: (1)
* Anyone else who needs more than one of the locks will be trying to lock
* them in increasing order; we don't want to release the other process
* until it can get all the locks it needs. (2) This avoids O(N^2)
* behavior inside LWLockRelease.
*/
check_done:
for (i = NUM_LOCK_PARTITIONS; --i >= 0;)
LWLockRelease(LockHashPartitionLockByIndex(i));
}
/*
* CheckDeadLock
*
* We only get to this routine if we got SIGALRM after DeadlockTimeout
* while waiting for a lock to be released by some other process. Look
* to see if there's a deadlock; if not, just return and continue waiting.
* (But signal ProcSleep to log a message, if log_lock_waits is true.)
* If we have a real deadlock, remove ourselves from the lock's wait queue
* and signal an error to ProcSleep.
*
* NB: this is run inside a signal handler, so be very wary about what is done
* here or in called routines.
*/
static void
CheckDeadLock(void)
{
int i;
/*
* Acquire exclusive lock on the entire shared lock data structures. Must
* grab LWLocks in partition-number order to avoid LWLock deadlock.
*
* Note that the deadlock check interrupt had better not be enabled
* anywhere that this process itself holds lock partition locks, else this
* will wait forever. Also note that LWLockAcquire creates a critical
* section, so that this routine cannot be interrupted by cancel/die
* interrupts.
*/
for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
LWLockAcquire(FirstLockMgrLock + i, LW_EXCLUSIVE);
/*
* Check to see if we've been awoken by anyone in the interim.
*
* If we have, we can return and resume our transaction -- happy day.
* Before we are awoken the process releasing the lock grants it to us
* so we know that we don't have to wait anymore.
*
* We check by looking to see if we've been unlinked from the wait queue.
* This is quicker than checking our semaphore's state, since no kernel
* call is needed, and it is safe because we hold the lock partition lock.
*/
if (MyProc->links.prev == INVALID_OFFSET ||
MyProc->links.next == INVALID_OFFSET)
goto check_done;
#ifdef LOCK_DEBUG
if (Debug_deadlocks)
DumpAllLocks();
#endif
if (!DeadLockCheck(MyProc))
{
/* No deadlock, so keep waiting */
goto check_done;
}
/*
* Unlock my semaphore so that the interrupted ProcSleep() call can
* finish.
*/
PGSemaphoreUnlock(&MyProc->sem);
/*
* We're done here. Transaction abort caused by the error that ProcSleep
* will raise will cause any other locks we hold to be released, thus
* allowing other processes to wake up; we don't need to do that here.
* NOTE: an exception is that releasing locks we hold doesn't consider the
* possibility of waiters that were blocked behind us on the lock we just
* failed to get, and might now be wakable because we're not in front of
* them anymore. However, RemoveFromWaitQueue took care of waking up any
* such processes.
*/
/*
* Release locks acquired at head of routine. Order is not critical, so
* do it back-to-front to avoid waking another CheckDeadLock instance
* before it can get all the locks.
*/
check_done:
for (i = NUM_LOCK_PARTITIONS; --i >= 0;)
LWLockRelease(FirstLockMgrLock + i);
}
