static void
node_options_show(FILE *fp, Options o, Tree k)
{
char buf[64];
sprintf(buf, "%s: ", T_NAME(k));
options_show(stdout, o, buf);
}
inline static void
PRINT_LWDEBUG(const char *where, const LWLock *lock)
{
if (Trace_lwlocks)
elog(LOG, "%s(%s %d): excl %d shared %d head %p rOK %d",
where, T_NAME(lock), T_ID(lock),
(int) lock->exclusive, lock->shared, lock->head,
(int) lock->releaseOK);
}
/*
* LWLockWaitForVar - Wait until lock is free, or a variable is updated.
*
* If the lock is held and *valptr equals oldval, waits until the lock is
* either freed, or the lock holder updates *valptr by calling
* LWLockUpdateVar. If the lock is free on exit (immediately or after
* waiting), returns true. If the lock is still held, but *valptr no longer
* matches oldval, returns false and sets *newval to the current value in
* *valptr.
*
* It's possible that the lock holder releases the lock, but another backend
* acquires it again before we get a chance to observe that the lock was
* momentarily released. We wouldn't need to wait for the new lock holder,
* but we cannot distinguish that case, so we will have to wait.
*
* Note: this function ignores shared lock holders; if the lock is held
* in shared mode, returns 'true'.
*/
bool
LWLockWaitForVar(LWLock *lock, uint64 *valptr, uint64 oldval, uint64 *newval)
{
PGPROC *proc = MyProc;
int extraWaits = 0;
bool result = false;
#ifdef LWLOCK_STATS
lwlock_stats *lwstats;
#endif
PRINT_LWDEBUG("LWLockWaitForVar", lock);
#ifdef LWLOCK_STATS
lwstats = get_lwlock_stats_entry(lock);
#endif /* LWLOCK_STATS */
/*
* Quick test first to see if it the slot is free right now.
*
* XXX: the caller uses a spinlock before this, so we don't need a memory
* barrier here as far as the current usage is concerned. But that might
* not be safe in general.
*/
if (lock->exclusive == 0)
return true;
/*
* Lock out cancel/die interrupts while we sleep on the lock. There is no
* cleanup mechanism to remove us from the wait queue if we got
* interrupted.
*/
HOLD_INTERRUPTS();
/*
* Loop here to check the lock's status after each time we are signaled.
*/
for (;;)
{
bool mustwait;
uint64 value;
/* Acquire mutex. Time spent holding mutex should be short! */
#ifdef LWLOCK_STATS
lwstats->spin_delay_count += SpinLockAcquire(&lock->mutex);
#else
SpinLockAcquire(&lock->mutex);
#endif
/* Is the lock now free, and if not, does the value match? */
if (lock->exclusive == 0)
{
result = true;
mustwait = false;
}
else
{
value = *valptr;
if (value != oldval)
{
result = false;
mustwait = false;
*newval = value;
}
else
mustwait = true;
}
if (!mustwait)
break; /* the lock was free or value didn't match */
/*
* Add myself to wait queue.
*/
proc->lwWaiting = true;
proc->lwWaitMode = LW_WAIT_UNTIL_FREE;
/* waiters are added to the front of the queue */
proc->lwWaitLink = lock->head;
if (lock->head == NULL)
lock->tail = proc;
lock->head = proc;
/*
* Set releaseOK, to make sure we get woken up as soon as the lock is
* released.
*/
lock->releaseOK = true;
/* Can release the mutex now */
SpinLockRelease(&lock->mutex);
/*
* Wait until awakened.
*
* Since we share the process wait semaphore with the regular lock
* manager and ProcWaitForSignal, and we may need to acquire an LWLock
* while one of those is pending, it is possible that we get awakened
* for a reason other than being signaled by LWLockRelease. If so,
* loop back and wait again. Once we've gotten the LWLock,
* re-increment the sema by the number of additional signals received,
* so that the lock manager or signal manager will see the received
* signal when it next waits.
*/
LOG_LWDEBUG("LWLockWaitForVar", T_NAME(lock), T_ID(lock), "waiting");
#ifdef LWLOCK_STATS
lwstats->block_count++;
#endif
TRACE_POSTGRESQL_LWLOCK_WAIT_START(T_NAME(lock), T_ID(lock),
LW_EXCLUSIVE);
for (;;)
{
/* "false" means cannot accept cancel/die interrupt here. */
PGSemaphoreLock(&proc->sem, false);
if (!proc->lwWaiting)
break;
extraWaits++;
}
TRACE_POSTGRESQL_LWLOCK_WAIT_DONE(T_NAME(lock), T_ID(lock),
LW_EXCLUSIVE);
LOG_LWDEBUG("LWLockWaitForVar", T_NAME(lock), T_ID(lock), "awakened");
/* Now loop back and check the status of the lock again. */
}
/* We are done updating shared state of the lock itself. */
SpinLockRelease(&lock->mutex);
TRACE_POSTGRESQL_LWLOCK_ACQUIRE(T_NAME(lock), T_ID(lock), LW_EXCLUSIVE);
/*
* Fix the process wait semaphore's count for any absorbed wakeups.
*/
while (extraWaits-- > 0)
PGSemaphoreUnlock(&proc->sem);
/*
* Now okay to allow cancel/die interrupts.
*/
RESUME_INTERRUPTS();
return result;
}
/*
* LWLockAcquireOrWait - Acquire lock, or wait until it's free
*
* The semantics of this function are a bit funky. If the lock is currently
* free, it is acquired in the given mode, and the function returns true. If
* the lock isn't immediately free, the function waits until it is released
* and returns false, but does not acquire the lock.
*
* This is currently used for WALWriteLock: when a backend flushes the WAL,
* holding WALWriteLock, it can flush the commit records of many other
* backends as a side-effect. Those other backends need to wait until the
* flush finishes, but don't need to acquire the lock anymore. They can just
* wake up, observe that their records have already been flushed, and return.
*/
bool
LWLockAcquireOrWait(LWLock *lock, LWLockMode mode)
{
PGPROC *proc = MyProc;
bool mustwait;
int extraWaits = 0;
#ifdef LWLOCK_STATS
lwlock_stats *lwstats;
#endif
PRINT_LWDEBUG("LWLockAcquireOrWait", lock);
#ifdef LWLOCK_STATS
lwstats = get_lwlock_stats_entry(lock);
#endif
/* Ensure we will have room to remember the lock */
if (num_held_lwlocks >= MAX_SIMUL_LWLOCKS)
elog(ERROR, "too many LWLocks taken");
/*
* Lock out cancel/die interrupts until we exit the code section protected
* by the LWLock. This ensures that interrupts will not interfere with
* manipulations of data structures in shared memory.
*/
HOLD_INTERRUPTS();
/* Acquire mutex. Time spent holding mutex should be short! */
SpinLockAcquire(&lock->mutex);
/* If I can get the lock, do so quickly. */
if (mode == LW_EXCLUSIVE)
{
if (lock->exclusive == 0 && lock->shared == 0)
{
lock->exclusive++;
mustwait = false;
}
else
mustwait = true;
}
else
{
if (lock->exclusive == 0)
{
lock->shared++;
mustwait = false;
}
else
mustwait = true;
}
if (mustwait)
{
/*
* Add myself to wait queue.
*
* If we don't have a PGPROC structure, there's no way to wait. This
* should never occur, since MyProc should only be null during shared
* memory initialization.
*/
if (proc == NULL)
elog(PANIC, "cannot wait without a PGPROC structure");
proc->lwWaiting = true;
proc->lwWaitMode = LW_WAIT_UNTIL_FREE;
proc->lwWaitLink = NULL;
if (lock->head == NULL)
lock->head = proc;
else
lock->tail->lwWaitLink = proc;
lock->tail = proc;
/* Can release the mutex now */
SpinLockRelease(&lock->mutex);
/*
* Wait until awakened. Like in LWLockAcquire, be prepared for bogus
* wakups, because we share the semaphore with ProcWaitForSignal.
*/
LOG_LWDEBUG("LWLockAcquireOrWait", T_NAME(lock), T_ID(lock),
"waiting");
#ifdef LWLOCK_STATS
lwstats->block_count++;
#endif
TRACE_POSTGRESQL_LWLOCK_WAIT_START(T_NAME(lock), T_ID(lock), mode);
for (;;)
{
/* "false" means cannot accept cancel/die interrupt here. */
PGSemaphoreLock(&proc->sem, false);
if (!proc->lwWaiting)
break;
extraWaits++;
}
TRACE_POSTGRESQL_LWLOCK_WAIT_DONE(T_NAME(lock), T_ID(lock), mode);
LOG_LWDEBUG("LWLockAcquireOrWait", T_NAME(lock), T_ID(lock),
"awakened");
}
else
{
/* We are done updating shared state of the lock itself. */
SpinLockRelease(&lock->mutex);
}
/*
* Fix the process wait semaphore's count for any absorbed wakeups.
*/
while (extraWaits-- > 0)
PGSemaphoreUnlock(&proc->sem);
if (mustwait)
{
/* Failed to get lock, so release interrupt holdoff */
RESUME_INTERRUPTS();
LOG_LWDEBUG("LWLockAcquireOrWait", T_NAME(lock), T_ID(lock), "failed");
TRACE_POSTGRESQL_LWLOCK_ACQUIRE_OR_WAIT_FAIL(T_NAME(lock), T_ID(lock),
mode);
}
else
{
/* Add lock to list of locks held by this backend */
held_lwlocks[num_held_lwlocks++] = lock;
TRACE_POSTGRESQL_LWLOCK_ACQUIRE_OR_WAIT(T_NAME(lock), T_ID(lock),
mode);
}
return !mustwait;
}
/*
* LWLockConditionalAcquire - acquire a lightweight lock in the specified mode
*
* If the lock is not available, return FALSE with no side-effects.
*
* If successful, cancel/die interrupts are held off until lock release.
*/
bool
LWLockConditionalAcquire(LWLock *lock, LWLockMode mode)
{
bool mustwait;
PRINT_LWDEBUG("LWLockConditionalAcquire", lock);
/* Ensure we will have room to remember the lock */
if (num_held_lwlocks >= MAX_SIMUL_LWLOCKS)
elog(ERROR, "too many LWLocks taken");
/*
* Lock out cancel/die interrupts until we exit the code section protected
* by the LWLock. This ensures that interrupts will not interfere with
* manipulations of data structures in shared memory.
*/
HOLD_INTERRUPTS();
/* Acquire mutex. Time spent holding mutex should be short! */
SpinLockAcquire(&lock->mutex);
/* If I can get the lock, do so quickly. */
if (mode == LW_EXCLUSIVE)
{
if (lock->exclusive == 0 && lock->shared == 0)
{
lock->exclusive++;
mustwait = false;
}
else
mustwait = true;
}
else
{
if (lock->exclusive == 0)
{
lock->shared++;
mustwait = false;
}
else
mustwait = true;
}
/* We are done updating shared state of the lock itself. */
SpinLockRelease(&lock->mutex);
if (mustwait)
{
/* Failed to get lock, so release interrupt holdoff */
RESUME_INTERRUPTS();
LOG_LWDEBUG("LWLockConditionalAcquire",
T_NAME(lock), T_ID(lock), "failed");
TRACE_POSTGRESQL_LWLOCK_CONDACQUIRE_FAIL(T_NAME(lock),
T_ID(lock), mode);
}
else
{
/* Add lock to list of locks held by this backend */
held_lwlocks[num_held_lwlocks++] = lock;
TRACE_POSTGRESQL_LWLOCK_CONDACQUIRE(T_NAME(lock), T_ID(lock), mode);
}
return !mustwait;
}
/* internal function to implement LWLockAcquire and LWLockAcquireWithVar */
static inline bool
LWLockAcquireCommon(LWLock *lock, LWLockMode mode, uint64 *valptr, uint64 val)
{
PGPROC *proc = MyProc;
bool retry = false;
bool result = true;
int extraWaits = 0;
#ifdef LWLOCK_STATS
lwlock_stats *lwstats;
#endif
PRINT_LWDEBUG("LWLockAcquire", lock);
#ifdef LWLOCK_STATS
lwstats = get_lwlock_stats_entry(lock);
/* Count lock acquisition attempts */
if (mode == LW_EXCLUSIVE)
lwstats->ex_acquire_count++;
else
lwstats->sh_acquire_count++;
#endif /* LWLOCK_STATS */
/*
* We can't wait if we haven't got a PGPROC. This should only occur
* during bootstrap or shared memory initialization. Put an Assert here
* to catch unsafe coding practices.
*/
Assert(!(proc == NULL && IsUnderPostmaster));
/* Ensure we will have room to remember the lock */
if (num_held_lwlocks >= MAX_SIMUL_LWLOCKS)
elog(ERROR, "too many LWLocks taken");
/*
* Lock out cancel/die interrupts until we exit the code section protected
* by the LWLock. This ensures that interrupts will not interfere with
* manipulations of data structures in shared memory.
*/
HOLD_INTERRUPTS();
/*
* Loop here to try to acquire lock after each time we are signaled by
* LWLockRelease.
*
* NOTE: it might seem better to have LWLockRelease actually grant us the
* lock, rather than retrying and possibly having to go back to sleep. But
* in practice that is no good because it means a process swap for every
* lock acquisition when two or more processes are contending for the same
* lock. Since LWLocks are normally used to protect not-very-long
* sections of computation, a process needs to be able to acquire and
* release the same lock many times during a single CPU time slice, even
* in the presence of contention. The efficiency of being able to do that
* outweighs the inefficiency of sometimes wasting a process dispatch
* cycle because the lock is not free when a released waiter finally gets
* to run. See pgsql-hackers archives for 29-Dec-01.
*/
for (;;)
{
bool mustwait;
/* Acquire mutex. Time spent holding mutex should be short! */
#ifdef LWLOCK_STATS
lwstats->spin_delay_count += SpinLockAcquire(&lock->mutex);
#else
SpinLockAcquire(&lock->mutex);
#endif
/* If retrying, allow LWLockRelease to release waiters again */
if (retry)
lock->releaseOK = true;
/* If I can get the lock, do so quickly. */
if (mode == LW_EXCLUSIVE)
{
if (lock->exclusive == 0 && lock->shared == 0)
{
lock->exclusive++;
mustwait = false;
}
else
mustwait = true;
}
else
{
if (lock->exclusive == 0)
{
lock->shared++;
mustwait = false;
}
else
mustwait = true;
}
if (!mustwait)
break; /* got the lock */
/*
* Add myself to wait queue.
*
* If we don't have a PGPROC structure, there's no way to wait. This
* should never occur, since MyProc should only be null during shared
* memory initialization.
*/
if (proc == NULL)
elog(PANIC, "cannot wait without a PGPROC structure");
proc->lwWaiting = true;
proc->lwWaitMode = mode;
proc->lwWaitLink = NULL;
if (lock->head == NULL)
lock->head = proc;
else
lock->tail->lwWaitLink = proc;
lock->tail = proc;
/* Can release the mutex now */
SpinLockRelease(&lock->mutex);
/*
* Wait until awakened.
*
* Since we share the process wait semaphore with the regular lock
* manager and ProcWaitForSignal, and we may need to acquire an LWLock
* while one of those is pending, it is possible that we get awakened
* for a reason other than being signaled by LWLockRelease. If so,
* loop back and wait again. Once we've gotten the LWLock,
* re-increment the sema by the number of additional signals received,
* so that the lock manager or signal manager will see the received
* signal when it next waits.
*/
LOG_LWDEBUG("LWLockAcquire", T_NAME(lock), T_ID(lock), "waiting");
#ifdef LWLOCK_STATS
lwstats->block_count++;
#endif
TRACE_POSTGRESQL_LWLOCK_WAIT_START(T_NAME(lock), T_ID(lock), mode);
for (;;)
{
/* "false" means cannot accept cancel/die interrupt here. */
PGSemaphoreLock(&proc->sem, false);
if (!proc->lwWaiting)
break;
extraWaits++;
}
TRACE_POSTGRESQL_LWLOCK_WAIT_DONE(T_NAME(lock), T_ID(lock), mode);
LOG_LWDEBUG("LWLockAcquire", T_NAME(lock), T_ID(lock), "awakened");
/* Now loop back and try to acquire lock again. */
retry = true;
result = false;
}
/* If there's a variable associated with this lock, initialize it */
if (valptr)
*valptr = val;
/* We are done updating shared state of the lock itself. */
SpinLockRelease(&lock->mutex);
TRACE_POSTGRESQL_LWLOCK_ACQUIRE(T_NAME(lock), T_ID(lock), mode);
/* Add lock to list of locks held by this backend */
held_lwlocks[num_held_lwlocks++] = lock;
/*
* Fix the process wait semaphore's count for any absorbed wakeups.
*/
while (extraWaits-- > 0)
PGSemaphoreUnlock(&proc->sem);
return result;
}
/*
* LWLockRelease - release a previously acquired lock
*/
void
LWLockRelease(LWLock *lock)
{
PGPROC *head;
PGPROC *proc;
int i;
PRINT_LWDEBUG("LWLockRelease", lock);
/*
* Remove lock from list of locks held. Usually, but not always, it will
* be the latest-acquired lock; so search array backwards.
*/
for (i = num_held_lwlocks; --i >= 0;)
{
if (lock == held_lwlocks[i])
break;
}
if (i < 0)
elog(ERROR, "lock %s %d is not held", T_NAME(lock), T_ID(lock));
num_held_lwlocks--;
for (; i < num_held_lwlocks; i++)
held_lwlocks[i] = held_lwlocks[i + 1];
/* Acquire mutex. Time spent holding mutex should be short! */
SpinLockAcquire(&lock->mutex);
/* Release my hold on lock */
if (lock->exclusive > 0)
lock->exclusive--;
else
{
Assert(lock->shared > 0);
lock->shared--;
}
/*
* See if I need to awaken any waiters. If I released a non-last shared
* hold, there cannot be anything to do. Also, do not awaken any waiters
* if someone has already awakened waiters that haven't yet acquired the
* lock.
*/
head = lock->head;
if (head != NULL)
{
if (lock->exclusive == 0 && lock->shared == 0 && lock->releaseOK)
{
/*
* Remove the to-be-awakened PGPROCs from the queue.
*/
bool releaseOK = true;
proc = head;
/*
* First wake up any backends that want to be woken up without
* acquiring the lock.
*/
while (proc->lwWaitMode == LW_WAIT_UNTIL_FREE && proc->lwWaitLink)
proc = proc->lwWaitLink;
/*
* If the front waiter wants exclusive lock, awaken him only.
* Otherwise awaken as many waiters as want shared access.
*/
if (proc->lwWaitMode != LW_EXCLUSIVE)
{
while (proc->lwWaitLink != NULL &&
proc->lwWaitLink->lwWaitMode != LW_EXCLUSIVE)
{
if (proc->lwWaitMode != LW_WAIT_UNTIL_FREE)
releaseOK = false;
proc = proc->lwWaitLink;
}
}
/* proc is now the last PGPROC to be released */
lock->head = proc->lwWaitLink;
proc->lwWaitLink = NULL;
/*
* Prevent additional wakeups until retryer gets to run. Backends
* that are just waiting for the lock to become free don't retry
* automatically.
*/
if (proc->lwWaitMode != LW_WAIT_UNTIL_FREE)
releaseOK = false;
lock->releaseOK = releaseOK;
}
else
{
/* lock is still held, can't awaken anything */
head = NULL;
}
}
/* We are done updating shared state of the lock itself. */
SpinLockRelease(&lock->mutex);
TRACE_POSTGRESQL_LWLOCK_RELEASE(T_NAME(lock), T_ID(lock));
/*
* Awaken any waiters I removed from the queue.
*/
while (head != NULL)
{
LOG_LWDEBUG("LWLockRelease", T_NAME(lock), T_ID(lock),
"release waiter");
proc = head;
head = proc->lwWaitLink;
proc->lwWaitLink = NULL;
/*
* Guarantee that lwWaiting being unset only becomes visible once the
* unlink from the link has completed. Otherwise the target backend
* could be woken up for other reason and enqueue for a new lock - if
* that happens before the list unlink happens, the list would end up
* being corrupted.
*
* The barrier pairs with the SpinLockAcquire() when enqueing for
* another lock.
*/
pg_write_barrier();
proc->lwWaiting = false;
PGSemaphoreUnlock(&proc->sem);
}
/*
* Now okay to allow cancel/die interrupts.
*/
RESUME_INTERRUPTS();
}
