Re: lock_timeout GUC patch - Review

diff -dcrpN pgsql.orig/doc/src/sgml/config.sgml pgsql/doc/src/sgml/config.sgml
*** pgsql.orig/doc/src/sgml/config.sgml	2010-07-26 10:05:37.000000000 +0200
--- pgsql/doc/src/sgml/config.sgml	2010-07-29 11:58:56.000000000 +0200
*************** COPY postgres_log FROM '/full/path/to/lo
*** 4479,4484 ****
--- 4479,4508 ----
        </listitem>
       </varlistentry>
  
+      <varlistentry id="guc-lock-timeout" xreflabel="lock_timeout">
+       <term><varname>lock_timeout</varname> (<type>integer</type>)</term>
+       <indexterm>
+        <primary><varname>lock_timeout</> configuration parameter</primary>
+       </indexterm>
+       <listitem>
+        <para>
+         Abort any statement that tries to acquire a heavy-weight lock (e.g. rows,
+         pages, tables, indices or other objects) and the lock has to wait more
+         than the specified number of milliseconds, starting from the time the
+         command arrives at the server from the client.
+         If <varname>log_min_error_statement</> is set to <literal>ERROR</> or lower,
+         the statement that timed out will also be logged. A value of zero
+         (the default) turns off the limitation.
+        </para>
+ 
+        <para>
+         Setting <varname>lock_timeout</> in
+         <filename>postgresql.conf</> is not recommended because it
+         affects all sessions.
+        </para>      
+       </listitem>   
+      </varlistentry>
+ 
       <varlistentry id="guc-vacuum-freeze-table-age" xreflabel="vacuum_freeze_table_age">
        <term><varname>vacuum_freeze_table_age</varname> (<type>integer</type>)</term>
        <indexterm>
diff -dcrpN pgsql.orig/doc/src/sgml/ref/lock.sgml pgsql/doc/src/sgml/ref/lock.sgml
*** pgsql.orig/doc/src/sgml/ref/lock.sgml	2010-04-03 09:23:01.000000000 +0200
--- pgsql/doc/src/sgml/ref/lock.sgml	2010-07-29 11:58:56.000000000 +0200
*************** LOCK [ TABLE ] [ ONLY ] <replaceable cla
*** 39,46 ****
     <literal>NOWAIT</literal> is specified, <command>LOCK
     TABLE</command> does not wait to acquire the desired lock: if it
     cannot be acquired immediately, the command is aborted and an
!    error is emitted.  Once obtained, the lock is held for the
!    remainder of the current transaction.  (There is no <command>UNLOCK
     TABLE</command> command; locks are always released at transaction
     end.)
    </para>
--- 39,49 ----
     <literal>NOWAIT</literal> is specified, <command>LOCK
     TABLE</command> does not wait to acquire the desired lock: if it
     cannot be acquired immediately, the command is aborted and an
!    error is emitted. If <varname>lock_timeout</varname> is set to a value
!    higher than 0, and the lock cannot be acquired under the specified
!    timeout value in milliseconds, the command is aborted and an error
!    is emitted. Once obtained, the lock is held for the remainder of  
!    the current transaction.  (There is no <command>UNLOCK
     TABLE</command> command; locks are always released at transaction
     end.)
    </para>
diff -dcrpN pgsql.orig/doc/src/sgml/ref/select.sgml pgsql/doc/src/sgml/ref/select.sgml
*** pgsql.orig/doc/src/sgml/ref/select.sgml	2010-06-20 13:59:13.000000000 +0200
--- pgsql/doc/src/sgml/ref/select.sgml	2010-07-29 11:58:56.000000000 +0200
*************** FOR SHARE [ OF <replaceable class="param
*** 1160,1165 ****
--- 1160,1173 ----
     </para>
  
     <para>
+     If <literal>NOWAIT</> option is not specified and <varname>lock_timeout</varname>
+     is set to a value higher than 0, and the lock needs to wait more than
+     the specified value in milliseconds, the command reports an error after
+     timing out, rather than waiting indefinitely. The note in the previous
+     paragraph applies to the <varname>lock_timeout</varname>, too.
+    </para>
+ 
+    <para>
      If specific tables are named in <literal>FOR UPDATE</literal>
      or <literal>FOR SHARE</literal>,
      then only rows coming from those tables are locked; any other
diff -dcrpN pgsql.orig/src/backend/port/posix_sema.c pgsql/src/backend/port/posix_sema.c
*** pgsql.orig/src/backend/port/posix_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql/src/backend/port/posix_sema.c	2010-07-29 11:58:56.000000000 +0200
***************
*** 24,29 ****
--- 24,30 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  
  #ifdef USE_NAMED_POSIX_SEMAPHORES
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 313,315 ****
--- 314,341 ----
  
  	return true;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0
+  * Return if lock_timeout expired
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	int			errStatus;
+ 
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 		errStatus = sem_wait(PG_SEM_REF(sema));
+ 		ImmediateInterruptOK = false;
+ 	} while (errStatus < 0 && errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errStatus < 0)
+ 		elog(FATAL, "sem_wait failed: %m");
+ }
diff -dcrpN pgsql.orig/src/backend/port/sysv_sema.c pgsql/src/backend/port/sysv_sema.c
*** pgsql.orig/src/backend/port/sysv_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql/src/backend/port/sysv_sema.c	2010-07-29 11:58:56.000000000 +0200
***************
*** 30,35 ****
--- 30,36 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  
  #ifndef HAVE_UNION_SEMUN
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 497,499 ****
--- 498,530 ----
  
  	return true;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0
+  * Return if lock_timeout expired
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	int			errStatus;
+ 	struct sembuf sops;
+ 
+ 	sops.sem_op = -1;			/* decrement */
+ 	sops.sem_flg = 0;
+ 	sops.sem_num = sema->semNum;
+ 
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 		errStatus = semop(sema->semId, &sops, 1);
+ 		ImmediateInterruptOK = false;
+ 	} while (errStatus < 0 && errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errStatus < 0)
+ 		elog(FATAL, "semop(id=%d) failed: %m", sema->semId);
+ }
diff -dcrpN pgsql.orig/src/backend/port/win32_sema.c pgsql/src/backend/port/win32_sema.c
*** pgsql.orig/src/backend/port/win32_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql/src/backend/port/win32_sema.c	2010-07-29 11:58:56.000000000 +0200
***************
*** 16,21 ****
--- 16,22 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  static HANDLE *mySemSet;		/* IDs of sema sets acquired so far */
  static int	numSems;			/* number of sema sets acquired so far */
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 205,207 ****
--- 206,263 ----
  	/* keep compiler quiet */
  	return false;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0.
+  * Serve the interrupt if interruptOK is true.
+  * Return if lock_timeout expired.
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	DWORD		ret;
+ 	HANDLE		wh[2];
+ 
+ 	wh[0] = *sema;
+ 	wh[1] = pgwin32_signal_event;
+ 
+ 	/*
+ 	 * As in other implementations of PGSemaphoreLock, we need to check for
+ 	 * cancel/die interrupts each time through the loop.  But here, there is
+ 	 * no hidden magic about whether the syscall will internally service a
+ 	 * signal --- we do that ourselves.
+ 	 */
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 
+ 		errno = 0;
+ 		ret = WaitForMultipleObjectsEx(2, wh, FALSE, INFINITE, TRUE);
+ 
+ 		if (ret == WAIT_OBJECT_0)
+ 		{
+ 			/* We got it! */
+ 			return;
+ 		}
+ 		else if (ret == WAIT_OBJECT_0 + 1)
+ 		{
+ 			/* Signal event is set - we have a signal to deliver */
+ 			pgwin32_dispatch_queued_signals();
+ 			errno = EINTR;
+ 		}
+ 		else
+ 			/* Otherwise we are in trouble */
+ 			errno = EIDRM;
+ 
+ 		ImmediateInterruptOK = false;
+ 	} while (errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errno != 0)
+ 		ereport(FATAL,
+ 				(errmsg("could not lock semaphore: error code %d", (int) GetLastError())));
+ }
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/lmgr.c pgsql/src/backend/storage/lmgr/lmgr.c
*** pgsql.orig/src/backend/storage/lmgr/lmgr.c	2010-01-02 17:57:52.000000000 +0100
--- pgsql/src/backend/storage/lmgr/lmgr.c	2010-07-29 11:58:56.000000000 +0200
***************
*** 19,26 ****
--- 19,29 ----
  #include "access/transam.h"
  #include "access/xact.h"
  #include "catalog/catalog.h"
+ #include "catalog/pg_database.h"
  #include "miscadmin.h"
  #include "storage/lmgr.h"
+ #include "utils/lsyscache.h"
+ #include "storage/proc.h"
  #include "storage/procarray.h"
  #include "utils/inval.h"
  
*************** LockRelationOid(Oid relid, LOCKMODE lock
*** 78,83 ****
--- 81,101 ----
  
  	res = LockAcquire(&tag, lockmode, false, false);
  
+ 	if (res == LOCKACQUIRE_NOT_AVAIL)
+ 	{
+ 		char	   *relname = get_rel_name(relid);
+ 		if (relname)
+ 			ereport(ERROR,
+ 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 						errmsg("could not obtain lock on relation \"%s\"",
+ 						relname)));
+ 		else
+ 			ereport(ERROR,
+ 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 						errmsg("could not obtain lock on relation with OID %u",
+ 						relid)));
+ 	}
+ 
  	/*
  	 * Now that we have the lock, check for invalidation messages, so that we
  	 * will update or flush any stale relcache entry before we try to use it.
*************** LockRelation(Relation relation, LOCKMODE
*** 173,178 ****
--- 191,202 ----
  
  	res = LockAcquire(&tag, lockmode, false, false);
  
+ 	if (res == LOCKACQUIRE_NOT_AVAIL)
+ 		ereport(ERROR,
+ 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 					errmsg("could not obtain lock on relation \"%s\"",
+ 				RelationGetRelationName(relation))));
+ 
  	/*
  	 * Now that we have the lock, check for invalidation messages; see notes
  	 * in LockRelationOid.
*************** LockRelationIdForSession(LockRelId *reli
*** 250,256 ****
  
  	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);
  
! 	(void) LockAcquire(&tag, lockmode, true, false);
  }
  
  /*
--- 274,293 ----
  
  	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);
  
! 	if (LockAcquire(&tag, lockmode, true, false) == LOCKACQUIRE_NOT_AVAIL)
! 	{
! 		char	   *relname = get_rel_name(relid->relId);
! 		if (relname)
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on relation \"%s\"",
! 						relname)));
! 		else
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on relation with OID %u",
! 						relid->relId)));
! 	}
  }
  
  /*
*************** LockRelationForExtension(Relation relati
*** 285,291 ****
  								relation->rd_lockInfo.lockRelId.dbId,
  								relation->rd_lockInfo.lockRelId.relId);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 322,332 ----
  								relation->rd_lockInfo.lockRelId.dbId,
  								relation->rd_lockInfo.lockRelId.relId);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on index \"%s\"",
! 				RelationGetRelationName(relation))));
  }
  
  /*
*************** LockPage(Relation relation, BlockNumber 
*** 319,325 ****
  					 relation->rd_lockInfo.lockRelId.relId,
  					 blkno);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 360,370 ----
  					 relation->rd_lockInfo.lockRelId.relId,
  					 blkno);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on page %u of relation \"%s\"",
! 				blkno, RelationGetRelationName(relation))));
  }
  
  /*
*************** LockTuple(Relation relation, ItemPointer
*** 375,381 ****
  					  ItemPointerGetBlockNumber(tid),
  					  ItemPointerGetOffsetNumber(tid));
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 420,430 ----
  					  ItemPointerGetBlockNumber(tid),
  					  ItemPointerGetOffsetNumber(tid));
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on row in relation \"%s\"",
! 				RelationGetRelationName(relation))));
  }
  
  /*
*************** XactLockTableInsert(TransactionId xid)
*** 429,435 ****
  
  	SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 	(void) LockAcquire(&tag, ExclusiveLock, false, false);
  }
  
  /*
--- 478,487 ----
  
  	SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 	if (LockAcquire(&tag, ExclusiveLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on transaction with ID %u", xid)));
  }
  
  /*
*************** XactLockTableWait(TransactionId xid)
*** 473,479 ****
  
  		SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 		(void) LockAcquire(&tag, ShareLock, false, false);
  
  		LockRelease(&tag, ShareLock, false);
  
--- 525,534 ----
  
  		SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 		if (LockAcquire(&tag, ShareLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on transaction with ID %u", xid)));
  
  		LockRelease(&tag, ShareLock, false);
  
*************** VirtualXactLockTableInsert(VirtualTransa
*** 531,537 ****
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	(void) LockAcquire(&tag, ExclusiveLock, false, false);
  }
  
  /*
--- 586,596 ----
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	if (LockAcquire(&tag, ExclusiveLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on virtual transaction with ID %u",
! 				vxid.localTransactionId)));
  }
  
  /*
*************** VirtualXactLockTableWait(VirtualTransact
*** 549,555 ****
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	(void) LockAcquire(&tag, ShareLock, false, false);
  
  	LockRelease(&tag, ShareLock, false);
  }
--- 608,618 ----
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	if (LockAcquire(&tag, ShareLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on virtual transaction with ID %u",
! 				vxid.localTransactionId)));
  
  	LockRelease(&tag, ShareLock, false);
  }
*************** LockDatabaseObject(Oid classid, Oid obji
*** 598,604 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 661,671 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on class:object: %u:%u",
! 				classid, objid)));
  }
  
  /*
*************** LockSharedObject(Oid classid, Oid objid,
*** 636,642 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  
  	/* Make sure syscaches are up-to-date with any changes we waited for */
  	AcceptInvalidationMessages();
--- 703,713 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on class:object: %u:%u",
! 				classid, objid)));
  
  	/* Make sure syscaches are up-to-date with any changes we waited for */
  	AcceptInvalidationMessages();
*************** LockSharedObjectForSession(Oid classid, 
*** 678,684 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, true, false);
  }
  
  /*
--- 749,770 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, true, false) == LOCKACQUIRE_NOT_AVAIL)
! 		switch(classid)
! 		{
! 		case DatabaseRelationId:
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on database with ID %u",
! 					objid)));
! 			break;
! 		default:
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on class:object: %u:%u",
! 					classid, objid)));
! 			break;
! 		}
  }
  
  /*
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/lock.c pgsql/src/backend/storage/lmgr/lock.c
*** pgsql.orig/src/backend/storage/lmgr/lock.c	2010-04-29 12:09:03.000000000 +0200
--- pgsql/src/backend/storage/lmgr/lock.c	2010-07-29 11:58:56.000000000 +0200
*************** PROCLOCK_PRINT(const char *where, const 
*** 255,261 ****
  static uint32 proclock_hash(const void *key, Size keysize);
  static void RemoveLocalLock(LOCALLOCK *locallock);
  static void GrantLockLocal(LOCALLOCK *locallock, ResourceOwner owner);
! static void WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner);
  static bool UnGrantLock(LOCK *lock, LOCKMODE lockmode,
  			PROCLOCK *proclock, LockMethod lockMethodTable);
  static void CleanUpLock(LOCK *lock, PROCLOCK *proclock,
--- 255,261 ----
  static uint32 proclock_hash(const void *key, Size keysize);
  static void RemoveLocalLock(LOCALLOCK *locallock);
  static void GrantLockLocal(LOCALLOCK *locallock, ResourceOwner owner);
! static int WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner);
  static bool UnGrantLock(LOCK *lock, LOCKMODE lockmode,
  			PROCLOCK *proclock, LockMethod lockMethodTable);
  static void CleanUpLock(LOCK *lock, PROCLOCK *proclock,
*************** ProcLockHashCode(const PROCLOCKTAG *proc
*** 447,453 ****
   *	dontWait: if true, don't wait to acquire lock
   *
   * Returns one of:
!  *		LOCKACQUIRE_NOT_AVAIL		lock not available, and dontWait=true
   *		LOCKACQUIRE_OK				lock successfully acquired
   *		LOCKACQUIRE_ALREADY_HELD	incremented count for lock already held
   *
--- 447,453 ----
   *	dontWait: if true, don't wait to acquire lock
   *
   * Returns one of:
!  *		LOCKACQUIRE_NOT_AVAIL		lock not available, either dontWait=true or timeout
   *		LOCKACQUIRE_OK				lock successfully acquired
   *		LOCKACQUIRE_ALREADY_HELD	incremented count for lock already held
   *
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 833,839 ****
  										 locktag->locktag_type,
  										 lockmode);
  
! 		WaitOnLock(locallock, owner);
  
  		TRACE_POSTGRESQL_LOCK_WAIT_DONE(locktag->locktag_field1,
  										locktag->locktag_field2,
--- 833,839 ----
  										 locktag->locktag_type,
  										 lockmode);
  
! 		status = WaitOnLock(locallock, owner);
  
  		TRACE_POSTGRESQL_LOCK_WAIT_DONE(locktag->locktag_field1,
  										locktag->locktag_field2,
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 848,867 ****
  		 * done when the lock was granted to us --- see notes in WaitOnLock.
  		 */
  
! 		/*
! 		 * Check the proclock entry status, in case something in the ipc
! 		 * communication doesn't work correctly.
! 		 */
! 		if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
  		{
! 			PROCLOCK_PRINT("LockAcquire: INCONSISTENT", proclock);
! 			LOCK_PRINT("LockAcquire: INCONSISTENT", lock, lockmode);
! 			/* Should we retry ? */
! 			LWLockRelease(partitionLock);
! 			elog(ERROR, "LockAcquire failed");
  		}
- 		PROCLOCK_PRINT("LockAcquire: granted", proclock);
- 		LOCK_PRINT("LockAcquire: granted", lock, lockmode);
  	}
  
  	LWLockRelease(partitionLock);
--- 848,879 ----
  		 * done when the lock was granted to us --- see notes in WaitOnLock.
  		 */
  
! 		switch (status)
  		{
! 		case STATUS_OK:
! 			/*
! 			 * Check the proclock entry status, in case something in the ipc
! 			 * communication doesn't work correctly.
! 			 */
! 			if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
! 			{
! 				PROCLOCK_PRINT("LockAcquire: INCONSISTENT", proclock);
! 				LOCK_PRINT("LockAcquire: INCONSISTENT", lock, lockmode);
! 				/* Should we retry ? */
! 				LWLockRelease(partitionLock);
! 				elog(ERROR, "LockAcquire failed");
! 			}
! 			PROCLOCK_PRINT("LockAcquire: granted", proclock);
! 			LOCK_PRINT("LockAcquire: granted", lock, lockmode);
! 			break;
! 		case STATUS_WAITING:
! 			PROCLOCK_PRINT("LockAcquire: timed out", proclock);
! 			LOCK_PRINT("LockAcquire: timed out", lock, lockmode);
! 			break;
! 		default:
! 			elog(ERROR, "LockAcquire invalid status");
! 			break;
  		}
  	}
  
  	LWLockRelease(partitionLock);
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 887,893 ****
  							   locktag->locktag_field2);
  	}
  
! 	return LOCKACQUIRE_OK;
  }
  
  /*
--- 899,905 ----
  							   locktag->locktag_field2);
  	}
  
! 	return (status == STATUS_OK ? LOCKACQUIRE_OK : LOCKACQUIRE_NOT_AVAIL);
  }
  
  /*
*************** GrantAwaitedLock(void)
*** 1165,1178 ****
   * Caller must have set MyProc->heldLocks to reflect locks already held
   * on the lockable object by this process.
   *
   * The appropriate partition lock must be held at entry.
   */
! static void
  WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner)
  {
  	LOCKMETHODID lockmethodid = LOCALLOCK_LOCKMETHOD(*locallock);
  	LockMethod	lockMethodTable = LockMethods[lockmethodid];
  	char	   *volatile new_status = NULL;
  
  	LOCK_PRINT("WaitOnLock: sleeping on lock",
  			   locallock->lock, locallock->tag.mode);
--- 1177,1196 ----
   * Caller must have set MyProc->heldLocks to reflect locks already held
   * on the lockable object by this process.
   *
+  * Result: returns value of ProcSleep()
+  *	STATUS_OK if we acquired the lock
+  *	STATUS_ERROR if not (deadlock)
+  *	STATUS_WAITING if not (timeout)
+  *
   * The appropriate partition lock must be held at entry.
   */
! static int
  WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner)
  {
  	LOCKMETHODID lockmethodid = LOCALLOCK_LOCKMETHOD(*locallock);
  	LockMethod	lockMethodTable = LockMethods[lockmethodid];
  	char	   *volatile new_status = NULL;
+ 	int		wait_status;
  
  	LOCK_PRINT("WaitOnLock: sleeping on lock",
  			   locallock->lock, locallock->tag.mode);
*************** WaitOnLock(LOCALLOCK *locallock, Resourc
*** 1214,1221 ****
  	 */
  	PG_TRY();
  	{
! 		if (ProcSleep(locallock, lockMethodTable) != STATUS_OK)
  		{
  			/*
  			 * We failed as a result of a deadlock, see CheckDeadLock(). Quit
  			 * now.
--- 1232,1244 ----
  	 */
  	PG_TRY();
  	{
! 		wait_status = ProcSleep(locallock, lockMethodTable);
! 		switch (wait_status)
  		{
+ 		case STATUS_OK:
+ 		case STATUS_WAITING:
+ 			break;
+ 		default:
  			/*
  			 * We failed as a result of a deadlock, see CheckDeadLock(). Quit
  			 * now.
*************** WaitOnLock(LOCALLOCK *locallock, Resourc
*** 1260,1267 ****
  		pfree(new_status);
  	}
  
! 	LOCK_PRINT("WaitOnLock: wakeup on lock",
  			   locallock->lock, locallock->tag.mode);
  }
  
  /*
--- 1283,1296 ----
  		pfree(new_status);
  	}
  
! 	if (wait_status == STATUS_OK)
! 		LOCK_PRINT("WaitOnLock: wakeup on lock",
! 			   locallock->lock, locallock->tag.mode);
! 	else if (wait_status == STATUS_WAITING)
! 		LOCK_PRINT("WaitOnLock: timeout on lock",
  			   locallock->lock, locallock->tag.mode);
+ 
+ 	return wait_status;
  }
  
  /*
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/proc.c pgsql/src/backend/storage/lmgr/proc.c
*** pgsql.orig/src/backend/storage/lmgr/proc.c	2010-07-11 11:14:54.000000000 +0200
--- pgsql/src/backend/storage/lmgr/proc.c	2010-07-29 13:08:19.000000000 +0200
***************
*** 52,57 ****
--- 52,59 ----
  /* GUC variables */
  int			DeadlockTimeout = 1000;
  int			StatementTimeout = 0;
+ int			LockTimeout = 0;
+ static int		CurrentLockTimeout = 0;
  bool		log_lock_waits = false;
  
  /* Pointer to this process's PGPROC struct, if any */
*************** static volatile bool statement_timeout_a
*** 79,98 ****
--- 81,107 ----
  static volatile bool deadlock_timeout_active = false;
  static volatile DeadLockState deadlock_state = DS_NOT_YET_CHECKED;
  volatile bool cancel_from_timeout = false;
+ static volatile bool lock_timeout_active = false;
+ volatile bool lock_timeout_detected = false;
  
  /* timeout_start_time is set when log_lock_waits is true */
  static TimestampTz timeout_start_time;
+ static TimestampTz timeout_fin_time;
  
  /* statement_fin_time is valid only if statement_timeout_active is true */
  static TimestampTz statement_fin_time;
  static TimestampTz statement_fin_time2; /* valid only in recovery */
  
+ /* lock_timeout_fin_time is valid only if lock_timeout_active is true */
+ static TimestampTz lock_timeout_fin_time;
  
  static void RemoveProcFromArray(int code, Datum arg);
  static void ProcKill(int code, Datum arg);
  static void AuxiliaryProcKill(int code, Datum arg);
  static bool CheckStatementTimeout(void);
+ static bool CheckLockTimeout(void);
  static bool CheckStandbyTimeout(void);
+ static bool enable_sig_alarm_for_lock_timeout(int delayms);
  
  
  /*
*************** ProcQueueInit(PROC_QUEUE *queue)
*** 797,803 ****
   * The lock table's partition lock must be held at entry, and will be held
   * at exit.
   *
!  * Result: STATUS_OK if we acquired the lock, STATUS_ERROR if not (deadlock).
   *
   * ASSUME: that no one will fiddle with the queue until after
   *		we release the partition lock.
--- 806,815 ----
   * The lock table's partition lock must be held at entry, and will be held
   * at exit.
   *
!  * Result:
!  *     STATUS_OK if we acquired the lock
!  *     STATUS_ERROR if not (deadlock)
!  *     STATUS_WAITING if not (timeout)
   *
   * ASSUME: that no one will fiddle with the queue until after
   *		we release the partition lock.
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 951,957 ****
  		elog(FATAL, "could not set timer for process wakeup");
  
  	/*
! 	 * If someone wakes us between LWLockRelease and PGSemaphoreLock,
  	 * PGSemaphoreLock will not block.	The wakeup is "saved" by the semaphore
  	 * implementation.	While this is normally good, there are cases where a
  	 * saved wakeup might be leftover from a previous operation (for example,
--- 963,978 ----
  		elog(FATAL, "could not set timer for process wakeup");
  
  	/*
! 	 * Reset timer so we are awaken in case of lock timeout.
! 	 * This doesn't modify the timer for deadlock check in case
! 	 * the deadlock check happens earlier.
! 	 */
! 	CurrentLockTimeout = LockTimeout;
! 	if (!enable_sig_alarm_for_lock_timeout(CurrentLockTimeout))
! 		elog(FATAL, "could not set timer for process wakeup");
! 
! 	/*
! 	 * If someone wakes us between LWLockRelease and PGSemaphoreTimedLock,
  	 * PGSemaphoreLock will not block.	The wakeup is "saved" by the semaphore
  	 * implementation.	While this is normally good, there are cases where a
  	 * saved wakeup might be leftover from a previous operation (for example,
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 969,975 ****
  	 */
  	do
  	{
! 		PGSemaphoreLock(&MyProc->sem, true);
  
  		/*
  		 * waitStatus could change from STATUS_WAITING to something else
--- 990,999 ----
  	 */
  	do
  	{
! 		PGSemaphoreTimedLock(&MyProc->sem, true);
! 
! 		if (lock_timeout_detected == true)
! 			break;
  
  		/*
  		 * waitStatus could change from STATUS_WAITING to something else
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 1109,1114 ****
--- 1133,1146 ----
  	LWLockAcquire(partitionLock, LW_EXCLUSIVE);
  
  	/*
+ 	 * If we're in timeout, so we're not waiting anymore and
+ 	 * we're not the one that the lock will be granted to.
+ 	 * So remove ourselves from the wait queue.
+ 	 */
+ 	if (lock_timeout_detected)
+ 		RemoveFromWaitQueue(MyProc, hashcode);
+ 
+ 	/*
  	 * We no longer want LockWaitCancel to do anything.
  	 */
  	lockAwaited = NULL;
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 1122,1129 ****
  	/*
  	 * We don't have to do anything else, because the awaker did all the
  	 * necessary update of the lock table and MyProc.
  	 */
! 	return MyProc->waitStatus;
  }
  
  
--- 1154,1163 ----
  	/*
  	 * We don't have to do anything else, because the awaker did all the
  	 * necessary update of the lock table and MyProc.
+ 	 * RemoveFromWaitQueue() have set MyProc->waitStatus = STATUS_ERROR,
+ 	 * we need to distinguish this case.
  	 */
! 	return (lock_timeout_detected ? STATUS_WAITING : MyProc->waitStatus);
  }
  
  
*************** enable_sig_alarm(int delayms, bool is_st
*** 1462,1479 ****
  		 * than normal, but that does no harm.
  		 */
  		timeout_start_time = GetCurrentTimestamp();
! 		fin_time = TimestampTzPlusMilliseconds(timeout_start_time, delayms);
  		deadlock_timeout_active = true;
! 		if (fin_time >= statement_fin_time)
  			return true;
  	}
  	else
  	{
  		/* Begin deadlock timeout with no statement-level timeout */
  		deadlock_timeout_active = true;
! 		/* GetCurrentTimestamp can be expensive, so only do it if we must */
! 		if (log_lock_waits)
! 			timeout_start_time = GetCurrentTimestamp();
  	}
  
  	/* If we reach here, okay to set the timer interrupt */
--- 1496,1564 ----
  		 * than normal, but that does no harm.
  		 */
  		timeout_start_time = GetCurrentTimestamp();
! 		timeout_fin_time = TimestampTzPlusMilliseconds(timeout_start_time, delayms);
  		deadlock_timeout_active = true;
! 		if (timeout_fin_time >= statement_fin_time)
  			return true;
  	}
  	else
  	{
  		/* Begin deadlock timeout with no statement-level timeout */
  		deadlock_timeout_active = true;
! 		/*
! 		 * Computing the timeout_fin_time is needed because
! 		 * the lock timeout logic checks for it.
! 		 */
! 		timeout_start_time = GetCurrentTimestamp();
! 		timeout_fin_time = TimestampTzPlusMilliseconds(timeout_start_time, delayms);
! 	}
! 
! 	/* If we reach here, okay to set the timer interrupt */
! 	MemSet(&timeval, 0, sizeof(struct itimerval));
! 	timeval.it_value.tv_sec = delayms / 1000;
! 	timeval.it_value.tv_usec = (delayms % 1000) * 1000;
! 	if (setitimer(ITIMER_REAL, &timeval, NULL))
! 		return false;
! 	return true;
! }
! 
! /*
!  * Enable the SIGALRM interrupt to fire after the specified delay
!  * in case LockTimeout is set.
!  *
!  * This code properly handles nesting of lock_timeout timeout alarm
!  * within deadlock timeout and statement timeout alarms.
!  *
!  * Returns TRUE if okay, FALSE on failure.
!  */
! static bool
! enable_sig_alarm_for_lock_timeout(int delayms)
! {
! 	struct itimerval	timeval;
! 	TimestampTz		fin_time;
! 
! 	lock_timeout_detected = false;
! 	if (LockTimeout == 0)
! 		return true;
! 
! 	if (deadlock_timeout_active)
! 		/*
! 		 * ensure the same starting time for deadlock_timeout and lock_timeout
! 		 */
! 		fin_time = timeout_start_time;
! 	else
! 		fin_time = GetCurrentTimestamp();
! 	fin_time = TimestampTzPlusMilliseconds(fin_time, delayms);
! 
! 	if (statement_timeout_active)
! 	{
! 		if (fin_time > statement_fin_time)
! 			return true;
! 	}
! 	else if (deadlock_timeout_active)
! 	{
! 		if (fin_time > timeout_fin_time)
! 			return true;
  	}
  
  	/* If we reach here, okay to set the timer interrupt */
*************** enable_sig_alarm(int delayms, bool is_st
*** 1482,1487 ****
--- 1567,1575 ----
  	timeval.it_value.tv_usec = (delayms % 1000) * 1000;
  	if (setitimer(ITIMER_REAL, &timeval, NULL))
  		return false;
+ 
+ 	lock_timeout_fin_time = fin_time;
+ 	lock_timeout_active = true;
  	return true;
  }
  
*************** disable_sig_alarm(bool is_statement_time
*** 1502,1508 ****
  	 *
  	 * We will re-enable the interrupt if necessary in CheckStatementTimeout.
  	 */
! 	if (statement_timeout_active || deadlock_timeout_active)
  	{
  		struct itimerval timeval;
  
--- 1590,1596 ----
  	 *
  	 * We will re-enable the interrupt if necessary in CheckStatementTimeout.
  	 */
! 	if (statement_timeout_active || deadlock_timeout_active || lock_timeout_active)
  	{
  		struct itimerval timeval;
  
*************** disable_sig_alarm(bool is_statement_time
*** 1512,1517 ****
--- 1600,1607 ----
  			statement_timeout_active = false;
  			cancel_from_timeout = false;
  			deadlock_timeout_active = false;
+ 			lock_timeout_active = false;
+ 			lock_timeout_detected = false;
  			return false;
  		}
  	}
*************** disable_sig_alarm(bool is_statement_time
*** 1525,1534 ****
  		statement_timeout_active = false;
  		cancel_from_timeout = false;
  	}
! 	else if (statement_timeout_active)
  	{
! 		if (!CheckStatementTimeout())
! 			return false;
  	}
  	return true;
  }
--- 1615,1633 ----
  		statement_timeout_active = false;
  		cancel_from_timeout = false;
  	}
! 	else
  	{
! 		if (statement_timeout_active)
! 		{
! 			if (!CheckStatementTimeout())
! 				return false;
! 		}
! 
! 		if (lock_timeout_active)
! 		{
! 			if (!CheckLockTimeout())
! 				return false;
! 		}
  	}
  	return true;
  }
*************** CheckStatementTimeout(void)
*** 1590,1595 ****
--- 1689,1744 ----
  
  
  /*
+  * Check for lock timeout.  If the timeout time has come,
+  * indicate it; if not, reschedule the SIGALRM interrupt to occur
+  * at the right time.
+  *
+  * Returns true if okay, false if failed to set the interrupt.
+  */
+ static bool
+ CheckLockTimeout(void)
+ {
+ 	TimestampTz now;
+ 
+ 	if (!lock_timeout_active)
+ 		return true;			/* do nothing if not active */
+ 
+ 	now = GetCurrentTimestamp();
+ 
+ 	if (now >= lock_timeout_fin_time)
+ 	{
+ 		/* Time to die */
+ 		lock_timeout_active = false;
+ 		lock_timeout_detected = true;
+ 	}
+ 	else
+ 	{
+ 		/* Not time yet, so (re)schedule the interrupt */
+ 		long		secs;
+ 		int			usecs;
+ 		struct itimerval timeval;
+ 
+ 		TimestampDifference(now, statement_fin_time,
+ 							&secs, &usecs);
+ 
+ 		/*
+ 		 * It's possible that the difference is less than a microsecond;
+ 		 * ensure we don't cancel, rather than set, the interrupt.
+ 		 */
+ 		if (secs == 0 && usecs == 0)
+ 			usecs = 1;
+ 		MemSet(&timeval, 0, sizeof(struct itimerval));
+ 		timeval.it_value.tv_sec = secs;
+ 		timeval.it_value.tv_usec = usecs;
+ 		if (setitimer(ITIMER_REAL, &timeval, NULL))
+ 			return false;
+ 	}
+ 
+ 	return true;
+ }
+ 
+ 
+ /*
   * Signal handler for SIGALRM for normal user backends
   *
   * Process deadlock check and/or statement timeout check, as needed.
*************** handle_sig_alarm(SIGNAL_ARGS)
*** 1608,1613 ****
--- 1757,1765 ----
  		CheckDeadLock();
  	}
  
+ 	if (lock_timeout_active)
+ 		(void) CheckLockTimeout();
+ 
  	if (statement_timeout_active)
  		(void) CheckStatementTimeout();
  
diff -dcrpN pgsql.orig/src/backend/utils/misc/guc.c pgsql/src/backend/utils/misc/guc.c
*** pgsql.orig/src/backend/utils/misc/guc.c	2010-07-26 10:05:55.000000000 +0200
--- pgsql/src/backend/utils/misc/guc.c	2010-07-29 11:58:56.000000000 +0200
*************** static struct config_int ConfigureNamesI
*** 1648,1653 ****
--- 1648,1663 ----
  	},
  
  	{
+ 		{"lock_timeout", PGC_USERSET, CLIENT_CONN_STATEMENT,
+ 			gettext_noop("Sets the maximum allowed timeout for any lock taken by a statement."),
+ 			gettext_noop("A value of 0 turns off the timeout."),
+ 			GUC_UNIT_MS
+ 		},
+ 		&LockTimeout,
+ 		0, 0, INT_MAX, NULL, NULL
+ 	},
+ 
+ 	{
  		{"vacuum_freeze_min_age", PGC_USERSET, CLIENT_CONN_STATEMENT,
  			gettext_noop("Minimum age at which VACUUM should freeze a table row."),
  			NULL
diff -dcrpN pgsql.orig/src/backend/utils/misc/postgresql.conf.sample pgsql/src/backend/utils/misc/postgresql.conf.sample
*** pgsql.orig/src/backend/utils/misc/postgresql.conf.sample	2010-07-26 10:05:55.000000000 +0200
--- pgsql/src/backend/utils/misc/postgresql.conf.sample	2010-07-29 11:58:56.000000000 +0200
***************
*** 492,497 ****
--- 492,500 ----
  #------------------------------------------------------------------------------
  
  #deadlock_timeout = 1s
+ #lock_timeout = 0			# timeout value for heavy-weight locks
+ 					# taken by statements. 0 disables timeout
+ 					# unit in milliseconds, default is 0
  #max_locks_per_transaction = 64		# min 10
  					# (change requires restart)
  # Note:  Each lock table slot uses ~270 bytes of shared memory, and there are
diff -dcrpN pgsql.orig/src/include/storage/pg_sema.h pgsql/src/include/storage/pg_sema.h
*** pgsql.orig/src/include/storage/pg_sema.h	2010-01-02 17:58:08.000000000 +0100
--- pgsql/src/include/storage/pg_sema.h	2010-07-29 11:58:56.000000000 +0200
*************** extern void PGSemaphoreUnlock(PGSemaphor
*** 80,83 ****
--- 80,86 ----
  /* Lock a semaphore only if able to do so without blocking */
  extern bool PGSemaphoreTryLock(PGSemaphore sema);
  
+ /* Lock a semaphore (decrement count), blocking if count would be < 0 */
+ extern void PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK);
+ 
  #endif   /* PG_SEMA_H */
diff -dcrpN pgsql.orig/src/include/storage/proc.h pgsql/src/include/storage/proc.h
*** pgsql.orig/src/include/storage/proc.h	2010-07-11 11:15:00.000000000 +0200
--- pgsql/src/include/storage/proc.h	2010-07-29 11:58:56.000000000 +0200
*************** typedef struct PROC_HDR
*** 163,170 ****
--- 163,172 ----
  /* configurable options */
  extern int	DeadlockTimeout;
  extern int	StatementTimeout;
+ extern int	LockTimeout;
  extern bool log_lock_waits;
  
+ extern volatile bool lock_timeout_detected;
  extern volatile bool cancel_from_timeout;
  
  

diff -dcrpN pgsql.orig/doc/src/sgml/config.sgml pgsql.lck-experimental-framework/doc/src/sgml/config.sgml
*** pgsql.orig/doc/src/sgml/config.sgml	2010-07-26 10:05:37.000000000 +0200
--- pgsql.lck-experimental-framework/doc/src/sgml/config.sgml	2010-07-26 10:53:11.000000000 +0200
*************** COPY postgres_log FROM '/full/path/to/lo
*** 4479,4484 ****
--- 4479,4508 ----
        </listitem>
       </varlistentry>
  
+      <varlistentry id="guc-lock-timeout" xreflabel="lock_timeout">
+       <term><varname>lock_timeout</varname> (<type>integer</type>)</term>
+       <indexterm>
+        <primary><varname>lock_timeout</> configuration parameter</primary>
+       </indexterm>
+       <listitem>
+        <para>
+         Abort any statement that tries to acquire a heavy-weight lock (e.g. rows,
+         pages, tables, indices or other objects) and the lock has to wait more
+         than the specified number of milliseconds, starting from the time the
+         command arrives at the server from the client.
+         If <varname>log_min_error_statement</> is set to <literal>ERROR</> or lower,
+         the statement that timed out will also be logged. A value of zero
+         (the default) turns off the limitation.
+        </para>
+ 
+        <para>
+         Setting <varname>lock_timeout</> in
+         <filename>postgresql.conf</> is not recommended because it
+         affects all sessions.
+        </para>      
+       </listitem>   
+      </varlistentry>
+ 
       <varlistentry id="guc-vacuum-freeze-table-age" xreflabel="vacuum_freeze_table_age">
        <term><varname>vacuum_freeze_table_age</varname> (<type>integer</type>)</term>
        <indexterm>
diff -dcrpN pgsql.orig/doc/src/sgml/ref/lock.sgml pgsql.lck-experimental-framework/doc/src/sgml/ref/lock.sgml
*** pgsql.orig/doc/src/sgml/ref/lock.sgml	2010-04-03 09:23:01.000000000 +0200
--- pgsql.lck-experimental-framework/doc/src/sgml/ref/lock.sgml	2010-07-26 10:53:11.000000000 +0200
*************** LOCK [ TABLE ] [ ONLY ] <replaceable cla
*** 39,46 ****
     <literal>NOWAIT</literal> is specified, <command>LOCK
     TABLE</command> does not wait to acquire the desired lock: if it
     cannot be acquired immediately, the command is aborted and an
!    error is emitted.  Once obtained, the lock is held for the
!    remainder of the current transaction.  (There is no <command>UNLOCK
     TABLE</command> command; locks are always released at transaction
     end.)
    </para>
--- 39,49 ----
     <literal>NOWAIT</literal> is specified, <command>LOCK
     TABLE</command> does not wait to acquire the desired lock: if it
     cannot be acquired immediately, the command is aborted and an
!    error is emitted. If <varname>lock_timeout</varname> is set to a value
!    higher than 0, and the lock cannot be acquired under the specified
!    timeout value in milliseconds, the command is aborted and an error
!    is emitted. Once obtained, the lock is held for the remainder of  
!    the current transaction.  (There is no <command>UNLOCK
     TABLE</command> command; locks are always released at transaction
     end.)
    </para>
diff -dcrpN pgsql.orig/doc/src/sgml/ref/select.sgml pgsql.lck-experimental-framework/doc/src/sgml/ref/select.sgml
*** pgsql.orig/doc/src/sgml/ref/select.sgml	2010-06-20 13:59:13.000000000 +0200
--- pgsql.lck-experimental-framework/doc/src/sgml/ref/select.sgml	2010-07-26 10:53:11.000000000 +0200
*************** FOR SHARE [ OF <replaceable class="param
*** 1160,1165 ****
--- 1160,1173 ----
     </para>
  
     <para>
+     If <literal>NOWAIT</> option is not specified and <varname>lock_timeout</varname>
+     is set to a value higher than 0, and the lock needs to wait more than
+     the specified value in milliseconds, the command reports an error after
+     timing out, rather than waiting indefinitely. The note in the previous
+     paragraph applies to the <varname>lock_timeout</varname>, too.
+    </para>
+ 
+    <para>
      If specific tables are named in <literal>FOR UPDATE</literal>
      or <literal>FOR SHARE</literal>,
      then only rows coming from those tables are locked; any other
diff -dcrpN pgsql.orig/src/backend/port/posix_sema.c pgsql.lck-experimental-framework/src/backend/port/posix_sema.c
*** pgsql.orig/src/backend/port/posix_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql.lck-experimental-framework/src/backend/port/posix_sema.c	2010-07-26 15:20:14.000000000 +0200
***************
*** 24,29 ****
--- 24,30 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  
  #ifdef USE_NAMED_POSIX_SEMAPHORES
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 313,315 ****
--- 314,341 ----
  
  	return true;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0
+  * Return if lock_timeout expired
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	int			errStatus;
+ 
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 		errStatus = sem_wait(PG_SEM_REF(sema));
+ 		ImmediateInterruptOK = false;
+ 	} while (errStatus < 0 && errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errStatus < 0)
+ 		elog(FATAL, "sem_wait failed: %m");
+ }
diff -dcrpN pgsql.orig/src/backend/port/sysv_sema.c pgsql.lck-experimental-framework/src/backend/port/sysv_sema.c
*** pgsql.orig/src/backend/port/sysv_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql.lck-experimental-framework/src/backend/port/sysv_sema.c	2010-07-26 15:20:19.000000000 +0200
***************
*** 30,35 ****
--- 30,36 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  
  #ifndef HAVE_UNION_SEMUN
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 497,499 ****
--- 498,530 ----
  
  	return true;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0
+  * Return if lock_timeout expired
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	int			errStatus;
+ 	struct sembuf sops;
+ 
+ 	sops.sem_op = -1;			/* decrement */
+ 	sops.sem_flg = 0;
+ 	sops.sem_num = sema->semNum;
+ 
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 		errStatus = semop(sema->semId, &sops, 1);
+ 		ImmediateInterruptOK = false;
+ 	} while (errStatus < 0 && errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errStatus < 0)
+ 		elog(FATAL, "semop(id=%d) failed: %m", sema->semId);
+ }
diff -dcrpN pgsql.orig/src/backend/port/win32_sema.c pgsql.lck-experimental-framework/src/backend/port/win32_sema.c
*** pgsql.orig/src/backend/port/win32_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql.lck-experimental-framework/src/backend/port/win32_sema.c	2010-07-26 15:20:27.000000000 +0200
***************
*** 16,21 ****
--- 16,22 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  static HANDLE *mySemSet;		/* IDs of sema sets acquired so far */
  static int	numSems;			/* number of sema sets acquired so far */
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 205,207 ****
--- 206,263 ----
  	/* keep compiler quiet */
  	return false;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0.
+  * Serve the interrupt if interruptOK is true.
+  * Return if lock_timeout expired.
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	DWORD		ret;
+ 	HANDLE		wh[2];
+ 
+ 	wh[0] = *sema;
+ 	wh[1] = pgwin32_signal_event;
+ 
+ 	/*
+ 	 * As in other implementations of PGSemaphoreLock, we need to check for
+ 	 * cancel/die interrupts each time through the loop.  But here, there is
+ 	 * no hidden magic about whether the syscall will internally service a
+ 	 * signal --- we do that ourselves.
+ 	 */
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 
+ 		errno = 0;
+ 		ret = WaitForMultipleObjectsEx(2, wh, FALSE, INFINITE, TRUE);
+ 
+ 		if (ret == WAIT_OBJECT_0)
+ 		{
+ 			/* We got it! */
+ 			return;
+ 		}
+ 		else if (ret == WAIT_OBJECT_0 + 1)
+ 		{
+ 			/* Signal event is set - we have a signal to deliver */
+ 			pgwin32_dispatch_queued_signals();
+ 			errno = EINTR;
+ 		}
+ 		else
+ 			/* Otherwise we are in trouble */
+ 			errno = EIDRM;
+ 
+ 		ImmediateInterruptOK = false;
+ 	} while (errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errno != 0)
+ 		ereport(FATAL,
+ 				(errmsg("could not lock semaphore: error code %d", (int) GetLastError())));
+ }
diff -dcrpN pgsql.orig/src/backend/postmaster/autovacuum.c pgsql.lck-experimental-framework/src/backend/postmaster/autovacuum.c
*** pgsql.orig/src/backend/postmaster/autovacuum.c	2010-04-29 12:09:03.000000000 +0200
--- pgsql.lck-experimental-framework/src/backend/postmaster/autovacuum.c	2010-07-28 18:45:56.000000000 +0200
*************** AutoVacLauncherMain(int argc, char *argv
*** 481,487 ****
  
  		/* Forget any pending QueryCancel request */
  		QueryCancelPending = false;
! 		disable_sig_alarm(true);
  		QueryCancelPending = false;		/* again in case timeout occurred */
  
  		/* Report the error to the server log */
--- 481,487 ----
  
  		/* Forget any pending QueryCancel request */
  		QueryCancelPending = false;
! 		disable_all_sig_alarm(); /* was disable_sig_alarm(true) a.k.a. disable_statement_sig_alarm() */
  		QueryCancelPending = false;		/* again in case timeout occurred */
  
  		/* Report the error to the server log */
diff -dcrpN pgsql.orig/src/backend/postmaster/postmaster.c pgsql.lck-experimental-framework/src/backend/postmaster/postmaster.c
*** pgsql.orig/src/backend/postmaster/postmaster.c	2010-07-26 10:05:47.000000000 +0200
--- pgsql.lck-experimental-framework/src/backend/postmaster/postmaster.c	2010-07-28 14:59:37.000000000 +0200
*************** BackendInitialize(Port *port)
*** 3414,3420 ****
  	 * indefinitely.  PreAuthDelay and any DNS interactions above don't count
  	 * against the time limit.
  	 */
! 	if (!enable_sig_alarm(AuthenticationTimeout * 1000, false))
  		elog(FATAL, "could not set timer for startup packet timeout");
  
  	/*
--- 3414,3420 ----
  	 * indefinitely.  PreAuthDelay and any DNS interactions above don't count
  	 * against the time limit.
  	 */
! 	if (!enable_sig_alarm(AuthenticationTimeout * 1000))
  		elog(FATAL, "could not set timer for startup packet timeout");
  
  	/*
*************** BackendInitialize(Port *port)
*** 3452,3458 ****
  	/*
  	 * Disable the timeout, and prevent SIGTERM/SIGQUIT again.
  	 */
! 	if (!disable_sig_alarm(false))
  		elog(FATAL, "could not disable timer for startup packet timeout");
  	PG_SETMASK(&BlockSig);
  }
--- 3452,3458 ----
  	/*
  	 * Disable the timeout, and prevent SIGTERM/SIGQUIT again.
  	 */
! 	if (!disable_sig_alarm())
  		elog(FATAL, "could not disable timer for startup packet timeout");
  	PG_SETMASK(&BlockSig);
  }
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/lmgr.c pgsql.lck-experimental-framework/src/backend/storage/lmgr/lmgr.c
*** pgsql.orig/src/backend/storage/lmgr/lmgr.c	2010-01-02 17:57:52.000000000 +0100
--- pgsql.lck-experimental-framework/src/backend/storage/lmgr/lmgr.c	2010-07-26 10:53:11.000000000 +0200
***************
*** 19,26 ****
--- 19,29 ----
  #include "access/transam.h"
  #include "access/xact.h"
  #include "catalog/catalog.h"
+ #include "catalog/pg_database.h"
  #include "miscadmin.h"
  #include "storage/lmgr.h"
+ #include "utils/lsyscache.h"
+ #include "storage/proc.h"
  #include "storage/procarray.h"
  #include "utils/inval.h"
  
*************** LockRelationOid(Oid relid, LOCKMODE lock
*** 78,83 ****
--- 81,101 ----
  
  	res = LockAcquire(&tag, lockmode, false, false);
  
+ 	if (res == LOCKACQUIRE_NOT_AVAIL)
+ 	{
+ 		char	   *relname = get_rel_name(relid);
+ 		if (relname)
+ 			ereport(ERROR,
+ 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 						errmsg("could not obtain lock on relation \"%s\"",
+ 						relname)));
+ 		else
+ 			ereport(ERROR,
+ 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 						errmsg("could not obtain lock on relation with OID %u",
+ 						relid)));
+ 	}
+ 
  	/*
  	 * Now that we have the lock, check for invalidation messages, so that we
  	 * will update or flush any stale relcache entry before we try to use it.
*************** LockRelation(Relation relation, LOCKMODE
*** 173,178 ****
--- 191,202 ----
  
  	res = LockAcquire(&tag, lockmode, false, false);
  
+ 	if (res == LOCKACQUIRE_NOT_AVAIL)
+ 		ereport(ERROR,
+ 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 					errmsg("could not obtain lock on relation \"%s\"",
+ 				RelationGetRelationName(relation))));
+ 
  	/*
  	 * Now that we have the lock, check for invalidation messages; see notes
  	 * in LockRelationOid.
*************** LockRelationIdForSession(LockRelId *reli
*** 250,256 ****
  
  	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);
  
! 	(void) LockAcquire(&tag, lockmode, true, false);
  }
  
  /*
--- 274,293 ----
  
  	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);
  
! 	if (LockAcquire(&tag, lockmode, true, false) == LOCKACQUIRE_NOT_AVAIL)
! 	{
! 		char	   *relname = get_rel_name(relid->relId);
! 		if (relname)
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on relation \"%s\"",
! 						relname)));
! 		else
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on relation with OID %u",
! 						relid->relId)));
! 	}
  }
  
  /*
*************** LockRelationForExtension(Relation relati
*** 285,291 ****
  								relation->rd_lockInfo.lockRelId.dbId,
  								relation->rd_lockInfo.lockRelId.relId);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 322,332 ----
  								relation->rd_lockInfo.lockRelId.dbId,
  								relation->rd_lockInfo.lockRelId.relId);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on index \"%s\"",
! 				RelationGetRelationName(relation))));
  }
  
  /*
*************** LockPage(Relation relation, BlockNumber 
*** 319,325 ****
  					 relation->rd_lockInfo.lockRelId.relId,
  					 blkno);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 360,370 ----
  					 relation->rd_lockInfo.lockRelId.relId,
  					 blkno);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on page %u of relation \"%s\"",
! 				blkno, RelationGetRelationName(relation))));
  }
  
  /*
*************** LockTuple(Relation relation, ItemPointer
*** 375,381 ****
  					  ItemPointerGetBlockNumber(tid),
  					  ItemPointerGetOffsetNumber(tid));
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 420,430 ----
  					  ItemPointerGetBlockNumber(tid),
  					  ItemPointerGetOffsetNumber(tid));
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on row in relation \"%s\"",
! 				RelationGetRelationName(relation))));
  }
  
  /*
*************** XactLockTableInsert(TransactionId xid)
*** 429,435 ****
  
  	SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 	(void) LockAcquire(&tag, ExclusiveLock, false, false);
  }
  
  /*
--- 478,487 ----
  
  	SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 	if (LockAcquire(&tag, ExclusiveLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on transaction with ID %u", xid)));
  }
  
  /*
*************** XactLockTableWait(TransactionId xid)
*** 473,479 ****
  
  		SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 		(void) LockAcquire(&tag, ShareLock, false, false);
  
  		LockRelease(&tag, ShareLock, false);
  
--- 525,534 ----
  
  		SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 		if (LockAcquire(&tag, ShareLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on transaction with ID %u", xid)));
  
  		LockRelease(&tag, ShareLock, false);
  
*************** VirtualXactLockTableInsert(VirtualTransa
*** 531,537 ****
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	(void) LockAcquire(&tag, ExclusiveLock, false, false);
  }
  
  /*
--- 586,596 ----
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	if (LockAcquire(&tag, ExclusiveLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on virtual transaction with ID %u",
! 				vxid.localTransactionId)));
  }
  
  /*
*************** VirtualXactLockTableWait(VirtualTransact
*** 549,555 ****
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	(void) LockAcquire(&tag, ShareLock, false, false);
  
  	LockRelease(&tag, ShareLock, false);
  }
--- 608,618 ----
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	if (LockAcquire(&tag, ShareLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on virtual transaction with ID %u",
! 				vxid.localTransactionId)));
  
  	LockRelease(&tag, ShareLock, false);
  }
*************** LockDatabaseObject(Oid classid, Oid obji
*** 598,604 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 661,671 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on class:object: %u:%u",
! 				classid, objid)));
  }
  
  /*
*************** LockSharedObject(Oid classid, Oid objid,
*** 636,642 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  
  	/* Make sure syscaches are up-to-date with any changes we waited for */
  	AcceptInvalidationMessages();
--- 703,713 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on class:object: %u:%u",
! 				classid, objid)));
  
  	/* Make sure syscaches are up-to-date with any changes we waited for */
  	AcceptInvalidationMessages();
*************** LockSharedObjectForSession(Oid classid, 
*** 678,684 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, true, false);
  }
  
  /*
--- 749,770 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, true, false) == LOCKACQUIRE_NOT_AVAIL)
! 		switch(classid)
! 		{
! 		case DatabaseRelationId:
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on database with ID %u",
! 					objid)));
! 			break;
! 		default:
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on class:object: %u:%u",
! 					classid, objid)));
! 			break;
! 		}
  }
  
  /*
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/lock.c pgsql.lck-experimental-framework/src/backend/storage/lmgr/lock.c
*** pgsql.orig/src/backend/storage/lmgr/lock.c	2010-04-29 12:09:03.000000000 +0200
--- pgsql.lck-experimental-framework/src/backend/storage/lmgr/lock.c	2010-07-26 10:53:11.000000000 +0200
*************** PROCLOCK_PRINT(const char *where, const 
*** 255,261 ****
  static uint32 proclock_hash(const void *key, Size keysize);
  static void RemoveLocalLock(LOCALLOCK *locallock);
  static void GrantLockLocal(LOCALLOCK *locallock, ResourceOwner owner);
! static void WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner);
  static bool UnGrantLock(LOCK *lock, LOCKMODE lockmode,
  			PROCLOCK *proclock, LockMethod lockMethodTable);
  static void CleanUpLock(LOCK *lock, PROCLOCK *proclock,
--- 255,261 ----
  static uint32 proclock_hash(const void *key, Size keysize);
  static void RemoveLocalLock(LOCALLOCK *locallock);
  static void GrantLockLocal(LOCALLOCK *locallock, ResourceOwner owner);
! static int WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner);
  static bool UnGrantLock(LOCK *lock, LOCKMODE lockmode,
  			PROCLOCK *proclock, LockMethod lockMethodTable);
  static void CleanUpLock(LOCK *lock, PROCLOCK *proclock,
*************** ProcLockHashCode(const PROCLOCKTAG *proc
*** 447,453 ****
   *	dontWait: if true, don't wait to acquire lock
   *
   * Returns one of:
!  *		LOCKACQUIRE_NOT_AVAIL		lock not available, and dontWait=true
   *		LOCKACQUIRE_OK				lock successfully acquired
   *		LOCKACQUIRE_ALREADY_HELD	incremented count for lock already held
   *
--- 447,453 ----
   *	dontWait: if true, don't wait to acquire lock
   *
   * Returns one of:
!  *		LOCKACQUIRE_NOT_AVAIL		lock not available, either dontWait=true or timeout
   *		LOCKACQUIRE_OK				lock successfully acquired
   *		LOCKACQUIRE_ALREADY_HELD	incremented count for lock already held
   *
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 833,839 ****
  										 locktag->locktag_type,
  										 lockmode);
  
! 		WaitOnLock(locallock, owner);
  
  		TRACE_POSTGRESQL_LOCK_WAIT_DONE(locktag->locktag_field1,
  										locktag->locktag_field2,
--- 833,839 ----
  										 locktag->locktag_type,
  										 lockmode);
  
! 		status = WaitOnLock(locallock, owner);
  
  		TRACE_POSTGRESQL_LOCK_WAIT_DONE(locktag->locktag_field1,
  										locktag->locktag_field2,
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 848,867 ****
  		 * done when the lock was granted to us --- see notes in WaitOnLock.
  		 */
  
! 		/*
! 		 * Check the proclock entry status, in case something in the ipc
! 		 * communication doesn't work correctly.
! 		 */
! 		if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
  		{
! 			PROCLOCK_PRINT("LockAcquire: INCONSISTENT", proclock);
! 			LOCK_PRINT("LockAcquire: INCONSISTENT", lock, lockmode);
! 			/* Should we retry ? */
! 			LWLockRelease(partitionLock);
! 			elog(ERROR, "LockAcquire failed");
  		}
- 		PROCLOCK_PRINT("LockAcquire: granted", proclock);
- 		LOCK_PRINT("LockAcquire: granted", lock, lockmode);
  	}
  
  	LWLockRelease(partitionLock);
--- 848,879 ----
  		 * done when the lock was granted to us --- see notes in WaitOnLock.
  		 */
  
! 		switch (status)
  		{
! 		case STATUS_OK:
! 			/*
! 			 * Check the proclock entry status, in case something in the ipc
! 			 * communication doesn't work correctly.
! 			 */
! 			if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
! 			{
! 				PROCLOCK_PRINT("LockAcquire: INCONSISTENT", proclock);
! 				LOCK_PRINT("LockAcquire: INCONSISTENT", lock, lockmode);
! 				/* Should we retry ? */
! 				LWLockRelease(partitionLock);
! 				elog(ERROR, "LockAcquire failed");
! 			}
! 			PROCLOCK_PRINT("LockAcquire: granted", proclock);
! 			LOCK_PRINT("LockAcquire: granted", lock, lockmode);
! 			break;
! 		case STATUS_WAITING:
! 			PROCLOCK_PRINT("LockAcquire: timed out", proclock);
! 			LOCK_PRINT("LockAcquire: timed out", lock, lockmode);
! 			break;
! 		default:
! 			elog(ERROR, "LockAcquire invalid status");
! 			break;
  		}
  	}
  
  	LWLockRelease(partitionLock);
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 887,893 ****
  							   locktag->locktag_field2);
  	}
  
! 	return LOCKACQUIRE_OK;
  }
  
  /*
--- 899,905 ----
  							   locktag->locktag_field2);
  	}
  
! 	return (status == STATUS_OK ? LOCKACQUIRE_OK : LOCKACQUIRE_NOT_AVAIL);
  }
  
  /*
*************** GrantAwaitedLock(void)
*** 1165,1178 ****
   * Caller must have set MyProc->heldLocks to reflect locks already held
   * on the lockable object by this process.
   *
   * The appropriate partition lock must be held at entry.
   */
! static void
  WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner)
  {
  	LOCKMETHODID lockmethodid = LOCALLOCK_LOCKMETHOD(*locallock);
  	LockMethod	lockMethodTable = LockMethods[lockmethodid];
  	char	   *volatile new_status = NULL;
  
  	LOCK_PRINT("WaitOnLock: sleeping on lock",
  			   locallock->lock, locallock->tag.mode);
--- 1177,1196 ----
   * Caller must have set MyProc->heldLocks to reflect locks already held
   * on the lockable object by this process.
   *
+  * Result: returns value of ProcSleep()
+  *	STATUS_OK if we acquired the lock
+  *	STATUS_ERROR if not (deadlock)
+  *	STATUS_WAITING if not (timeout)
+  *
   * The appropriate partition lock must be held at entry.
   */
! static int
  WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner)
  {
  	LOCKMETHODID lockmethodid = LOCALLOCK_LOCKMETHOD(*locallock);
  	LockMethod	lockMethodTable = LockMethods[lockmethodid];
  	char	   *volatile new_status = NULL;
+ 	int		wait_status;
  
  	LOCK_PRINT("WaitOnLock: sleeping on lock",
  			   locallock->lock, locallock->tag.mode);
*************** WaitOnLock(LOCALLOCK *locallock, Resourc
*** 1214,1221 ****
  	 */
  	PG_TRY();
  	{
! 		if (ProcSleep(locallock, lockMethodTable) != STATUS_OK)
  		{
  			/*
  			 * We failed as a result of a deadlock, see CheckDeadLock(). Quit
  			 * now.
--- 1232,1244 ----
  	 */
  	PG_TRY();
  	{
! 		wait_status = ProcSleep(locallock, lockMethodTable);
! 		switch (wait_status)
  		{
+ 		case STATUS_OK:
+ 		case STATUS_WAITING:
+ 			break;
+ 		default:
  			/*
  			 * We failed as a result of a deadlock, see CheckDeadLock(). Quit
  			 * now.
*************** WaitOnLock(LOCALLOCK *locallock, Resourc
*** 1260,1267 ****
  		pfree(new_status);
  	}
  
! 	LOCK_PRINT("WaitOnLock: wakeup on lock",
  			   locallock->lock, locallock->tag.mode);
  }
  
  /*
--- 1283,1296 ----
  		pfree(new_status);
  	}
  
! 	if (wait_status == STATUS_OK)
! 		LOCK_PRINT("WaitOnLock: wakeup on lock",
! 			   locallock->lock, locallock->tag.mode);
! 	else if (wait_status == STATUS_WAITING)
! 		LOCK_PRINT("WaitOnLock: timeout on lock",
  			   locallock->lock, locallock->tag.mode);
+ 
+ 	return wait_status;
  }
  
  /*
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/proc.c pgsql.lck-experimental-framework/src/backend/storage/lmgr/proc.c
*** pgsql.orig/src/backend/storage/lmgr/proc.c	2010-07-11 11:14:54.000000000 +0200
--- pgsql.lck-experimental-framework/src/backend/storage/lmgr/proc.c	2010-07-28 18:43:28.000000000 +0200
***************
*** 52,57 ****
--- 52,59 ----
  /* GUC variables */
  int			DeadlockTimeout = 1000;
  int			StatementTimeout = 0;
+ int			LockTimeout = 0;
+ 
  bool		log_lock_waits = false;
  
  /* Pointer to this process's PGPROC struct, if any */
*************** static LOCALLOCK *lockAwaited = NULL;
*** 75,99 ****
  
  /* Mark these volatile because they can be changed by signal handler */
  static volatile bool standby_timeout_active = false;
- static volatile bool statement_timeout_active = false;
- static volatile bool deadlock_timeout_active = false;
  static volatile DeadLockState deadlock_state = DS_NOT_YET_CHECKED;
  volatile bool cancel_from_timeout = false;
  
  /* timeout_start_time is set when log_lock_waits is true */
  static TimestampTz timeout_start_time;
  
  /* statement_fin_time is valid only if statement_timeout_active is true */
- static TimestampTz statement_fin_time;
- static TimestampTz statement_fin_time2; /* valid only in recovery */
  
  
  static void RemoveProcFromArray(int code, Datum arg);
  static void ProcKill(int code, Datum arg);
  static void AuxiliaryProcKill(int code, Datum arg);
  static bool CheckStatementTimeout(void);
  static bool CheckStandbyTimeout(void);
  
  
  /*
   * Report shared-memory space needed by InitProcGlobal.
--- 77,134 ----
  
  /* Mark these volatile because they can be changed by signal handler */
  static volatile bool standby_timeout_active = false;
  static volatile DeadLockState deadlock_state = DS_NOT_YET_CHECKED;
  volatile bool cancel_from_timeout = false;
+ volatile bool lock_timeout_detected = false;
  
  /* timeout_start_time is set when log_lock_waits is true */
  static TimestampTz timeout_start_time;
+ static TimestampTz timeout_fin_time;
  
  /* statement_fin_time is valid only if statement_timeout_active is true */
  
  
  static void RemoveProcFromArray(int code, Datum arg);
  static void ProcKill(int code, Datum arg);
  static void AuxiliaryProcKill(int code, Datum arg);
+ static bool CheckDeadLock(void);
  static bool CheckStatementTimeout(void);
+ static bool CheckLockTimeout(void);
  static bool CheckStandbyTimeout(void);
+ static bool enable_lock_timeout_sig_alarm(int delayms);
+ static bool disable_lock_timeout_sig_alarm(void);
+ 
+ /*
+  * Infrastructure for multiple timeouts
+  */
+ typedef bool (*timeout_check)(void);
+ 
+ typedef struct {
+ 	int			index;
+ 	bool			reschedule;	/* can be rescheduled if the previous one triggered */
+ 	timeout_check		timeout_check_fn;
+ 	TimestampTz		fin_time;
+ } timeout_params;
  
+ typedef enum {
+ 	DEADLOCK_TIMEOUT,
+ 	STATEMENT_TIMEOUT,
+ 	LOCK_TIMEOUT,
+ 	TIMEOUT_MAX
+ } TimeoutName;
+ 
+ static timeout_params	base_timeouts[TIMEOUT_MAX] = {
+ 	{ DEADLOCK_TIMEOUT,	false,	CheckDeadLock,		0 },
+ 	{ STATEMENT_TIMEOUT,	true,	CheckStatementTimeout,	0 },
+ 	{ LOCK_TIMEOUT,		true,	CheckLockTimeout,	0 }
+ };
+ 
+ /*
+  * List of active timeouts ordered by their fin_time.
+  * A particular timeout is active if it's in the list.
+  */
+ static int		n_timeouts = 0;
+ static timeout_params	*timeouts[TIMEOUT_MAX];
  
  /*
   * Report shared-memory space needed by InitProcGlobal.
*************** LockWaitCancel(void)
*** 584,590 ****
  		return;
  
  	/* Turn off the deadlock timer, if it's still running (see ProcSleep) */
! 	disable_sig_alarm(false);
  
  	/* Unlink myself from the wait queue, if on it (might not be anymore!) */
  	partitionLock = LockHashPartitionLock(lockAwaited->hashcode);
--- 619,625 ----
  		return;
  
  	/* Turn off the deadlock timer, if it's still running (see ProcSleep) */
! 	disable_sig_alarm();
  
  	/* Unlink myself from the wait queue, if on it (might not be anymore!) */
  	partitionLock = LockHashPartitionLock(lockAwaited->hashcode);
*************** ProcQueueInit(PROC_QUEUE *queue)
*** 797,803 ****
   * The lock table's partition lock must be held at entry, and will be held
   * at exit.
   *
!  * Result: STATUS_OK if we acquired the lock, STATUS_ERROR if not (deadlock).
   *
   * ASSUME: that no one will fiddle with the queue until after
   *		we release the partition lock.
--- 832,841 ----
   * The lock table's partition lock must be held at entry, and will be held
   * at exit.
   *
!  * Result:
!  *     STATUS_OK if we acquired the lock
!  *     STATUS_ERROR if not (deadlock)
!  *     STATUS_WAITING if not (timeout)
   *
   * ASSUME: that no one will fiddle with the queue until after
   *		we release the partition lock.
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 947,957 ****
  	 * By delaying the check until we've waited for a bit, we can avoid
  	 * running the rather expensive deadlock-check code in most cases.
  	 */
! 	if (!enable_sig_alarm(DeadlockTimeout, false))
  		elog(FATAL, "could not set timer for process wakeup");
  
  	/*
! 	 * If someone wakes us between LWLockRelease and PGSemaphoreLock,
  	 * PGSemaphoreLock will not block.	The wakeup is "saved" by the semaphore
  	 * implementation.	While this is normally good, there are cases where a
  	 * saved wakeup might be leftover from a previous operation (for example,
--- 985,1003 ----
  	 * By delaying the check until we've waited for a bit, we can avoid
  	 * running the rather expensive deadlock-check code in most cases.
  	 */
! 	if (!enable_sig_alarm(DeadlockTimeout))
  		elog(FATAL, "could not set timer for process wakeup");
  
  	/*
! 	 * Reset timer so we are awaken in case of lock timeout.
! 	 * This doesn't modify the timer for deadlock check in case
! 	 * the deadlock check happens earlier.
! 	 */
! 	if (!enable_lock_timeout_sig_alarm(LockTimeout))
! 		elog(FATAL, "could not set timer for process wakeup");
! 
! 	/*
! 	 * If someone wakes us between LWLockRelease and PGSemaphoreTimedLock,
  	 * PGSemaphoreLock will not block.	The wakeup is "saved" by the semaphore
  	 * implementation.	While this is normally good, there are cases where a
  	 * saved wakeup might be leftover from a previous operation (for example,
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 969,975 ****
  	 */
  	do
  	{
! 		PGSemaphoreLock(&MyProc->sem, true);
  
  		/*
  		 * waitStatus could change from STATUS_WAITING to something else
--- 1015,1021 ----
  	 */
  	do
  	{
! 		PGSemaphoreTimedLock(&MyProc->sem, true);
  
  		/*
  		 * waitStatus could change from STATUS_WAITING to something else
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 1098,1104 ****
  	/*
  	 * Disable the timer, if it's still running
  	 */
! 	if (!disable_sig_alarm(false))
  		elog(FATAL, "could not disable timer for process wakeup");
  
  	/*
--- 1144,1153 ----
  	/*
  	 * Disable the timer, if it's still running
  	 */
! 	if (!disable_sig_alarm())
! 		elog(FATAL, "could not disable timer for process wakeup");
! 
! 	if (!disable_lock_timeout_sig_alarm())
  		elog(FATAL, "could not disable timer for process wakeup");
  
  	/*
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 1109,1114 ****
--- 1158,1171 ----
  	LWLockAcquire(partitionLock, LW_EXCLUSIVE);
  
  	/*
+ 	 * If we're in timeout, so we're not waiting anymore and
+ 	 * we're not the one that the lock will be granted to.
+ 	 * So remove ourselves from the wait queue.
+ 	 */
+ 	if (lock_timeout_detected)
+ 		RemoveFromWaitQueue(MyProc, hashcode);
+ 
+ 	/*
  	 * We no longer want LockWaitCancel to do anything.
  	 */
  	lockAwaited = NULL;
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 1122,1129 ****
  	/*
  	 * We don't have to do anything else, because the awaker did all the
  	 * necessary update of the lock table and MyProc.
  	 */
! 	return MyProc->waitStatus;
  }
  
  
--- 1179,1188 ----
  	/*
  	 * We don't have to do anything else, because the awaker did all the
  	 * necessary update of the lock table and MyProc.
+ 	 * RemoveFromWaitQueue() have set MyProc->waitStatus = STATUS_ERROR,
+ 	 * we need to distinguish this case.
  	 */
! 	return (lock_timeout_detected ? STATUS_WAITING : MyProc->waitStatus);
  }
  
  
*************** ProcLockWakeup(LockMethod lockMethodTabl
*** 1242,1248 ****
   * 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;
--- 1301,1307 ----
   * NB: this is run inside a signal handler, so be very wary about what is done
   * here or in called routines.
   */
! static bool
  CheckDeadLock(void)
  {
  	int			i;
*************** CheckDeadLock(void)
*** 1341,1346 ****
--- 1400,1407 ----
  check_done:
  	for (i = NUM_LOCK_PARTITIONS; --i >= 0;)
  		LWLockRelease(FirstLockMgrLock + i);
+ 
+ 	return true;
  }
  
  
*************** ProcSendSignal(int pid)
*** 1404,1538 ****
   * Maybe these should be in pqsignal.c?
   *****************************************************************************/
  
  /*
!  * Enable the SIGALRM interrupt to fire after the specified delay
!  *
!  * Delay is given in milliseconds.	Caller should be sure a SIGALRM
!  * signal handler is installed before this is called.
!  *
!  * This code properly handles nesting of deadlock timeout alarms within
!  * statement timeout alarms.
   *
!  * Returns TRUE if okay, FALSE on failure.
   */
! bool
! enable_sig_alarm(int delayms, bool is_statement_timeout)
  {
! 	TimestampTz fin_time;
! 	struct itimerval timeval;
  
! 	if (is_statement_timeout)
! 	{
! 		/*
! 		 * Begin statement-level timeout
! 		 *
! 		 * Note that we compute statement_fin_time with reference to the
! 		 * statement_timestamp, but apply the specified delay without any
! 		 * correction; that is, we ignore whatever time has elapsed since
! 		 * statement_timestamp was set.  In the normal case only a small
! 		 * interval will have elapsed and so this doesn't matter, but there
! 		 * are corner cases (involving multi-statement query strings with
! 		 * embedded COMMIT or ROLLBACK) where we might re-initialize the
! 		 * statement timeout long after initial receipt of the message. In
! 		 * such cases the enforcement of the statement timeout will be a bit
! 		 * inconsistent.  This annoyance is judged not worth the cost of
! 		 * performing an additional gettimeofday() here.
! 		 */
! 		Assert(!deadlock_timeout_active);
! 		fin_time = GetCurrentStatementStartTimestamp();
! 		fin_time = TimestampTzPlusMilliseconds(fin_time, delayms);
! 		statement_fin_time = fin_time;
! 		cancel_from_timeout = false;
! 		statement_timeout_active = true;
! 	}
! 	else if (statement_timeout_active)
  	{
! 		/*
! 		 * Begin deadlock timeout with statement-level timeout active
! 		 *
! 		 * Here, we want to interrupt at the closer of the two timeout times.
! 		 * If fin_time >= statement_fin_time then we need not touch the
! 		 * existing timer setting; else set up to interrupt at the deadlock
! 		 * timeout time.
! 		 *
! 		 * NOTE: in this case it is possible that this routine will be
! 		 * interrupted by the previously-set timer alarm.  This is okay
! 		 * because the signal handler will do only what it should do according
! 		 * to the state variables.	The deadlock checker may get run earlier
! 		 * than normal, but that does no harm.
! 		 */
! 		timeout_start_time = GetCurrentTimestamp();
! 		fin_time = TimestampTzPlusMilliseconds(timeout_start_time, delayms);
! 		deadlock_timeout_active = true;
! 		if (fin_time >= statement_fin_time)
! 			return true;
  	}
  	else
! 	{
! 		/* Begin deadlock timeout with no statement-level timeout */
! 		deadlock_timeout_active = true;
! 		/* GetCurrentTimestamp can be expensive, so only do it if we must */
! 		if (log_lock_waits)
! 			timeout_start_time = GetCurrentTimestamp();
! 	}
  
! 	/* If we reach here, okay to set the timer interrupt */
! 	MemSet(&timeval, 0, sizeof(struct itimerval));
! 	timeval.it_value.tv_sec = delayms / 1000;
! 	timeval.it_value.tv_usec = (delayms % 1000) * 1000;
! 	if (setitimer(ITIMER_REAL, &timeval, NULL))
! 		return false;
! 	return true;
  }
  
  /*
!  * Cancel the SIGALRM timer, either for a deadlock timeout or a statement
!  * timeout.  If a deadlock timeout is canceled, any active statement timeout
!  * remains in force.
   *
   * Returns TRUE if okay, FALSE on failure.
   */
  bool
! disable_sig_alarm(bool is_statement_timeout)
  {
  	/*
! 	 * Always disable the interrupt if it is active; this avoids being
! 	 * interrupted by the signal handler and thereby possibly getting
! 	 * confused.
  	 *
! 	 * We will re-enable the interrupt if necessary in CheckStatementTimeout.
  	 */
- 	if (statement_timeout_active || deadlock_timeout_active)
- 	{
- 		struct itimerval timeval;
  
! 		MemSet(&timeval, 0, sizeof(struct itimerval));
! 		if (setitimer(ITIMER_REAL, &timeval, NULL))
! 		{
! 			statement_timeout_active = false;
! 			cancel_from_timeout = false;
! 			deadlock_timeout_active = false;
! 			return false;
! 		}
! 	}
  
! 	/* Always cancel deadlock timeout, in case this is error cleanup */
! 	deadlock_timeout_active = false;
  
- 	/* Cancel or reschedule statement timeout */
- 	if (is_statement_timeout)
- 	{
- 		statement_timeout_active = false;
- 		cancel_from_timeout = false;
- 	}
- 	else if (statement_timeout_active)
- 	{
- 		if (!CheckStatementTimeout())
- 			return false;
- 	}
  	return true;
  }
  
  
  /*
   * Check for statement timeout.  If the timeout time has come,
--- 1465,1764 ----
   * Maybe these should be in pqsignal.c?
   *****************************************************************************/
  
+ static bool
+ schedule_sigalarm(void)
+ {
+ 	TimestampTz	now;
+ 	long		secs;
+ 	int			usecs;
+ 	struct itimerval timeval;
+ 
+ 	if (n_timeouts == 0)
+ 		return true;
+ 
+ 	now = GetCurrentTimestamp();
+ 
+ 	TimestampDifference(now, timeouts[0]->fin_time, &secs, &usecs);
+ 	if (secs == 0 && usecs == 0)
+ 		usecs = 1;
+ 	MemSet(&timeval, 0, sizeof(struct itimerval));
+ 	timeval.it_value.tv_sec = secs;
+ 	timeval.it_value.tv_usec = usecs;
+ 	if (setitimer(ITIMER_REAL, &timeval, NULL))
+ 		return false;
+ 
+ 	return true;
+ }
+ 
+ static bool
+ disable_sigalarm(void)
+ {
+ 	struct itimerval timeval;
+ 
+ 	MemSet(&timeval, 0, sizeof(struct itimerval));
+ 	if (setitimer(ITIMER_REAL, &timeval, NULL))
+ 		return false;
+ 	return true;
+ }
+ 
+ 
+ 
+ static int
+ timeout_active(TimeoutName timeout)
+ {
+ 	int	i;
+ 
+ 	for (i = 0; i < n_timeouts; i++)
+ 		if (timeouts[i]->index == timeout)
+ 			return i;
+ 	return -1;
+ }
+ 
  /*
!  * Add a new timeout
   *
!  * Flag for reschedule is necessary is returned
   */
! static void
! add_timeout(TimeoutName timeout, TimestampTz fin_time, bool *reschedule)
  {
! 	int		i, j;
! 	TimestampTz	tmp;
! 	TimeoutName	old = TIMEOUT_MAX;
  
! 	if (reschedule && n_timeouts > 0)
! 		old = timeouts[0]->index;
! 
! 	/* Add the new timeout */
! 	i = n_timeouts;
! 	timeouts[i] = &base_timeouts[timeout];
! 	timeouts[i]->fin_time = fin_time;
! 	n_timeouts++;
! 
! 	/*
! 	 * Sort them according to their fin_time.
! 	 * Bubble sort is not a problem for an array with at most 3 elements.
! 	 */
! 	for (i = 0; i < n_timeouts - 1; i++)
! 		for (j = i + 1; j < n_timeouts; j++)
! 		{
! 			if (timeouts[i]->fin_time > timeouts[j]->fin_time)
! 			{
! 				tmp = timeouts[i]->fin_time;
! 				timeouts[i]->fin_time = timeouts[j]->fin_time;
! 				timeouts[j]->fin_time = tmp;
! 			}
! 		}
! 
! 	/* if the first timeout is different then reschedule is necessary */
! 	if (reschedule)
! 		*reschedule = (old != timeouts[0]->index);
! }
! 
! /*
!  * Delete the specified timeout and reschedule SIGALRM if necessary.
!  */
! static bool
! del_timeout(TimeoutName timeout)
! {
! 	int	i;
! 	bool	reschedule = false;
! 
! 	for (i = 0; i < n_timeouts; i++)
! 		if (timeouts[i]->index == timeout)
! 			break;
! 
! 	if (i == n_timeouts)
! 		return true;
! 
! 	if (i == 0)
! 		reschedule = true;
! 
! 	for (; i < n_timeouts - 1; i++)
! 		timeouts[i] = timeouts[i + 1];
! 
! 	n_timeouts--;
! 
! 	if (n_timeouts > 0)
  	{
! 		if (reschedule)
! 			return schedule_sigalarm();
! 		return true;
  	}
  	else
! 		return disable_sigalarm();
! }
  
! /*
!  * Delete the timeout that will expire first 
!  */
! static void
! pop_timeout(void)
! {
! 	int	i;
! 
! 	for (i = 0; i < n_timeouts - 1; i++)
! 		timeouts[i] = timeouts[i + 1];
! 
! 	n_timeouts--;
  }
  
  /*
!  * Enable SIGALRM interrupt to fire after a specified delay
!  * for statement timeout
!  *
!  * Delay is given in milliseconds.	Caller should be sure a SIGALRM
!  * signal handler is installed before this is called.
   *
   * Returns TRUE if okay, FALSE on failure.
   */
  bool
! enable_statement_sig_alarm(int delayms)
  {
+ 	TimestampTz	fin_time;
+ 	bool		reschedule;
+ 
  	/*
! 	 * Begin statement-level timeout
  	 *
! 	 * Note that we compute statement_fin_time with reference to the
! 	 * statement_timestamp, but apply the specified delay without any
! 	 * correction; that is, we ignore whatever time has elapsed since
! 	 * statement_timestamp was set.  In the normal case only a small
! 	 * interval will have elapsed and so this doesn't matter, but there
! 	 * are corner cases (involving multi-statement query strings with
! 	 * embedded COMMIT or ROLLBACK) where we might re-initialize the
! 	 * statement timeout long after initial receipt of the message. In
! 	 * such cases the enforcement of the statement timeout will be a bit
! 	 * inconsistent.  This annoyance is judged not worth the cost of
! 	 * performing an additional gettimeofday() here.
  	 */
  
! 	Assert(n_timeouts == 0); /* There should be no other timeouts active yet. */
  
! 	if (delayms == 0)
! 		return true;
! 
! 	fin_time = GetCurrentStatementStartTimestamp();
! 	fin_time = TimestampTzPlusMilliseconds(fin_time, delayms);
! 
! 	add_timeout(STATEMENT_TIMEOUT, fin_time, &reschedule);
! 	Assert(reschedule);
! 
! 	cancel_from_timeout = false;
! 
! 	return schedule_sigalarm();
! }
! 
! /*
!  * Enable the SIGALRM interrupt to fire after the specified delay
!  * for deadlock_timeout. The deadlock check is also used for
!  * authentication timeouts.
!  *
!  * Delay is given in milliseconds.	Caller should be sure a SIGALRM
!  * signal handler is installed before this is called.
!  *
!  * Returns TRUE if okay, FALSE on failure.
!  */
! bool
! enable_sig_alarm(int delayms)
! {
! 	bool	reschedule;
! 
! 	if (delayms == 0)
! 		return true;
! 
! 	timeout_start_time = GetCurrentTimestamp();
! 	timeout_fin_time = TimestampTzPlusMilliseconds(timeout_start_time, delayms);
! 
! 	add_timeout(DEADLOCK_TIMEOUT, timeout_fin_time, &reschedule);
! 
! 	if (reschedule)
! 		return schedule_sigalarm();
  
  	return true;
  }
  
+ /*
+  * Enable the SIGALRM interrupt to fire after the specified delay
+  * in case LockTimeout is set.
+  *
+  * This code properly handles nesting of lock_timeout timeout alarm
+  * within deadlock timeout and statement timeout alarms.
+  *
+  * Returns TRUE if okay, FALSE on failure.
+  */
+ static bool
+ enable_lock_timeout_sig_alarm(int delayms)
+ {
+ 	TimestampTz		fin_time;
+ 	bool			reschedule;
+ 
+ 	if (delayms == 0)
+ 		return true;
+ 
+ 	fin_time = GetCurrentTimestamp();
+ 	fin_time = TimestampTzPlusMilliseconds(fin_time, delayms);
+ 
+ 	add_timeout(LOCK_TIMEOUT, fin_time, &reschedule);
+ 
+ 	if (reschedule)
+ 		return schedule_sigalarm();
+ 
+ 	return true;
+ }
+ 
+ /*
+  * Cancel the SIGALRM timer for statement timeout
+  * Any active statement timeout remains in force.
+  *
+  * Returns TRUE if okay, FALSE on failure.
+  */
+ bool
+ disable_statement_sig_alarm(void) 
+ {
+ 	cancel_from_timeout = false;
+ 	return del_timeout(STATEMENT_TIMEOUT);
+ }
+  
+ /*
+  * Cancel the SIGALRM timer for deadlock timeout
+  * Any active statement timeout remains in force.
+  *
+  * Returns TRUE if okay, FALSE on failure.
+  */
+ bool
+ disable_sig_alarm(void)
+ {
+ 	return del_timeout(DEADLOCK_TIMEOUT);
+ }
+ 
+ /*
+  * Cancel SIGALRM for all timeouts at once
+  */
+ bool
+ disable_all_sig_alarm(void)
+ {
+ 	bool	ret;
+ 
+ 	ret = disable_sigalarm();
+ 	n_timeouts = 0;
+ 
+ 	return ret;
+ }
+ 
+ /*
+  * Cancel the SIGALRM timer for the lock timeout
+  * Any active statement timeout remains in force.
+  *
+  * Returns TRUE if okay, FALSE on failure.
+  */
+ static bool
+ disable_lock_timeout_sig_alarm(void)
+ {
+ 	return del_timeout(LOCK_TIMEOUT);
+ }
+ 
  
  /*
   * Check for statement timeout.  If the timeout time has come,
*************** CheckStatementTimeout(void)
*** 1546,1560 ****
  {
  	TimestampTz now;
  
! 	if (!statement_timeout_active)
  		return true;			/* do nothing if not active */
  
  	now = GetCurrentTimestamp();
  
! 	if (now >= statement_fin_time)
  	{
  		/* Time to die */
! 		statement_timeout_active = false;
  		cancel_from_timeout = true;
  #ifdef HAVE_SETSID
  		/* try to signal whole process group */
--- 1772,1790 ----
  {
  	TimestampTz now;
  
! 	if (!timeout_active(STATEMENT_TIMEOUT))
  		return true;			/* do nothing if not active */
  
+ 	/* also do nothing if the statement timeout is not the first to trigger */
+ 	if (timeouts[0]->index != STATEMENT_TIMEOUT)
+ 		return true;
+ 
  	now = GetCurrentTimestamp();
  
! 	if (now >= timeouts[0]->fin_time)
  	{
  		/* Time to die */
! 		pop_timeout();
  		cancel_from_timeout = true;
  #ifdef HAVE_SETSID
  		/* try to signal whole process group */
*************** CheckStatementTimeout(void)
*** 1563,1593 ****
  		kill(MyProcPid, SIGINT);
  	}
  	else
- 	{
  		/* Not time yet, so (re)schedule the interrupt */
! 		long		secs;
! 		int			usecs;
! 		struct itimerval timeval;
  
! 		TimestampDifference(now, statement_fin_time,
! 							&secs, &usecs);
  
! 		/*
! 		 * It's possible that the difference is less than a microsecond;
! 		 * ensure we don't cancel, rather than set, the interrupt.
! 		 */
! 		if (secs == 0 && usecs == 0)
! 			usecs = 1;
! 		MemSet(&timeval, 0, sizeof(struct itimerval));
! 		timeval.it_value.tv_sec = secs;
! 		timeval.it_value.tv_usec = usecs;
! 		if (setitimer(ITIMER_REAL, &timeval, NULL))
! 			return false;
  	}
  
  	return true;
- }
  
  
  /*
   * Signal handler for SIGALRM for normal user backends
--- 1793,1832 ----
  		kill(MyProcPid, SIGINT);
  	}
  	else
  		/* Not time yet, so (re)schedule the interrupt */
! 		return schedule_sigalarm();
  
! 	return true;
! }
  
! static bool
! CheckLockTimeout(void)
! {
! 	TimestampTz now;
! 
! 	if (!timeout_active(LOCK_TIMEOUT))
! 		return true;			/* do nothing if not active */
! 
! 	/* also do nothing if the lock timeout is not the first to trigger */
! 	if (timeouts[0]->index != LOCK_TIMEOUT)
! 		return true;
! 
! 	now = GetCurrentTimestamp();
! 
! 	if (now >= timeouts[0]->fin_time)
! 	{
! 		/* Time to die */
! 		pop_timeout();
! 
! 		lock_timeout_detected = true;
  	}
+ 	else
+ 		/* Not time yet, so (re)schedule the interrupt */
+ 		return schedule_sigalarm();
  
  	return true;
  
+ }
  
  /*
   * Signal handler for SIGALRM for normal user backends
*************** handle_sig_alarm(SIGNAL_ARGS)
*** 1602,1615 ****
  {
  	int			save_errno = errno;
  
! 	if (deadlock_timeout_active)
! 	{
! 		deadlock_timeout_active = false;
! 		CheckDeadLock();
! 	}
  
! 	if (statement_timeout_active)
! 		(void) CheckStatementTimeout();
  
  	errno = save_errno;
  }
--- 1841,1851 ----
  {
  	int			save_errno = errno;
  
! 	Assert(n_timeouts > 0);
! 	Assert(timeouts[0] != NULL);
! 	Assert(timeouts[0]->timeout_check_fn != NULL);
  
! 	(void) timeouts[0]->timeout_check_fn();
  
  	errno = save_errno;
  }
*************** enable_standby_sig_alarm(TimestampTz now
*** 1635,1681 ****
  		/*
  		 * Wake up at deadlock_time only, then wait forever
  		 */
! 		statement_fin_time = deadlock_time;
! 		deadlock_timeout_active = true;
! 		statement_timeout_active = false;
  	}
  	else if (fin_time > deadlock_time)
  	{
  		/*
  		 * Wake up at deadlock_time, then again at fin_time
  		 */
! 		statement_fin_time = deadlock_time;
! 		statement_fin_time2 = fin_time;
! 		deadlock_timeout_active = true;
! 		statement_timeout_active = true;
  	}
  	else
  	{
  		/*
  		 * Wake only at fin_time because its fairly soon
  		 */
! 		statement_fin_time = fin_time;
! 		deadlock_timeout_active = false;
! 		statement_timeout_active = true;
  	}
  
! 	if (deadlock_timeout_active || statement_timeout_active)
! 	{
! 		long		secs;
! 		int			usecs;
! 		struct itimerval timeval;
  
! 		TimestampDifference(now, statement_fin_time,
! 							&secs, &usecs);
! 		if (secs == 0 && usecs == 0)
! 			usecs = 1;
! 		MemSet(&timeval, 0, sizeof(struct itimerval));
! 		timeval.it_value.tv_sec = secs;
! 		timeval.it_value.tv_usec = usecs;
! 		if (setitimer(ITIMER_REAL, &timeval, NULL))
! 			return false;
! 		standby_timeout_active = true;
! 	}
  
  	return true;
  }
--- 1871,1898 ----
  		/*
  		 * Wake up at deadlock_time only, then wait forever
  		 */
! 		add_timeout(DEADLOCK_TIMEOUT, DeadlockTimeout, NULL);
  	}
  	else if (fin_time > deadlock_time)
  	{
  		/*
  		 * Wake up at deadlock_time, then again at fin_time
  		 */
! 		add_timeout(DEADLOCK_TIMEOUT, deadlock_time, NULL);
! 		add_timeout(STATEMENT_TIMEOUT, fin_time, NULL);
  	}
  	else
  	{
  		/*
  		 * Wake only at fin_time because its fairly soon
  		 */
! 		add_timeout(STATEMENT_TIMEOUT, fin_time, NULL);
  	}
  
! 	if (!schedule_sigalarm())
! 		return false;
  
! 	standby_timeout_active = true;
  
  	return true;
  }
*************** disable_standby_sig_alarm(void)
*** 1692,1705 ****
  	 */
  	if (standby_timeout_active)
  	{
! 		struct itimerval timeval;
! 
! 		MemSet(&timeval, 0, sizeof(struct itimerval));
! 		if (setitimer(ITIMER_REAL, &timeval, NULL))
! 		{
! 			standby_timeout_active = false;
! 			return false;
! 		}
  	}
  
  	standby_timeout_active = false;
--- 1909,1916 ----
  	 */
  	if (standby_timeout_active)
  	{
! 		standby_timeout_active = false;
! 		return disable_sigalarm();
  	}
  
  	standby_timeout_active = false;
*************** static bool
*** 1716,1722 ****
  CheckStandbyTimeout(void)
  {
  	TimestampTz now;
- 	bool		reschedule = false;
  
  	standby_timeout_active = false;
  
--- 1927,1932 ----
*************** CheckStandbyTimeout(void)
*** 1726,1734 ****
  	 * Reschedule the timer if its not time to wake yet, or if we have both
  	 * timers set and the first one has just been reached.
  	 */
! 	if (now >= statement_fin_time)
  	{
! 		if (deadlock_timeout_active)
  		{
  			/*
  			 * We're still waiting when we reach deadlock timeout, so send out
--- 1936,1944 ----
  	 * Reschedule the timer if its not time to wake yet, or if we have both
  	 * timers set and the first one has just been reached.
  	 */
! 	if (now >= timeouts[STATEMENT_TIMEOUT]->fin_time)
  	{
! 		if (timeout_active(DEADLOCK_TIMEOUT))
  		{
  			/*
  			 * We're still waiting when we reach deadlock timeout, so send out
*************** CheckStandbyTimeout(void)
*** 1736,1751 ****
  			 * Then continue waiting until statement_fin_time, if that's set.
  			 */
  			SendRecoveryConflictWithBufferPin(PROCSIG_RECOVERY_CONFLICT_STARTUP_DEADLOCK);
- 			deadlock_timeout_active = false;
  
  			/*
! 			 * Begin second waiting period if required.
  			 */
! 			if (statement_timeout_active)
! 			{
! 				reschedule = true;
! 				statement_fin_time = statement_fin_time2;
! 			}
  		}
  		else
  		{
--- 1946,1957 ----
  			 * Then continue waiting until statement_fin_time, if that's set.
  			 */
  			SendRecoveryConflictWithBufferPin(PROCSIG_RECOVERY_CONFLICT_STARTUP_DEADLOCK);
  
  			/*
! 			 * Delete the deadlock timer. It reschedules the second waiting period
! 			 * automatically, if statement_timeout was also added.
  			 */
! 			del_timeout(DEADLOCK_TIMEOUT);
  		}
  		else
  		{
*************** CheckStandbyTimeout(void)
*** 1757,1778 ****
  		}
  	}
  	else
- 		reschedule = true;
- 
- 	if (reschedule)
  	{
! 		long		secs;
! 		int			usecs;
! 		struct itimerval timeval;
! 
! 		TimestampDifference(now, statement_fin_time,
! 							&secs, &usecs);
! 		if (secs == 0 && usecs == 0)
! 			usecs = 1;
! 		MemSet(&timeval, 0, sizeof(struct itimerval));
! 		timeval.it_value.tv_sec = secs;
! 		timeval.it_value.tv_usec = usecs;
! 		if (setitimer(ITIMER_REAL, &timeval, NULL))
  			return false;
  		standby_timeout_active = true;
  	}
--- 1963,1970 ----
  		}
  	}
  	else
  	{
! 		if (!schedule_sigalarm())
  			return false;
  		standby_timeout_active = true;
  	}
diff -dcrpN pgsql.orig/src/backend/tcop/postgres.c pgsql.lck-experimental-framework/src/backend/tcop/postgres.c
*** pgsql.orig/src/backend/tcop/postgres.c	2010-07-11 11:14:55.000000000 +0200
--- pgsql.lck-experimental-framework/src/backend/tcop/postgres.c	2010-07-28 18:45:10.000000000 +0200
*************** start_xact_command(void)
*** 2461,2467 ****
  		/* Set statement timeout running, if any */
  		/* NB: this mustn't be enabled until we are within an xact */
  		if (StatementTimeout > 0)
! 			enable_sig_alarm(StatementTimeout, true);
  		else
  			cancel_from_timeout = false;
  
--- 2461,2467 ----
  		/* Set statement timeout running, if any */
  		/* NB: this mustn't be enabled until we are within an xact */
  		if (StatementTimeout > 0)
! 			enable_statement_sig_alarm(StatementTimeout);
  		else
  			cancel_from_timeout = false;
  
*************** finish_xact_command(void)
*** 2475,2481 ****
  	if (xact_started)
  	{
  		/* Cancel any active statement timeout before committing */
! 		disable_sig_alarm(true);
  
  		/* Now commit the command */
  		ereport(DEBUG3,
--- 2475,2481 ----
  	if (xact_started)
  	{
  		/* Cancel any active statement timeout before committing */
! 		disable_statement_sig_alarm();
  
  		/* Now commit the command */
  		ereport(DEBUG3,
*************** PostgresMain(int argc, char *argv[], con
*** 3703,3709 ****
  		 * the idle loop anyway, and cancel the statement timer if running.
  		 */
  		QueryCancelPending = false;
! 		disable_sig_alarm(true);
  		QueryCancelPending = false;		/* again in case timeout occurred */
  
  		/*
--- 3703,3709 ----
  		 * the idle loop anyway, and cancel the statement timer if running.
  		 */
  		QueryCancelPending = false;
! 		disable_all_sig_alarm(); /* was disable_sig_alarm(true) a.k.a. disable_statement_sig_alarm() */
  		QueryCancelPending = false;		/* again in case timeout occurred */
  
  		/*
diff -dcrpN pgsql.orig/src/backend/utils/init/postinit.c pgsql.lck-experimental-framework/src/backend/utils/init/postinit.c
*** pgsql.orig/src/backend/utils/init/postinit.c	2010-07-11 11:14:55.000000000 +0200
--- pgsql.lck-experimental-framework/src/backend/utils/init/postinit.c	2010-07-28 14:57:09.000000000 +0200
*************** PerformAuthentication(Port *port)
*** 203,209 ****
  	 * during authentication.  Since we're inside a transaction and might do
  	 * database access, we have to use the statement_timeout infrastructure.
  	 */
! 	if (!enable_sig_alarm(AuthenticationTimeout * 1000, true))
  		elog(FATAL, "could not set timer for authorization timeout");
  
  	/*
--- 203,209 ----
  	 * during authentication.  Since we're inside a transaction and might do
  	 * database access, we have to use the statement_timeout infrastructure.
  	 */
! 	if (!enable_statement_sig_alarm(AuthenticationTimeout * 1000))
  		elog(FATAL, "could not set timer for authorization timeout");
  
  	/*
*************** PerformAuthentication(Port *port)
*** 214,220 ****
  	/*
  	 * Done with authentication.  Disable the timeout, and log if needed.
  	 */
! 	if (!disable_sig_alarm(true))
  		elog(FATAL, "could not disable timer for authorization timeout");
  
  	/*
--- 214,220 ----
  	/*
  	 * Done with authentication.  Disable the timeout, and log if needed.
  	 */
! 	if (!disable_statement_sig_alarm())
  		elog(FATAL, "could not disable timer for authorization timeout");
  
  	/*
diff -dcrpN pgsql.orig/src/backend/utils/misc/guc.c pgsql.lck-experimental-framework/src/backend/utils/misc/guc.c
*** pgsql.orig/src/backend/utils/misc/guc.c	2010-07-26 10:05:55.000000000 +0200
--- pgsql.lck-experimental-framework/src/backend/utils/misc/guc.c	2010-07-26 10:53:11.000000000 +0200
*************** static struct config_int ConfigureNamesI
*** 1648,1653 ****
--- 1648,1663 ----
  	},
  
  	{
+ 		{"lock_timeout", PGC_USERSET, CLIENT_CONN_STATEMENT,
+ 			gettext_noop("Sets the maximum allowed timeout for any lock taken by a statement."),
+ 			gettext_noop("A value of 0 turns off the timeout."),
+ 			GUC_UNIT_MS
+ 		},
+ 		&LockTimeout,
+ 		0, 0, INT_MAX, NULL, NULL
+ 	},
+ 
+ 	{
  		{"vacuum_freeze_min_age", PGC_USERSET, CLIENT_CONN_STATEMENT,
  			gettext_noop("Minimum age at which VACUUM should freeze a table row."),
  			NULL
diff -dcrpN pgsql.orig/src/backend/utils/misc/postgresql.conf.sample pgsql.lck-experimental-framework/src/backend/utils/misc/postgresql.conf.sample
*** pgsql.orig/src/backend/utils/misc/postgresql.conf.sample	2010-07-26 10:05:55.000000000 +0200
--- pgsql.lck-experimental-framework/src/backend/utils/misc/postgresql.conf.sample	2010-07-26 10:53:11.000000000 +0200
***************
*** 492,497 ****
--- 492,500 ----
  #------------------------------------------------------------------------------
  
  #deadlock_timeout = 1s
+ #lock_timeout = 0			# timeout value for heavy-weight locks
+ 					# taken by statements. 0 disables timeout
+ 					# unit in milliseconds, default is 0
  #max_locks_per_transaction = 64		# min 10
  					# (change requires restart)
  # Note:  Each lock table slot uses ~270 bytes of shared memory, and there are
diff -dcrpN pgsql.orig/src/include/storage/pg_sema.h pgsql.lck-experimental-framework/src/include/storage/pg_sema.h
*** pgsql.orig/src/include/storage/pg_sema.h	2010-01-02 17:58:08.000000000 +0100
--- pgsql.lck-experimental-framework/src/include/storage/pg_sema.h	2010-07-26 10:53:11.000000000 +0200
*************** extern void PGSemaphoreUnlock(PGSemaphor
*** 80,83 ****
--- 80,86 ----
  /* Lock a semaphore only if able to do so without blocking */
  extern bool PGSemaphoreTryLock(PGSemaphore sema);
  
+ /* Lock a semaphore (decrement count), blocking if count would be < 0 */
+ extern void PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK);
+ 
  #endif   /* PG_SEMA_H */
diff -dcrpN pgsql.orig/src/include/storage/proc.h pgsql.lck-experimental-framework/src/include/storage/proc.h
*** pgsql.orig/src/include/storage/proc.h	2010-07-11 11:15:00.000000000 +0200
--- pgsql.lck-experimental-framework/src/include/storage/proc.h	2010-07-28 18:24:16.000000000 +0200
*************** typedef struct PROC_HDR
*** 163,170 ****
--- 163,172 ----
  /* configurable options */
  extern int	DeadlockTimeout;
  extern int	StatementTimeout;
+ extern int	LockTimeout;
  extern bool log_lock_waits;
  
+ extern volatile bool lock_timeout_detected;
  extern volatile bool cancel_from_timeout;
  
  
*************** extern void LockWaitCancel(void);
*** 195,202 ****
  extern void ProcWaitForSignal(void);
  extern void ProcSendSignal(int pid);
  
! extern bool enable_sig_alarm(int delayms, bool is_statement_timeout);
! extern bool disable_sig_alarm(bool is_statement_timeout);
  extern void handle_sig_alarm(SIGNAL_ARGS);
  
  extern bool enable_standby_sig_alarm(TimestampTz now,
--- 197,207 ----
  extern void ProcWaitForSignal(void);
  extern void ProcSendSignal(int pid);
  
! extern bool enable_statement_sig_alarm(int delayms);
! extern bool disable_statement_sig_alarm(void);
! extern bool enable_sig_alarm(int delayms);
! extern bool disable_sig_alarm(void);
! extern bool disable_all_sig_alarm(void);
  extern void handle_sig_alarm(SIGNAL_ARGS);
  
  extern bool enable_standby_sig_alarm(TimestampTz now,

diff -dcrpN pgsql.orig/doc/src/sgml/config.sgml pgsql/doc/src/sgml/config.sgml
*** pgsql.orig/doc/src/sgml/config.sgml	2010-07-26 10:05:37.000000000 +0200
--- pgsql/doc/src/sgml/config.sgml	2010-07-29 11:58:56.000000000 +0200
*************** COPY postgres_log FROM '/full/path/to/lo
*** 4479,4484 ****
--- 4479,4508 ----
        </listitem>
       </varlistentry>
  
+      <varlistentry id="guc-lock-timeout" xreflabel="lock_timeout">
+       <term><varname>lock_timeout</varname> (<type>integer</type>)</term>
+       <indexterm>
+        <primary><varname>lock_timeout</> configuration parameter</primary>
+       </indexterm>
+       <listitem>
+        <para>
+         Abort any statement that tries to acquire a heavy-weight lock (e.g. rows,
+         pages, tables, indices or other objects) and the lock has to wait more
+         than the specified number of milliseconds, starting from the time the
+         command arrives at the server from the client.
+         If <varname>log_min_error_statement</> is set to <literal>ERROR</> or lower,
+         the statement that timed out will also be logged. A value of zero
+         (the default) turns off the limitation.
+        </para>
+ 
+        <para>
+         Setting <varname>lock_timeout</> in
+         <filename>postgresql.conf</> is not recommended because it
+         affects all sessions.
+        </para>      
+       </listitem>   
+      </varlistentry>
+ 
       <varlistentry id="guc-vacuum-freeze-table-age" xreflabel="vacuum_freeze_table_age">
        <term><varname>vacuum_freeze_table_age</varname> (<type>integer</type>)</term>
        <indexterm>
diff -dcrpN pgsql.orig/doc/src/sgml/ref/lock.sgml pgsql/doc/src/sgml/ref/lock.sgml
*** pgsql.orig/doc/src/sgml/ref/lock.sgml	2010-04-03 09:23:01.000000000 +0200
--- pgsql/doc/src/sgml/ref/lock.sgml	2010-07-29 11:58:56.000000000 +0200
*************** LOCK [ TABLE ] [ ONLY ] <replaceable cla
*** 39,46 ****
     <literal>NOWAIT</literal> is specified, <command>LOCK
     TABLE</command> does not wait to acquire the desired lock: if it
     cannot be acquired immediately, the command is aborted and an
!    error is emitted.  Once obtained, the lock is held for the
!    remainder of the current transaction.  (There is no <command>UNLOCK
     TABLE</command> command; locks are always released at transaction
     end.)
    </para>
--- 39,49 ----
     <literal>NOWAIT</literal> is specified, <command>LOCK
     TABLE</command> does not wait to acquire the desired lock: if it
     cannot be acquired immediately, the command is aborted and an
!    error is emitted. If <varname>lock_timeout</varname> is set to a value
!    higher than 0, and the lock cannot be acquired under the specified
!    timeout value in milliseconds, the command is aborted and an error
!    is emitted. Once obtained, the lock is held for the remainder of  
!    the current transaction.  (There is no <command>UNLOCK
     TABLE</command> command; locks are always released at transaction
     end.)
    </para>
diff -dcrpN pgsql.orig/doc/src/sgml/ref/select.sgml pgsql/doc/src/sgml/ref/select.sgml
*** pgsql.orig/doc/src/sgml/ref/select.sgml	2010-06-20 13:59:13.000000000 +0200
--- pgsql/doc/src/sgml/ref/select.sgml	2010-07-29 11:58:56.000000000 +0200
*************** FOR SHARE [ OF <replaceable class="param
*** 1160,1165 ****
--- 1160,1173 ----
     </para>
  
     <para>
+     If <literal>NOWAIT</> option is not specified and <varname>lock_timeout</varname>
+     is set to a value higher than 0, and the lock needs to wait more than
+     the specified value in milliseconds, the command reports an error after
+     timing out, rather than waiting indefinitely. The note in the previous
+     paragraph applies to the <varname>lock_timeout</varname>, too.
+    </para>
+ 
+    <para>
      If specific tables are named in <literal>FOR UPDATE</literal>
      or <literal>FOR SHARE</literal>,
      then only rows coming from those tables are locked; any other
diff -dcrpN pgsql.orig/src/backend/port/posix_sema.c pgsql/src/backend/port/posix_sema.c
*** pgsql.orig/src/backend/port/posix_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql/src/backend/port/posix_sema.c	2010-07-29 11:58:56.000000000 +0200
***************
*** 24,29 ****
--- 24,30 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  
  #ifdef USE_NAMED_POSIX_SEMAPHORES
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 313,315 ****
--- 314,341 ----
  
  	return true;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0
+  * Return if lock_timeout expired
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	int			errStatus;
+ 
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 		errStatus = sem_wait(PG_SEM_REF(sema));
+ 		ImmediateInterruptOK = false;
+ 	} while (errStatus < 0 && errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errStatus < 0)
+ 		elog(FATAL, "sem_wait failed: %m");
+ }
diff -dcrpN pgsql.orig/src/backend/port/sysv_sema.c pgsql/src/backend/port/sysv_sema.c
*** pgsql.orig/src/backend/port/sysv_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql/src/backend/port/sysv_sema.c	2010-07-29 11:58:56.000000000 +0200
***************
*** 30,35 ****
--- 30,36 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  
  #ifndef HAVE_UNION_SEMUN
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 497,499 ****
--- 498,530 ----
  
  	return true;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0
+  * Return if lock_timeout expired
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	int			errStatus;
+ 	struct sembuf sops;
+ 
+ 	sops.sem_op = -1;			/* decrement */
+ 	sops.sem_flg = 0;
+ 	sops.sem_num = sema->semNum;
+ 
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 		errStatus = semop(sema->semId, &sops, 1);
+ 		ImmediateInterruptOK = false;
+ 	} while (errStatus < 0 && errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errStatus < 0)
+ 		elog(FATAL, "semop(id=%d) failed: %m", sema->semId);
+ }
diff -dcrpN pgsql.orig/src/backend/port/win32_sema.c pgsql/src/backend/port/win32_sema.c
*** pgsql.orig/src/backend/port/win32_sema.c	2010-01-02 17:57:50.000000000 +0100
--- pgsql/src/backend/port/win32_sema.c	2010-07-29 11:58:56.000000000 +0200
***************
*** 16,21 ****
--- 16,22 ----
  #include "miscadmin.h"
  #include "storage/ipc.h"
  #include "storage/pg_sema.h"
+ #include "storage/proc.h"
  
  static HANDLE *mySemSet;		/* IDs of sema sets acquired so far */
  static int	numSems;			/* number of sema sets acquired so far */
*************** PGSemaphoreTryLock(PGSemaphore sema)
*** 205,207 ****
--- 206,263 ----
  	/* keep compiler quiet */
  	return false;
  }
+ 
+ /*
+  * PGSemaphoreTimedLock
+  *
+  * Lock a semaphore (decrement count), blocking if count would be < 0.
+  * Serve the interrupt if interruptOK is true.
+  * Return if lock_timeout expired.
+  */
+ void
+ PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK)
+ {
+ 	DWORD		ret;
+ 	HANDLE		wh[2];
+ 
+ 	wh[0] = *sema;
+ 	wh[1] = pgwin32_signal_event;
+ 
+ 	/*
+ 	 * As in other implementations of PGSemaphoreLock, we need to check for
+ 	 * cancel/die interrupts each time through the loop.  But here, there is
+ 	 * no hidden magic about whether the syscall will internally service a
+ 	 * signal --- we do that ourselves.
+ 	 */
+ 	do
+ 	{
+ 		ImmediateInterruptOK = interruptOK;
+ 		CHECK_FOR_INTERRUPTS();
+ 
+ 		errno = 0;
+ 		ret = WaitForMultipleObjectsEx(2, wh, FALSE, INFINITE, TRUE);
+ 
+ 		if (ret == WAIT_OBJECT_0)
+ 		{
+ 			/* We got it! */
+ 			return;
+ 		}
+ 		else if (ret == WAIT_OBJECT_0 + 1)
+ 		{
+ 			/* Signal event is set - we have a signal to deliver */
+ 			pgwin32_dispatch_queued_signals();
+ 			errno = EINTR;
+ 		}
+ 		else
+ 			/* Otherwise we are in trouble */
+ 			errno = EIDRM;
+ 
+ 		ImmediateInterruptOK = false;
+ 	} while (errno == EINTR && !lock_timeout_detected);
+ 
+ 	if (lock_timeout_detected)
+ 		return;
+ 	if (errno != 0)
+ 		ereport(FATAL,
+ 				(errmsg("could not lock semaphore: error code %d", (int) GetLastError())));
+ }
diff -dcrpN pgsql.orig/src/backend/postmaster/autovacuum.c pgsql/src/backend/postmaster/autovacuum.c
*** pgsql.orig/src/backend/postmaster/autovacuum.c	2010-04-29 12:09:03.000000000 +0200
--- pgsql/src/backend/postmaster/autovacuum.c	2010-08-02 09:36:21.000000000 +0200
*************** AutoVacWorkerMain(int argc, char *argv[]
*** 1521,1530 ****
  	SetConfigOption("zero_damaged_pages", "false", PGC_SUSET, PGC_S_OVERRIDE);
  
  	/*
! 	 * Force statement_timeout to zero to avoid a timeout setting from
! 	 * preventing regular maintenance from being executed.
  	 */
  	SetConfigOption("statement_timeout", "0", PGC_SUSET, PGC_S_OVERRIDE);
  
  	/*
  	 * Get the info about the database we're going to work on.
--- 1521,1531 ----
  	SetConfigOption("zero_damaged_pages", "false", PGC_SUSET, PGC_S_OVERRIDE);
  
  	/*
! 	 * Force statement_timeout and lock_timeout to zero to avoid a timeout setting
! 	 * from preventing regular maintenance from being executed.
  	 */
  	SetConfigOption("statement_timeout", "0", PGC_SUSET, PGC_S_OVERRIDE);
+ 	SetConfigOption("lock_timeout", "0", PGC_SUSET, PGC_S_OVERRIDE);
  
  	/*
  	 * Get the info about the database we're going to work on.
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/lmgr.c pgsql/src/backend/storage/lmgr/lmgr.c
*** pgsql.orig/src/backend/storage/lmgr/lmgr.c	2010-01-02 17:57:52.000000000 +0100
--- pgsql/src/backend/storage/lmgr/lmgr.c	2010-07-29 11:58:56.000000000 +0200
***************
*** 19,26 ****
--- 19,29 ----
  #include "access/transam.h"
  #include "access/xact.h"
  #include "catalog/catalog.h"
+ #include "catalog/pg_database.h"
  #include "miscadmin.h"
  #include "storage/lmgr.h"
+ #include "utils/lsyscache.h"
+ #include "storage/proc.h"
  #include "storage/procarray.h"
  #include "utils/inval.h"
  
*************** LockRelationOid(Oid relid, LOCKMODE lock
*** 78,83 ****
--- 81,101 ----
  
  	res = LockAcquire(&tag, lockmode, false, false);
  
+ 	if (res == LOCKACQUIRE_NOT_AVAIL)
+ 	{
+ 		char	   *relname = get_rel_name(relid);
+ 		if (relname)
+ 			ereport(ERROR,
+ 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 						errmsg("could not obtain lock on relation \"%s\"",
+ 						relname)));
+ 		else
+ 			ereport(ERROR,
+ 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 						errmsg("could not obtain lock on relation with OID %u",
+ 						relid)));
+ 	}
+ 
  	/*
  	 * Now that we have the lock, check for invalidation messages, so that we
  	 * will update or flush any stale relcache entry before we try to use it.
*************** LockRelation(Relation relation, LOCKMODE
*** 173,178 ****
--- 191,202 ----
  
  	res = LockAcquire(&tag, lockmode, false, false);
  
+ 	if (res == LOCKACQUIRE_NOT_AVAIL)
+ 		ereport(ERROR,
+ 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+ 					errmsg("could not obtain lock on relation \"%s\"",
+ 				RelationGetRelationName(relation))));
+ 
  	/*
  	 * Now that we have the lock, check for invalidation messages; see notes
  	 * in LockRelationOid.
*************** LockRelationIdForSession(LockRelId *reli
*** 250,256 ****
  
  	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);
  
! 	(void) LockAcquire(&tag, lockmode, true, false);
  }
  
  /*
--- 274,293 ----
  
  	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);
  
! 	if (LockAcquire(&tag, lockmode, true, false) == LOCKACQUIRE_NOT_AVAIL)
! 	{
! 		char	   *relname = get_rel_name(relid->relId);
! 		if (relname)
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on relation \"%s\"",
! 						relname)));
! 		else
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on relation with OID %u",
! 						relid->relId)));
! 	}
  }
  
  /*
*************** LockRelationForExtension(Relation relati
*** 285,291 ****
  								relation->rd_lockInfo.lockRelId.dbId,
  								relation->rd_lockInfo.lockRelId.relId);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 322,332 ----
  								relation->rd_lockInfo.lockRelId.dbId,
  								relation->rd_lockInfo.lockRelId.relId);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on index \"%s\"",
! 				RelationGetRelationName(relation))));
  }
  
  /*
*************** LockPage(Relation relation, BlockNumber 
*** 319,325 ****
  					 relation->rd_lockInfo.lockRelId.relId,
  					 blkno);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 360,370 ----
  					 relation->rd_lockInfo.lockRelId.relId,
  					 blkno);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on page %u of relation \"%s\"",
! 				blkno, RelationGetRelationName(relation))));
  }
  
  /*
*************** LockTuple(Relation relation, ItemPointer
*** 375,381 ****
  					  ItemPointerGetBlockNumber(tid),
  					  ItemPointerGetOffsetNumber(tid));
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 420,430 ----
  					  ItemPointerGetBlockNumber(tid),
  					  ItemPointerGetOffsetNumber(tid));
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on row in relation \"%s\"",
! 				RelationGetRelationName(relation))));
  }
  
  /*
*************** XactLockTableInsert(TransactionId xid)
*** 429,435 ****
  
  	SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 	(void) LockAcquire(&tag, ExclusiveLock, false, false);
  }
  
  /*
--- 478,487 ----
  
  	SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 	if (LockAcquire(&tag, ExclusiveLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on transaction with ID %u", xid)));
  }
  
  /*
*************** XactLockTableWait(TransactionId xid)
*** 473,479 ****
  
  		SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 		(void) LockAcquire(&tag, ShareLock, false, false);
  
  		LockRelease(&tag, ShareLock, false);
  
--- 525,534 ----
  
  		SET_LOCKTAG_TRANSACTION(tag, xid);
  
! 		if (LockAcquire(&tag, ShareLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on transaction with ID %u", xid)));
  
  		LockRelease(&tag, ShareLock, false);
  
*************** VirtualXactLockTableInsert(VirtualTransa
*** 531,537 ****
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	(void) LockAcquire(&tag, ExclusiveLock, false, false);
  }
  
  /*
--- 586,596 ----
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	if (LockAcquire(&tag, ExclusiveLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on virtual transaction with ID %u",
! 				vxid.localTransactionId)));
  }
  
  /*
*************** VirtualXactLockTableWait(VirtualTransact
*** 549,555 ****
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	(void) LockAcquire(&tag, ShareLock, false, false);
  
  	LockRelease(&tag, ShareLock, false);
  }
--- 608,618 ----
  
  	SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
  
! 	if (LockAcquire(&tag, ShareLock, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on virtual transaction with ID %u",
! 				vxid.localTransactionId)));
  
  	LockRelease(&tag, ShareLock, false);
  }
*************** LockDatabaseObject(Oid classid, Oid obji
*** 598,604 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  }
  
  /*
--- 661,671 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on class:object: %u:%u",
! 				classid, objid)));
  }
  
  /*
*************** LockSharedObject(Oid classid, Oid objid,
*** 636,642 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, false, false);
  
  	/* Make sure syscaches are up-to-date with any changes we waited for */
  	AcceptInvalidationMessages();
--- 703,713 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, false, false) == LOCKACQUIRE_NOT_AVAIL)
! 		ereport(ERROR,
! 				(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 					errmsg("could not obtain lock on class:object: %u:%u",
! 				classid, objid)));
  
  	/* Make sure syscaches are up-to-date with any changes we waited for */
  	AcceptInvalidationMessages();
*************** LockSharedObjectForSession(Oid classid, 
*** 678,684 ****
  					   objid,
  					   objsubid);
  
! 	(void) LockAcquire(&tag, lockmode, true, false);
  }
  
  /*
--- 749,770 ----
  					   objid,
  					   objsubid);
  
! 	if (LockAcquire(&tag, lockmode, true, false) == LOCKACQUIRE_NOT_AVAIL)
! 		switch(classid)
! 		{
! 		case DatabaseRelationId:
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on database with ID %u",
! 					objid)));
! 			break;
! 		default:
! 			ereport(ERROR,
! 					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
! 						errmsg("could not obtain lock on class:object: %u:%u",
! 					classid, objid)));
! 			break;
! 		}
  }
  
  /*
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/lock.c pgsql/src/backend/storage/lmgr/lock.c
*** pgsql.orig/src/backend/storage/lmgr/lock.c	2010-04-29 12:09:03.000000000 +0200
--- pgsql/src/backend/storage/lmgr/lock.c	2010-07-29 11:58:56.000000000 +0200
*************** PROCLOCK_PRINT(const char *where, const 
*** 255,261 ****
  static uint32 proclock_hash(const void *key, Size keysize);
  static void RemoveLocalLock(LOCALLOCK *locallock);
  static void GrantLockLocal(LOCALLOCK *locallock, ResourceOwner owner);
! static void WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner);
  static bool UnGrantLock(LOCK *lock, LOCKMODE lockmode,
  			PROCLOCK *proclock, LockMethod lockMethodTable);
  static void CleanUpLock(LOCK *lock, PROCLOCK *proclock,
--- 255,261 ----
  static uint32 proclock_hash(const void *key, Size keysize);
  static void RemoveLocalLock(LOCALLOCK *locallock);
  static void GrantLockLocal(LOCALLOCK *locallock, ResourceOwner owner);
! static int WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner);
  static bool UnGrantLock(LOCK *lock, LOCKMODE lockmode,
  			PROCLOCK *proclock, LockMethod lockMethodTable);
  static void CleanUpLock(LOCK *lock, PROCLOCK *proclock,
*************** ProcLockHashCode(const PROCLOCKTAG *proc
*** 447,453 ****
   *	dontWait: if true, don't wait to acquire lock
   *
   * Returns one of:
!  *		LOCKACQUIRE_NOT_AVAIL		lock not available, and dontWait=true
   *		LOCKACQUIRE_OK				lock successfully acquired
   *		LOCKACQUIRE_ALREADY_HELD	incremented count for lock already held
   *
--- 447,453 ----
   *	dontWait: if true, don't wait to acquire lock
   *
   * Returns one of:
!  *		LOCKACQUIRE_NOT_AVAIL		lock not available, either dontWait=true or timeout
   *		LOCKACQUIRE_OK				lock successfully acquired
   *		LOCKACQUIRE_ALREADY_HELD	incremented count for lock already held
   *
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 833,839 ****
  										 locktag->locktag_type,
  										 lockmode);
  
! 		WaitOnLock(locallock, owner);
  
  		TRACE_POSTGRESQL_LOCK_WAIT_DONE(locktag->locktag_field1,
  										locktag->locktag_field2,
--- 833,839 ----
  										 locktag->locktag_type,
  										 lockmode);
  
! 		status = WaitOnLock(locallock, owner);
  
  		TRACE_POSTGRESQL_LOCK_WAIT_DONE(locktag->locktag_field1,
  										locktag->locktag_field2,
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 848,867 ****
  		 * done when the lock was granted to us --- see notes in WaitOnLock.
  		 */
  
! 		/*
! 		 * Check the proclock entry status, in case something in the ipc
! 		 * communication doesn't work correctly.
! 		 */
! 		if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
  		{
! 			PROCLOCK_PRINT("LockAcquire: INCONSISTENT", proclock);
! 			LOCK_PRINT("LockAcquire: INCONSISTENT", lock, lockmode);
! 			/* Should we retry ? */
! 			LWLockRelease(partitionLock);
! 			elog(ERROR, "LockAcquire failed");
  		}
- 		PROCLOCK_PRINT("LockAcquire: granted", proclock);
- 		LOCK_PRINT("LockAcquire: granted", lock, lockmode);
  	}
  
  	LWLockRelease(partitionLock);
--- 848,879 ----
  		 * done when the lock was granted to us --- see notes in WaitOnLock.
  		 */
  
! 		switch (status)
  		{
! 		case STATUS_OK:
! 			/*
! 			 * Check the proclock entry status, in case something in the ipc
! 			 * communication doesn't work correctly.
! 			 */
! 			if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
! 			{
! 				PROCLOCK_PRINT("LockAcquire: INCONSISTENT", proclock);
! 				LOCK_PRINT("LockAcquire: INCONSISTENT", lock, lockmode);
! 				/* Should we retry ? */
! 				LWLockRelease(partitionLock);
! 				elog(ERROR, "LockAcquire failed");
! 			}
! 			PROCLOCK_PRINT("LockAcquire: granted", proclock);
! 			LOCK_PRINT("LockAcquire: granted", lock, lockmode);
! 			break;
! 		case STATUS_WAITING:
! 			PROCLOCK_PRINT("LockAcquire: timed out", proclock);
! 			LOCK_PRINT("LockAcquire: timed out", lock, lockmode);
! 			break;
! 		default:
! 			elog(ERROR, "LockAcquire invalid status");
! 			break;
  		}
  	}
  
  	LWLockRelease(partitionLock);
*************** LockAcquireExtended(const LOCKTAG *lockt
*** 887,893 ****
  							   locktag->locktag_field2);
  	}
  
! 	return LOCKACQUIRE_OK;
  }
  
  /*
--- 899,905 ----
  							   locktag->locktag_field2);
  	}
  
! 	return (status == STATUS_OK ? LOCKACQUIRE_OK : LOCKACQUIRE_NOT_AVAIL);
  }
  
  /*
*************** GrantAwaitedLock(void)
*** 1165,1178 ****
   * Caller must have set MyProc->heldLocks to reflect locks already held
   * on the lockable object by this process.
   *
   * The appropriate partition lock must be held at entry.
   */
! static void
  WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner)
  {
  	LOCKMETHODID lockmethodid = LOCALLOCK_LOCKMETHOD(*locallock);
  	LockMethod	lockMethodTable = LockMethods[lockmethodid];
  	char	   *volatile new_status = NULL;
  
  	LOCK_PRINT("WaitOnLock: sleeping on lock",
  			   locallock->lock, locallock->tag.mode);
--- 1177,1196 ----
   * Caller must have set MyProc->heldLocks to reflect locks already held
   * on the lockable object by this process.
   *
+  * Result: returns value of ProcSleep()
+  *	STATUS_OK if we acquired the lock
+  *	STATUS_ERROR if not (deadlock)
+  *	STATUS_WAITING if not (timeout)
+  *
   * The appropriate partition lock must be held at entry.
   */
! static int
  WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner)
  {
  	LOCKMETHODID lockmethodid = LOCALLOCK_LOCKMETHOD(*locallock);
  	LockMethod	lockMethodTable = LockMethods[lockmethodid];
  	char	   *volatile new_status = NULL;
+ 	int		wait_status;
  
  	LOCK_PRINT("WaitOnLock: sleeping on lock",
  			   locallock->lock, locallock->tag.mode);
*************** WaitOnLock(LOCALLOCK *locallock, Resourc
*** 1214,1221 ****
  	 */
  	PG_TRY();
  	{
! 		if (ProcSleep(locallock, lockMethodTable) != STATUS_OK)
  		{
  			/*
  			 * We failed as a result of a deadlock, see CheckDeadLock(). Quit
  			 * now.
--- 1232,1244 ----
  	 */
  	PG_TRY();
  	{
! 		wait_status = ProcSleep(locallock, lockMethodTable);
! 		switch (wait_status)
  		{
+ 		case STATUS_OK:
+ 		case STATUS_WAITING:
+ 			break;
+ 		default:
  			/*
  			 * We failed as a result of a deadlock, see CheckDeadLock(). Quit
  			 * now.
*************** WaitOnLock(LOCALLOCK *locallock, Resourc
*** 1260,1267 ****
  		pfree(new_status);
  	}
  
! 	LOCK_PRINT("WaitOnLock: wakeup on lock",
  			   locallock->lock, locallock->tag.mode);
  }
  
  /*
--- 1283,1296 ----
  		pfree(new_status);
  	}
  
! 	if (wait_status == STATUS_OK)
! 		LOCK_PRINT("WaitOnLock: wakeup on lock",
! 			   locallock->lock, locallock->tag.mode);
! 	else if (wait_status == STATUS_WAITING)
! 		LOCK_PRINT("WaitOnLock: timeout on lock",
  			   locallock->lock, locallock->tag.mode);
+ 
+ 	return wait_status;
  }
  
  /*
diff -dcrpN pgsql.orig/src/backend/storage/lmgr/proc.c pgsql/src/backend/storage/lmgr/proc.c
*** pgsql.orig/src/backend/storage/lmgr/proc.c	2010-07-11 11:14:54.000000000 +0200
--- pgsql/src/backend/storage/lmgr/proc.c	2010-08-02 12:41:13.000000000 +0200
***************
*** 52,57 ****
--- 52,58 ----
  /* GUC variables */
  int			DeadlockTimeout = 1000;
  int			StatementTimeout = 0;
+ int			LockTimeout = 0;
  bool		log_lock_waits = false;
  
  /* Pointer to this process's PGPROC struct, if any */
*************** static volatile bool statement_timeout_a
*** 79,98 ****
  static volatile bool deadlock_timeout_active = false;
  static volatile DeadLockState deadlock_state = DS_NOT_YET_CHECKED;
  volatile bool cancel_from_timeout = false;
  
! /* timeout_start_time is set when log_lock_waits is true */
  static TimestampTz timeout_start_time;
  
  /* statement_fin_time is valid only if statement_timeout_active is true */
  static TimestampTz statement_fin_time;
  static TimestampTz statement_fin_time2; /* valid only in recovery */
  
  
  static void RemoveProcFromArray(int code, Datum arg);
  static void ProcKill(int code, Datum arg);
  static void AuxiliaryProcKill(int code, Datum arg);
  static bool CheckStatementTimeout(void);
  static bool CheckStandbyTimeout(void);
  
  
  /*
--- 80,106 ----
  static volatile bool deadlock_timeout_active = false;
  static volatile DeadLockState deadlock_state = DS_NOT_YET_CHECKED;
  volatile bool cancel_from_timeout = false;
+ static volatile bool lock_timeout_active = false;
+ volatile bool lock_timeout_detected = false;
  
! /* timeout_start_time and timeout_fin_time are valid when deadlock_timeout_active is true */
  static TimestampTz timeout_start_time;
+ static TimestampTz timeout_fin_time;
  
  /* statement_fin_time is valid only if statement_timeout_active is true */
  static TimestampTz statement_fin_time;
  static TimestampTz statement_fin_time2; /* valid only in recovery */
  
+ /* lock_timeout_fin_time is valid only if lock_timeout_active is true */
+ static TimestampTz lock_timeout_fin_time;
  
  static void RemoveProcFromArray(int code, Datum arg);
  static void ProcKill(int code, Datum arg);
  static void AuxiliaryProcKill(int code, Datum arg);
  static bool CheckStatementTimeout(void);
+ static bool CheckLockTimeout(void);
  static bool CheckStandbyTimeout(void);
+ static bool enable_sig_alarm_for_lock_timeout(int delayms);
  
  
  /*
*************** ProcQueueInit(PROC_QUEUE *queue)
*** 797,803 ****
   * The lock table's partition lock must be held at entry, and will be held
   * at exit.
   *
!  * Result: STATUS_OK if we acquired the lock, STATUS_ERROR if not (deadlock).
   *
   * ASSUME: that no one will fiddle with the queue until after
   *		we release the partition lock.
--- 805,814 ----
   * The lock table's partition lock must be held at entry, and will be held
   * at exit.
   *
!  * Result:
!  *     STATUS_OK if we acquired the lock
!  *     STATUS_ERROR if not (deadlock)
!  *     STATUS_WAITING if not (timeout)
   *
   * ASSUME: that no one will fiddle with the queue until after
   *		we release the partition lock.
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 951,957 ****
  		elog(FATAL, "could not set timer for process wakeup");
  
  	/*
! 	 * If someone wakes us between LWLockRelease and PGSemaphoreLock,
  	 * PGSemaphoreLock will not block.	The wakeup is "saved" by the semaphore
  	 * implementation.	While this is normally good, there are cases where a
  	 * saved wakeup might be leftover from a previous operation (for example,
--- 962,976 ----
  		elog(FATAL, "could not set timer for process wakeup");
  
  	/*
! 	 * Reset timer so we are awaken in case of lock timeout.
! 	 * This doesn't modify the timer for deadlock check in case
! 	 * the deadlock check happens earlier.
! 	 */
! 	if (!enable_sig_alarm_for_lock_timeout(LockTimeout))
! 		elog(FATAL, "could not set timer for process wakeup");
! 
! 	/*
! 	 * If someone wakes us between LWLockRelease and PGSemaphoreTimedLock,
  	 * PGSemaphoreLock will not block.	The wakeup is "saved" by the semaphore
  	 * implementation.	While this is normally good, there are cases where a
  	 * saved wakeup might be leftover from a previous operation (for example,
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 969,975 ****
  	 */
  	do
  	{
! 		PGSemaphoreLock(&MyProc->sem, true);
  
  		/*
  		 * waitStatus could change from STATUS_WAITING to something else
--- 988,994 ----
  	 */
  	do
  	{
! 		PGSemaphoreTimedLock(&MyProc->sem, true);
  
  		/*
  		 * waitStatus could change from STATUS_WAITING to something else
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 1093,1099 ****
  
  			pfree(buf.data);
  		}
! 	} while (myWaitStatus == STATUS_WAITING);
  
  	/*
  	 * Disable the timer, if it's still running
--- 1112,1118 ----
  
  			pfree(buf.data);
  		}
! 	} while (myWaitStatus == STATUS_WAITING && !lock_timeout_detected);
  
  	/*
  	 * Disable the timer, if it's still running
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 1109,1114 ****
--- 1128,1141 ----
  	LWLockAcquire(partitionLock, LW_EXCLUSIVE);
  
  	/*
+ 	 * If we're in timeout, so we're not waiting anymore and
+ 	 * we're not the one that the lock will be granted to.
+ 	 * So remove ourselves from the wait queue.
+ 	 */
+ 	if (lock_timeout_detected)
+ 		RemoveFromWaitQueue(MyProc, hashcode);
+ 
+ 	/*
  	 * We no longer want LockWaitCancel to do anything.
  	 */
  	lockAwaited = NULL;
*************** ProcSleep(LOCALLOCK *locallock, LockMeth
*** 1122,1129 ****
  	/*
  	 * We don't have to do anything else, because the awaker did all the
  	 * necessary update of the lock table and MyProc.
  	 */
! 	return MyProc->waitStatus;
  }
  
  
--- 1149,1158 ----
  	/*
  	 * We don't have to do anything else, because the awaker did all the
  	 * necessary update of the lock table and MyProc.
+ 	 * RemoveFromWaitQueue() have set MyProc->waitStatus = STATUS_ERROR,
+ 	 * we need to distinguish this case.
  	 */
! 	return (lock_timeout_detected ? STATUS_WAITING : MyProc->waitStatus);
  }
  
  
*************** CheckDeadLock(void)
*** 1301,1306 ****
--- 1330,1352 ----
  		RemoveFromWaitQueue(MyProc, LockTagHashCode(&(MyProc->waitLock->tag)));
  
  		/*
+ 		 * We found a deadlock, we already removed ourselves from
+ 		 * the wait queue above. Disable the lock_timeout check,
+ 		 * so RemoveFromWaitQueue() is not called again. This can happen
+ 		 * in the case when deadlock_timeout and lock_timeout are so close
+ 		 * that the system's clock resolution effectively makes them equal,
+ 		 * so the checks below are both true in the same signal handler:
+ 		 *
+ 		 *	TimestampTz now = GetCurrentTimestamp()
+ 		 *
+ 		 *	if (timeout_fin_time <= now) ...
+ 		 *
+ 		 *	if (lock_timeout_fin_time <= now) ...
+ 		 *
+ 		 */
+ 		lock_timeout_active = false;
+ 
+ 		/*
  		 * Unlock my semaphore so that the interrupted ProcSleep() call can
  		 * finish.
  		 */
*************** enable_sig_alarm(int delayms, bool is_st
*** 1462,1479 ****
  		 * than normal, but that does no harm.
  		 */
  		timeout_start_time = GetCurrentTimestamp();
! 		fin_time = TimestampTzPlusMilliseconds(timeout_start_time, delayms);
! 		deadlock_timeout_active = true;
! 		if (fin_time >= statement_fin_time)
  			return true;
  	}
  	else
  	{
  		/* Begin deadlock timeout with no statement-level timeout */
  		deadlock_timeout_active = true;
! 		/* GetCurrentTimestamp can be expensive, so only do it if we must */
! 		if (log_lock_waits)
! 			timeout_start_time = GetCurrentTimestamp();
  	}
  
  	/* If we reach here, okay to set the timer interrupt */
--- 1508,1533 ----
  		 * than normal, but that does no harm.
  		 */
  		timeout_start_time = GetCurrentTimestamp();
! 		timeout_fin_time = TimestampTzPlusMilliseconds(timeout_start_time, delayms);
! 
! 		/*
! 		 * Activate deadlock_timeout only if it should happen earlier
! 		 * than statement_timeout.
! 		 */
! 		if (timeout_fin_time >= statement_fin_time)
  			return true;
+ 		deadlock_timeout_active = true;
  	}
  	else
  	{
  		/* Begin deadlock timeout with no statement-level timeout */
  		deadlock_timeout_active = true;
! 		/*
! 		 * Computing the timeout_fin_time is needed because
! 		 * the lock timeout logic checks for it.
! 		 */
! 		timeout_start_time = GetCurrentTimestamp();
! 		timeout_fin_time = TimestampTzPlusMilliseconds(timeout_start_time, delayms);
  	}
  
  	/* If we reach here, okay to set the timer interrupt */
*************** enable_sig_alarm(int delayms, bool is_st
*** 1486,1491 ****
--- 1540,1618 ----
  }
  
  /*
+  * Enable the SIGALRM interrupt to fire after the specified delay
+  * in case LockTimeout is set.
+  *
+  * This code properly handles nesting of lock_timeout timeout alarm
+  * within deadlock timeout and statement timeout alarms.
+  *
+  * Returns TRUE if okay, FALSE on failure.
+  */
+ static bool
+ enable_sig_alarm_for_lock_timeout(int delayms)
+ {
+ 	struct itimerval	timeval;
+ 	TimestampTz		fin_time;
+ 
+ 	lock_timeout_detected = false;
+ 	if (LockTimeout == 0)
+ 		return true;
+ 
+ 	if (deadlock_timeout_active)
+ 		/*
+ 		 * ensure the same starting time for deadlock_timeout and lock_timeout
+ 		 */
+ 		fin_time = timeout_start_time;
+ 	else
+ 		fin_time = GetCurrentTimestamp();
+ 	fin_time = TimestampTzPlusMilliseconds(fin_time, delayms);
+ 
+ 	if (statement_timeout_active)
+ 	{
+ 		/*
+ 		 * If statement_timeout is active and should happen before us
+ 		 * then don't bother setting up lock_timeout. statement_timeout
+ 		 * may span over multiple acquired locks during the same statement
+ 		 * so leave it in place.
+ 		 */
+ 		if (fin_time >= statement_fin_time)
+ 			return true;
+ 	}
+ 
+ 	if (deadlock_timeout_active)
+ 	{
+ 		/*
+ 		 * If deadlock_timeout is active but happens earlier then
+ 		 * don't modify the timer but set lock_timeout_active
+ 		 * so the timer will be re-set when deadlock_timeout triggers.
+ 		 */
+ 		if (fin_time >= timeout_fin_time)
+ 		{
+ 			lock_timeout_active = true;
+ 			return true;
+ 		}
+ 		/*
+ 		 * On the other hand, if deadlock_timeout should happens later
+ 		 * than lock_timeout, disable it. Life span of deadlock_timeout and
+ 		 * lock_timeout is the same.
+ 		 */
+ 		else
+ 			deadlock_timeout_active = false;
+ 	}
+ 
+ 	/* If we reach here, okay to set the timer interrupt */
+ 	MemSet(&timeval, 0, sizeof(struct itimerval));
+ 	timeval.it_value.tv_sec = delayms / 1000;
+ 	timeval.it_value.tv_usec = (delayms % 1000) * 1000;
+ 	if (setitimer(ITIMER_REAL, &timeval, NULL))
+ 		return false;
+ 
+ 	lock_timeout_fin_time = fin_time;
+ 	lock_timeout_active = true;
+ 	return true;
+ }
+ 
+ /*
   * Cancel the SIGALRM timer, either for a deadlock timeout or a statement
   * timeout.  If a deadlock timeout is canceled, any active statement timeout
   * remains in force.
*************** disable_sig_alarm(bool is_statement_time
*** 1502,1508 ****
  	 *
  	 * We will re-enable the interrupt if necessary in CheckStatementTimeout.
  	 */
! 	if (statement_timeout_active || deadlock_timeout_active)
  	{
  		struct itimerval timeval;
  
--- 1629,1635 ----
  	 *
  	 * We will re-enable the interrupt if necessary in CheckStatementTimeout.
  	 */
! 	if (statement_timeout_active || deadlock_timeout_active || lock_timeout_active)
  	{
  		struct itimerval timeval;
  
*************** disable_sig_alarm(bool is_statement_time
*** 1512,1517 ****
--- 1639,1646 ----
  			statement_timeout_active = false;
  			cancel_from_timeout = false;
  			deadlock_timeout_active = false;
+ 			lock_timeout_active = false;
+ 			lock_timeout_detected = false;
  			return false;
  		}
  	}
*************** disable_sig_alarm(bool is_statement_time
*** 1519,1524 ****
--- 1648,1656 ----
  	/* Always cancel deadlock timeout, in case this is error cleanup */
  	deadlock_timeout_active = false;
  
+ 	/* Ditto for lock_timeout */
+ 	lock_timeout_active = false;
+ 
  	/* Cancel or reschedule statement timeout */
  	if (is_statement_timeout)
  	{
*************** CheckStatementTimeout(void)
*** 1590,1595 ****
--- 1722,1777 ----
  
  
  /*
+  * Check for lock timeout.  If the timeout time has come,
+  * indicate it; if not, reschedule the SIGALRM interrupt to occur
+  * at the right time.
+  *
+  * Returns true if okay, false if failed to set the interrupt.
+  */
+ static bool
+ CheckLockTimeout(void)
+ {
+ 	TimestampTz now;
+ 
+ 	if (!lock_timeout_active)
+ 		return true;			/* do nothing if not active */
+ 
+ 	now = GetCurrentTimestamp();
+ 
+ 	if (now >= lock_timeout_fin_time)
+ 	{
+ 		/* Time to die */
+ 		lock_timeout_active = false;
+ 		lock_timeout_detected = true;
+ 	}
+ 	else
+ 	{
+ 		/* Not time yet, so (re)schedule the interrupt */
+ 		long		secs;
+ 		int			usecs;
+ 		struct itimerval timeval;
+ 
+ 		TimestampDifference(now, statement_fin_time,
+ 							&secs, &usecs);
+ 
+ 		/*
+ 		 * It's possible that the difference is less than a microsecond;
+ 		 * ensure we don't cancel, rather than set, the interrupt.
+ 		 */
+ 		if (secs == 0 && usecs == 0)
+ 			usecs = 1;
+ 		MemSet(&timeval, 0, sizeof(struct itimerval));
+ 		timeval.it_value.tv_sec = secs;
+ 		timeval.it_value.tv_usec = usecs;
+ 		if (setitimer(ITIMER_REAL, &timeval, NULL))
+ 			return false;
+ 	}
+ 
+ 	return true;
+ }
+ 
+ 
+ /*
   * Signal handler for SIGALRM for normal user backends
   *
   * Process deadlock check and/or statement timeout check, as needed.
*************** handle_sig_alarm(SIGNAL_ARGS)
*** 1608,1613 ****
--- 1790,1798 ----
  		CheckDeadLock();
  	}
  
+ 	if (lock_timeout_active)
+ 		(void) CheckLockTimeout();
+ 
  	if (statement_timeout_active)
  		(void) CheckStatementTimeout();
  
diff -dcrpN pgsql.orig/src/backend/utils/misc/guc.c pgsql/src/backend/utils/misc/guc.c
*** pgsql.orig/src/backend/utils/misc/guc.c	2010-07-26 10:05:55.000000000 +0200
--- pgsql/src/backend/utils/misc/guc.c	2010-07-29 11:58:56.000000000 +0200
*************** static struct config_int ConfigureNamesI
*** 1648,1653 ****
--- 1648,1663 ----
  	},
  
  	{
+ 		{"lock_timeout", PGC_USERSET, CLIENT_CONN_STATEMENT,
+ 			gettext_noop("Sets the maximum allowed timeout for any lock taken by a statement."),
+ 			gettext_noop("A value of 0 turns off the timeout."),
+ 			GUC_UNIT_MS
+ 		},
+ 		&LockTimeout,
+ 		0, 0, INT_MAX, NULL, NULL
+ 	},
+ 
+ 	{
  		{"vacuum_freeze_min_age", PGC_USERSET, CLIENT_CONN_STATEMENT,
  			gettext_noop("Minimum age at which VACUUM should freeze a table row."),
  			NULL
diff -dcrpN pgsql.orig/src/backend/utils/misc/postgresql.conf.sample pgsql/src/backend/utils/misc/postgresql.conf.sample
*** pgsql.orig/src/backend/utils/misc/postgresql.conf.sample	2010-07-26 10:05:55.000000000 +0200
--- pgsql/src/backend/utils/misc/postgresql.conf.sample	2010-07-29 11:58:56.000000000 +0200
***************
*** 492,497 ****
--- 492,500 ----
  #------------------------------------------------------------------------------
  
  #deadlock_timeout = 1s
+ #lock_timeout = 0			# timeout value for heavy-weight locks
+ 					# taken by statements. 0 disables timeout
+ 					# unit in milliseconds, default is 0
  #max_locks_per_transaction = 64		# min 10
  					# (change requires restart)
  # Note:  Each lock table slot uses ~270 bytes of shared memory, and there are
diff -dcrpN pgsql.orig/src/include/storage/pg_sema.h pgsql/src/include/storage/pg_sema.h
*** pgsql.orig/src/include/storage/pg_sema.h	2010-01-02 17:58:08.000000000 +0100
--- pgsql/src/include/storage/pg_sema.h	2010-07-29 11:58:56.000000000 +0200
*************** extern void PGSemaphoreUnlock(PGSemaphor
*** 80,83 ****
--- 80,86 ----
  /* Lock a semaphore only if able to do so without blocking */
  extern bool PGSemaphoreTryLock(PGSemaphore sema);
  
+ /* Lock a semaphore (decrement count), blocking if count would be < 0 */
+ extern void PGSemaphoreTimedLock(PGSemaphore sema, bool interruptOK);
+ 
  #endif   /* PG_SEMA_H */
diff -dcrpN pgsql.orig/src/include/storage/proc.h pgsql/src/include/storage/proc.h
*** pgsql.orig/src/include/storage/proc.h	2010-07-11 11:15:00.000000000 +0200
--- pgsql/src/include/storage/proc.h	2010-07-29 11:58:56.000000000 +0200
*************** typedef struct PROC_HDR
*** 163,170 ****
--- 163,172 ----
  /* configurable options */
  extern int	DeadlockTimeout;
  extern int	StatementTimeout;
+ extern int	LockTimeout;
  extern bool log_lock_waits;
  
+ extern volatile bool lock_timeout_detected;
  extern volatile bool cancel_from_timeout;