lock.c

postgresql8.3.4源码,开源数据库

/*-------------------------------------------------------------------------
 *
 * lock.c
 *	  POSTGRES primary lock mechanism
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/storage/lmgr/lock.c,v 1.181.2.1 2008/03/04 19:54:13 tgl Exp $
 *
 * NOTES
 *	  A lock table is a shared memory hash table.  When
 *	  a process tries to acquire a lock of a type that conflicts
 *	  with existing locks, it is put to sleep using the routines
 *	  in storage/lmgr/proc.c.
 *
 *	  For the most part, this code should be invoked via lmgr.c
 *	  or another lock-management module, not directly.
 *
 *	Interface:
 *
 *	InitLocks(), GetLocksMethodTable(),
 *	LockAcquire(), LockRelease(), LockReleaseAll(),
 *	LockCheckConflicts(), GrantLock()
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include <signal.h>
#include <unistd.h>

#include "access/transam.h"
#include "access/twophase.h"
#include "access/twophase_rmgr.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "utils/memutils.h"
#include "utils/ps_status.h"
#include "utils/resowner.h"


/* This configuration variable is used to set the lock table size */
int			max_locks_per_xact; /* set by guc.c */

#define NLOCKENTS() \
	mul_size(max_locks_per_xact, add_size(MaxBackends, max_prepared_xacts))


/*
 * Data structures defining the semantics of the standard lock methods.
 *
 * The conflict table defines the semantics of the various lock modes.
 */
static const LOCKMASK LockConflicts[] = {
	0,

	/* AccessShareLock */
	(1 << AccessExclusiveLock),

	/* RowShareLock */
	(1 << ExclusiveLock) | (1 << AccessExclusiveLock),

	/* RowExclusiveLock */
	(1 << ShareLock) | (1 << ShareRowExclusiveLock) |
	(1 << ExclusiveLock) | (1 << AccessExclusiveLock),

	/* ShareUpdateExclusiveLock */
	(1 << ShareUpdateExclusiveLock) |
	(1 << ShareLock) | (1 << ShareRowExclusiveLock) |
	(1 << ExclusiveLock) | (1 << AccessExclusiveLock),

	/* ShareLock */
	(1 << RowExclusiveLock) | (1 << ShareUpdateExclusiveLock) |
	(1 << ShareRowExclusiveLock) |
	(1 << ExclusiveLock) | (1 << AccessExclusiveLock),

	/* ShareRowExclusiveLock */
	(1 << RowExclusiveLock) | (1 << ShareUpdateExclusiveLock) |
	(1 << ShareLock) | (1 << ShareRowExclusiveLock) |
	(1 << ExclusiveLock) | (1 << AccessExclusiveLock),

	/* ExclusiveLock */
	(1 << RowShareLock) |
	(1 << RowExclusiveLock) | (1 << ShareUpdateExclusiveLock) |
	(1 << ShareLock) | (1 << ShareRowExclusiveLock) |
	(1 << ExclusiveLock) | (1 << AccessExclusiveLock),

	/* AccessExclusiveLock */
	(1 << AccessShareLock) | (1 << RowShareLock) |
	(1 << RowExclusiveLock) | (1 << ShareUpdateExclusiveLock) |
	(1 << ShareLock) | (1 << ShareRowExclusiveLock) |
	(1 << ExclusiveLock) | (1 << AccessExclusiveLock)

};

/* Names of lock modes, for debug printouts */
static const char *const lock_mode_names[] =
{
	"INVALID",
	"AccessShareLock",
	"RowShareLock",
	"RowExclusiveLock",
	"ShareUpdateExclusiveLock",
	"ShareLock",
	"ShareRowExclusiveLock",
	"ExclusiveLock",
	"AccessExclusiveLock"
};

#ifndef LOCK_DEBUG
static bool Dummy_trace = false;
#endif

static const LockMethodData default_lockmethod = {
	AccessExclusiveLock,		/* highest valid lock mode number */
	true,
	LockConflicts,
	lock_mode_names,
#ifdef LOCK_DEBUG
	&Trace_locks
#else
	&Dummy_trace
#endif
};

static const LockMethodData user_lockmethod = {
	AccessExclusiveLock,		/* highest valid lock mode number */
	false,
	LockConflicts,
	lock_mode_names,
#ifdef LOCK_DEBUG
	&Trace_userlocks
#else
	&Dummy_trace
#endif
};

/*
 * map from lock method id to the lock table data structures
 */
static const LockMethod LockMethods[] = {
	NULL,
	&default_lockmethod,
	&user_lockmethod
};


/* Record that's written to 2PC state file when a lock is persisted */
typedef struct TwoPhaseLockRecord
{
	LOCKTAG		locktag;
	LOCKMODE	lockmode;
} TwoPhaseLockRecord;


/*
 * Pointers to hash tables containing lock state
 *
 * The LockMethodLockHash and LockMethodProcLockHash hash tables are in
 * shared memory; LockMethodLocalHash is local to each backend.
 */
static HTAB *LockMethodLockHash;
static HTAB *LockMethodProcLockHash;
static HTAB *LockMethodLocalHash;


/* private state for GrantAwaitedLock */
static LOCALLOCK *awaitedLock;
static ResourceOwner awaitedOwner;


#ifdef LOCK_DEBUG

/*------
 * The following configuration options are available for lock debugging:
 *
 *	   TRACE_LOCKS		-- give a bunch of output what's going on in this file
 *	   TRACE_USERLOCKS	-- same but for user locks
 *	   TRACE_LOCK_OIDMIN-- do not trace locks for tables below this oid
 *						   (use to avoid output on system tables)
 *	   TRACE_LOCK_TABLE -- trace locks on this table (oid) unconditionally
 *	   DEBUG_DEADLOCKS	-- currently dumps locks at untimely occasions ;)
 *
 * Furthermore, but in storage/lmgr/lwlock.c:
 *	   TRACE_LWLOCKS	-- trace lightweight locks (pretty useless)
 *
 * Define LOCK_DEBUG at compile time to get all these enabled.
 * --------
 */

int			Trace_lock_oidmin = FirstNormalObjectId;
bool		Trace_locks = false;
bool		Trace_userlocks = false;
int			Trace_lock_table = 0;
bool		Debug_deadlocks = false;


inline static bool
LOCK_DEBUG_ENABLED(const LOCKTAG *tag)
{
	return
		(*(LockMethods[tag->locktag_lockmethodid]->trace_flag) &&
		 ((Oid) tag->locktag_field2 >= (Oid) Trace_lock_oidmin))
		|| (Trace_lock_table &&
			(tag->locktag_field2 == Trace_lock_table));
}


inline static void
LOCK_PRINT(const char *where, const LOCK *lock, LOCKMODE type)
{
	if (LOCK_DEBUG_ENABLED(&lock->tag))
		elog(LOG,
			 "%s: lock(%p) id(%u,%u,%u,%u,%u,%u) grantMask(%x) "
			 "req(%d,%d,%d,%d,%d,%d,%d)=%d "
			 "grant(%d,%d,%d,%d,%d,%d,%d)=%d wait(%d) type(%s)",
			 where, lock,
			 lock->tag.locktag_field1, lock->tag.locktag_field2,
			 lock->tag.locktag_field3, lock->tag.locktag_field4,
			 lock->tag.locktag_type, lock->tag.locktag_lockmethodid,
			 lock->grantMask,
			 lock->requested[1], lock->requested[2], lock->requested[3],
			 lock->requested[4], lock->requested[5], lock->requested[6],
			 lock->requested[7], lock->nRequested,
			 lock->granted[1], lock->granted[2], lock->granted[3],
			 lock->granted[4], lock->granted[5], lock->granted[6],
			 lock->granted[7], lock->nGranted,
			 lock->waitProcs.size,
			 LockMethods[LOCK_LOCKMETHOD(*lock)]->lockModeNames[type]);
}


inline static void
PROCLOCK_PRINT(const char *where, const PROCLOCK *proclockP)
{
	if (LOCK_DEBUG_ENABLED(&proclockP->tag.myLock->tag))
		elog(LOG,
			 "%s: proclock(%p) lock(%p) method(%u) proc(%p) hold(%x)",
			 where, proclockP, proclockP->tag.myLock,
			 PROCLOCK_LOCKMETHOD(*(proclockP)),
			 proclockP->tag.myProc, (int) proclockP->holdMask);
}
#else							/* not LOCK_DEBUG */

#define LOCK_PRINT(where, lock, type)
#define PROCLOCK_PRINT(where, proclockP)
#endif   /* not LOCK_DEBUG */


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,
			LockMethod lockMethodTable, uint32 hashcode,
			bool wakeupNeeded);


/*
 * InitLocks -- Initialize the lock manager's data structures.
 *
 * This is called from CreateSharedMemoryAndSemaphores(), which see for
 * more comments.  In the normal postmaster case, the shared hash tables
 * are created here, as well as a locallock hash table that will remain
 * unused and empty in the postmaster itself.  Backends inherit the pointers
 * to the shared tables via fork(), and also inherit an image of the locallock
 * hash table, which they proceed to use.  In the EXEC_BACKEND case, each
 * backend re-executes this code to obtain pointers to the already existing
 * shared hash tables and to create its locallock hash table.
 */
void
InitLocks(void)
{
	HASHCTL		info;
	int			hash_flags;
	long		init_table_size,
				max_table_size;

	/*
	 * Compute init/max size to request for lock hashtables.  Note these
	 * calculations must agree with LockShmemSize!
	 */
	max_table_size = NLOCKENTS();
	init_table_size = max_table_size / 2;

	/*
	 * Allocate hash table for LOCK structs.  This stores per-locked-object
	 * information.
	 */
	MemSet(&info, 0, sizeof(info));
	info.keysize = sizeof(LOCKTAG);
	info.entrysize = sizeof(LOCK);
	info.hash = tag_hash;
	info.num_partitions = NUM_LOCK_PARTITIONS;
	hash_flags = (HASH_ELEM | HASH_FUNCTION | HASH_PARTITION);

	LockMethodLockHash = ShmemInitHash("LOCK hash",
									   init_table_size,
									   max_table_size,
									   &info,
									   hash_flags);
	if (!LockMethodLockHash)
		elog(FATAL, "could not initialize lock hash table");

	/* Assume an average of 2 holders per lock */
	max_table_size *= 2;
	init_table_size *= 2;

	/*
	 * Allocate hash table for PROCLOCK structs.  This stores
	 * per-lock-per-holder information.
	 */
	info.keysize = sizeof(PROCLOCKTAG);
	info.entrysize = sizeof(PROCLOCK);
	info.hash = proclock_hash;
	info.num_partitions = NUM_LOCK_PARTITIONS;
	hash_flags = (HASH_ELEM | HASH_FUNCTION | HASH_PARTITION);

	LockMethodProcLockHash = ShmemInitHash("PROCLOCK hash",
										   init_table_size,
										   max_table_size,
										   &info,
										   hash_flags);
	if (!LockMethodProcLockHash)
		elog(FATAL, "could not initialize proclock hash table");

	/*
	 * Allocate non-shared hash table for LOCALLOCK structs.  This stores lock
	 * counts and resource owner information.
	 *
	 * The non-shared table could already exist in this process (this occurs
	 * when the postmaster is recreating shared memory after a backend crash).
	 * If so, delete and recreate it.  (We could simply leave it, since it
	 * ought to be empty in the postmaster, but for safety let's zap it.)
	 */
	if (LockMethodLocalHash)
		hash_destroy(LockMethodLocalHash);

	info.keysize = sizeof(LOCALLOCKTAG);
	info.entrysize = sizeof(LOCALLOCK);
	info.hash = tag_hash;
	hash_flags = (HASH_ELEM | HASH_FUNCTION);

	LockMethodLocalHash = hash_create("LOCALLOCK hash",
									  128,
									  &info,
									  hash_flags);
}


/*
 * Fetch the lock method table associated with a given lock
 */
LockMethod
GetLocksMethodTable(const LOCK *lock)
{
	LOCKMETHODID lockmethodid = LOCK_LOCKMETHOD(*lock);

	Assert(0 < lockmethodid && lockmethodid < lengthof(LockMethods));
	return LockMethods[lockmethodid];
}


/*
 * Compute the hash code associated with a LOCKTAG.
 *
 * To avoid unnecessary recomputations of the hash code, we try to do this
 * just once per function, and then pass it around as needed.  Aside from
 * passing the hashcode to hash_search_with_hash_value(), we can extract
 * the lock partition number from the hashcode.
 */
uint32
LockTagHashCode(const LOCKTAG *locktag)
{
	return get_hash_value(LockMethodLockHash, (const void *) locktag);
}

/*
 * Compute the hash code associated with a PROCLOCKTAG.
 *
 * Because we want to use just one set of partition locks for both the
 * LOCK and PROCLOCK hash tables, we have to make sure that PROCLOCKs
 * fall into the same partition number as their associated LOCKs.
 * dynahash.c expects the partition number to be the low-order bits of
 * the hash code, and therefore a PROCLOCKTAG's hash code must have the
 * same low-order bits as the associated LOCKTAG's hash code.  We achieve
 * this with this specialized hash function.
 */
static uint32
proclock_hash(const void *key, Size keysize)
{
	const PROCLOCKTAG *proclocktag = (const PROCLOCKTAG *) key;
	uint32		lockhash;
	Datum		procptr;

	Assert(keysize == sizeof(PROCLOCKTAG));

	/* Look into the associated LOCK object, and compute its hash code */
	lockhash = LockTagHashCode(&proclocktag->myLock->tag);

	/*
	 * To make the hash code also depend on the PGPROC, we xor the proc
	 * struct's address into the hash code, left-shifted so that the
	 * partition-number bits don't change.  Since this is only a hash, we
	 * don't care if we lose high-order bits of the address; use an
	 * intermediate variable to suppress cast-pointer-to-int warnings.
	 */
	procptr = PointerGetDatum(proclocktag->myProc);
	lockhash ^= ((uint32) procptr) << LOG2_NUM_LOCK_PARTITIONS;

	return lockhash;
}

/*
 * Compute the hash code associated with a PROCLOCKTAG, given the hashcode
 * for its underlying LOCK.
 *
 * We use this just to avoid redundant calls of LockTagHashCode().
 */
static inline uint32
ProcLockHashCode(const PROCLOCKTAG *proclocktag, uint32 hashcode)
{
	uint32		lockhash = hashcode;
	Datum		procptr;

	/*
	 * This must match proclock_hash()!
	 */
	procptr = PointerGetDatum(proclocktag->myProc);
	lockhash ^= ((uint32) procptr) << LOG2_NUM_LOCK_PARTITIONS;

	return lockhash;
}


/*
 * LockAcquire -- Check for lock conflicts, sleep if conflict found,
 *		set lock if/when no conflicts.
 *
 * Inputs:
 *	locktag: unique identifier for the lockable object
 *	lockmode: lock mode to acquire
 *	sessionLock: if true, acquire lock for session not current transaction
 *	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