* might be higher than the real number if another backend has transferred
* our locks to the primary lock table, but it can never be lower than the
* real value, since only we can acquire locks on our own behalf.
+ *
+ * XXX Allocate a static array of the maximum size. We could use a pointer
+ * and then allocate just the right size to save a couple kB, but then we
+ * would have to initialize that, while for the static array that happens
+ * automatically. Doesn't seem worth the extra complexity.
*/
-static int FastPathLocalUseCount = 0;
+static int FastPathLocalUseCounts[FP_LOCK_GROUPS_PER_BACKEND_MAX];
/*
* Flag to indicate if the relation extension lock is held by this backend.
*/
static bool IsRelationExtensionLockHeld PG_USED_FOR_ASSERTS_ONLY = false;
+/*
+ * Number of fast-path locks per backend - size of the arrays in PGPROC.
+ * This is set only once during start, before initializing shared memory,
+ * and remains constant after that.
+ *
+ * We set the limit based on max_locks_per_transaction GUC, because that's
+ * the best information about expected number of locks per backend we have.
+ * See InitializeFastPathLocks() for details.
+ */
+int FastPathLockGroupsPerBackend = 0;
+
+/*
+ * Macros to calculate the fast-path group and index for a relation.
+ *
+ * The formula is a simple hash function, designed to spread the OIDs a bit,
+ * so that even contiguous values end up in different groups. In most cases
+ * there will be gaps anyway, but the multiplication should help a bit.
+ *
+ * The selected constant (49157) is a prime not too close to 2^k, and it's
+ * small enough to not cause overflows (in 64-bit).
+ */
+#define FAST_PATH_REL_GROUP(rel) \
+ (((uint64) (rel) * 49157) % FastPathLockGroupsPerBackend)
+
+/*
+ * Given the group/slot indexes, calculate the slot index in the whole array
+ * of fast-path lock slots.
+ */
+#define FAST_PATH_SLOT(group, index) \
+ (AssertMacro(((group) >= 0) && ((group) < FastPathLockGroupsPerBackend)), \
+ AssertMacro(((index) >= 0) && ((index) < FP_LOCK_SLOTS_PER_GROUP)), \
+ ((group) * FP_LOCK_SLOTS_PER_GROUP + (index)))
+
+/*
+ * Given a slot index (into the whole per-backend array), calculated using
+ * the FAST_PATH_SLOT macro, split it into group and index (in the group).
+ */
+#define FAST_PATH_GROUP(index) \
+ (AssertMacro(((index) >= 0) && ((index) < FP_LOCK_SLOTS_PER_BACKEND)), \
+ ((index) / FP_LOCK_SLOTS_PER_GROUP))
+#define FAST_PATH_INDEX(index) \
+ (AssertMacro(((index) >= 0) && ((index) < FP_LOCK_SLOTS_PER_BACKEND)), \
+ ((index) % FP_LOCK_SLOTS_PER_GROUP))
+
/* Macros for manipulating proc->fpLockBits */
#define FAST_PATH_BITS_PER_SLOT 3
#define FAST_PATH_LOCKNUMBER_OFFSET 1
#define FAST_PATH_MASK ((1 << FAST_PATH_BITS_PER_SLOT) - 1)
+#define FAST_PATH_BITS(proc, n) (proc)->fpLockBits[FAST_PATH_GROUP(n)]
#define FAST_PATH_GET_BITS(proc, n) \
- (((proc)->fpLockBits >> (FAST_PATH_BITS_PER_SLOT * n)) & FAST_PATH_MASK)
+ ((FAST_PATH_BITS(proc, n) >> (FAST_PATH_BITS_PER_SLOT * FAST_PATH_INDEX(n))) & FAST_PATH_MASK)
#define FAST_PATH_BIT_POSITION(n, l) \
(AssertMacro((l) >= FAST_PATH_LOCKNUMBER_OFFSET), \
AssertMacro((l) < FAST_PATH_BITS_PER_SLOT+FAST_PATH_LOCKNUMBER_OFFSET), \
AssertMacro((n) < FP_LOCK_SLOTS_PER_BACKEND), \
- ((l) - FAST_PATH_LOCKNUMBER_OFFSET + FAST_PATH_BITS_PER_SLOT * (n)))
+ ((l) - FAST_PATH_LOCKNUMBER_OFFSET + FAST_PATH_BITS_PER_SLOT * (FAST_PATH_INDEX(n))))
#define FAST_PATH_SET_LOCKMODE(proc, n, l) \
- (proc)->fpLockBits |= UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l)
+ FAST_PATH_BITS(proc, n) |= UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l)
#define FAST_PATH_CLEAR_LOCKMODE(proc, n, l) \
- (proc)->fpLockBits &= ~(UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l))
+ FAST_PATH_BITS(proc, n) &= ~(UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l))
#define FAST_PATH_CHECK_LOCKMODE(proc, n, l) \
- ((proc)->fpLockBits & (UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l)))
+ (FAST_PATH_BITS(proc, n) & (UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l)))
/*
* The fast-path lock mechanism is concerned only with relation locks on
* for now we don't worry about that case either.
*/
if (EligibleForRelationFastPath(locktag, lockmode) &&
- FastPathLocalUseCount < FP_LOCK_SLOTS_PER_BACKEND)
+ FastPathLocalUseCounts[FAST_PATH_REL_GROUP(locktag->locktag_field2)] < FP_LOCK_SLOTS_PER_GROUP)
{
uint32 fasthashcode = FastPathStrongLockHashPartition(hashcode);
bool acquired;
/* Attempt fast release of any lock eligible for the fast path. */
if (EligibleForRelationFastPath(locktag, lockmode) &&
- FastPathLocalUseCount > 0)
+ FastPathLocalUseCounts[FAST_PATH_REL_GROUP(locktag->locktag_field2)] > 0)
{
bool released;
static bool
FastPathGrantRelationLock(Oid relid, LOCKMODE lockmode)
{
- uint32 f;
+ uint32 i;
uint32 unused_slot = FP_LOCK_SLOTS_PER_BACKEND;
+ /* fast-path group the lock belongs to */
+ uint32 group = FAST_PATH_REL_GROUP(relid);
+
/* Scan for existing entry for this relid, remembering empty slot. */
- for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
+ for (i = 0; i < FP_LOCK_SLOTS_PER_GROUP; i++)
{
+ /* index into the whole per-backend array */
+ uint32 f = FAST_PATH_SLOT(group, i);
+
if (FAST_PATH_GET_BITS(MyProc, f) == 0)
unused_slot = f;
else if (MyProc->fpRelId[f] == relid)
{
MyProc->fpRelId[unused_slot] = relid;
FAST_PATH_SET_LOCKMODE(MyProc, unused_slot, lockmode);
- ++FastPathLocalUseCount;
+ ++FastPathLocalUseCounts[group];
return true;
}
static bool
FastPathUnGrantRelationLock(Oid relid, LOCKMODE lockmode)
{
- uint32 f;
+ uint32 i;
bool result = false;
- FastPathLocalUseCount = 0;
- for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
+ /* fast-path group the lock belongs to */
+ uint32 group = FAST_PATH_REL_GROUP(relid);
+
+ FastPathLocalUseCounts[group] = 0;
+ for (i = 0; i < FP_LOCK_SLOTS_PER_GROUP; i++)
{
+ /* index into the whole per-backend array */
+ uint32 f = FAST_PATH_SLOT(group, i);
+
if (MyProc->fpRelId[f] == relid
&& FAST_PATH_CHECK_LOCKMODE(MyProc, f, lockmode))
{
/* we continue iterating so as to update FastPathLocalUseCount */
}
if (FAST_PATH_GET_BITS(MyProc, f) != 0)
- ++FastPathLocalUseCount;
+ ++FastPathLocalUseCounts[group];
}
return result;
}
for (i = 0; i < ProcGlobal->allProcCount; i++)
{
PGPROC *proc = &ProcGlobal->allProcs[i];
- uint32 f;
+ uint32 j,
+ group;
LWLockAcquire(&proc->fpInfoLock, LW_EXCLUSIVE);
continue;
}
- for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
+ /* fast-path group the lock belongs to */
+ group = FAST_PATH_REL_GROUP(relid);
+
+ for (j = 0; j < FP_LOCK_SLOTS_PER_GROUP; j++)
{
uint32 lockmode;
+ /* index into the whole per-backend array */
+ uint32 f = FAST_PATH_SLOT(group, j);
+
/* Look for an allocated slot matching the given relid. */
if (relid != proc->fpRelId[f] || FAST_PATH_GET_BITS(proc, f) == 0)
continue;
PROCLOCK *proclock = NULL;
LWLock *partitionLock = LockHashPartitionLock(locallock->hashcode);
Oid relid = locktag->locktag_field2;
- uint32 f;
+ uint32 i,
+ group;
+
+ /* fast-path group the lock belongs to */
+ group = FAST_PATH_REL_GROUP(relid);
LWLockAcquire(&MyProc->fpInfoLock, LW_EXCLUSIVE);
- for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
+ for (i = 0; i < FP_LOCK_SLOTS_PER_GROUP; i++)
{
uint32 lockmode;
+ /* index into the whole per-backend array */
+ uint32 f = FAST_PATH_SLOT(group, i);
+
/* Look for an allocated slot matching the given relid. */
if (relid != MyProc->fpRelId[f] || FAST_PATH_GET_BITS(MyProc, f) == 0)
continue;
for (i = 0; i < ProcGlobal->allProcCount; i++)
{
PGPROC *proc = &ProcGlobal->allProcs[i];
- uint32 f;
+ uint32 j,
+ group;
/* A backend never blocks itself */
if (proc == MyProc)
continue;
}
- for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
+ /* fast-path group the lock belongs to */
+ group = FAST_PATH_REL_GROUP(relid);
+
+ for (j = 0; j < FP_LOCK_SLOTS_PER_GROUP; j++)
{
uint32 lockmask;
+ /* index into the whole per-backend array */
+ uint32 f = FAST_PATH_SLOT(group, j);
+
/* Look for an allocated slot matching the given relid. */
if (relid != proc->fpRelId[f])
continue;
Size size = 0;
Size TotalProcs =
add_size(MaxBackends, add_size(NUM_AUXILIARY_PROCS, max_prepared_xacts));
+ Size fpLockBitsSize,
+ fpRelIdSize;
/* ProcGlobal */
size = add_size(size, sizeof(PROC_HDR));
size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->subxidStates)));
size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->statusFlags)));
+ /*
+ * Memory needed for PGPROC fast-path lock arrays. Make sure the sizes are
+ * nicely aligned in each backend.
+ */
+ fpLockBitsSize = MAXALIGN(FastPathLockGroupsPerBackend * sizeof(uint64));
+ fpRelIdSize = MAXALIGN(FastPathLockGroupsPerBackend * sizeof(Oid) * FP_LOCK_SLOTS_PER_GROUP);
+
+ size = add_size(size, mul_size(TotalProcs, (fpLockBitsSize + fpRelIdSize)));
+
return size;
}
bool found;
uint32 TotalProcs = MaxBackends + NUM_AUXILIARY_PROCS + max_prepared_xacts;
+ /* Used for setup of per-backend fast-path slots. */
+ char *fpPtr,
+ *fpEndPtr PG_USED_FOR_ASSERTS_ONLY;
+ Size fpLockBitsSize,
+ fpRelIdSize;
+
/* Create the ProcGlobal shared structure */
ProcGlobal = (PROC_HDR *)
ShmemInitStruct("Proc Header", sizeof(PROC_HDR), &found);
ProcGlobal->statusFlags = (uint8 *) ShmemAlloc(TotalProcs * sizeof(*ProcGlobal->statusFlags));
MemSet(ProcGlobal->statusFlags, 0, TotalProcs * sizeof(*ProcGlobal->statusFlags));
+ /*
+ * Allocate arrays for fast-path locks. Those are variable-length, so
+ * can't be included in PGPROC directly. We allocate a separate piece of
+ * shared memory and then divide that between backends.
+ */
+ fpLockBitsSize = MAXALIGN(FastPathLockGroupsPerBackend * sizeof(uint64));
+ fpRelIdSize = MAXALIGN(FastPathLockGroupsPerBackend * sizeof(Oid) * FP_LOCK_SLOTS_PER_GROUP);
+
+ fpPtr = ShmemAlloc(TotalProcs * (fpLockBitsSize + fpRelIdSize));
+ MemSet(fpPtr, 0, TotalProcs * (fpLockBitsSize + fpRelIdSize));
+
+ /* For asserts checking we did not overflow. */
+ fpEndPtr = fpPtr + (TotalProcs * (fpLockBitsSize + fpRelIdSize));
+
for (i = 0; i < TotalProcs; i++)
{
PGPROC *proc = &procs[i];
/* Common initialization for all PGPROCs, regardless of type. */
+ /*
+ * Set the fast-path lock arrays, and move the pointer. We interleave
+ * the two arrays, to (hopefully) get some locality for each backend.
+ */
+ proc->fpLockBits = (uint64 *) fpPtr;
+ fpPtr += fpLockBitsSize;
+
+ proc->fpRelId = (Oid *) fpPtr;
+ fpPtr += fpRelIdSize;
+
+ Assert(fpPtr <= fpEndPtr);
+
/*
* Set up per-PGPROC semaphore, latch, and fpInfoLock. Prepared xact
* dummy PGPROCs don't need these though - they're never associated
pg_atomic_init_u64(&(proc->waitStart), 0);
}
+ /* Should have consumed exactly the expected amount of fast-path memory. */
+ Assert(fpPtr = fpEndPtr);
+
/*
* Save pointers to the blocks of PGPROC structures reserved for auxiliary
* processes and prepared transactions.
projects / postgresql.git / commitdiff