Improve accounting for PredXactList, RWConflictPool and PGPROC

Various places allocated shared memory by first allocating a small chunk
using ShmemInitStruct(), followed by ShmemAlloc() calls to allocate more
memory. Unfortunately, ShmemAlloc() does not update ShmemIndex, so this
affected pg_shmem_allocations - it only shown the initial chunk.

This commit modifies the following allocations, to allocate everything
as a single chunk, and then split it internally.

- PredXactList
- RWConflictPool
- PGPROC structures
- Fast-Path Lock Array

The fast-path lock array is allocated separately, not as a part of the
PGPROC structures allocation.

Author: Rahila Syed <rahilasyed90@gmail.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Reviewed-by: Nazir Bilal Yavuz <byavuz81@gmail.com>
Reviewed-by: Tomas Vondra <tomas@vondra.me>
Discussion: https://postgr.es/m/CAH2L28vHzRankszhqz7deXURxKncxfirnuW68zD7+hVAqaS5GQ@mail.gmail.com

Author: tvondra

src/backend/storage/lmgr/predicate.c

@@ -1226,14 +1226,21 @@ PredicateLockShmemInit(void)
 	 */
 	max_table_size *= 10;
 
+	requestSize = add_size(PredXactListDataSize,
+						   (mul_size((Size) max_table_size,
+									 sizeof(SERIALIZABLEXACT))));
+
 	PredXact = ShmemInitStruct("PredXactList",
-							   PredXactListDataSize,
+							   requestSize,
 							   &found);
 	Assert(found == IsUnderPostmaster);
 	if (!found)
 	{
 		int			i;
 
+		/* clean everything, both the header and the element */
+		memset(PredXact, 0, requestSize);
+
 		dlist_init(&PredXact->availableList);
 		dlist_init(&PredXact->activeList);
 		PredXact->SxactGlobalXmin = InvalidTransactionId;
@@ -1242,11 +1249,9 @@ PredicateLockShmemInit(void)
 		PredXact->LastSxactCommitSeqNo = FirstNormalSerCommitSeqNo - 1;
 		PredXact->CanPartialClearThrough = 0;
 		PredXact->HavePartialClearedThrough = 0;
-		requestSize = mul_size((Size) max_table_size,
-							   sizeof(SERIALIZABLEXACT));
-		PredXact->element = ShmemAlloc(requestSize);
+		PredXact->element
+			= (SERIALIZABLEXACT *) ((char *) PredXact + PredXactListDataSize);
 		/* Add all elements to available list, clean. */
-		memset(PredXact->element, 0, requestSize);
 		for (i = 0; i < max_table_size; i++)
 		{
 			LWLockInitialize(&PredXact->element[i].perXactPredicateListLock,
@@ -1300,20 +1305,25 @@ PredicateLockShmemInit(void)
 	 */
 	max_table_size *= 5;
 
+	requestSize = RWConflictPoolHeaderDataSize +
+		mul_size((Size) max_table_size,
+				 RWConflictDataSize);
+
 	RWConflictPool = ShmemInitStruct("RWConflictPool",
-									 RWConflictPoolHeaderDataSize,
+									 requestSize,
 									 &found);
 	Assert(found == IsUnderPostmaster);
 	if (!found)
 	{
 		int			i;
 
+		/* clean everything, including the elements */
+		memset(RWConflictPool, 0, requestSize);
+
 		dlist_init(&RWConflictPool->availableList);
-		requestSize = mul_size((Size) max_table_size,
-							   RWConflictDataSize);
-		RWConflictPool->element = ShmemAlloc(requestSize);
+		RWConflictPool->element = (RWConflict) ((char *) RWConflictPool +
+												RWConflictPoolHeaderDataSize);
 		/* Add all elements to available list, clean. */
-		memset(RWConflictPool->element, 0, requestSize);
 		for (i = 0; i < max_table_size; i++)
 		{
 			dlist_push_tail(&RWConflictPool->availableList,

src/backend/storage/lmgr/proc.c

@@ -91,26 +91,35 @@ static void CheckDeadLock(void);
 
 
 /*
- * Report shared-memory space needed by InitProcGlobal.
+ * Report shared-memory space needed by PGPROC.
  */
-Size
-ProcGlobalShmemSize(void)
+static Size
+PGProcShmemSize(void)
 {
 	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(PGPROC)));
-	size = add_size(size, sizeof(slock_t));
-
 	size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->xids)));
 	size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->subxidStates)));
 	size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->statusFlags)));
 
+	return size;
+}
+
+/*
+ * Report shared-memory space needed by Fast-Path locks.
+ */
+static Size
+FastPathLockShmemSize(void)
+{
+	Size		size = 0;
+	Size		TotalProcs =
+		add_size(MaxBackends, add_size(NUM_AUXILIARY_PROCS, max_prepared_xacts));
+	Size		fpLockBitsSize,
+				fpRelIdSize;
+
 	/*
 	 * Memory needed for PGPROC fast-path lock arrays. Make sure the sizes are
 	 * nicely aligned in each backend.
@@ -123,6 +132,24 @@ ProcGlobalShmemSize(void)
 	return size;
 }
 
+/*
+ * Report shared-memory space needed by InitProcGlobal.
+ */
+Size
+ProcGlobalShmemSize(void)
+{
+	Size		size = 0;
+
+	/* ProcGlobal */
+	size = add_size(size, sizeof(PROC_HDR));
+	size = add_size(size, sizeof(slock_t));
+
+	size = add_size(size, PGProcShmemSize());
+	size = add_size(size, FastPathLockShmemSize());
+
+	return size;
+}
+
 /*
  * Report number of semaphores needed by InitProcGlobal.
  */
@@ -175,6 +202,8 @@ InitProcGlobal(void)
 			   *fpEndPtr PG_USED_FOR_ASSERTS_ONLY;
 	Size		fpLockBitsSize,
 				fpRelIdSize;
+	Size		requestSize;
+	char	   *ptr;
 
 	/* Create the ProcGlobal shared structure */
 	ProcGlobal = (PROC_HDR *)
@@ -204,8 +233,17 @@ InitProcGlobal(void)
 	 * with a single freelist.)  Each PGPROC structure is dedicated to exactly
 	 * one of these purposes, and they do not move between groups.
 	 */
-	procs = (PGPROC *) ShmemAlloc(TotalProcs * sizeof(PGPROC));
-	MemSet(procs, 0, TotalProcs * sizeof(PGPROC));
+	requestSize = PGProcShmemSize();
+
+	ptr = ShmemInitStruct("PGPROC structures",
+						  requestSize,
+						  &found);
+
+	MemSet(ptr, 0, requestSize);
+
+	procs = (PGPROC *) ptr;
+	ptr = (char *) ptr + TotalProcs * sizeof(PGPROC);
+
 	ProcGlobal->allProcs = procs;
 	/* XXX allProcCount isn't really all of them; it excludes prepared xacts */
 	ProcGlobal->allProcCount = MaxBackends + NUM_AUXILIARY_PROCS;
@@ -217,13 +255,17 @@ InitProcGlobal(void)
 	 * XXX: It might make sense to increase padding for these arrays, given
 	 * how hotly they are accessed.
 	 */
-	ProcGlobal->xids =
-		(TransactionId *) ShmemAlloc(TotalProcs * sizeof(*ProcGlobal->xids));
-	MemSet(ProcGlobal->xids, 0, TotalProcs * sizeof(*ProcGlobal->xids));
-	ProcGlobal->subxidStates = (XidCacheStatus *) ShmemAlloc(TotalProcs * sizeof(*ProcGlobal->subxidStates));
-	MemSet(ProcGlobal->subxidStates, 0, TotalProcs * sizeof(*ProcGlobal->subxidStates));
-	ProcGlobal->statusFlags = (uint8 *) ShmemAlloc(TotalProcs * sizeof(*ProcGlobal->statusFlags));
-	MemSet(ProcGlobal->statusFlags, 0, TotalProcs * sizeof(*ProcGlobal->statusFlags));
+	ProcGlobal->xids = (TransactionId *) ptr;
+	ptr = (char *) ptr + (TotalProcs * sizeof(*ProcGlobal->xids));
+
+	ProcGlobal->subxidStates = (XidCacheStatus *) ptr;
+	ptr = (char *) ptr + (TotalProcs * sizeof(*ProcGlobal->subxidStates));
+
+	ProcGlobal->statusFlags = (uint8 *) ptr;
+	ptr = (char *) ptr + (TotalProcs * sizeof(*ProcGlobal->statusFlags));
+
+	/* make sure wer didn't overflow */
+	Assert((ptr > (char *) procs) && (ptr <= (char *) procs + requestSize));
 
 	/*
 	 * Allocate arrays for fast-path locks. Those are variable-length, so
@@ -233,11 +275,16 @@ InitProcGlobal(void)
 	fpLockBitsSize = MAXALIGN(FastPathLockGroupsPerBackend * sizeof(uint64));
 	fpRelIdSize = MAXALIGN(FastPathLockSlotsPerBackend() * sizeof(Oid));
 
-	fpPtr = ShmemAlloc(TotalProcs * (fpLockBitsSize + fpRelIdSize));
-	MemSet(fpPtr, 0, TotalProcs * (fpLockBitsSize + fpRelIdSize));
+	requestSize = FastPathLockShmemSize();
+
+	fpPtr = ShmemInitStruct("Fast-Path Lock Array",
+							requestSize,
+							&found);
+
+	MemSet(fpPtr, 0, requestSize);
 
 	/* For asserts checking we did not overflow. */
-	fpEndPtr = fpPtr + (TotalProcs * (fpLockBitsSize + fpRelIdSize));
+	fpEndPtr = fpPtr + requestSize;
 
 	for (i = 0; i < TotalProcs; i++)
 	{
@@ -330,7 +377,9 @@ InitProcGlobal(void)
 	PreparedXactProcs = &procs[MaxBackends + NUM_AUXILIARY_PROCS];
 
 	/* Create ProcStructLock spinlock, too */
-	ProcStructLock = (slock_t *) ShmemAlloc(sizeof(slock_t));
+	ProcStructLock = (slock_t *) ShmemInitStruct("ProcStructLock spinlock",
+												 sizeof(slock_t),
+												 &found);
 	SpinLockInit(ProcStructLock);
 }