Use the new "Slab" context for some allocations in reorderbuffer.h.

Note that this change alone does not yet fully address the performance
problems triggering this work, a large portion of the slowdown is
triggered by the tuple allocator, which isn't converted to the new
allocator.  It would be possible to do so, but using evenly sized
objects, like both the current implementation in reorderbuffer.c and
slab.c, wastes a fair amount of memory.  A later patch by Tomas will
introduce a better approach.

Author: Tomas Vondra
Reviewed-By: Andres Freund
Discussion: https://postgr.es/m/d15dff83-0b37-28ed-0809-95a5cc7292ad@2ndquadrant.com

Author: anarazel

src/backend/replication/logical/reorderbuffer.c

@@ -156,10 +156,7 @@ static const Size max_changes_in_memory = 4096;
  * major bottleneck, especially when spilling to disk while decoding batch
  * workloads.
  */
-static const Size max_cached_changes = 4096 * 2;
 static const Size max_cached_tuplebufs = 4096 * 2;		/* ~8MB */
-static const Size max_cached_transactions = 512;
-
 
 /* ---------------------------------------
  * primary reorderbuffer support routines
@@ -241,6 +238,16 @@ ReorderBufferAllocate(void)
 
 	buffer->context = new_ctx;
 
+	buffer->change_context = SlabContextCreate(new_ctx,
+											   "Change",
+											   SLAB_DEFAULT_BLOCK_SIZE,
+											   sizeof(ReorderBufferChange));
+
+	buffer->txn_context = SlabContextCreate(new_ctx,
+											"TXN",
+											SLAB_DEFAULT_BLOCK_SIZE,
+											sizeof(ReorderBufferTXN));
+
 	hash_ctl.keysize = sizeof(TransactionId);
 	hash_ctl.entrysize = sizeof(ReorderBufferTXNByIdEnt);
 	hash_ctl.hcxt = buffer->context;
@@ -251,8 +258,6 @@ ReorderBufferAllocate(void)
 	buffer->by_txn_last_xid = InvalidTransactionId;
 	buffer->by_txn_last_txn = NULL;
 
-	buffer->nr_cached_transactions = 0;
-	buffer->nr_cached_changes = 0;
 	buffer->nr_cached_tuplebufs = 0;
 
 	buffer->outbuf = NULL;
@@ -261,8 +266,6 @@ ReorderBufferAllocate(void)
 	buffer->current_restart_decoding_lsn = InvalidXLogRecPtr;
 
 	dlist_init(&buffer->toplevel_by_lsn);
-	dlist_init(&buffer->cached_transactions);
-	dlist_init(&buffer->cached_changes);
 	slist_init(&buffer->cached_tuplebufs);
 
 	return buffer;
@@ -291,19 +294,8 @@ ReorderBufferGetTXN(ReorderBuffer *rb)
 {
 	ReorderBufferTXN *txn;
 
-	/* check the slab cache */
-	if (rb->nr_cached_transactions > 0)
-	{
-		rb->nr_cached_transactions--;
-		txn = (ReorderBufferTXN *)
-			dlist_container(ReorderBufferTXN, node,
-							dlist_pop_head_node(&rb->cached_transactions));
-	}
-	else
-	{
-		txn = (ReorderBufferTXN *)
-			MemoryContextAlloc(rb->context, sizeof(ReorderBufferTXN));
-	}
+	txn = (ReorderBufferTXN *)
+		MemoryContextAlloc(rb->txn_context, sizeof(ReorderBufferTXN));
 
 	memset(txn, 0, sizeof(ReorderBufferTXN));
 
@@ -344,18 +336,7 @@ ReorderBufferReturnTXN(ReorderBuffer *rb, ReorderBufferTXN *txn)
 		txn->invalidations = NULL;
 	}
 
-	/* check whether to put into the slab cache */
-	if (rb->nr_cached_transactions < max_cached_transactions)
-	{
-		rb->nr_cached_transactions++;
-		dlist_push_head(&rb->cached_transactions, &txn->node);
-		VALGRIND_MAKE_MEM_UNDEFINED(txn, sizeof(ReorderBufferTXN));
-		VALGRIND_MAKE_MEM_DEFINED(&txn->node, sizeof(txn->node));
-	}
-	else
-	{
-		pfree(txn);
-	}
+	pfree(txn);
 }
 
 /*
@@ -366,19 +347,8 @@ ReorderBufferGetChange(ReorderBuffer *rb)
 {
 	ReorderBufferChange *change;
 
-	/* check the slab cache */
-	if (rb->nr_cached_changes)
-	{
-		rb->nr_cached_changes--;
-		change = (ReorderBufferChange *)
-			dlist_container(ReorderBufferChange, node,
-							dlist_pop_head_node(&rb->cached_changes));
-	}
-	else
-	{
-		change = (ReorderBufferChange *)
-			MemoryContextAlloc(rb->context, sizeof(ReorderBufferChange));
-	}
+	change = (ReorderBufferChange *)
+		MemoryContextAlloc(rb->change_context, sizeof(ReorderBufferChange));
 
 	memset(change, 0, sizeof(ReorderBufferChange));
 	return change;
@@ -434,21 +404,9 @@ ReorderBufferReturnChange(ReorderBuffer *rb, ReorderBufferChange *change)
 			break;
 	}
 
-	/* check whether to put into the slab cache */
-	if (rb->nr_cached_changes < max_cached_changes)
-	{
-		rb->nr_cached_changes++;
-		dlist_push_head(&rb->cached_changes, &change->node);
-		VALGRIND_MAKE_MEM_UNDEFINED(change, sizeof(ReorderBufferChange));
-		VALGRIND_MAKE_MEM_DEFINED(&change->node, sizeof(change->node));
-	}
-	else
-	{
-		pfree(change);
-	}
+	pfree(change);
 }
 
-
 /*
  * Get an unused, possibly preallocated, ReorderBufferTupleBuf fitting at
  * least a tuple of size tuple_len (excluding header overhead).

src/include/replication/reorderbuffer.h

@@ -330,6 +330,12 @@ struct ReorderBuffer
 	 */
 	MemoryContext context;
 
+	/*
+	 * Memory contexts for specific types objects
+	 */
+	MemoryContext change_context;
+	MemoryContext txn_context;
+
 	/*
 	 * Data structure slab cache.
 	 *
@@ -340,14 +346,6 @@ struct ReorderBuffer
 	 * on top of reorderbuffer.c
 	 */
 
-	/* cached ReorderBufferTXNs */
-	dlist_head	cached_transactions;
-	Size		nr_cached_transactions;
-
-	/* cached ReorderBufferChanges */
-	dlist_head	cached_changes;
-	Size		nr_cached_changes;
-
 	/* cached ReorderBufferTupleBufs */
 	slist_head	cached_tuplebufs;
 	Size		nr_cached_tuplebufs;