From b69f8be6f87afa5afdfea8a776955161c1da3e87 Mon Sep 17 00:00:00 2001
From: amit <amitlangote09@gmail.com>
Date: Thu, 15 Dec 2016 17:39:19 +0900
Subject: [PATCH 5/7] Fix oddities of tuple-routing and TupleTableSlots

We must use the partition's tuple descriptor *after* a tuple is routed,
not the root table's.  Partition's attributes, for example, may be
ordered diferently from the root table's.

We must then switch back to the root table's for the next tuple and
so on.  A dedicated TupleTableSlot is allocated within EState called
es_partition_tuple_slot whose descriptor is set to a given leaf
partition for every row after it's routed.
---
 src/backend/commands/copy.c            | 28 +++++++++++++++++++++++++++-
 src/backend/executor/nodeModifyTable.c | 25 +++++++++++++++++++++++++
 src/include/nodes/execnodes.h          |  3 +++
 3 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c
index a0eb4241e2..bec8c73903 100644
--- a/src/backend/commands/copy.c
+++ b/src/backend/commands/copy.c
@@ -2441,6 +2441,15 @@ CopyFrom(CopyState cstate)
 	estate->es_trig_tuple_slot = ExecInitExtraTupleSlot(estate);
 
 	/*
+	 * Initialize a dedicated slot to manipulate tuples of any given
+	 * partition's rowtype.
+	 */
+	if (cstate->partition_dispatch_info)
+		estate->es_partition_tuple_slot = ExecInitExtraTupleSlot(estate);
+	else
+		estate->es_partition_tuple_slot = NULL;
+
+	/*
 	 * It's more efficient to prepare a bunch of tuples for insertion, and
 	 * insert them in one heap_multi_insert() call, than call heap_insert()
 	 * separately for every tuple. However, we can't do that if there are
@@ -2489,7 +2498,8 @@ CopyFrom(CopyState cstate)
 
 	for (;;)
 	{
-		TupleTableSlot *slot;
+		TupleTableSlot *slot,
+					   *oldslot = NULL;
 		bool		skip_tuple;
 		Oid			loaded_oid = InvalidOid;
 
@@ -2576,7 +2586,19 @@ CopyFrom(CopyState cstate)
 			map = cstate->partition_tupconv_maps[leaf_part_index];
 			if (map)
 			{
+				Relation	partrel = resultRelInfo->ri_RelationDesc;
+
 				tuple = do_convert_tuple(tuple, map);
+
+				/*
+				 * We must use the partition's tuple descriptor from this
+				 * point on.  Use a dedicated slot from this point on until
+				 * we're finished dealing with the partition.
+				 */
+				oldslot = slot;
+				slot = estate->es_partition_tuple_slot;
+				Assert(slot != NULL);
+				ExecSetSlotDescriptor(slot, RelationGetDescr(partrel));
 				ExecStoreTuple(tuple, slot, InvalidBuffer, true);
 			}
 
@@ -2672,6 +2694,10 @@ CopyFrom(CopyState cstate)
 			{
 				resultRelInfo = saved_resultRelInfo;
 				estate->es_result_relation_info = resultRelInfo;
+
+				/* Switch back to the slot corresponding to the root table */
+				Assert(oldslot != NULL);
+				slot = oldslot;
 			}
 		}
 	}
diff --git a/src/backend/executor/nodeModifyTable.c b/src/backend/executor/nodeModifyTable.c
index a9546106ce..da4c96a863 100644
--- a/src/backend/executor/nodeModifyTable.c
+++ b/src/backend/executor/nodeModifyTable.c
@@ -262,6 +262,7 @@ ExecInsert(ModifyTableState *mtstate,
 	Relation	resultRelationDesc;
 	Oid			newId;
 	List	   *recheckIndexes = NIL;
+	TupleTableSlot *oldslot = NULL;
 
 	/*
 	 * get the heap tuple out of the tuple table slot, making sure we have a
@@ -318,7 +319,19 @@ ExecInsert(ModifyTableState *mtstate,
 		map = mtstate->mt_partition_tupconv_maps[leaf_part_index];
 		if (map)
 		{
+			Relation partrel = resultRelInfo->ri_RelationDesc;
+
 			tuple = do_convert_tuple(tuple, map);
+
+			/*
+			 * We must use the partition's tuple descriptor from this
+			 * point on, until we're finished dealing with the partition.
+			 * Use the dedicated slot for that.
+			 */
+			oldslot = slot;
+			slot = estate->es_partition_tuple_slot;
+			Assert(slot != NULL);
+			ExecSetSlotDescriptor(slot, RelationGetDescr(partrel));
 			ExecStoreTuple(tuple, slot, InvalidBuffer, true);
 		}
 	}
@@ -566,6 +579,10 @@ ExecInsert(ModifyTableState *mtstate,
 	{
 		resultRelInfo = saved_resultRelInfo;
 		estate->es_result_relation_info = resultRelInfo;
+
+		/* Switch back to the slot corresponding to the root table */
+		Assert(oldslot != NULL);
+		slot = oldslot;
 	}
 
 	/*
@@ -1734,7 +1751,15 @@ ExecInitModifyTable(ModifyTable *node, EState *estate, int eflags)
 		mtstate->mt_partitions = partitions;
 		mtstate->mt_num_partitions = num_partitions;
 		mtstate->mt_partition_tupconv_maps = partition_tupconv_maps;
+
+		/*
+		 * Initialize a dedicated slot to manipulate tuples of any given
+		 * partition's rowtype.
+		 */
+		estate->es_partition_tuple_slot = ExecInitExtraTupleSlot(estate);
 	}
+	else
+		estate->es_partition_tuple_slot = NULL;
 
 	/*
 	 * Initialize any WITH CHECK OPTION constraints if needed.
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 1de5c8196d..be9a5e23cb 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -384,6 +384,9 @@ typedef struct EState
 	TupleTableSlot *es_trig_oldtup_slot;		/* for TriggerEnabled */
 	TupleTableSlot *es_trig_newtup_slot;		/* for TriggerEnabled */
 
+	/* Slot used to manipulate a tuple after it is routed to a partition */
+	TupleTableSlot *es_partition_tuple_slot;
+
 	/* Parameter info: */
 	ParamListInfo es_param_list_info;	/* values of external params */
 	ParamExecData *es_param_exec_vals;	/* values of internal params */
-- 
2.11.0