Directly modify foreign tables.

postgres_fdw can now sent an UPDATE or DELETE statement directly to
the foreign server in simple cases, rather than sending a SELECT FOR
UPDATE statement and then updating or deleting rows one-by-one.

Etsuro Fujita, reviewed by Rushabh Lathia, Shigeru Hanada, Kyotaro
Horiguchi, Albe Laurenz, Thom Brown, and me.

src/backend/commands/explain.c

@@ -900,7 +900,29 @@ ExplainNode(PlanState *planstate, List *ancestors,
 			pname = sname = "WorkTable Scan";
 			break;
 		case T_ForeignScan:
-			pname = sname = "Foreign Scan";
+			sname = "Foreign Scan";
+			switch (((ForeignScan *) plan)->operation)
+			{
+				case CMD_SELECT:
+					pname = "Foreign Scan";
+					operation = "Select";
+					break;
+				case CMD_INSERT:
+					pname = "Foreign Insert";
+					operation = "Insert";
+					break;
+				case CMD_UPDATE:
+					pname = "Foreign Update";
+					operation = "Update";
+					break;
+				case CMD_DELETE:
+					pname = "Foreign Delete";
+					operation = "Delete";
+					break;
+				default:
+					pname = "???";
+					break;
+			}
 			break;
 		case T_CustomScan:
 			sname = "Custom Scan";
@@ -1648,6 +1670,19 @@ show_plan_tlist(PlanState *planstate, List *ancestors, ExplainState *es)
 		return;
 	if (IsA(plan, RecursiveUnion))
 		return;
+	/*
+	 * Likewise for ForeignScan that executes a direct INSERT/UPDATE/DELETE
+	 *
+	 * Note: the tlist for a ForeignScan that executes a direct INSERT/UPDATE
+	 * might contain subplan output expressions that are confusing in this
+	 * context.  The tlist for a ForeignScan that executes a direct UPDATE/
+	 * DELETE always contains "junk" target columns to identify the exact row
+	 * to update or delete, which would be confusing in this context.  So, we
+	 * suppress it in all the cases.
+	 */
+	if (IsA(plan, ForeignScan) &&
+		((ForeignScan *) plan)->operation != CMD_SELECT)
+		return;
 
 	/* Set up deparsing context */
 	context = set_deparse_context_planstate(es->deparse_cxt,
@@ -2236,8 +2271,16 @@ show_foreignscan_info(ForeignScanState *fsstate, ExplainState *es)
 	FdwRoutine *fdwroutine = fsstate->fdwroutine;
 
 	/* Let the FDW emit whatever fields it wants */
-	if (fdwroutine->ExplainForeignScan != NULL)
-		fdwroutine->ExplainForeignScan(fsstate, es);
+	if (((ForeignScan *) fsstate->ss.ps.plan)->operation != CMD_SELECT)
+	{
+		if (fdwroutine->ExplainDirectModify != NULL)
+			fdwroutine->ExplainDirectModify(fsstate, es);
+	}
+	else
+	{
+		if (fdwroutine->ExplainForeignScan != NULL)
+			fdwroutine->ExplainForeignScan(fsstate, es);
+	}
 }
 
 /*
@@ -2623,8 +2666,10 @@ show_modifytable_info(ModifyTableState *mtstate, List *ancestors,
 			}
 		}
 
-		/* Give FDW a chance */
-		if (fdwroutine && fdwroutine->ExplainForeignModify != NULL)
+		/* Give FDW a chance if needed */
+		if (!resultRelInfo->ri_usesFdwDirectModify &&
+			fdwroutine != NULL &&
+			fdwroutine->ExplainForeignModify != NULL)
 		{
 			List	   *fdw_private = (List *) list_nth(node->fdwPrivLists, j);
 

src/backend/executor/execMain.c

@@ -1245,6 +1245,7 @@ InitResultRelInfo(ResultRelInfo *resultRelInfo,
 	else
 		resultRelInfo->ri_FdwRoutine = NULL;
 	resultRelInfo->ri_FdwState = NULL;
+	resultRelInfo->ri_usesFdwDirectModify = false;
 	resultRelInfo->ri_ConstraintExprs = NULL;
 	resultRelInfo->ri_junkFilter = NULL;
 	resultRelInfo->ri_projectReturning = NULL;

src/backend/executor/nodeForeignscan.c

@@ -48,7 +48,10 @@ ForeignNext(ForeignScanState *node)
 
 	/* Call the Iterate function in short-lived context */
 	oldcontext = MemoryContextSwitchTo(econtext->ecxt_per_tuple_memory);
-	slot = node->fdwroutine->IterateForeignScan(node);
+	if (plan->operation != CMD_SELECT)
+		slot = node->fdwroutine->IterateDirectModify(node);
+	else
+		slot = node->fdwroutine->IterateForeignScan(node);
 	MemoryContextSwitchTo(oldcontext);
 
 	/*
@@ -226,7 +229,10 @@ ExecInitForeignScan(ForeignScan *node, EState *estate, int eflags)
 	/*
 	 * Tell the FDW to initialize the scan.
 	 */
-	fdwroutine->BeginForeignScan(scanstate, eflags);
+	if (node->operation != CMD_SELECT)
+		fdwroutine->BeginDirectModify(scanstate, eflags);
+	else
+		fdwroutine->BeginForeignScan(scanstate, eflags);
 
 	return scanstate;
 }
@@ -240,8 +246,13 @@ ExecInitForeignScan(ForeignScan *node, EState *estate, int eflags)
 void
 ExecEndForeignScan(ForeignScanState *node)
 {
+	ForeignScan *plan = (ForeignScan *) node->ss.ps.plan;
+
 	/* Let the FDW shut down */
-	node->fdwroutine->EndForeignScan(node);
+	if (plan->operation != CMD_SELECT)
+		node->fdwroutine->EndDirectModify(node);
+	else
+		node->fdwroutine->EndForeignScan(node);
 
 	/* Shut down any outer plan. */
 	if (outerPlanState(node))

src/backend/executor/nodeModifyTable.c

@@ -138,13 +138,17 @@ ExecCheckPlanOutput(Relation resultRel, List *targetList)
  * tupleSlot: slot holding tuple actually inserted/updated/deleted
  * planSlot: slot holding tuple returned by top subplan node
  *
+ * Note: If tupleSlot is NULL, the FDW should have already provided econtext's
+ * scan tuple.
+ *
  * Returns a slot holding the result tuple
  */
 static TupleTableSlot *
-ExecProcessReturning(ProjectionInfo *projectReturning,
+ExecProcessReturning(ResultRelInfo *resultRelInfo,
 					 TupleTableSlot *tupleSlot,
 					 TupleTableSlot *planSlot)
 {
+	ProjectionInfo *projectReturning = resultRelInfo->ri_projectReturning;
 	ExprContext *econtext = projectReturning->pi_exprContext;
 
 	/*
@@ -154,7 +158,20 @@ ExecProcessReturning(ProjectionInfo *projectReturning,
 	ResetExprContext(econtext);
 
 	/* Make tuple and any needed join variables available to ExecProject */
-	econtext->ecxt_scantuple = tupleSlot;
+	if (tupleSlot)
+		econtext->ecxt_scantuple = tupleSlot;
+	else
+	{
+		HeapTuple	tuple;
+
+		/*
+		 * RETURNING expressions might reference the tableoid column, so
+		 * initialize t_tableOid before evaluating them.
+		 */
+		Assert(!TupIsNull(econtext->ecxt_scantuple));
+		tuple = ExecMaterializeSlot(econtext->ecxt_scantuple);
+		tuple->t_tableOid = RelationGetRelid(resultRelInfo->ri_RelationDesc);
+	}
 	econtext->ecxt_outertuple = planSlot;
 
 	/* Compute the RETURNING expressions */
@@ -496,8 +513,7 @@ ExecInsert(ModifyTableState *mtstate,
 
 	/* Process RETURNING if present */
 	if (resultRelInfo->ri_projectReturning)
-		return ExecProcessReturning(resultRelInfo->ri_projectReturning,
-									slot, planSlot);
+		return ExecProcessReturning(resultRelInfo, slot, planSlot);
 
 	return NULL;
 }
@@ -738,8 +754,7 @@ ldelete:;
 			ExecStoreTuple(&deltuple, slot, InvalidBuffer, false);
 		}
 
-		rslot = ExecProcessReturning(resultRelInfo->ri_projectReturning,
-									 slot, planSlot);
+		rslot = ExecProcessReturning(resultRelInfo, slot, planSlot);
 
 		/*
 		 * Before releasing the target tuple again, make sure rslot has a
@@ -1024,8 +1039,7 @@ lreplace:;
 
 	/* Process RETURNING if present */
 	if (resultRelInfo->ri_projectReturning)
-		return ExecProcessReturning(resultRelInfo->ri_projectReturning,
-									slot, planSlot);
+		return ExecProcessReturning(resultRelInfo, slot, planSlot);
 
 	return NULL;
 }
@@ -1380,6 +1394,26 @@ ExecModifyTable(ModifyTableState *node)
 				break;
 		}
 
+		/*
+		 * If resultRelInfo->ri_usesFdwDirectModify is true, all we need to do
+		 * here is compute the RETURNING expressions.
+		 */
+		if (resultRelInfo->ri_usesFdwDirectModify)
+		{
+			Assert(resultRelInfo->ri_projectReturning);
+
+			/*
+			 * A scan slot containing the data that was actually inserted,
+			 * updated or deleted has already been made available to
+			 * ExecProcessReturning by IterateDirectModify, so no need to
+			 * provide it here.
+			 */
+			slot = ExecProcessReturning(resultRelInfo, NULL, planSlot);
+
+			estate->es_result_relation_info = saved_resultRelInfo;
+			return slot;
+		}
+
 		EvalPlanQualSetSlot(&node->mt_epqstate, planSlot);
 		slot = planSlot;
 
@@ -1559,6 +1593,10 @@ ExecInitModifyTable(ModifyTable *node, EState *estate, int eflags)
 	{
 		subplan = (Plan *) lfirst(l);
 
+		/* Initialize the usesFdwDirectModify flag */
+		resultRelInfo->ri_usesFdwDirectModify = bms_is_member(i,
+												node->fdwDirectModifyPlans);
+
 		/*
 		 * Verify result relation is a valid target for the current operation
 		 */
@@ -1583,7 +1621,8 @@ ExecInitModifyTable(ModifyTable *node, EState *estate, int eflags)
 		mtstate->mt_plans[i] = ExecInitNode(subplan, estate, eflags);
 
 		/* Also let FDWs init themselves for foreign-table result rels */
-		if (resultRelInfo->ri_FdwRoutine != NULL &&
+		if (!resultRelInfo->ri_usesFdwDirectModify &&
+			resultRelInfo->ri_FdwRoutine != NULL &&
 			resultRelInfo->ri_FdwRoutine->BeginForeignModify != NULL)
 		{
 			List	   *fdw_private = (List *) list_nth(node->fdwPrivLists, i);
@@ -1910,7 +1949,8 @@ ExecEndModifyTable(ModifyTableState *node)
 	{
 		ResultRelInfo *resultRelInfo = node->resultRelInfo + i;
 
-		if (resultRelInfo->ri_FdwRoutine != NULL &&
+		if (!resultRelInfo->ri_usesFdwDirectModify &&
+			resultRelInfo->ri_FdwRoutine != NULL &&
 			resultRelInfo->ri_FdwRoutine->EndForeignModify != NULL)
 			resultRelInfo->ri_FdwRoutine->EndForeignModify(node->ps.state,
 														   resultRelInfo);

src/backend/nodes/copyfuncs.c

@@ -188,6 +188,7 @@ _copyModifyTable(const ModifyTable *from)
 	COPY_NODE_FIELD(withCheckOptionLists);
 	COPY_NODE_FIELD(returningLists);
 	COPY_NODE_FIELD(fdwPrivLists);
+	COPY_BITMAPSET_FIELD(fdwDirectModifyPlans);
 	COPY_NODE_FIELD(rowMarks);
 	COPY_SCALAR_FIELD(epqParam);
 	COPY_SCALAR_FIELD(onConflictAction);
@@ -648,6 +649,7 @@ _copyForeignScan(const ForeignScan *from)
 	/*
 	 * copy remainder of node
 	 */
+	COPY_SCALAR_FIELD(operation);
 	COPY_SCALAR_FIELD(fs_server);
 	COPY_NODE_FIELD(fdw_exprs);
 	COPY_NODE_FIELD(fdw_private);

src/backend/nodes/outfuncs.c

@@ -356,6 +356,7 @@ _outModifyTable(StringInfo str, const ModifyTable *node)
 	WRITE_NODE_FIELD(withCheckOptionLists);
 	WRITE_NODE_FIELD(returningLists);
 	WRITE_NODE_FIELD(fdwPrivLists);
+	WRITE_BITMAPSET_FIELD(fdwDirectModifyPlans);
 	WRITE_NODE_FIELD(rowMarks);
 	WRITE_INT_FIELD(epqParam);
 	WRITE_ENUM_FIELD(onConflictAction, OnConflictAction);
@@ -608,6 +609,7 @@ _outForeignScan(StringInfo str, const ForeignScan *node)
 
 	_outScanInfo(str, (const Scan *) node);
 
+	WRITE_ENUM_FIELD(operation, CmdType);
 	WRITE_OID_FIELD(fs_server);
 	WRITE_NODE_FIELD(fdw_exprs);
 	WRITE_NODE_FIELD(fdw_private);

src/backend/nodes/readfuncs.c

@@ -1481,6 +1481,7 @@ _readModifyTable(void)
 	READ_NODE_FIELD(withCheckOptionLists);
 	READ_NODE_FIELD(returningLists);
 	READ_NODE_FIELD(fdwPrivLists);
+	READ_BITMAPSET_FIELD(fdwDirectModifyPlans);
 	READ_NODE_FIELD(rowMarks);
 	READ_INT_FIELD(epqParam);
 	READ_ENUM_FIELD(onConflictAction, OnConflictAction);

src/backend/optimizer/plan/createplan.c

@@ -4906,6 +4906,7 @@ make_foreignscan(List *qptlist,
 	plan->lefttree = outer_plan;
 	plan->righttree = NULL;
 	node->scan.scanrelid = scanrelid;
+	node->operation = CMD_SELECT;
 	/* fs_server will be filled in by create_foreignscan_plan */
 	node->fs_server = InvalidOid;
 	node->fdw_exprs = fdw_exprs;
@@ -6021,6 +6022,7 @@ make_modifytable(PlannerInfo *root,
 {
 	ModifyTable *node = makeNode(ModifyTable);
 	List	   *fdw_private_list;
+	Bitmapset  *direct_modify_plans;
 	ListCell   *lc;
 	int			i;
 
@@ -6078,12 +6080,14 @@ make_modifytable(PlannerInfo *root,
 	 * construct private plan data, and accumulate it all into a list.
 	 */
 	fdw_private_list = NIL;
+	direct_modify_plans = NULL;
 	i = 0;
 	foreach(lc, resultRelations)
 	{
 		Index		rti = lfirst_int(lc);
 		FdwRoutine *fdwroutine;
 		List	   *fdw_private;
+		bool		direct_modify;
 
 		/*
 		 * If possible, we want to get the FdwRoutine from our RelOptInfo for
@@ -6110,7 +6114,23 @@ make_modifytable(PlannerInfo *root,
 				fdwroutine = NULL;
 		}
 
+		/*
+		 * If the target foreign table has any row-level triggers, we can't
+		 * modify the foreign table directly.
+		 */
+		direct_modify = false;
 		if (fdwroutine != NULL &&
+			fdwroutine->PlanDirectModify != NULL &&
+			fdwroutine->BeginDirectModify != NULL &&
+			fdwroutine->IterateDirectModify != NULL &&
+			fdwroutine->EndDirectModify != NULL &&
+			!has_row_triggers(root, rti, operation))
+			direct_modify = fdwroutine->PlanDirectModify(root, node, rti, i);
+		if (direct_modify)
+			direct_modify_plans = bms_add_member(direct_modify_plans, i);
+
+		if (!direct_modify &&
+			fdwroutine != NULL &&
 			fdwroutine->PlanForeignModify != NULL)
 			fdw_private = fdwroutine->PlanForeignModify(root, node, rti, i);
 		else
@@ -6119,6 +6139,7 @@ make_modifytable(PlannerInfo *root,
 		i++;
 	}
 	node->fdwPrivLists = fdw_private_list;
+	node->fdwDirectModifyPlans = direct_modify_plans;
 
 	return node;
 }

src/backend/optimizer/util/plancat.c

@@ -1540,3 +1540,50 @@ has_unique_index(RelOptInfo *rel, AttrNumber attno)
 	}
 	return false;
 }
+
+
+/*
+ * has_row_triggers
+ *
+ * Detect whether the specified relation has any row-level triggers for event.
+ */
+bool
+has_row_triggers(PlannerInfo *root, Index rti, CmdType event)
+{
+	RangeTblEntry *rte = planner_rt_fetch(rti, root);
+	Relation	relation;
+	TriggerDesc *trigDesc;
+	bool		result = false;
+
+	/* Assume we already have adequate lock */
+	relation = heap_open(rte->relid, NoLock);
+
+	trigDesc = relation->trigdesc;
+	switch (event)
+	{
+		case CMD_INSERT:
+			if (trigDesc &&
+				(trigDesc->trig_insert_after_row ||
+				 trigDesc->trig_insert_before_row))
+				result = true;
+			break;
+		case CMD_UPDATE:
+			if (trigDesc &&
+				(trigDesc->trig_update_after_row ||
+				 trigDesc->trig_update_before_row))
+				result = true;
+			break;
+		case CMD_DELETE:
+			if (trigDesc &&
+				(trigDesc->trig_delete_after_row ||
+				 trigDesc->trig_delete_before_row))
+				result = true;
+			break;
+		default:
+			elog(ERROR, "unrecognized CmdType: %d", (int) event);
+			break;
+	}
+
+	heap_close(relation, NoLock);
+	return result;
+}

src/include/foreign/fdwapi.h

@@ -97,6 +97,18 @@ typedef void (*EndForeignModify_function) (EState *estate,
 
 typedef int (*IsForeignRelUpdatable_function) (Relation rel);
 
+typedef bool (*PlanDirectModify_function) (PlannerInfo *root,
+										   ModifyTable *plan,
+										   Index resultRelation,
+										   int subplan_index);
+
+typedef void (*BeginDirectModify_function) (ForeignScanState *node,
+											int eflags);
+
+typedef TupleTableSlot *(*IterateDirectModify_function) (ForeignScanState *node);
+
+typedef void (*EndDirectModify_function) (ForeignScanState *node);
+
 typedef RowMarkType (*GetForeignRowMarkType_function) (RangeTblEntry *rte,
 												LockClauseStrength strength);
 
@@ -114,6 +126,9 @@ typedef void (*ExplainForeignModify_function) (ModifyTableState *mtstate,
 														   int subplan_index,
 													struct ExplainState *es);
 
+typedef void (*ExplainDirectModify_function) (ForeignScanState *node,
+													struct ExplainState *es);
+
 typedef int (*AcquireSampleRowsFunc) (Relation relation, int elevel,
 											   HeapTuple *rows, int targrows,
 												  double *totalrows,
@@ -181,6 +196,10 @@ typedef struct FdwRoutine
 	ExecForeignDelete_function ExecForeignDelete;
 	EndForeignModify_function EndForeignModify;
 	IsForeignRelUpdatable_function IsForeignRelUpdatable;
+	PlanDirectModify_function PlanDirectModify;
+	BeginDirectModify_function BeginDirectModify;
+	IterateDirectModify_function IterateDirectModify;
+	EndDirectModify_function EndDirectModify;
 
 	/* Functions for SELECT FOR UPDATE/SHARE row locking */
 	GetForeignRowMarkType_function GetForeignRowMarkType;
@@ -190,6 +209,7 @@ typedef struct FdwRoutine
 	/* Support functions for EXPLAIN */
 	ExplainForeignScan_function ExplainForeignScan;
 	ExplainForeignModify_function ExplainForeignModify;
+	ExplainDirectModify_function ExplainDirectModify;
 
 	/* Support functions for ANALYZE */
 	AnalyzeForeignTable_function AnalyzeForeignTable;

src/include/nodes/execnodes.h

@@ -311,6 +311,7 @@ typedef struct JunkFilter
  *		TrigInstrument			optional runtime measurements for triggers
  *		FdwRoutine				FDW callback functions, if foreign table
  *		FdwState				available to save private state of FDW
+ *		usesFdwDirectModify		true when modifying foreign table directly
  *		WithCheckOptions		list of WithCheckOption's to be checked
  *		WithCheckOptionExprs	list of WithCheckOption expr states
  *		ConstraintExprs			array of constraint-checking expr states
@@ -334,6 +335,7 @@ typedef struct ResultRelInfo
 	Instrumentation *ri_TrigInstrument;
 	struct FdwRoutine *ri_FdwRoutine;
 	void	   *ri_FdwState;
+	bool		ri_usesFdwDirectModify;
 	List	   *ri_WithCheckOptions;
 	List	   *ri_WithCheckOptionExprs;
 	List	  **ri_ConstraintExprs;

src/include/nodes/pg_list.h

@@ -134,16 +134,19 @@ list_length(const List *l)
 #define list_make2(x1,x2)			lcons(x1, list_make1(x2))
 #define list_make3(x1,x2,x3)		lcons(x1, list_make2(x2, x3))
 #define list_make4(x1,x2,x3,x4)		lcons(x1, list_make3(x2, x3, x4))
+#define list_make5(x1,x2,x3,x4,x5)	lcons(x1, list_make4(x2, x3, x4, x5))
 
 #define list_make1_int(x1)			lcons_int(x1, NIL)
 #define list_make2_int(x1,x2)		lcons_int(x1, list_make1_int(x2))
 #define list_make3_int(x1,x2,x3)	lcons_int(x1, list_make2_int(x2, x3))
 #define list_make4_int(x1,x2,x3,x4) lcons_int(x1, list_make3_int(x2, x3, x4))
+#define list_make5_int(x1,x2,x3,x4,x5)	lcons_int(x1, list_make4_int(x2, x3, x4, x5))
 
 #define list_make1_oid(x1)			lcons_oid(x1, NIL)
 #define list_make2_oid(x1,x2)		lcons_oid(x1, list_make1_oid(x2))
 #define list_make3_oid(x1,x2,x3)	lcons_oid(x1, list_make2_oid(x2, x3))
 #define list_make4_oid(x1,x2,x3,x4) lcons_oid(x1, list_make3_oid(x2, x3, x4))
+#define list_make5_oid(x1,x2,x3,x4,x5)	lcons_oid(x1, list_make4_oid(x2, x3, x4, x5))
 
 /*
  * foreach -

src/include/nodes/plannodes.h

@@ -189,6 +189,7 @@ typedef struct ModifyTable
 	List	   *withCheckOptionLists;	/* per-target-table WCO lists */
 	List	   *returningLists; /* per-target-table RETURNING tlists */
 	List	   *fdwPrivLists;	/* per-target-table FDW private data lists */
+	Bitmapset  *fdwDirectModifyPlans;	/* indices of FDW DM plans */
 	List	   *rowMarks;		/* PlanRowMarks (non-locking only) */
 	int			epqParam;		/* ID of Param for EvalPlanQual re-eval */
 	OnConflictAction onConflictAction;	/* ON CONFLICT action */
@@ -531,6 +532,7 @@ typedef struct WorkTableScan
 typedef struct ForeignScan
 {
 	Scan		scan;
+	CmdType		operation;		/* SELECT/INSERT/UPDATE/DELETE */
 	Oid			fs_server;		/* OID of foreign server */
 	List	   *fdw_exprs;		/* expressions that FDW may evaluate */
 	List	   *fdw_private;	/* private data for FDW */

src/include/optimizer/plancat.h

@@ -55,4 +55,6 @@ extern Selectivity join_selectivity(PlannerInfo *root,
 				 JoinType jointype,
 				 SpecialJoinInfo *sjinfo);
 
+extern bool has_row_triggers(PlannerInfo *root, Index rti, CmdType event);
+
 #endif   /* PLANCAT_H */