Fix EXPLAIN ANALYZE for async-capable nodes.

EXPLAIN ANALYZE for an async-capable ForeignScan node associated with
postgres_fdw is done just by using instrumentation for ExecProcNode()
called from the node's callbacks, causing the following problems:

1) If the remote table to scan is empty, the node is incorrectly
   considered as "never executed" by the command even if the node is
   executed, as ExecProcNode() isn't called from the node's callbacks at
   all in that case.
2) The command fails to collect timings for things other than
   ExecProcNode() done in the node, such as creating a cursor for the
   node's remote query.

To fix these problems, add instrumentation for async-capable nodes, and
modify postgres_fdw accordingly.

My oversight in commit 27e1f1456.

While at it, update a comment for the AsyncRequest struct in execnodes.h
and the documentation for the ForeignAsyncRequest API in fdwhandler.sgml
to match the code in ExecAsyncAppendResponse() in nodeAppend.c, and fix
typos in comments in nodeAppend.c.

Per report from Andrey Lepikhov, though I didn't use his patch.

Reviewed-by: Andrey Lepikhov
Discussion: https://postgr.es/m/2eb662bb-105d-fc20-7412-2f027cc3ca72%40postgrespro.ru

src/backend/executor/execAsync.c

@@ -15,6 +15,7 @@
 #include "postgres.h"
 
 #include "executor/execAsync.h"
+#include "executor/executor.h"
 #include "executor/nodeAppend.h"
 #include "executor/nodeForeignscan.h"
 
@@ -24,6 +25,13 @@
 void
 ExecAsyncRequest(AsyncRequest *areq)
 {
+	if (areq->requestee->chgParam != NULL)	/* something changed? */
+		ExecReScan(areq->requestee);		/* let ReScan handle this */
+
+	/* must provide our own instrumentation support */
+	if (areq->requestee->instrument)
+		InstrStartNode(areq->requestee->instrument);
+
 	switch (nodeTag(areq->requestee))
 	{
 		case T_ForeignScanState:
@@ -36,6 +44,11 @@ ExecAsyncRequest(AsyncRequest *areq)
 	}
 
 	ExecAsyncResponse(areq);
+
+	/* must provide our own instrumentation support */
+	if (areq->requestee->instrument)
+		InstrStopNode(areq->requestee->instrument,
+					  TupIsNull(areq->result) ? 0.0 : 1.0);
 }
 
 /*
@@ -48,6 +61,10 @@ ExecAsyncRequest(AsyncRequest *areq)
 void
 ExecAsyncConfigureWait(AsyncRequest *areq)
 {
+	/* must provide our own instrumentation support */
+	if (areq->requestee->instrument)
+		InstrStartNode(areq->requestee->instrument);
+
 	switch (nodeTag(areq->requestee))
 	{
 		case T_ForeignScanState:
@@ -58,6 +75,10 @@ ExecAsyncConfigureWait(AsyncRequest *areq)
 			elog(ERROR, "unrecognized node type: %d",
 				 (int) nodeTag(areq->requestee));
 	}
+
+	/* must provide our own instrumentation support */
+	if (areq->requestee->instrument)
+		InstrStopNode(areq->requestee->instrument, 0.0);
 }
 
 /*
@@ -66,6 +87,10 @@ ExecAsyncConfigureWait(AsyncRequest *areq)
 void
 ExecAsyncNotify(AsyncRequest *areq)
 {
+	/* must provide our own instrumentation support */
+	if (areq->requestee->instrument)
+		InstrStartNode(areq->requestee->instrument);
+
 	switch (nodeTag(areq->requestee))
 	{
 		case T_ForeignScanState:
@@ -78,6 +103,11 @@ ExecAsyncNotify(AsyncRequest *areq)
 	}
 
 	ExecAsyncResponse(areq);
+
+	/* must provide our own instrumentation support */
+	if (areq->requestee->instrument)
+		InstrStopNode(areq->requestee->instrument,
+					  TupIsNull(areq->result) ? 0.0 : 1.0);
 }
 
 /*

src/backend/executor/execMain.c

@@ -1214,7 +1214,7 @@ InitResultRelInfo(ResultRelInfo *resultRelInfo,
 		resultRelInfo->ri_TrigWhenExprs = (ExprState **)
 			palloc0(n * sizeof(ExprState *));
 		if (instrument_options)
-			resultRelInfo->ri_TrigInstrument = InstrAlloc(n, instrument_options);
+			resultRelInfo->ri_TrigInstrument = InstrAlloc(n, instrument_options, false);
 	}
 	else
 	{

src/backend/executor/execProcnode.c

@@ -407,7 +407,8 @@ ExecInitNode(Plan *node, EState *estate, int eflags)
 
 	/* Set up instrumentation for this node if requested */
 	if (estate->es_instrument)
-		result->instrument = InstrAlloc(1, estate->es_instrument);
+		result->instrument = InstrAlloc(1, estate->es_instrument,
+										result->async_capable);
 
 	return result;
 }

src/backend/executor/instrument.c

@@ -28,7 +28,7 @@ static void WalUsageAdd(WalUsage *dst, WalUsage *add);
 
 /* Allocate new instrumentation structure(s) */
 Instrumentation *
-InstrAlloc(int n, int instrument_options)
+InstrAlloc(int n, int instrument_options, bool async_mode)
 {
 	Instrumentation *instr;
 
@@ -46,6 +46,7 @@ InstrAlloc(int n, int instrument_options)
 			instr[i].need_bufusage = need_buffers;
 			instr[i].need_walusage = need_wal;
 			instr[i].need_timer = need_timer;
+			instr[i].async_mode = async_mode;
 		}
 	}
 
@@ -82,6 +83,7 @@ InstrStartNode(Instrumentation *instr)
 void
 InstrStopNode(Instrumentation *instr, double nTuples)
 {
+	double		save_tuplecount = instr->tuplecount;
 	instr_time	endtime;
 
 	/* count the returned tuples */
@@ -114,6 +116,23 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		instr->running = true;
 		instr->firsttuple = INSTR_TIME_GET_DOUBLE(instr->counter);
 	}
+	else
+	{
+		/*
+		 * In async mode, if the plan node hadn't emitted any tuples before,
+		 * this might be the first tuple
+		 */
+		if (instr->async_mode && save_tuplecount < 1.0)
+			instr->firsttuple = INSTR_TIME_GET_DOUBLE(instr->counter);
+	}
+}
+
+/* Update tuple count */
+void
+InstrUpdateTupleCount(Instrumentation *instr, double nTuples)
+{
+	/* count the returned tuples */
+	instr->tuplecount += nTuples;
 }
 
 /* Finish a run cycle for a plan node */

src/backend/executor/nodeAppend.c

@@ -362,9 +362,9 @@ ExecAppend(PlanState *pstate)
 		}
 
 		/*
-		 * wait or poll async events if any. We do this before checking for
-		 * the end of iteration, because it might drain the remaining async
-		 * subplans.
+		 * wait or poll for async events if any. We do this before checking
+		 * for the end of iteration, because it might drain the remaining
+		 * async subplans.
 		 */
 		if (node->as_nasyncremain > 0)
 			ExecAppendAsyncEventWait(node);
@@ -440,7 +440,7 @@ ExecReScanAppend(AppendState *node)
 
 		/*
 		 * If chgParam of subnode is not null then plan will be re-scanned by
-		 * first ExecProcNode.
+		 * first ExecProcNode or by first ExecAsyncRequest.
 		 */
 		if (subnode->chgParam == NULL)
 			ExecReScan(subnode);
@@ -911,7 +911,7 @@ ExecAppendAsyncGetNext(AppendState *node, TupleTableSlot **result)
 	{
 		CHECK_FOR_INTERRUPTS();
 
-		/* Wait or poll async events. */
+		/* Wait or poll for async events. */
 		ExecAppendAsyncEventWait(node);
 
 		/* Request a tuple asynchronously. */
@@ -1084,7 +1084,7 @@ ExecAsyncAppendResponse(AsyncRequest *areq)
 	/* Nothing to do if the request is pending. */
 	if (!areq->request_complete)
 	{
-		/* The request would have been pending for a callback */
+		/* The request would have been pending for a callback. */
 		Assert(areq->callback_pending);
 		return;
 	}

src/backend/executor/nodeForeignscan.c

@@ -209,6 +209,13 @@ ExecInitForeignScan(ForeignScan *node, EState *estate, int eflags)
 	scanstate->fdw_recheck_quals =
 		ExecInitQual(node->fdw_recheck_quals, (PlanState *) scanstate);
 
+	/*
+	 * Determine whether to scan the foreign relation asynchronously or not;
+	 * this has to be kept in sync with the code in ExecInitAppend().
+	 */
+	scanstate->ss.ps.async_capable = (((Plan *) node)->async_capable &&
+									  estate->es_epq_active == NULL);
+
 	/*
 	 * Initialize FDW-related state.
 	 */