Fix buffer usage stats for parallel nodes.

Amit Kapila · Amit Kapila · commit b805b63ac277 · 2018-08-03T11:27:11.000+05:30
The buffer usage stats is accounted only for the execution phase of the node. For Gather and Gather Merge nodes, such stats are accumulated at the time of shutdown of workers which is done after execution of node due to which we missed to account them for such nodes. Fix it by treating nodes as running while we shut down them. We can also miss accounting for a Limit node when Gather or Gather Merge is beneath it, because it can finish the execution before shutting down such nodes. So we allow a Limit node to shut down the resources before it completes the execution. In the passing fix the gather node code to allow workers to shut down as soon as we find that all the tuples from the workers have been retrieved. The original code use to do that, but is accidently removed by commit 01edb5c. Reported-by: Adrien Nayrat Author: Amit Kapila and Robert Haas Reviewed-by: Robert Haas and Andres Freund Backpatch-through: 9.6 where this code was introduced Discussion: https://postgr.es/m/86137f17-1dfb-42f9-7421-82fd786b04a1@anayrat.info
diff --git a/src/backend/executor/execProcnode.c b/src/backend/executor/execProcnode.c
@@ -737,6 +737,19 @@ ExecShutdownNode(PlanState *node)
 
 	planstate_tree_walker(node, ExecShutdownNode, NULL);
 
+	/*
+	 * Treat the node as running while we shut it down, but only if it's run
+	 * at least once already.  We don't expect much CPU consumption during
+	 * node shutdown, but in the case of Gather or Gather Merge, we may shut
+	 * down workers at this stage.  If so, their buffer usage will get
+	 * propagated into pgBufferUsage at this point, and we want to make sure
+	 * that it gets associated with the Gather node.  We skip this if the node
+	 * has never been executed, so as to avoid incorrectly making it appear
+	 * that it has.
+	 */
+	if (node->instrument && node->instrument->running)
+		InstrStartNode(node->instrument);
+
 	switch (nodeTag(node))
 	{
 		case T_GatherState:
@@ -755,5 +768,9 @@ ExecShutdownNode(PlanState *node)
 			break;
 	}
 
+	/* Stop the node if we started it above, reporting 0 tuples. */
+	if (node->instrument && node->instrument->running)
+		InstrStopNode(node->instrument, 0);
+
 	return false;
 }
diff --git a/src/backend/executor/nodeGather.c b/src/backend/executor/nodeGather.c
@@ -327,7 +327,10 @@ gather_readnext(GatherState *gatherstate)
 			Assert(!tup);
 			--gatherstate->nreaders;
 			if (gatherstate->nreaders == 0)
+			{
+				ExecShutdownGatherWorkers(gatherstate);
 				return NULL;
+			}
 			memmove(&gatherstate->reader[gatherstate->nextreader],
 					&gatherstate->reader[gatherstate->nextreader + 1],
 					sizeof(TupleQueueReader *)
diff --git a/src/backend/executor/nodeLimit.c b/src/backend/executor/nodeLimit.c
@@ -134,6 +134,8 @@ ExecLimit(PlanState *pstate)
 					node->position - node->offset >= node->count)
 				{
 					node->lstate = LIMIT_WINDOWEND;
+					/* Allow nodes to release or shut down resources. */
+					(void) ExecShutdownNode(outerPlan);
 					return NULL;
 				}
 

Original file line number	Diff line number	Diff line change
`@@ -134,6 +134,8 @@ ExecLimit(PlanState *pstate)`
`134`	`134`	`node->position - node->offset >= node->count)`
`135`	`135`	`{`
`136`	`136`	`node->lstate = LIMIT_WINDOWEND;`
	`137`	`+ /* Allow nodes to release or shut down resources. */`
	`138`	`+ (void) ExecShutdownNode(outerPlan);`
`137`	`139`	`return NULL;`
`138`	`140`	`}`
`139`	`141`