Propagate sort instrumentation from workers back to leader.

Up until now, when parallel query was used, no details about the
sort method or space used by the workers were available; details
were shown only for any sorting done by the leader.  Fix that.

Commit 1177ab1dabf72bafee8f19d904cee3a299f25892 forced the test case
added by commit 1f6d515a67ec98194c23a5db25660856c9aab944 to run
without parallelism; now that we have this infrastructure, allow
that again, with a little tweaking to make it pass with and without
force_parallel_mode.

Robert Haas and Tom Lane

Discussion: http://postgr.es/m/CA+Tgmoa2VBZW6S8AAXfhpHczb=Rf6RqQ2br+zJvEgwJ0uoD_tQ@mail.gmail.com

1 files changed, 97 insertions, 0 deletions

diff --git a/src/backend/executor/nodeSort.c b/src/backend/executor/nodeSort.c
index aae4150e2c8..66ef109c122 100644
--- a/src/backend/executor/nodeSort.c
+++ b/src/backend/executor/nodeSort.c
@@ -15,6 +15,7 @@
 
 #include "postgres.h"
 
+#include "access/parallel.h"
 #include "executor/execdebug.h"
 #include "executor/nodeSort.h"
 #include "miscadmin.h"
@@ -127,6 +128,15 @@ ExecSort(PlanState *pstate)
 		node->sort_Done = true;
 		node->bounded_Done = node->bounded;
 		node->bound_Done = node->bound;
+		if (node->shared_info && node->am_worker)
+		{
+			TuplesortInstrumentation *si;
+
+			Assert(IsParallelWorker());
+			Assert(ParallelWorkerNumber <= node->shared_info->num_workers);
+			si = &node->shared_info->sinstrument[ParallelWorkerNumber];
+			tuplesort_get_stats(tuplesortstate, si);
+		}
 		SO1_printf("ExecSort: %s\n", "sorting done");
 	}
 
@@ -334,3 +344,90 @@ ExecReScanSort(SortState *node)
 	else
 		tuplesort_rescan((Tuplesortstate *) node->tuplesortstate);
 }
+
+/* ----------------------------------------------------------------
+ *						Parallel Query Support
+ * ----------------------------------------------------------------
+ */
+
+/* ----------------------------------------------------------------
+ *		ExecSortEstimate
+ *
+ *		Estimate space required to propagate sort statistics.
+ * ----------------------------------------------------------------
+ */
+void
+ExecSortEstimate(SortState *node, ParallelContext *pcxt)
+{
+	Size		size;
+
+	/* don't need this if not instrumenting or no workers */
+	if (!node->ss.ps.instrument || pcxt->nworkers == 0)
+		return;
+
+	size = mul_size(pcxt->nworkers, sizeof(TuplesortInstrumentation));
+	size = add_size(size, offsetof(SharedSortInfo, sinstrument));
+	shm_toc_estimate_chunk(&pcxt->estimator, size);
+	shm_toc_estimate_keys(&pcxt->estimator, 1);
+}
+
+/* ----------------------------------------------------------------
+ *		ExecSortInitializeDSM
+ *
+ *		Initialize DSM space for sort statistics.
+ * ----------------------------------------------------------------
+ */
+void
+ExecSortInitializeDSM(SortState *node, ParallelContext *pcxt)
+{
+	Size		size;
+
+	/* don't need this if not instrumenting or no workers */
+	if (!node->ss.ps.instrument || pcxt->nworkers == 0)
+		return;
+
+	size = offsetof(SharedSortInfo, sinstrument)
+		+ pcxt->nworkers * sizeof(TuplesortInstrumentation);
+	node->shared_info = shm_toc_allocate(pcxt->toc, size);
+	/* ensure any unfilled slots will contain zeroes */
+	memset(node->shared_info, 0, size);
+	node->shared_info->num_workers = pcxt->nworkers;
+	shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id,
+				   node->shared_info);
+}
+
+/* ----------------------------------------------------------------
+ *		ExecSortInitializeWorker
+ *
+ *		Attach worker to DSM space for sort statistics.
+ * ----------------------------------------------------------------
+ */
+void
+ExecSortInitializeWorker(SortState *node, shm_toc *toc)
+{
+	node->shared_info =
+		shm_toc_lookup(toc, node->ss.ps.plan->plan_node_id, true);
+	node->am_worker = true;
+}
+
+/* ----------------------------------------------------------------
+ *		ExecSortRetrieveInstrumentation
+ *
+ *		Transfer sort statistics from DSM to private memory.
+ * ----------------------------------------------------------------
+ */
+void
+ExecSortRetrieveInstrumentation(SortState *node)
+{
+	Size		size;
+	SharedSortInfo *si;
+
+	if (node->shared_info == NULL)
+		return;
+
+	size = offsetof(SharedSortInfo, sinstrument)
+		+ node->shared_info->num_workers * sizeof(TuplesortInstrumentation);
+	si = palloc(size);
+	memcpy(si, node->shared_info, size);
+	node->shared_info = si;
+}