fix: every columnar node reports Columnar Vectors Skipped, not just the scalar one

src/columnar.h

@@ -932,6 +932,7 @@ typedef struct PgColumnarGroupStats
 	uint64		groupsTotal;
 	uint64		groupsRead;
 	uint64		groupsRemoved;
+	uint64		vectorsSkipped;
 } PgColumnarGroupStats;
 
 extern void PgColumnarExplainPushedDown(int64 nfilters, ExplainState *es);

src/columnar_customscan.c

@@ -2170,6 +2170,15 @@ PgColumnarExplainGroupStats(const PgColumnarGroupStats *stats, ExplainState *es)
 						   (int64) stats->groupsRead, es);
 	ExplainPropertyInteger("Columnar Chunk Groups Removed by Filter", NULL,
 						   (int64) stats->groupsRemoved, es);
+	/*
+	 * Vectors skipped belongs with the group counters rather than beside them:
+	 * it was printed by the scalar node alone, so a plan could not say whether
+	 * per-vector skipping happened on the vectorized aggregate path -- the path
+	 * where it matters most, since #512 is about the fold and the skip vector
+	 * disagreeing and this is the number that would show it.
+	 */
+	ExplainPropertyInteger("Columnar Vectors Skipped", NULL,
+						   (int64) stats->vectorsSkipped, es);
 }
 
 /* -------------------------------------------------------------------------
@@ -2298,9 +2307,8 @@ PgColumnarExplainCustomScan(CustomScanState *node, List *ancestors,
 		gs.groupsTotal = groupsTotal;
 		gs.groupsRead = groupsRead;
 		gs.groupsRemoved = groupsSkipped;
+		gs.vectorsSkipped = PgColumnarVectorsSkipped(cstate->readState);
 		PgColumnarExplainGroupStats(&gs, es);
-		ExplainPropertyInteger("Columnar Vectors Skipped", NULL,
-							   (int64) PgColumnarVectorsSkipped(cstate->readState), es);
 
 		/*
 		 * Rows the qual rejected before their remaining projected columns were

src/columnar_vector.c

@@ -595,6 +595,7 @@ typedef struct PgColumnarAggScanState
 	bool		haveStats;
 	uint64		groupsRead;
 	uint64		groupsSkipped;
+	uint64		vectorsSkipped;
 	uint64		groupsTotal;
 
 	/*
@@ -696,6 +697,7 @@ typedef struct PgColumnarGroupAggScanState
 	bool		haveStats;
 	uint64		groupsRead;
 	uint64		groupsSkipped;
+	uint64		vectorsSkipped;
 	uint64		groupsTotal;
 	int			usablePreds;	/* of npreds, how many can exclude (#479) */
 } PgColumnarGroupAggScanState;
@@ -3268,6 +3270,7 @@ pgcolumnar_native_batch_fold(PgColumnarAggScanState *state, Relation rel,
 	PgColumnarReadStats(rs, &state->groupsRead, &state->groupsSkipped,
 					  &state->groupsTotal);
 	state->usablePreds = PgColumnarReadUsablePredicates(rs);
+	state->vectorsSkipped = PgColumnarVectorsSkipped(rs);
 	state->haveStats = true;
 	state->batchFolded = true;
 	PgColumnarEndRead(rs);
@@ -3402,6 +3405,7 @@ pgcolumnar_native_scan_agg(PgColumnarAggScanState *state,
 		PgColumnarReadStats(rs, &state->groupsRead, &state->groupsSkipped,
 						  &state->groupsTotal);
 		state->usablePreds = PgColumnarReadUsablePredicates(rs);
+	state->vectorsSkipped = PgColumnarVectorsSkipped(rs);
 		state->haveStats = true;
 	}
 
@@ -3558,6 +3562,7 @@ PgColumnarExplainAggScan(CustomScanState *node, List *ancestors, ExplainState *e
 		gs.groupsTotal = state->groupsTotal;
 		gs.groupsRead = state->groupsRead;
 		gs.groupsRemoved = state->groupsSkipped;
+		gs.vectorsSkipped = state->vectorsSkipped;
 		PgColumnarExplainGroupStats(&gs, es);
 	}
 }
@@ -4119,6 +4124,7 @@ pgcolumnar_groupagg_build(PgColumnarGroupAggScanState *state)
 	PgColumnarReadStats(rs, &state->groupsRead, &state->groupsSkipped,
 					  &state->groupsTotal);
 	state->usablePreds = PgColumnarReadUsablePredicates(rs);
+	state->vectorsSkipped = PgColumnarVectorsSkipped(rs);
 	state->haveStats = true;
 
 	PgColumnarEndRead(rs);
@@ -4238,6 +4244,7 @@ PgColumnarExplainGroupAggScan(CustomScanState *node, List *ancestors,
 		gs.groupsTotal = state->groupsTotal;
 		gs.groupsRead = state->groupsRead;
 		gs.groupsRemoved = state->groupsSkipped;
+		gs.vectorsSkipped = state->vectorsSkipped;
 		PgColumnarExplainGroupStats(&gs, es);
 	}
 }

test/native_vecskip.sh

@@ -72,6 +72,42 @@ check "no whole group removed" "$(counter 'Columnar Chunk Groups Removed by Filt
 check "non-selective removes no vectors" \
 	"$(counter 'Columnar Vectors Skipped' 'SELECT id FROM n WHERE id > 0')" "0"
 
+# ---- the vectorized aggregate must report the counter too --------------------
+#
+# "Columnar Vectors Skipped" is emitted by the scalar node only. The two
+# vectorized aggregate nodes print Chunk Groups Total/Read/Removed, Usable Skip
+# Predicates and Vector Predicates -- but not this one -- so a plan cannot say
+# whether per-vector skipping happened on the aggregate path. That is the path
+# where it matters most: #512 is precisely about the fold and the skip vector
+# disagreeing, and the number that would show it is the one not printed.
+#
+# Same table, same predicate as the scalar checks above, so the two arms differ
+# only in the node.
+# pgcolumnar.enable_ungrouped_vector_agg defaults to OFF, so the aggregate node
+# has to be asked for. Without the SET this falls back to the scalar scan -- which
+# is what the first version of this check did, and the premise below caught it
+# passing for that reason.
+AGGQ="SELECT count(*), sum(v) FROM n WHERE id BETWEEN 100 AND 200"
+explain_agg() {
+	env PATH="$PGC_BINDIR:$PATH" psql -h 127.0.0.1 -p "$PGC_PORT" -U postgres \
+		-d "$PGC_DB" -At \
+		-c "SET pgcolumnar.enable_ungrouped_vector_agg = on;
+		    EXPLAIN (ANALYZE, COSTS OFF, TIMING OFF, SUMMARY OFF) $1" 2>/dev/null
+}
+
+# Premise, and it has teeth: if the planner declines the vectorized aggregate,
+# this query falls back to the scalar scan -- which DOES print the line, so the
+# check below would pass while testing nothing at all.
+check "premise: the aggregate arm really is a vectorized aggregate" \
+	"$(explain_agg "$AGGQ" | grep -q 'Columnar Vectorized Aggregates' && echo yes || echo no)" \
+	"yes"
+check "premise: and it is not the scalar scan" \
+	"$(explain_agg "$AGGQ" | grep -q 'Columnar Projected Columns' && echo yes || echo no)" "no"
+
+check "the vectorized aggregate reports Columnar Vectors Skipped" \
+	"$(explain_agg "$AGGQ" | grep -q 'Columnar Vectors Skipped' && echo yes || echo no)" \
+	"yes"
+
 # Boundary and cross-vector ranges still return exactly the heap rows.
 check "cross-vector range parity" \
 	"$(pgc_set_hash 'SELECT id, v FROM n WHERE id BETWEEN 2000 AND 5000')" \