agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v9 4/7] Row pattern recognition patch (executor).
301+ messages / 2 participants
[nested] [flat]

* [PATCH v9 4/7] Row pattern recognition patch (executor).
@ 2023-10-04 05:51 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Tatsuo Ishii @ 2023-10-04 05:51 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 1021 +++++++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  |   37 +-
 src/include/catalog/pg_proc.dat      |    6 +
 src/include/nodes/execnodes.h        |   26 +
 4 files changed, 1077 insertions(+), 13 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 77724a6daa..5da1bb5a6f 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -36,6 +36,7 @@
 #include "access/htup_details.h"
 #include "catalog/objectaccess.h"
 #include "catalog/pg_aggregate.h"
+#include "catalog/pg_collation_d.h"
 #include "catalog/pg_proc.h"
 #include "executor/executor.h"
 #include "executor/nodeWindowAgg.h"
@@ -48,6 +49,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +161,12 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+typedef struct StringSet {
+	StringInfo	*str_set;
+	Size		set_size;	/* current array allocation size in number of items */
+	int			set_index;	/* current used size */
+} StringSet;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -182,8 +190,9 @@ static void begin_partition(WindowAggState *winstate);
 static void spool_tuples(WindowAggState *winstate, int64 pos);
 static void release_partition(WindowAggState *winstate);
 
-static int	row_is_in_frame(WindowAggState *winstate, int64 pos,
+static int  row_is_in_frame(WindowAggState *winstate, int64 pos,
 							TupleTableSlot *slot);
+
 static void update_frameheadpos(WindowAggState *winstate);
 static void update_frametailpos(WindowAggState *winstate);
 static void update_grouptailpos(WindowAggState *winstate);
@@ -195,9 +204,37 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static int	WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							  int relpos, int seektype, bool set_mark,
+							  bool *isnull, bool *isout);
+static bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+static void attno_map(Node *node);
+static bool attno_map_walker(Node *node, void *context);
+static int	row_is_in_reduced_frame(WindowObject winobj, int64 pos);
+static bool rpr_is_defined(WindowAggState *winstate);
+
+static void create_reduced_frame_map(WindowAggState *winstate);
+static int	get_reduced_frame_map(WindowAggState *winstate, int64 pos);
+static void register_reduced_frame_map(WindowAggState *winstate, int64 pos, int val);
+static void clear_reduced_frame_map(WindowAggState *winstate);
+static void update_reduced_frame(WindowObject winobj, int64 pos);
+
+static int64 evaluate_pattern(WindowObject winobj, int64 current_pos,
+							  char *vname, StringInfo encoded_str, bool *result);
+
+static bool get_slots(WindowObject winobj, int64 current_pos);
+
+static int	search_str_set(char *pattern, StringSet *str_set);
+static char	pattern_initial(WindowAggState *winstate, char *vname);
+static int do_pattern_match(char *pattern, char *encoded_str);
+
+static StringSet *string_set_init(void);
+static void string_set_add(StringSet *string_set, StringInfo str);
+static StringInfo string_set_get(StringSet *string_set, int index);
+static int string_set_get_size(StringSet *string_set);
+static void string_set_discard(StringSet *string_set);
 
 /*
  * initialize_windowaggregate
@@ -673,6 +710,7 @@ eval_windowaggregates(WindowAggState *winstate)
 	WindowObject agg_winobj;
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot;
+	bool		agg_result_isnull;
 
 	numaggs = winstate->numaggs;
 	if (numaggs == 0)
@@ -778,6 +816,9 @@ eval_windowaggregates(WindowAggState *winstate)
 	 * Note that we don't strictly need to restart in the last case, but if
 	 * we're going to remove all rows from the aggregation anyway, a restart
 	 * surely is faster.
+	 *
+	 *   - if RPR is enabled and skip mode is SKIP TO NEXT ROW,
+	 *     we restart aggregation too.
 	 *----------
 	 */
 	numaggs_restart = 0;
@@ -788,8 +829,11 @@ eval_windowaggregates(WindowAggState *winstate)
 			(winstate->aggregatedbase != winstate->frameheadpos &&
 			 !OidIsValid(peraggstate->invtransfn_oid)) ||
 			(winstate->frameOptions & FRAMEOPTION_EXCLUSION) ||
-			winstate->aggregatedupto <= winstate->frameheadpos)
+			winstate->aggregatedupto <= winstate->frameheadpos ||
+			(rpr_is_defined(winstate) &&
+			 winstate->rpSkipTo == ST_NEXT_ROW))
 		{
+			elog(DEBUG1, "peraggstate->restart is set");
 			peraggstate->restart = true;
 			numaggs_restart++;
 		}
@@ -861,8 +905,10 @@ eval_windowaggregates(WindowAggState *winstate)
 	 * If we created a mark pointer for aggregates, keep it pushed up to frame
 	 * head, so that tuplestore can discard unnecessary rows.
 	 */
+#ifdef NOT_USED
 	if (agg_winobj->markptr >= 0)
 		WinSetMarkPosition(agg_winobj, winstate->frameheadpos);
+#endif
 
 	/*
 	 * Now restart the aggregates that require it.
@@ -917,6 +963,29 @@ eval_windowaggregates(WindowAggState *winstate)
 	{
 		winstate->aggregatedupto = winstate->frameheadpos;
 		ExecClearTuple(agg_row_slot);
+
+		/*
+		 * If RPR is defined, we do not use aggregatedupto_nonrestarted.  To
+		 * avoid assertion failure below, we reset aggregatedupto_nonrestarted
+		 * to frameheadpos.
+		 */
+		if (rpr_is_defined(winstate))
+			aggregatedupto_nonrestarted = winstate->frameheadpos;
+	}
+
+	agg_result_isnull = false;
+	/* RPR is defined? */
+	if (rpr_is_defined(winstate))
+	{
+		/*
+		 * If the skip mode is SKIP TO PAST LAST ROW and we already know that
+		 * current row is a skipped row, we don't need to accumulate rows,
+		 * just return NULL. Note that for unamtched row, we need to do
+		 * aggregation so that count(*) shows 0, rather than NULL.
+		 */
+		if (winstate->rpSkipTo == ST_PAST_LAST_ROW &&
+			get_reduced_frame_map(winstate, winstate->currentpos) == RF_SKIPPED)
+			agg_result_isnull = true;
 	}
 
 	/*
@@ -930,6 +999,11 @@ eval_windowaggregates(WindowAggState *winstate)
 	{
 		int			ret;
 
+		elog(DEBUG1, "===== loop in frame starts: " INT64_FORMAT, winstate->aggregatedupto);
+
+		if (agg_result_isnull)
+			break;
+
 		/* Fetch next row if we didn't already */
 		if (TupIsNull(agg_row_slot))
 		{
@@ -945,9 +1019,28 @@ eval_windowaggregates(WindowAggState *winstate)
 		ret = row_is_in_frame(winstate, winstate->aggregatedupto, agg_row_slot);
 		if (ret < 0)
 			break;
+
 		if (ret == 0)
 			goto next_tuple;
 
+		if (rpr_is_defined(winstate))
+		{
+			/*
+			 * If the row status at currentpos is already decided and current
+			 * row status is not decided yet, it means we passed the last
+			 * reduced frame. Time to break the loop.
+			 */
+			if (get_reduced_frame_map(winstate, winstate->currentpos) != RF_NOT_DETERMINED &&
+				get_reduced_frame_map(winstate, winstate->aggregatedupto) == RF_NOT_DETERMINED)
+				break;
+			/*
+			 * Otherwise we need to calculate the reduced frame.
+			 */
+			ret = row_is_in_reduced_frame(winstate->agg_winobj, winstate->aggregatedupto);
+			if (ret == -1)	/* unmatched row */
+				break;
+		}
+
 		/* Set tuple context for evaluation of aggregate arguments */
 		winstate->tmpcontext->ecxt_outertuple = agg_row_slot;
 
@@ -976,6 +1069,7 @@ next_tuple:
 		ExecClearTuple(agg_row_slot);
 	}
 
+
 	/* The frame's end is not supposed to move backwards, ever */
 	Assert(aggregatedupto_nonrestarted <= winstate->aggregatedupto);
 
@@ -996,6 +1090,16 @@ next_tuple:
 								 peraggstate,
 								 result, isnull);
 
+		/*
+		 * RPR is defined and we just return NULL because skip mode is SKIP
+		 * TO PAST LAST ROW and current row is skipped row.
+		 */
+		if (agg_result_isnull)
+		{
+			*isnull = true;
+			*result = (Datum) 0;
+		}
+
 		/*
 		 * save the result in case next row shares the same frame.
 		 *
@@ -1090,6 +1194,7 @@ begin_partition(WindowAggState *winstate)
 	winstate->framehead_valid = false;
 	winstate->frametail_valid = false;
 	winstate->grouptail_valid = false;
+	create_reduced_frame_map(winstate);
 	winstate->spooled_rows = 0;
 	winstate->currentpos = 0;
 	winstate->frameheadpos = 0;
@@ -2053,6 +2158,8 @@ ExecWindowAgg(PlanState *pstate)
 
 	CHECK_FOR_INTERRUPTS();
 
+	elog(DEBUG1, "ExecWindowAgg called. pos: " INT64_FORMAT , winstate->currentpos);
+
 	if (winstate->status == WINDOWAGG_DONE)
 		return NULL;
 
@@ -2221,6 +2328,17 @@ ExecWindowAgg(PlanState *pstate)
 		/* don't evaluate the window functions when we're in pass-through mode */
 		if (winstate->status == WINDOWAGG_RUN)
 		{
+			/*
+			 * If RPR is defined and skip mode is next row, we need to clear existing
+			 * reduced frame info so that we newly calculate the info starting from
+			 * current row.
+			 */
+			if (rpr_is_defined(winstate))
+			{
+				if (winstate->rpSkipTo == ST_NEXT_ROW)
+					clear_reduced_frame_map(winstate);
+			}
+
 			/*
 			 * Evaluate true window functions
 			 */
@@ -2388,6 +2506,9 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2604,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2798,39 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+	winstate->defineInitial = node->defineInitial;
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		/*
+		 * Tweak arg var of PREV/NEXT so that it refers to scan/inner slot.
+		 */
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			attno_map((Node *)expr);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2838,57 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite varno of Var node that is the argument of PREV/NET so that it sees
+ * scan tuple (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node)
+{
+	(void) expression_tree_walker(node, attno_map_walker, NULL);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+
+	if (node == NULL)
+		return false;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				/*
+				 * Rewrite varno from OUTER_VAR to regular var no so that the
+				 * var references scan tuple.
+				 */
+				var->varno = var->varnosyn;
+			else
+				var->varno = INNER_VAR;
+			elog(DEBUG1, "PREV/NEXT's varno is rewritten to: %d", var->varno);
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, NULL);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2723,6 +2938,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3083,7 +3300,7 @@ window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 		return false;
 
 	if (pos < winobj->markpos)
-		elog(ERROR, "cannot fetch row before WindowObject's mark position");
+		elog(ERROR, "cannot fetch row: " INT64_FORMAT " before WindowObject's mark position: " INT64_FORMAT,  pos, winobj->markpos );
 
 	oldcontext = MemoryContextSwitchTo(winstate->ss.ps.ps_ExprContext->ecxt_per_query_memory);
 
@@ -3403,14 +3620,54 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+static int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+	int			num_reduced_frame;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3477,11 +3734,21 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 						 winstate->frameOptions);
 					break;
 			}
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				if (relpos >= num_reduced_frame)
+					goto out_of_frame;
 			break;
 		case WINDOW_SEEK_TAIL:
 			/* rejecting relpos > 0 is easy and simplifies code below */
 			if (relpos > 0)
 				goto out_of_frame;
+
+			/* RPR cares about frame head pos. Need to call update_frameheadpos */
+			update_frameheadpos(winstate);
+
 			update_frametailpos(winstate);
 			abs_pos = winstate->frametailpos - 1 + relpos;
 
@@ -3548,6 +3815,12 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 					mark_pos = 0;	/* keep compiler quiet */
 					break;
 			}
+
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos + relpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				abs_pos = winstate->frameheadpos + relpos + num_reduced_frame - 1;
 			break;
 		default:
 			elog(ERROR, "unrecognized window seek type: %d", seektype);
@@ -3566,15 +3839,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3605,3 +3876,731 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+/*
+ * rpr_is_defined
+ * return true if Row pattern recognition is defined.
+ */
+static
+bool rpr_is_defined(WindowAggState *winstate)
+{
+	return winstate->patternVariableList != NIL;
+}
+
+/*
+ * row_is_in_reduced_frame
+ * Determine whether a row is in the current row's reduced window frame according
+ * to row pattern matching
+ *
+ * The row must has been already determined that it is in a full window frame
+ * and fetched it into slot.
+ *
+ * Returns:
+ * = 0, RPR is not defined.
+ * >0, if the row is the first in the reduced frame. Return the number of rows in the reduced frame.
+ * -1, if the row is unmatched row
+ * -2, if the row is in the reduced frame but needed to be skipped because of
+ * AFTER MATCH SKIP PAST LAST ROW
+ */
+static
+int row_is_in_reduced_frame(WindowObject winobj, int64 pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	int		state;
+	int		rtn;
+
+	if (!rpr_is_defined(winstate))
+	{
+		/*
+		 * RPR is not defined. Assume that we are always in the the reduced
+		 * window frame.
+		 */
+		rtn = 0;
+		elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, rtn, pos);
+		return rtn;
+	}
+
+	state = get_reduced_frame_map(winstate, pos);
+
+	if (state == RF_NOT_DETERMINED)
+	{
+		update_frameheadpos(winstate);
+		update_reduced_frame(winobj, pos);
+	}
+
+	state = get_reduced_frame_map(winstate, pos);
+
+	switch (state)
+	{
+		int64	i;
+		int		num_reduced_rows;
+
+		case RF_FRAME_HEAD:
+			num_reduced_rows = 1;
+			for (i = pos + 1; get_reduced_frame_map(winstate,i) == RF_SKIPPED; i++)
+				num_reduced_rows++;
+			rtn = num_reduced_rows;
+			break;
+
+		case RF_SKIPPED:
+			rtn = -2;
+			break;
+
+		case RF_UNMATCHED:
+			rtn = -1;
+			break;
+
+		default:
+			elog(ERROR, "Unrecognized state: %d at: " INT64_FORMAT, state, pos);
+			break;
+	}
+
+	elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, rtn, pos);
+	return rtn;
+}
+
+#define REDUCED_FRAME_MAP_INIT_SIZE	1024L
+
+/*
+ * Create reduced frame map
+ */
+static
+void create_reduced_frame_map(WindowAggState *winstate)
+{
+	winstate->reduced_frame_map =
+		MemoryContextAlloc(winstate->partcontext, REDUCED_FRAME_MAP_INIT_SIZE);
+	winstate->alloc_sz = REDUCED_FRAME_MAP_INIT_SIZE;
+	clear_reduced_frame_map(winstate);
+}
+
+/*
+ * Clear reduced frame map
+ */
+static
+void clear_reduced_frame_map(WindowAggState *winstate)
+{
+	Assert(winstate->reduced_frame_map != NULL);
+	MemSet(winstate->reduced_frame_map, RF_NOT_DETERMINED,
+		   winstate->alloc_sz);
+}
+
+/*
+ * Get reduced frame map specified by pos
+ */
+static
+int get_reduced_frame_map(WindowAggState *winstate, int64 pos)
+{
+	Assert(winstate->reduced_frame_map != NULL);
+
+	if (pos < 0 || pos >= winstate->alloc_sz)
+		elog(ERROR, "wrong pos: " INT64_FORMAT, pos);
+
+	return winstate->reduced_frame_map[pos];
+}
+
+/*
+ * Add/replace reduced frame map member at pos.
+ * If there's no enough space, expand the map.
+ */
+static
+void register_reduced_frame_map(WindowAggState *winstate, int64 pos, int val)
+{
+	int64	realloc_sz;
+
+	Assert(winstate->reduced_frame_map != NULL);
+
+	if (pos < 0)
+		elog(ERROR, "wrong pos: " INT64_FORMAT, pos);
+
+	if (pos > winstate->alloc_sz - 1)
+	{
+		realloc_sz = winstate->alloc_sz * 2;
+
+		winstate->reduced_frame_map =
+			repalloc(winstate->reduced_frame_map, realloc_sz);
+
+		MemSet(winstate->reduced_frame_map + winstate->alloc_sz,
+			   RF_NOT_DETERMINED, realloc_sz - winstate->alloc_sz);
+
+		winstate->alloc_sz = realloc_sz;
+	}
+
+	winstate->reduced_frame_map[pos] = val;
+}
+
+/*
+ * update_reduced_frame
+ *		Update reduced frame info.
+ */
+static
+void update_reduced_frame(WindowObject winobj, int64 pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	ListCell	*lc1, *lc2;
+	bool		expression_result;
+	int			num_matched_rows;
+	int64		original_pos;
+	bool		anymatch;
+	StringInfo	encoded_str;
+	StringInfo	pattern_str = makeStringInfo();
+	StringSet	*str_set;
+	int			str_set_index = 0;
+
+	/*
+	 * Set of pattern variables evaluted to true.
+	 * Each character corresponds to pattern variable.
+	 * Example:
+	 * str_set[0] = "AB";
+	 * str_set[1] = "AC";
+	 * In this case at row 0 A and B are true, and A and C are true in row 1.
+	 */
+
+	/* initialize pattern variables set */
+	str_set = string_set_init();
+
+	/* save original pos */
+	original_pos = pos;
+
+	/*
+	 * Loop over until none of pattern matches or encounters end of frame.
+	 */
+	for (;;)
+	{
+		int64	result_pos = -1;
+
+		/*
+		 * Loop over each PATTERN variable.
+		 */
+		anymatch = false;
+		encoded_str = makeStringInfo();
+
+		forboth(lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+		{
+			char	*vname = strVal(lfirst(lc1));
+			char	*quantifier = strVal(lfirst(lc2));
+
+			elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s quantifier: %s", pos, vname, quantifier);
+
+			expression_result = false;
+
+			/* evaluate row pattern against current row */
+			result_pos = evaluate_pattern(winobj, pos, vname, encoded_str, &expression_result);
+			if (expression_result)
+			{
+				elog(DEBUG1, "expression result is true");
+				anymatch = true;
+			}
+
+			/*
+			 * If out of frame, we are done.
+			 */
+			 if (result_pos < 0)
+				 break;
+		}
+
+		if (!anymatch)
+		{
+			/* none of patterns matched. */
+			break;
+		}
+
+		string_set_add(str_set, encoded_str);
+
+		elog(DEBUG1, "pos: " INT64_FORMAT " str_set_index: %d encoded_str: %s", pos, str_set_index, encoded_str->data);
+
+		/* move to next row */
+		pos++;
+
+		if (result_pos < 0)
+		{
+			/* out of frame */
+			break;
+		}
+	}
+
+	if (string_set_get_size(str_set) == 0)
+	{
+		/* no match found in the first row */
+		register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED);
+		return;
+	}
+
+	elog(DEBUG2, "pos: " INT64_FORMAT " encoded_str: %s", pos, encoded_str->data);
+
+	/* build regular expression */
+	pattern_str = makeStringInfo();
+	appendStringInfoChar(pattern_str, '^');
+	forboth (lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc1));
+		char	*quantifier = strVal(lfirst(lc2));
+		char	 initial;
+
+		initial = pattern_initial(winstate, vname);
+		Assert(initial != 0);
+		appendStringInfoChar(pattern_str, initial);
+		if (quantifier[0])
+			appendStringInfoChar(pattern_str, quantifier[0]);
+		elog(DEBUG1, "vname: %s initial: %c quantifier: %s", vname, initial, quantifier);
+	}
+
+	elog(DEBUG2, "pos: " INT64_FORMAT " pattern: %s", pos, pattern_str->data);
+
+	/* look for matching pattern variable sequence */
+	num_matched_rows = search_str_set(pattern_str->data, str_set);
+	/*
+	 * We are at the first row in the reduced frame.  Save the number of
+	 * matched rows as the number of rows in the reduced frame.
+	 */
+	if (num_matched_rows <= 0)
+	{
+		/* no match */
+		register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED);
+	}
+	else
+	{
+		int64		i;
+
+		register_reduced_frame_map(winstate, original_pos, RF_FRAME_HEAD);
+
+		for (i = original_pos + 1; i < original_pos + num_matched_rows; i++)
+		{
+			register_reduced_frame_map(winstate, i, RF_SKIPPED);
+		}
+	}
+
+	return;
+}
+
+/*
+ * Perform pattern matching using pattern against str_set.  str_set is a set
+ * of StringInfo. Each StringInfo has a string comprising initial characters
+ * of pattern variables being true in a row.  Returns the longest number of
+ * the matching rows.
+ */
+static
+int search_str_set(char *pattern, StringSet *str_set)
+{
+	int			set_size;	/* number of rows in the set */
+	int			resultlen = 0;
+	int			index;
+	StringSet	*old_str_set, *new_str_set;
+	int			new_str_size;
+
+	set_size = string_set_get_size(str_set);
+	new_str_set = string_set_init();
+
+	/*
+	 * Generate all possible pattern variable name initials as a set of
+	 * StringInfo named "new_str_set".  For example, if we have two rows
+	 * having "ab" (row 0) and "ac" (row 1) in the input str_set, new_str_set
+	 * will have set of StringInfo "aa", "ac", "ba" and "bc" in the end.
+	 */
+	for (index = 0; index < set_size; index++)
+	{
+		StringInfo	str;	/* search target row */
+		char	*p;
+		int		old_set_size;
+		int		i;
+
+		if (index == 0)
+		{
+			/* copy variables in row 0 */
+			str = string_set_get(str_set, index);
+			p = str->data;
+
+			/*
+			 * loop over each new pattern variable char in previous result
+			 * char.
+			 */
+			while (*p)
+			{
+				StringInfo	new = makeStringInfo();
+
+				/* add pattern variable char */
+				appendStringInfoChar(new, *p);
+				/* add new one to string set */
+				string_set_add(new_str_set, new);
+				p++;	/* next pattern variable */
+			}
+		}
+		else
+		{
+			old_str_set = new_str_set;
+			new_str_set = string_set_init();
+			str = string_set_get(str_set, index);
+			old_set_size = string_set_get_size(old_str_set);
+
+			/*
+			 * loop over each rows in the previous result set.
+			 */
+			for (i = 0; i < old_set_size ; i++)
+			{
+				StringInfo	old = string_set_get(old_str_set, i);
+
+				p = str->data;
+
+				/*
+				 * loop over each pattern variable char in the input set.
+				 */
+				while (*p)
+				{
+					StringInfo	new = makeStringInfo();
+
+					/* copy source string */
+					appendStringInfoString(new, old->data);
+					/* add pattern variable char */
+					appendStringInfoChar(new, *p);
+					/* add new one to string set */
+					string_set_add(new_str_set, new);
+					p++;	/* next pattern variable */
+				}
+			}
+			/* we no long need old string set */
+			string_set_discard(old_str_set);
+		}
+	}
+
+	/*
+	 * Perform pattern matching to find out the longest match.
+	 */
+	new_str_size = string_set_get_size(new_str_set);
+
+	for (index = 0; index < new_str_size; index++)
+	{
+		int			len;
+		StringInfo	s;
+
+		s = string_set_get(new_str_set, index);
+		if (s == NULL)
+			continue;	/* no data */
+
+		len = do_pattern_match(pattern, s->data);
+		if (len > resultlen)
+		{
+			/* remember the longest match */
+			resultlen = len;
+
+			/*
+			 * If the size of result set is equal to the number of rows in the
+			 * set, we are done because it's not possible that the number of
+			 * matching rows exceeds the number of rows in the set.
+			 */
+			if (resultlen >= set_size)
+				break;
+		}
+	}
+
+	/* we no long need new string set */
+	string_set_discard(new_str_set);
+
+	return resultlen;
+}
+
+/*
+ * do_pattern_match
+ * perform pattern match using pattern against encoded_str.
+ * returns matching number of rows if matching is succeeded.
+ * Otherwise returns 0.
+ */
+static
+int do_pattern_match(char *pattern, char *encoded_str)
+{
+	Datum	d;
+	text	*res;
+	char	*substr;
+	int		len = 0;
+
+
+	/*
+	 * We first perform pattern matching using regexp_instr, then call
+	 * textregexsubstr to get matched substring to know how long the
+	 * matched string is. That is the number of rows in the reduced window
+	 * frame.  The reason why we can't call textregexsubstr in the first
+	 * place is, it errors out if pattern does not match.
+	 */
+	if (DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+											  PointerGetDatum(cstring_to_text(encoded_str)),
+											  PointerGetDatum(cstring_to_text(pattern)))) > 0)
+	{
+		d = DirectFunctionCall2Coll(textregexsubstr,
+									DEFAULT_COLLATION_OID,
+									PointerGetDatum(cstring_to_text(encoded_str)),
+									PointerGetDatum(cstring_to_text(pattern)));
+		if (d != 0)
+		{
+			res = DatumGetTextPP(d);
+			substr = text_to_cstring(res);
+			len = strlen(substr);
+		}
+	}
+	return len;
+}
+
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match absolute row position
+ * other wise out of frame.
+ */
+static
+int64 evaluate_pattern(WindowObject winobj, int64 current_pos,
+						char *vname, StringInfo encoded_str, bool *result)
+{
+	WindowAggState	*winstate = winobj->winstate;
+	ExprContext		*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell		*lc1, *lc2, *lc3;
+	ExprState		*pat;
+	Datum			eval_result;
+	bool			out_of_frame = false;
+	bool			isnull;
+
+	forthree (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList, lc3, winstate->defineInitial)
+	{
+		char	initial;
+		char	*name = strVal(lfirst(lc1));
+
+		if (strcmp(vname, name))
+			continue;
+
+		initial = *(strVal(lfirst(lc3)));
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		/* get current, previous and next tuples */
+		if (!get_slots(winobj, current_pos))
+		{
+			out_of_frame = true;
+		}
+		else
+		{
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: " INT64_FORMAT, vname, current_pos);
+				*result = false;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: " INT64_FORMAT, vname, current_pos);
+					*result = false;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: " INT64_FORMAT, vname, current_pos);
+					appendStringInfoChar(encoded_str, initial);
+					*result = true;
+				}
+			}
+			break;
+		}
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+	}
+	return current_pos;
+}
+
+/*
+ * Get current, previous and next tuples.
+ * Returns false if current row is out of partition/full frame.
+ */
+static
+bool get_slots(WindowObject winobj, int64 current_pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	TupleTableSlot *slot;
+	int		ret;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* set up current row tuple slot */
+	slot = winstate->temp_slot_1;
+	if (!window_gettupleslot(winobj, current_pos, slot))
+	{
+		elog(DEBUG1, "current row is out of partition at:" INT64_FORMAT, current_pos);
+		return false;
+	}
+	ret = row_is_in_frame(winstate, current_pos, slot);
+	if (ret <= 0)
+	{
+		elog(DEBUG1, "current row is out of frame at: " INT64_FORMAT, current_pos);
+		return false;
+	}
+	econtext->ecxt_outertuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		if (!window_gettupleslot(winobj, current_pos - 1, slot))
+		{
+			elog(DEBUG1, "previous row is out of partition at: " INT64_FORMAT, current_pos - 1);
+			econtext->ecxt_scantuple = winstate->null_slot;
+		}
+		else
+		{
+			ret = row_is_in_frame(winstate, current_pos - 1, slot);
+			if (ret <= 0)
+			{
+				elog(DEBUG1, "previous row is out of frame at: " INT64_FORMAT, current_pos - 1);
+				econtext->ecxt_scantuple = winstate->null_slot;
+			}
+			else
+			{
+				econtext->ecxt_scantuple = slot;
+			}
+		}
+	}
+	else
+		econtext->ecxt_scantuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	if (!window_gettupleslot(winobj, current_pos + 1, slot))
+	{
+		elog(DEBUG1, "next row is out of partiton at: " INT64_FORMAT, current_pos + 1);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+	{
+		ret = row_is_in_frame(winstate, current_pos + 1, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "next row is out of frame at: " INT64_FORMAT, current_pos + 1);
+			econtext->ecxt_innertuple = winstate->null_slot;
+		}
+		else
+			econtext->ecxt_innertuple = slot;
+	}
+	return true;
+}
+
+/*
+ * Return pattern variable initial character
+ * matching with pattern variable name vname.
+ * If not found, return 0.
+ */
+static
+char	pattern_initial(WindowAggState *winstate, char *vname)
+{
+	char		initial;
+	char		*name;
+	ListCell	*lc1, *lc2;
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineInitial)
+	{
+		name = strVal(lfirst(lc1));				/* DEFINE variable name */
+		initial = *(strVal(lfirst(lc2)));		/* DEFINE variable initial */
+
+
+		if (!strcmp(name, vname))
+				return initial;					/* found */
+	}
+	return 0;
+}
+
+/*
+ * string_set_init
+ * Create dynamic set of StringInfo.
+ */
+static
+StringSet *string_set_init(void)
+{
+/* Initial allocation size of str_set */
+#define STRING_SET_ALLOC_SIZE	1024
+
+	StringSet	*string_set;
+	Size		set_size;
+
+	string_set = palloc0(sizeof(StringSet));
+	string_set->set_index = 0;
+	set_size = STRING_SET_ALLOC_SIZE;
+	string_set->str_set = palloc(set_size * sizeof(StringInfo));
+	string_set->set_size = set_size;
+
+	return string_set;
+}
+
+/*
+ * Add StringInfo str to StringSet string_set.
+ */
+static
+void string_set_add(StringSet *string_set, StringInfo str)
+{
+	Size	set_size;
+
+	set_size = string_set->set_size;
+	if (string_set->set_index >= set_size)
+	{
+		set_size *= 2;
+		string_set->str_set = repalloc(string_set->str_set,
+									   set_size * sizeof(StringInfo));
+		string_set->set_size = set_size;
+	}
+
+	string_set->str_set[string_set->set_index++] = str;
+
+	return;
+}
+
+/*
+ * Returns StringInfo specified by index.
+ * If there's no data yet, returns NULL.
+ */
+static
+StringInfo string_set_get(StringSet *string_set, int index)
+{
+	/* no data? */
+	if (index == 0 && string_set->set_index == 0)
+		return NULL;
+
+	if (index < 0 ||index >= string_set->set_index)
+		elog(ERROR, "invalid index: %d", index);
+
+	return string_set->str_set[index];
+}
+
+/*
+ * Returns the size of StringSet.
+ */
+static
+int string_set_get_size(StringSet *string_set)
+{
+	return string_set->set_index;
+}
+
+/*
+ * Discard StringSet.
+ * All memory including StringSet itself is freed.
+ */
+static
+void string_set_discard(StringSet *string_set)
+{
+	int		i;
+
+	for (i = 0; i < string_set->set_index; i++)
+	{
+		StringInfo str = string_set->str_set[i];
+		pfree(str->data);
+		pfree(str);
+	}
+	pfree(string_set);
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..9ebcc7b5d2 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,11 +39,19 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
 
-
 /*
  * utility routine for *_rank functions.
  */
@@ -673,7 +684,7 @@ window_last_value(PG_FUNCTION_ARGS)
 	bool		isnull;
 
 	result = WinGetFuncArgInFrame(winobj, 0,
-								  0, WINDOW_SEEK_TAIL, true,
+								  0, WINDOW_SEEK_TAIL, false,
 								  &isnull, NULL);
 	if (isnull)
 		PG_RETURN_NULL();
@@ -713,3 +724,25 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index f0b7b9cbd8..24d288336a 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10416,6 +10416,12 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6123', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 108d69ba28..28d098b1cf 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2470,6 +2470,11 @@ typedef enum WindowAggStatus
 									 * tuples during spool */
 } WindowAggStatus;
 
+#define	RF_NOT_DETERMINED	0
+#define	RF_FRAME_HEAD		1
+#define	RF_SKIPPED			2
+#define	RF_UNMATCHED		3
+
 typedef struct WindowAggState
 {
 	ScanState	ss;				/* its first field is NodeTag */
@@ -2518,6 +2523,15 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+	List	   *defineInitial;		/* list of row pattern definition variable initials (list of String) */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2554,6 +2568,18 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
+
+	/*
+	 * Each byte corresponds to a row positioned at absolute its pos in
+	 * partition.  See above definition for RF_*
+	 */
+	char		*reduced_frame_map;
+	int64		alloc_sz;	/* size of the map */
 } WindowAggState;
 
 /* ----------------
-- 
2.25.1


----Next_Part(Wed_Oct__4_15_03_28_2023_821)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v9-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v9 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/access/heap/vacuumlazy.c         |   3 +-
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 239 +++++++++++++++----
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  19 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 9 files changed, 275 insertions(+), 78 deletions(-)
   5.9% src/backend/postmaster/
  60.4% src/backend/utils/activity/
   4.9% src/backend/utils/adt/
   3.0% src/include/catalog/
   7.1% src/include/
  17.5% src/test/recovery/t/

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 62035b7f9c3..30778a15639 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -961,8 +961,7 @@ heap_vacuum_rel(Relation rel, const VacuumParams params,
 	 * soon in cases where the failsafe prevented significant amounts of heap
 	 * vacuuming.
 	 */
-	pgstat_report_vacuum(RelationGetRelid(rel),
-						 rel->rd_rel->relisshared,
+	pgstat_report_vacuum(rel,
 						 Max(vacrel->new_live_tuples, 0),
 						 vacrel->recently_dead_tuples +
 						 vacrel->missed_dead_tuples,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 1bd3924e35e..a11174b25ad 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2014,12 +2014,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2048,8 +2052,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2114,6 +2117,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2122,6 +2126,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2141,8 +2148,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2945,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index b90754f8578..48bf93cae6e 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -207,27 +245,29 @@ pgstat_drop_relation(Relation rel)
  * Report that the table was just vacuumed and flush IO statistics.
  */
 void
-pgstat_report_vacuum(Oid tableoid, bool shared,
-					 PgStat_Counter livetuples, PgStat_Counter deadtuples,
-					 TimestampTz starttime)
+pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
+					 PgStat_Counter deadtuples, TimestampTz starttime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
-											dboid, tableoid, false);
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -286,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -326,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -469,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -477,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -504,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -707,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -751,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -786,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -921,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1010,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..60ffb1679ec 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2305,5 +2310,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index 1302a3d75cd..9430970fffd 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 7816d779d8c..0e2d8051d69 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index f23dd5870da..3102f86aa24 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -17,6 +17,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "replication/worker_internal.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -35,6 +36,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -175,11 +182,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -669,8 +676,8 @@ extern void pgstat_init_relation(Relation rel);
 extern void pgstat_assoc_relation(Relation rel);
 extern void pgstat_unlink_relation(Relation rel);
 
-extern void pgstat_report_vacuum(Oid tableoid, bool shared,
-								 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+extern void pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
+								 PgStat_Counter deadtuples,
 								 TimestampTz starttime);
 extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
@@ -735,8 +742,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 5c1ce4d3d6a..7b24928b00d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -764,6 +764,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--tV2Nti+lXhoeT6I5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0002-handle-relation-statistics-correctly-during-rewri.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v14 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  21 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 71 deletions(-)
   6.1% src/backend/postmaster/
  61.7% src/backend/utils/activity/
   4.9% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 219673db930..4bef7ab7543 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1992,12 +1992,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2026,8 +2030,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2092,6 +2095,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2100,6 +2104,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2119,8 +2126,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2917,8 +2923,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..89bf0cbed56 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 9185a8e6b83..db882339f1e 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -30,6 +30,7 @@
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 #include "utils/tuplestore.h"
 #include "utils/wait_event.h"
@@ -2004,9 +2005,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2363,5 +2369,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index c4cde415219..73ed046be31 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 3bd4a74f003..e5e818eb0c5 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 8e3549c3752..ef740aff26e 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -16,6 +16,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "storage/locktag.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -39,6 +40,12 @@ typedef struct RelationData *Relation;
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -179,11 +186,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -766,8 +773,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 97704421a92..e34b008e893 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -786,6 +786,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index cdc427dbc78..4d00087dc6f 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--96iU9DKeu+W+YlSa
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v14-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v12 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 72 deletions(-)
   6.1% src/backend/postmaster/
  61.6% src/backend/utils/activity/
   5.1% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 695e187ba11..5d80e0bd212 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1991,12 +1991,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2025,8 +2029,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2091,6 +2094,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2099,6 +2103,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2118,8 +2125,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2916,8 +2922,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..89bf0cbed56 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 50ea9e8fb83..3f59739de7c 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 #include "utils/wait_event.h"
 
@@ -1962,9 +1962,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2318,5 +2323,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index c4cde415219..73ed046be31 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 3bd4a74f003..e5e818eb0c5 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 216b93492ba..689c624f373 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -15,6 +15,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -38,6 +39,12 @@ typedef struct RelationData *Relation;
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -178,11 +185,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -738,8 +745,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..42f29496551 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -765,6 +765,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index cdc427dbc78..4d00087dc6f 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--sdA5zuaL94ts0rne
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v12-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v9 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/access/heap/vacuumlazy.c         |   3 +-
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 239 +++++++++++++++----
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  19 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 9 files changed, 275 insertions(+), 78 deletions(-)
   5.9% src/backend/postmaster/
  60.4% src/backend/utils/activity/
   4.9% src/backend/utils/adt/
   3.0% src/include/catalog/
   7.1% src/include/
  17.5% src/test/recovery/t/

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 62035b7f9c3..30778a15639 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -961,8 +961,7 @@ heap_vacuum_rel(Relation rel, const VacuumParams params,
 	 * soon in cases where the failsafe prevented significant amounts of heap
 	 * vacuuming.
 	 */
-	pgstat_report_vacuum(RelationGetRelid(rel),
-						 rel->rd_rel->relisshared,
+	pgstat_report_vacuum(rel,
 						 Max(vacrel->new_live_tuples, 0),
 						 vacrel->recently_dead_tuples +
 						 vacrel->missed_dead_tuples,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 1bd3924e35e..a11174b25ad 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2014,12 +2014,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2048,8 +2052,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2114,6 +2117,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2122,6 +2126,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2141,8 +2148,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2945,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index b90754f8578..48bf93cae6e 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -207,27 +245,29 @@ pgstat_drop_relation(Relation rel)
  * Report that the table was just vacuumed and flush IO statistics.
  */
 void
-pgstat_report_vacuum(Oid tableoid, bool shared,
-					 PgStat_Counter livetuples, PgStat_Counter deadtuples,
-					 TimestampTz starttime)
+pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
+					 PgStat_Counter deadtuples, TimestampTz starttime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
-											dboid, tableoid, false);
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -286,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -326,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -469,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -477,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -504,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -707,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -751,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -786,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -921,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1010,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..60ffb1679ec 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2305,5 +2310,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index 1302a3d75cd..9430970fffd 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 7816d779d8c..0e2d8051d69 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index f23dd5870da..3102f86aa24 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -17,6 +17,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "replication/worker_internal.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -35,6 +36,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -175,11 +182,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -669,8 +676,8 @@ extern void pgstat_init_relation(Relation rel);
 extern void pgstat_assoc_relation(Relation rel);
 extern void pgstat_unlink_relation(Relation rel);
 
-extern void pgstat_report_vacuum(Oid tableoid, bool shared,
-								 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+extern void pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
+								 PgStat_Counter deadtuples,
 								 TimestampTz starttime);
 extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
@@ -735,8 +742,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 5c1ce4d3d6a..7b24928b00d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -764,6 +764,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--tV2Nti+lXhoeT6I5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0002-handle-relation-statistics-correctly-during-rewri.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v7 2/3] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/access/heap/vacuumlazy.c         |   3 +-
 src/backend/postmaster/autovacuum.c          |   9 +-
 src/backend/utils/activity/pgstat_relation.c | 234 +++++++++++++++----
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/pgstat.h                         |  18 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 7 files changed, 249 insertions(+), 78 deletions(-)
   3.3% src/backend/postmaster/
  64.6% src/backend/utils/activity/
   5.3% src/backend/utils/adt/
   7.0% src/include/
  18.7% src/test/recovery/t/

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 61fe623cc60..073f1ff3fe4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -947,8 +947,7 @@ heap_vacuum_rel(Relation rel, const VacuumParams params,
 	 * soon in cases where the failsafe prevented significant amounts of heap
 	 * vacuuming.
 	 */
-	pgstat_report_vacuum(RelationGetRelid(rel),
-						 rel->rd_rel->relisshared,
+	pgstat_report_vacuum(rel->rd_locator,
 						 Max(vacrel->new_live_tuples, 0),
 						 vacrel->recently_dead_tuples +
 						 vacrel->missed_dead_tuples,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index ed19c74bb19..662495c72fc 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2048,8 +2048,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2141,8 +2140,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2937,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 1de477cbeeb..7debb14bb5d 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,38 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = InvalidOid;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +198,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +216,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -207,14 +246,12 @@ pgstat_drop_relation(Relation rel)
  * Report that the table was just vacuumed and flush IO statistics.
  */
 void
-pgstat_report_vacuum(Oid tableoid, bool shared,
-					 PgStat_Counter livetuples, PgStat_Counter deadtuples,
-					 TimestampTz starttime)
+pgstat_report_vacuum(RelFileLocator locator, PgStat_Counter livetuples,
+					 PgStat_Counter deadtuples, TimestampTz starttime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
 
@@ -227,7 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
-											dboid, tableoid, false);
+											locator.dbOid, RelFileLocatorToPgStatObjid(locator), false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -286,9 +323,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -326,9 +363,26 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = InvalidOid;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -469,7 +523,7 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
 }
 
 /*
@@ -477,12 +531,19 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	PgStat_StatTabEntry *tabentry;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	/* fetch the stats entry using the relfilenode based key */
+	tabentry = (PgStat_StatTabEntry *) pgstat_fetch_entry(PGSTAT_KIND_RELATION,
+														  locator.dbOid,
+														  RelFileLocatorToPgStatObjid(locator));
+	return tabentry;
 }
 
 /*
@@ -504,14 +565,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc(sizeof(PgStat_TableStatus));
@@ -707,8 +771,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -751,7 +819,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -786,8 +854,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -921,17 +989,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1010,3 +1082,83 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = InvalidOid;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index a710508979e..7924cdf5b97 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2290,5 +2295,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 7ae503e71a2..5d0fe79f7e3 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -16,6 +16,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -34,6 +35,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -173,11 +180,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -664,8 +671,8 @@ extern void pgstat_init_relation(Relation rel);
 extern void pgstat_assoc_relation(Relation rel);
 extern void pgstat_unlink_relation(Relation rel);
 
-extern void pgstat_report_vacuum(Oid tableoid, bool shared,
-								 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+extern void pgstat_report_vacuum(RelFileLocator locator, PgStat_Counter livetuples,
+								 PgStat_Counter deadtuples,
 								 TimestampTz starttime);
 extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
@@ -730,8 +737,7 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 4d2b8aa6081..1252249231d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -718,6 +718,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--KMYjwlsACqdYx2P8
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v7-0003-handle-relation-statistics-correctly-during-rewri.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v14 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  21 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 71 deletions(-)
   6.1% src/backend/postmaster/
  61.7% src/backend/utils/activity/
   4.9% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 219673db930..4bef7ab7543 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1992,12 +1992,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2026,8 +2030,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2092,6 +2095,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2100,6 +2104,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2119,8 +2126,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2917,8 +2923,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..89bf0cbed56 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 9185a8e6b83..db882339f1e 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -30,6 +30,7 @@
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 #include "utils/tuplestore.h"
 #include "utils/wait_event.h"
@@ -2004,9 +2005,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2363,5 +2369,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index c4cde415219..73ed046be31 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 3bd4a74f003..e5e818eb0c5 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 8e3549c3752..ef740aff26e 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -16,6 +16,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "storage/locktag.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -39,6 +40,12 @@ typedef struct RelationData *Relation;
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -179,11 +186,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -766,8 +773,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 97704421a92..e34b008e893 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -786,6 +786,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index cdc427dbc78..4d00087dc6f 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--96iU9DKeu+W+YlSa
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v14-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v12 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 72 deletions(-)
   6.1% src/backend/postmaster/
  61.6% src/backend/utils/activity/
   5.1% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 695e187ba11..5d80e0bd212 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1991,12 +1991,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2025,8 +2029,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2091,6 +2094,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2099,6 +2103,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2118,8 +2125,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2916,8 +2922,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..89bf0cbed56 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 50ea9e8fb83..3f59739de7c 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 #include "utils/wait_event.h"
 
@@ -1962,9 +1962,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2318,5 +2323,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index c4cde415219..73ed046be31 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 3bd4a74f003..e5e818eb0c5 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 216b93492ba..689c624f373 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -15,6 +15,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -38,6 +39,12 @@ typedef struct RelationData *Relation;
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -178,11 +185,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -738,8 +745,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..42f29496551 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -765,6 +765,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index cdc427dbc78..4d00087dc6f 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--sdA5zuaL94ts0rne
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v12-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v9 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/access/heap/vacuumlazy.c         |   3 +-
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 239 +++++++++++++++----
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  19 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 9 files changed, 275 insertions(+), 78 deletions(-)
   5.9% src/backend/postmaster/
  60.4% src/backend/utils/activity/
   4.9% src/backend/utils/adt/
   3.0% src/include/catalog/
   7.1% src/include/
  17.5% src/test/recovery/t/

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 62035b7f9c3..30778a15639 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -961,8 +961,7 @@ heap_vacuum_rel(Relation rel, const VacuumParams params,
 	 * soon in cases where the failsafe prevented significant amounts of heap
 	 * vacuuming.
 	 */
-	pgstat_report_vacuum(RelationGetRelid(rel),
-						 rel->rd_rel->relisshared,
+	pgstat_report_vacuum(rel,
 						 Max(vacrel->new_live_tuples, 0),
 						 vacrel->recently_dead_tuples +
 						 vacrel->missed_dead_tuples,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 1bd3924e35e..a11174b25ad 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2014,12 +2014,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2048,8 +2052,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2114,6 +2117,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2122,6 +2126,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2141,8 +2148,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2945,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index b90754f8578..48bf93cae6e 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -207,27 +245,29 @@ pgstat_drop_relation(Relation rel)
  * Report that the table was just vacuumed and flush IO statistics.
  */
 void
-pgstat_report_vacuum(Oid tableoid, bool shared,
-					 PgStat_Counter livetuples, PgStat_Counter deadtuples,
-					 TimestampTz starttime)
+pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
+					 PgStat_Counter deadtuples, TimestampTz starttime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
-											dboid, tableoid, false);
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -286,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -326,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -469,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -477,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -504,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -707,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -751,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -786,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -921,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1010,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..60ffb1679ec 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2305,5 +2310,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index 1302a3d75cd..9430970fffd 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 7816d779d8c..0e2d8051d69 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index f23dd5870da..3102f86aa24 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -17,6 +17,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "replication/worker_internal.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -35,6 +36,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -175,11 +182,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -669,8 +676,8 @@ extern void pgstat_init_relation(Relation rel);
 extern void pgstat_assoc_relation(Relation rel);
 extern void pgstat_unlink_relation(Relation rel);
 
-extern void pgstat_report_vacuum(Oid tableoid, bool shared,
-								 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+extern void pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
+								 PgStat_Counter deadtuples,
 								 TimestampTz starttime);
 extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
@@ -735,8 +742,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 5c1ce4d3d6a..7b24928b00d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -764,6 +764,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--tV2Nti+lXhoeT6I5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0002-handle-relation-statistics-correctly-during-rewri.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v8 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/access/heap/vacuumlazy.c         |   3 +-
 src/backend/postmaster/autovacuum.c          |   9 +-
 src/backend/utils/activity/pgstat_relation.c | 234 +++++++++++++++----
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/pgstat.h                         |  18 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 7 files changed, 249 insertions(+), 78 deletions(-)
   3.3% src/backend/postmaster/
  64.6% src/backend/utils/activity/
   5.3% src/backend/utils/adt/
   7.0% src/include/
  18.7% src/test/recovery/t/

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 62035b7f9c3..a9b2b4e1033 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -961,8 +961,7 @@ heap_vacuum_rel(Relation rel, const VacuumParams params,
 	 * soon in cases where the failsafe prevented significant amounts of heap
 	 * vacuuming.
 	 */
-	pgstat_report_vacuum(RelationGetRelid(rel),
-						 rel->rd_rel->relisshared,
+	pgstat_report_vacuum(rel->rd_locator,
 						 Max(vacrel->new_live_tuples, 0),
 						 vacrel->recently_dead_tuples +
 						 vacrel->missed_dead_tuples,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 1bd3924e35e..563a3697690 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2048,8 +2048,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2141,8 +2140,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2937,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index b90754f8578..ee6f2eb2bdb 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,38 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = InvalidOid;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +198,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +216,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -207,14 +246,12 @@ pgstat_drop_relation(Relation rel)
  * Report that the table was just vacuumed and flush IO statistics.
  */
 void
-pgstat_report_vacuum(Oid tableoid, bool shared,
-					 PgStat_Counter livetuples, PgStat_Counter deadtuples,
-					 TimestampTz starttime)
+pgstat_report_vacuum(RelFileLocator locator, PgStat_Counter livetuples,
+					 PgStat_Counter deadtuples, TimestampTz starttime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
 
@@ -227,7 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
-											dboid, tableoid, false);
+											locator.dbOid, RelFileLocatorToPgStatObjid(locator), false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -286,9 +323,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -326,9 +363,26 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = InvalidOid;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -469,7 +523,7 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
 }
 
 /*
@@ -477,12 +531,19 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	PgStat_StatTabEntry *tabentry;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	/* fetch the stats entry using the relfilenode based key */
+	tabentry = (PgStat_StatTabEntry *) pgstat_fetch_entry(PGSTAT_KIND_RELATION,
+														  locator.dbOid,
+														  RelFileLocatorToPgStatObjid(locator));
+	return tabentry;
 }
 
 /*
@@ -504,14 +565,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -707,8 +771,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -751,7 +819,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -786,8 +854,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -921,17 +989,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1010,3 +1082,83 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = InvalidOid;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..60ffb1679ec 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2305,5 +2310,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index f23dd5870da..c9e451094f3 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -17,6 +17,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "replication/worker_internal.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -35,6 +36,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -175,11 +182,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -669,8 +676,8 @@ extern void pgstat_init_relation(Relation rel);
 extern void pgstat_assoc_relation(Relation rel);
 extern void pgstat_unlink_relation(Relation rel);
 
-extern void pgstat_report_vacuum(Oid tableoid, bool shared,
-								 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+extern void pgstat_report_vacuum(RelFileLocator locator, PgStat_Counter livetuples,
+								 PgStat_Counter deadtuples,
 								 TimestampTz starttime);
 extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
@@ -735,8 +742,7 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 5c1ce4d3d6a..7b24928b00d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -764,6 +764,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--BHD/2LBqtxMXWADJ
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v8-0002-handle-relation-statistics-correctly-during-rewri.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v10 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 72 deletions(-)
   6.1% src/backend/postmaster/
  61.6% src/backend/utils/activity/
   5.1% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 1bd3924e35e..a11174b25ad 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2014,12 +2014,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2048,8 +2052,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2114,6 +2117,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2122,6 +2126,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2141,8 +2148,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2945,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 55a10c299db..a267e93f8be 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..60ffb1679ec 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2305,5 +2310,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index 1302a3d75cd..9430970fffd 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 7816d779d8c..0e2d8051d69 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 6714363144a..3102f86aa24 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -17,6 +17,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "replication/worker_internal.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -35,6 +36,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -175,11 +182,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -735,8 +742,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 5c1ce4d3d6a..7b24928b00d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -764,6 +764,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--xJsrX25x3tm7Tn81
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v10-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v13 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  21 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 71 deletions(-)
   6.1% src/backend/postmaster/
  61.7% src/backend/utils/activity/
   4.9% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 219673db930..4bef7ab7543 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1992,12 +1992,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2026,8 +2030,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2092,6 +2095,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2100,6 +2104,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2119,8 +2126,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2917,8 +2923,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..89bf0cbed56 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 5f907335990..106d1e577a7 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -30,6 +30,7 @@
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 #include "utils/tuplestore.h"
 #include "utils/wait_event.h"
@@ -1965,9 +1966,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2324,5 +2330,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index c4cde415219..73ed046be31 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 3bd4a74f003..e5e818eb0c5 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 216b93492ba..689c624f373 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -15,6 +15,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -38,6 +39,12 @@ typedef struct RelationData *Relation;
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -178,11 +185,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -738,8 +745,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..42f29496551 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -765,6 +765,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index cdc427dbc78..4d00087dc6f 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--USlF2Vr25us5UpvY
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v13 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  21 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 71 deletions(-)
   6.1% src/backend/postmaster/
  61.7% src/backend/utils/activity/
   4.9% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 219673db930..4bef7ab7543 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1992,12 +1992,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2026,8 +2030,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2092,6 +2095,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2100,6 +2104,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2119,8 +2126,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2917,8 +2923,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..89bf0cbed56 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 5f907335990..106d1e577a7 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -30,6 +30,7 @@
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 #include "utils/tuplestore.h"
 #include "utils/wait_event.h"
@@ -1965,9 +1966,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2324,5 +2330,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index c4cde415219..73ed046be31 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 3bd4a74f003..e5e818eb0c5 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 216b93492ba..689c624f373 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -15,6 +15,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -38,6 +39,12 @@ typedef struct RelationData *Relation;
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -178,11 +185,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -738,8 +745,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..42f29496551 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -765,6 +765,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index cdc427dbc78..4d00087dc6f 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--USlF2Vr25us5UpvY
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v12 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 72 deletions(-)
   6.1% src/backend/postmaster/
  61.6% src/backend/utils/activity/
   5.1% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 695e187ba11..5d80e0bd212 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1991,12 +1991,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2025,8 +2029,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2091,6 +2094,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2099,6 +2103,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2118,8 +2125,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2916,8 +2922,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..89bf0cbed56 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 50ea9e8fb83..3f59739de7c 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 #include "utils/wait_event.h"
 
@@ -1962,9 +1962,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2318,5 +2323,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index c4cde415219..73ed046be31 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 3bd4a74f003..e5e818eb0c5 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 216b93492ba..689c624f373 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -15,6 +15,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -38,6 +39,12 @@ typedef struct RelationData *Relation;
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -178,11 +185,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -738,8 +745,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..42f29496551 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -765,6 +765,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index cdc427dbc78..4d00087dc6f 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--sdA5zuaL94ts0rne
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v12-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v11 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 72 deletions(-)
   6.1% src/backend/postmaster/
  61.6% src/backend/utils/activity/
   5.1% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 6fde740465f..4bd5a6824bd 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1990,12 +1990,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2024,8 +2028,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2090,6 +2093,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2098,6 +2102,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2117,8 +2124,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2915,8 +2921,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..89bf0cbed56 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index b1df96e7b0b..a5a00d6f018 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1961,9 +1961,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2317,5 +2322,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index c4cde415219..73ed046be31 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index fe7a5ab538f..f511adc3965 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 9bb777c3d5a..e9e4d32c3b8 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -16,6 +16,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -34,6 +35,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -174,11 +181,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -734,8 +741,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..42f29496551 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -765,6 +765,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index cdc427dbc78..4d00087dc6f 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--zLA8DXafBEP889wv
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v11-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v8 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/access/heap/vacuumlazy.c         |   3 +-
 src/backend/postmaster/autovacuum.c          |   9 +-
 src/backend/utils/activity/pgstat_relation.c | 234 +++++++++++++++----
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/pgstat.h                         |  18 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 7 files changed, 249 insertions(+), 78 deletions(-)
   3.3% src/backend/postmaster/
  64.6% src/backend/utils/activity/
   5.3% src/backend/utils/adt/
   7.0% src/include/
  18.7% src/test/recovery/t/

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 62035b7f9c3..a9b2b4e1033 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -961,8 +961,7 @@ heap_vacuum_rel(Relation rel, const VacuumParams params,
 	 * soon in cases where the failsafe prevented significant amounts of heap
 	 * vacuuming.
 	 */
-	pgstat_report_vacuum(RelationGetRelid(rel),
-						 rel->rd_rel->relisshared,
+	pgstat_report_vacuum(rel->rd_locator,
 						 Max(vacrel->new_live_tuples, 0),
 						 vacrel->recently_dead_tuples +
 						 vacrel->missed_dead_tuples,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 1bd3924e35e..563a3697690 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2048,8 +2048,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2141,8 +2140,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2937,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index b90754f8578..ee6f2eb2bdb 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,38 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = InvalidOid;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +198,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +216,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -207,14 +246,12 @@ pgstat_drop_relation(Relation rel)
  * Report that the table was just vacuumed and flush IO statistics.
  */
 void
-pgstat_report_vacuum(Oid tableoid, bool shared,
-					 PgStat_Counter livetuples, PgStat_Counter deadtuples,
-					 TimestampTz starttime)
+pgstat_report_vacuum(RelFileLocator locator, PgStat_Counter livetuples,
+					 PgStat_Counter deadtuples, TimestampTz starttime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
 
@@ -227,7 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
-											dboid, tableoid, false);
+											locator.dbOid, RelFileLocatorToPgStatObjid(locator), false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -286,9 +323,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -326,9 +363,26 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = InvalidOid;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -469,7 +523,7 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
 }
 
 /*
@@ -477,12 +531,19 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	PgStat_StatTabEntry *tabentry;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	/* fetch the stats entry using the relfilenode based key */
+	tabentry = (PgStat_StatTabEntry *) pgstat_fetch_entry(PGSTAT_KIND_RELATION,
+														  locator.dbOid,
+														  RelFileLocatorToPgStatObjid(locator));
+	return tabentry;
 }
 
 /*
@@ -504,14 +565,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -707,8 +771,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -751,7 +819,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -786,8 +854,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -921,17 +989,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1010,3 +1082,83 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use the relation OID as relNumber.
+		 * No collision with regular relations is possible because relNumbers
+		 * are also assigned from the pg_class OID space (see
+		 * GetNewRelFileNumber()), making each value unique across the
+		 * database regardless of spcOid.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = InvalidOid;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..60ffb1679ec 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2305,5 +2310,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index f23dd5870da..c9e451094f3 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -17,6 +17,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "replication/worker_internal.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -35,6 +36,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -175,11 +182,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -669,8 +676,8 @@ extern void pgstat_init_relation(Relation rel);
 extern void pgstat_assoc_relation(Relation rel);
 extern void pgstat_unlink_relation(Relation rel);
 
-extern void pgstat_report_vacuum(Oid tableoid, bool shared,
-								 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+extern void pgstat_report_vacuum(RelFileLocator locator, PgStat_Counter livetuples,
+								 PgStat_Counter deadtuples,
 								 TimestampTz starttime);
 extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
@@ -735,8 +742,7 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 5c1ce4d3d6a..7b24928b00d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -764,6 +764,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--BHD/2LBqtxMXWADJ
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v8-0002-handle-relation-statistics-correctly-during-rewri.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread

* [PATCH v9 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 301+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/access/heap/vacuumlazy.c         |   3 +-
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 239 +++++++++++++++----
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  19 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 9 files changed, 275 insertions(+), 78 deletions(-)
   5.9% src/backend/postmaster/
  60.4% src/backend/utils/activity/
   4.9% src/backend/utils/adt/
   3.0% src/include/catalog/
   7.1% src/include/
  17.5% src/test/recovery/t/

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 62035b7f9c3..30778a15639 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -961,8 +961,7 @@ heap_vacuum_rel(Relation rel, const VacuumParams params,
 	 * soon in cases where the failsafe prevented significant amounts of heap
 	 * vacuuming.
 	 */
-	pgstat_report_vacuum(RelationGetRelid(rel),
-						 rel->rd_rel->relisshared,
+	pgstat_report_vacuum(rel,
 						 Max(vacrel->new_live_tuples, 0),
 						 vacrel->recently_dead_tuples +
 						 vacrel->missed_dead_tuples,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 1bd3924e35e..a11174b25ad 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2014,12 +2014,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2048,8 +2052,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2114,6 +2117,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2122,6 +2126,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2141,8 +2148,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2945,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index b90754f8578..48bf93cae6e 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -207,27 +245,29 @@ pgstat_drop_relation(Relation rel)
  * Report that the table was just vacuumed and flush IO statistics.
  */
 void
-pgstat_report_vacuum(Oid tableoid, bool shared,
-					 PgStat_Counter livetuples, PgStat_Counter deadtuples,
-					 TimestampTz starttime)
+pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
+					 PgStat_Counter deadtuples, TimestampTz starttime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
-											dboid, tableoid, false);
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -286,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -326,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -469,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -477,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -504,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -707,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -751,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -786,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -921,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1010,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..60ffb1679ec 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2305,5 +2310,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index 1302a3d75cd..9430970fffd 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 7816d779d8c..0e2d8051d69 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index f23dd5870da..3102f86aa24 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -17,6 +17,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "replication/worker_internal.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -35,6 +36,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -175,11 +182,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -669,8 +676,8 @@ extern void pgstat_init_relation(Relation rel);
 extern void pgstat_assoc_relation(Relation rel);
 extern void pgstat_unlink_relation(Relation rel);
 
-extern void pgstat_report_vacuum(Oid tableoid, bool shared,
-								 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+extern void pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
+								 PgStat_Counter deadtuples,
 								 TimestampTz starttime);
 extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
@@ -735,8 +742,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 5c1ce4d3d6a..7b24928b00d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -764,6 +764,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--tV2Nti+lXhoeT6I5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0002-handle-relation-statistics-correctly-during-rewri.patch"



^ permalink  raw  reply  [nested|flat] 301+ messages in thread