Add missing query ID reporting in extended query protocol

This commit adds query ID reports for two code paths when processing
extended query protocol messages:
- When receiving a bind message, setting it to the first Query retrieved
from a cached cache.
- When receiving an execute message, setting it to the first PlannedStmt
stored in a portal.

An advantage of this method is that this is able to cover all the types
of portals handled in the extended query protocol, particularly these
two when the report done in ExecutorStart() is not enough (neither is an
addition in ExecutorRun(), actually, for the second point):
- Multiple execute messages, with multiple ExecutorRun().
- Portal with execute/fetch messages, like a query with a RETURNING
clause and a fetch size that stores the tuples in a first execute
message going though ExecutorStart() and ExecuteRun(), followed by one
or more execute messages doing only fetches from the tuplestore created
in the first message.  This corresponds to the case where
execute_is_fetch is set, for example.

Note that the query ID reporting done in ExecutorStart() is still
necessary, as an EXECUTE requires it.  Query ID reporting is optimistic
and more calls to pgstat_report_query_id() don't matter as the first
report takes priority except if the report is forced.  The comment in
ExecutorStart() is adjusted to reflect better the reality with the
extended query protocol.

The test added in pg_stat_statements is a courtesy of Robert Haas.  This
uses psql's \bind metacommand, hence this part is backpatched down to
v16.

Reported-by:  Kaido Vaikla, Erik Wienhold
Author: Sami Imseih
Reviewed-by: Jian He, Andrei Lepikhov, Michael Paquier
Discussion: https://postgr.es/m/CA+427g8DiW3aZ6pOpVgkPbqK97ouBdf18VLiHFesea2jUk3XoQ@mail.gmail.com
Discussion: https://postgr.es/m/CA+TgmoZxtnf_jZ=VqBSyaU8hfUkkwoJCJ6ufy4LGpXaunKrjrg@mail.gmail.com
Discussion: https://postgr.es/m/1391613709.939460.1684777418070@office.mailbox.org
Backpatch-through: 14

6 files changed, 49 insertions, 5 deletions

diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index 5578a9dd4e3..31e4fdeeb96 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -18,7 +18,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
-	user_activity wal cleanup oldextversions
+	user_activity wal extended cleanup oldextversions
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/extended.out b/contrib/pg_stat_statements/expected/extended.out
new file mode 100644
index 00000000000..dbc78680226
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/extended.out
@@ -0,0 +1,10 @@
+-- Tests with extended query protocol
+SET pg_stat_statements.track_utility = FALSE;
+-- This test checks that an execute message sets a query ID.
+SELECT query_id IS NOT NULL AS query_id_set
+  FROM pg_stat_activity WHERE pid = pg_backend_pid() \bind \g
+ query_id_set 
+--------------
+ t
+(1 row)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 3e3062ada9c..d1a02c3e8fe 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -48,6 +48,7 @@ tests += {
       'planning',
       'user_activity',
       'wal',
+      'extended',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/extended.sql b/contrib/pg_stat_statements/sql/extended.sql
new file mode 100644
index 00000000000..07b6c5a93d6
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/extended.sql
@@ -0,0 +1,7 @@
+-- Tests with extended query protocol
+
+SET pg_stat_statements.track_utility = FALSE;
+
+-- This test checks that an execute message sets a query ID.
+SELECT query_id IS NOT NULL AS query_id_set
+  FROM pg_stat_activity WHERE pid = pg_backend_pid() \bind \g
diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c
index 4c5a7bbf620..fddcd086e68 100644
--- a/src/backend/executor/execMain.c
+++ b/src/backend/executor/execMain.c
@@ -132,10 +132,12 @@ void
 ExecutorStart(QueryDesc *queryDesc, int eflags)
 {
 	/*
-	 * In some cases (e.g. an EXECUTE statement) a query execution will skip
-	 * parse analysis, which means that the query_id won't be reported.  Note
-	 * that it's harmless to report the query_id multiple times, as the call
-	 * will be ignored if the top level query_id has already been reported.
+	 * In some cases (e.g. an EXECUTE statement or an execute message with the
+	 * extended query protocol) the query_id won't be reported, so do it now.
+	 *
+	 * Note that it's harmless to report the query_id multiple times, as the
+	 * call will be ignored if the top level query_id has already been
+	 * reported.
 	 */
 	pgstat_report_query_id(queryDesc->plannedstmt->queryId, false);
 
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index e7d486ca2fc..3f427f1b47f 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -1648,6 +1648,7 @@ exec_bind_message(StringInfo input_message)
 	char		msec_str[32];
 	ParamsErrorCbData params_data;
 	ErrorContextCallback params_errcxt;
+	ListCell   *lc;
 
 	/* Get the fixed part of the message */
 	portal_name = pq_getmsgstring(input_message);
@@ -1683,6 +1684,17 @@ exec_bind_message(StringInfo input_message)
 
 	pgstat_report_activity(STATE_RUNNING, psrc->query_string);
 
+	foreach(lc, psrc->query_list)
+	{
+		Query	   *query = lfirst_node(Query, lc);
+
+		if (query->queryId != UINT64CONST(0))
+		{
+			pgstat_report_query_id(query->queryId, false);
+			break;
+		}
+	}
+
 	set_ps_display("BIND");
 
 	if (save_log_statement_stats)
@@ -2109,6 +2121,7 @@ exec_execute_message(const char *portal_name, long max_rows)
 	ErrorContextCallback params_errcxt;
 	const char *cmdtagname;
 	size_t		cmdtaglen;
+	ListCell   *lc;
 
 	/* Adjust destination to tell printtup.c what to do */
 	dest = whereToSendOutput;
@@ -2155,6 +2168,17 @@ exec_execute_message(const char *portal_name, long max_rows)
 
 	pgstat_report_activity(STATE_RUNNING, sourceText);
 
+	foreach(lc, portal->stmts)
+	{
+		PlannedStmt *stmt = lfirst_node(PlannedStmt, lc);
+
+		if (stmt->queryId != UINT64CONST(0))
+		{
+			pgstat_report_query_id(stmt->queryId, false);
+			break;
+		}
+	}
+
 	cmdtagname = GetCommandTagNameAndLen(portal->commandTag, &cmdtaglen);
 
 	set_ps_display_with_len(cmdtagname, cmdtaglen);