Add backend-level statistics to pgstats

This adds a new variable-numbered statistics kind in pgstats, where the
object ID key of the stats entries is based on the proc number of the
backends.  This acts as an upper-bound for the number of stats entries
that can exist at once.  The entries are created when a backend starts
after authentication succeeds, and are removed when the backend exits,
making the stats entry exist for as long as their backend is up and
running.  These are not written to the pgstats file at shutdown (note
that write_to_file is disabled, as a safety measure).

Currently, these stats include only information about the I/O generated
by a backend, using the same layer as pg_stat_io, except that it is now
possible to know how much activity is happening in each backend rather
than an overall aggregate of all the activity.  A function called
pg_stat_get_backend_io() is added to access this data depending on the
PID of a backend.  The existing structure could be expanded in the
future to add more information about other statistics related to
backends, depending on requirements or ideas.

Auxiliary processes are not included in this set of statistics.  These
are less interesting to have than normal backends as they have dedicated
entries in pg_stat_io, and stats kinds of their own.

This commit includes also pg_stat_reset_backend_stats(), function able
to reset all the stats associated to a single backend.

Bump catalog version and PGSTAT_FILE_FORMAT_ID.

Author: Bertrand Drouvot
Reviewed-by: Álvaro Herrera, Kyotaro Horiguchi, Michael Paquier, Nazir
Bilal Yavuz
Discussion: https://postgr.es/m/ZtXR+CtkEVVE/LHF@ip-10-97-1-34.eu-west-3.compute.internal

1 files changed, 94 insertions, 5 deletions

diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 03dd8cd335a..6fc34f74949 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1274,8 +1274,9 @@ pg_stat_get_buf_alloc(PG_FUNCTION_ARGS)
 }
 
 /*
-* When adding a new column to the pg_stat_io view, add a new enum value
-* here above IO_NUM_COLUMNS.
+* When adding a new column to the pg_stat_io view and the
+* pg_stat_get_backend_io() function, add a new enum value here above
+* IO_NUM_COLUMNS.
 */
 typedef enum io_stat_col
 {
@@ -1368,9 +1369,9 @@ pg_stat_us_to_ms(PgStat_Counter val_ms)
 /*
  * pg_stat_io_build_tuples
  *
- * Helper routine for pg_stat_get_io() filling a result tuplestore with one
- * tuple for each object and each context supported by the caller, based on the
- * contents of bktype_stats.
+ * Helper routine for pg_stat_get_io() and pg_stat_get_backend_io()
+ * filling a result tuplestore with one tuple for each object and each
+ * context supported by the caller, based on the contents of bktype_stats.
  */
 static void
 pg_stat_io_build_tuples(ReturnSetInfo *rsinfo,
@@ -1495,6 +1496,70 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 }
 
 /*
+ * Returns I/O statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	BackendType bktype;
+	int			pid;
+	PGPROC	   *proc;
+	ProcNumber	procNumber;
+	PgStat_Backend *backend_stats;
+	PgStat_BktypeIO *bktype_stats;
+	PgBackendStatus *beentry;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	pid = PG_GETARG_INT32(0);
+	proc = BackendPidGetProc(pid);
+
+	/*
+	 * This could be an auxiliary process but these do not report backend
+	 * statistics due to pgstat_tracks_backend_bktype(), so there is no need
+	 * for an extra call to AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		return (Datum) 0;
+
+	procNumber = GetNumberFromPGProc(proc);
+
+	beentry = pgstat_get_beentry_by_proc_number(procNumber);
+	if (!beentry)
+		return (Datum) 0;
+
+	backend_stats = pgstat_fetch_stat_backend(procNumber);
+	if (!backend_stats)
+		return (Datum) 0;
+
+	bktype = beentry->st_backendType;
+
+	/* if PID does not match, leave */
+	if (beentry->st_procpid != pid)
+		return (Datum) 0;
+
+	/* backend may be gone, so recheck in case */
+	if (bktype == B_INVALID)
+		return (Datum) 0;
+
+	bktype_stats = &backend_stats->stats;
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters (in pg_stat_io_build_tuples()), checking that only expected
+	 * stats are non-zero, since it keeps the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	/* save tuples with data from this PgStat_BktypeIO */
+	pg_stat_io_build_tuples(rsinfo, bktype_stats, bktype,
+							backend_stats->stat_reset_timestamp);
+	return (Datum) 0;
+}
+
+/*
  * Returns statistics of WAL activity
  */
 Datum
@@ -1799,6 +1864,30 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+/*
+ * Reset statistics of backend with given PID.
+ */
+Datum
+pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/*
+	 * This could be an auxiliary process but these do not report backend
+	 * statistics due to pgstat_tracks_backend_bktype(), so there is no need
+	 * for an extra call to AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)