Split pgstat_bestart() into three different routines

pgstat_bestart(), used post-authentication to set up a backend entry
in the PgBackendStatus array, so as its data becomes visible in
pg_stat_activity and related catalogs, has its logic divided into three
routines with this commit, called in order at different steps of the
backend initialization:
* pgstat_bestart_initial() sets up the backend entry with a minimal
amount of information, reporting it with a new BackendState called
STATE_STARTING while waiting for backend initialization and client
authentication to complete.  The main benefit that this offers is
observability, so as it is possible to monitor the backend activity
during authentication.  This step happens earlier than in the logic
prior to this commit.  pgstat_beinit() happens earlier as well, before
authentication.
* pgstat_bestart_security() reports the SSL/GSS status of the
connection, once authentication completes.  Auxiliary processes, for
example, do not need to call this step, hence it is optional.  This
step is called after performing authentication, same as previously.
* pgstat_bestart_final() reports the user and database IDs, takes the
entry out of STATE_STARTING, and reports its application_name.  This is
called as the last step of the three, once authentication completes.

An injection point is added, with a test checking that the "starting"
phase of a backend entry is visible in pg_stat_activity.  Some follow-up
patches are planned to take advantage of this refactoring with more
information provided in backend entries during authentication (LDAP
hanging was a problem for the author, initially).

Author: Jacob Champion <[email protected]>
Reviewed-by: Michael Paquier <[email protected]>
Reviewed-by: Andres Freund <[email protected]>
Discussion: https://postgr.es/m/CAOYmi+=60deN20WDyCoHCiecgivJxr=98s7s7-C8SkXwrCfHXg@mail.gmail.com

Author: michaelpq

doc/src/sgml/monitoring.sgml

@@ -899,6 +899,12 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        Current overall state of this backend.
        Possible values are:
        <itemizedlist>
+        <listitem>
+         <para>
+          <literal>starting</literal>: The backend is in initial startup. Client
+          authentication is performed during this phase.
+         </para>
+        </listitem>
         <listitem>
         <para>
           <literal>active</literal>: The backend is executing a query.

src/backend/postmaster/auxprocess.c

@@ -78,7 +78,8 @@ AuxiliaryProcessMainCommon(void)
 
 	/* Initialize backend status information */
 	pgstat_beinit();
-	pgstat_bestart();
+	pgstat_bestart_initial();
+	pgstat_bestart_final();
 
 	/* register a before-shutdown callback for LWLock cleanup */
 	before_shmem_exit(ShutdownAuxiliaryProcess, 0);

src/backend/utils/activity/backend_status.c

@@ -255,29 +255,22 @@ pgstat_beinit(void)
 
 
 /* ----------
- * pgstat_bestart() -
+ * pgstat_bestart_initial() -
  *
- *	Initialize this backend's entry in the PgBackendStatus array.
- *	Called from InitPostgres.
+ * Initialize this backend's entry in the PgBackendStatus array.  Called
+ * from InitPostgres and AuxiliaryProcessMain.
  *
- *	Apart from auxiliary processes, MyDatabaseId, session userid, and
- *	application_name must already be set (hence, this cannot be combined
- *	with pgstat_beinit).  Note also that we must be inside a transaction
- *	if this isn't an aux process, as we may need to do encoding conversion
- *	on some strings.
- *----------
+ * Clears out a new pgstat entry, initializing it to suitable defaults and
+ * reporting STATE_STARTING.  Backends should continue filling in any
+ * transport security details as needed with pgstat_bestart_security(), and
+ * must finally exit STATE_STARTING by calling pgstat_bestart_final().
+ * ----------
  */
 void
-pgstat_bestart(void)
+pgstat_bestart_initial(void)
 {
 	volatile PgBackendStatus *vbeentry = MyBEEntry;
 	PgBackendStatus lbeentry;
-#ifdef USE_SSL
-	PgBackendSSLStatus lsslstatus;
-#endif
-#ifdef ENABLE_GSS
-	PgBackendGSSStatus lgssstatus;
-#endif
 
 	/* pgstats state must be initialized from pgstat_beinit() */
 	Assert(vbeentry != NULL);
@@ -297,14 +290,6 @@ pgstat_bestart(void)
 		   unvolatize(PgBackendStatus *, vbeentry),
 		   sizeof(PgBackendStatus));
 
-	/* These structs can just start from zeroes each time, though */
-#ifdef USE_SSL
-	memset(&lsslstatus, 0, sizeof(lsslstatus));
-#endif
-#ifdef ENABLE_GSS
-	memset(&lgssstatus, 0, sizeof(lgssstatus));
-#endif
-
 	/*
 	 * Now fill in all the fields of lbeentry, except for strings that are
 	 * out-of-line data.  Those have to be handled separately, below.
@@ -315,15 +300,8 @@ pgstat_bestart(void)
 	lbeentry.st_activity_start_timestamp = 0;
 	lbeentry.st_state_start_timestamp = 0;
 	lbeentry.st_xact_start_timestamp = 0;
-	lbeentry.st_databaseid = MyDatabaseId;
-
-	/* We have userid for client-backends, wal-sender and bgworker processes */
-	if (lbeentry.st_backendType == B_BACKEND
-		|| lbeentry.st_backendType == B_WAL_SENDER
-		|| lbeentry.st_backendType == B_BG_WORKER)
-		lbeentry.st_userid = GetSessionUserId();
-	else
-		lbeentry.st_userid = InvalidOid;
+	lbeentry.st_databaseid = InvalidOid;
+	lbeentry.st_userid = InvalidOid;
 
 	/*
 	 * We may not have a MyProcPort (eg, if this is the autovacuum process).
@@ -336,46 +314,10 @@ pgstat_bestart(void)
 	else
 		MemSet(&lbeentry.st_clientaddr, 0, sizeof(lbeentry.st_clientaddr));
 
-#ifdef USE_SSL
-	if (MyProcPort && MyProcPort->ssl_in_use)
-	{
-		lbeentry.st_ssl = true;
-		lsslstatus.ssl_bits = be_tls_get_cipher_bits(MyProcPort);
-		strlcpy(lsslstatus.ssl_version, be_tls_get_version(MyProcPort), NAMEDATALEN);
-		strlcpy(lsslstatus.ssl_cipher, be_tls_get_cipher(MyProcPort), NAMEDATALEN);
-		be_tls_get_peer_subject_name(MyProcPort, lsslstatus.ssl_client_dn, NAMEDATALEN);
-		be_tls_get_peer_serial(MyProcPort, lsslstatus.ssl_client_serial, NAMEDATALEN);
-		be_tls_get_peer_issuer_name(MyProcPort, lsslstatus.ssl_issuer_dn, NAMEDATALEN);
-	}
-	else
-	{
-		lbeentry.st_ssl = false;
-	}
-#else
 	lbeentry.st_ssl = false;
-#endif
-
-#ifdef ENABLE_GSS
-	if (MyProcPort && MyProcPort->gss != NULL)
-	{
-		const char *princ = be_gssapi_get_princ(MyProcPort);
-
-		lbeentry.st_gss = true;
-		lgssstatus.gss_auth = be_gssapi_get_auth(MyProcPort);
-		lgssstatus.gss_enc = be_gssapi_get_enc(MyProcPort);
-		lgssstatus.gss_delegation = be_gssapi_get_delegation(MyProcPort);
-		if (princ)
-			strlcpy(lgssstatus.gss_princ, princ, NAMEDATALEN);
-	}
-	else
-	{
-		lbeentry.st_gss = false;
-	}
-#else
 	lbeentry.st_gss = false;
-#endif
 
-	lbeentry.st_state = STATE_UNDEFINED;
+	lbeentry.st_state = STATE_STARTING;
 	lbeentry.st_progress_command = PROGRESS_COMMAND_INVALID;
 	lbeentry.st_progress_command_target = InvalidOid;
 	lbeentry.st_query_id = UINT64CONST(0);
@@ -417,14 +359,138 @@ pgstat_bestart(void)
 	lbeentry.st_clienthostname[NAMEDATALEN - 1] = '\0';
 	lbeentry.st_activity_raw[pgstat_track_activity_query_size - 1] = '\0';
 
+	/* These structs can just start from zeroes each time */
 #ifdef USE_SSL
-	memcpy(lbeentry.st_sslstatus, &lsslstatus, sizeof(PgBackendSSLStatus));
+	memset(lbeentry.st_sslstatus, 0, sizeof(PgBackendSSLStatus));
 #endif
 #ifdef ENABLE_GSS
-	memcpy(lbeentry.st_gssstatus, &lgssstatus, sizeof(PgBackendGSSStatus));
+	memset(lbeentry.st_gssstatus, 0, sizeof(PgBackendGSSStatus));
 #endif
 
 	PGSTAT_END_WRITE_ACTIVITY(vbeentry);
+}
+
+/* ----------
+ * pgstat_bestart_security() -
+ *
+ * Fill in SSL and GSS information for the pgstat entry.  This is the second
+ * optional step taken when filling a backend's entry, not required for
+ * auxiliary processes.
+ *
+ * This should only be called from backends with a MyProcPort.
+ * ----------
+ */
+void
+pgstat_bestart_security(void)
+{
+	volatile PgBackendStatus *beentry = MyBEEntry;
+	bool		ssl = false;
+	bool		gss = false;
+#ifdef USE_SSL
+	PgBackendSSLStatus lsslstatus;
+	PgBackendSSLStatus *st_sslstatus;
+#endif
+#ifdef ENABLE_GSS
+	PgBackendGSSStatus lgssstatus;
+	PgBackendGSSStatus *st_gssstatus;
+#endif
+
+	/* pgstats state must be initialized from pgstat_beinit() */
+	Assert(beentry != NULL);
+	Assert(MyProcPort);			/* otherwise there's no point */
+
+#ifdef USE_SSL
+	st_sslstatus = beentry->st_sslstatus;
+	memset(&lsslstatus, 0, sizeof(lsslstatus));
+
+	if (MyProcPort->ssl_in_use)
+	{
+		ssl = true;
+		lsslstatus.ssl_bits = be_tls_get_cipher_bits(MyProcPort);
+		strlcpy(lsslstatus.ssl_version, be_tls_get_version(MyProcPort), NAMEDATALEN);
+		strlcpy(lsslstatus.ssl_cipher, be_tls_get_cipher(MyProcPort), NAMEDATALEN);
+		be_tls_get_peer_subject_name(MyProcPort, lsslstatus.ssl_client_dn, NAMEDATALEN);
+		be_tls_get_peer_serial(MyProcPort, lsslstatus.ssl_client_serial, NAMEDATALEN);
+		be_tls_get_peer_issuer_name(MyProcPort, lsslstatus.ssl_issuer_dn, NAMEDATALEN);
+	}
+#endif
+
+#ifdef ENABLE_GSS
+	st_gssstatus = beentry->st_gssstatus;
+	memset(&lgssstatus, 0, sizeof(lgssstatus));
+
+	if (MyProcPort->gss != NULL)
+	{
+		const char *princ = be_gssapi_get_princ(MyProcPort);
+
+		gss = true;
+		lgssstatus.gss_auth = be_gssapi_get_auth(MyProcPort);
+		lgssstatus.gss_enc = be_gssapi_get_enc(MyProcPort);
+		lgssstatus.gss_delegation = be_gssapi_get_delegation(MyProcPort);
+		if (princ)
+			strlcpy(lgssstatus.gss_princ, princ, NAMEDATALEN);
+	}
+#endif
+
+	/*
+	 * Update my status entry, following the protocol of bumping
+	 * st_changecount before and after.  We use a volatile pointer here to
+	 * ensure the compiler doesn't try to get cute.
+	 */
+	PGSTAT_BEGIN_WRITE_ACTIVITY(beentry);
+
+	beentry->st_ssl = ssl;
+	beentry->st_gss = gss;
+
+#ifdef USE_SSL
+	memcpy(st_sslstatus, &lsslstatus, sizeof(PgBackendSSLStatus));
+#endif
+#ifdef ENABLE_GSS
+	memcpy(st_gssstatus, &lgssstatus, sizeof(PgBackendGSSStatus));
+#endif
+
+	PGSTAT_END_WRITE_ACTIVITY(beentry);
+}
+
+/* ----------
+ * pgstat_bestart_final() -
+ *
+ * Finalizes the state of this backend's entry by filling in the user and
+ * database IDs, clearing STATE_STARTING, and reporting the application_name.
+ *
+ * We must be inside a transaction if this is not an auxiliary process, as
+ * we may need to do encoding conversion.
+ * ----------
+ */
+void
+pgstat_bestart_final(void)
+{
+	volatile PgBackendStatus *beentry = MyBEEntry;
+	Oid			userid;
+
+	/* pgstats state must be initialized from pgstat_beinit() */
+	Assert(beentry != NULL);
+
+	/* We have userid for client-backends, wal-sender and bgworker processes */
+	if (MyBackendType == B_BACKEND
+		|| MyBackendType == B_WAL_SENDER
+		|| MyBackendType == B_BG_WORKER)
+		userid = GetSessionUserId();
+	else
+		userid = InvalidOid;
+
+	/*
+	 * Update my status entry, following the protocol of bumping
+	 * st_changecount before and after.  We use a volatile pointer here to
+	 * ensure the compiler doesn't try to get cute.
+	 */
+	PGSTAT_BEGIN_WRITE_ACTIVITY(beentry);
+
+	beentry->st_databaseid = MyDatabaseId;
+	beentry->st_userid = userid;
+	beentry->st_state = STATE_UNDEFINED;
+
+	PGSTAT_END_WRITE_ACTIVITY(beentry);
 
 	/* Create the backend statistics entry */
 	if (pgstat_tracks_backend_bktype(MyBackendType))

src/backend/utils/adt/pgstatfuncs.c

@@ -393,6 +393,9 @@ pg_stat_get_activity(PG_FUNCTION_ARGS)
 
 			switch (beentry->st_state)
 			{
+				case STATE_STARTING:
+					values[4] = CStringGetTextDatum("starting");
+					break;
 				case STATE_IDLE:
 					values[4] = CStringGetTextDatum("idle");
 					break;

src/backend/utils/init/postinit.c

@@ -59,6 +59,7 @@
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
 #include "utils/guc_hooks.h"
+#include "utils/injection_point.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
 #include "utils/portal.h"
@@ -718,6 +719,20 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	 */
 	InitProcessPhase2();
 
+	/* Initialize status reporting */
+	pgstat_beinit();
+
+	/*
+	 * And initialize an entry in the PgBackendStatus array.  That way, if
+	 * LWLocks or third-party authentication should happen to hang, it is
+	 * possible to retrieve some information about what is going on.
+	 */
+	if (!bootstrap)
+	{
+		pgstat_bestart_initial();
+		INJECTION_POINT("init-pre-auth");
+	}
+
 	/*
 	 * Initialize my entry in the shared-invalidation manager's array of
 	 * per-backend data.
@@ -786,9 +801,6 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
-	/* Initialize status reporting */
-	pgstat_beinit();
-
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
@@ -809,8 +821,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* The autovacuum launcher is done here */
 	if (AmAutoVacuumLauncherProcess())
 	{
-		/* report this backend in the PgBackendStatus array */
-		pgstat_bestart();
+		/* fill in the remainder of this entry in the PgBackendStatus array */
+		pgstat_bestart_final();
 
 		return;
 	}
@@ -884,6 +896,14 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		am_superuser = superuser();
 	}
 
+	/* Report any SSL/GSS details for the session. */
+	if (MyProcPort != NULL)
+	{
+		Assert(!bootstrap);
+
+		pgstat_bestart_security();
+	}
+
 	/*
 	 * Binary upgrades only allowed super-user connections
 	 */
@@ -953,8 +973,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		/* initialize client encoding */
 		InitializeClientEncoding();
 
-		/* report this backend in the PgBackendStatus array */
-		pgstat_bestart();
+		/* fill in the remainder of this entry in the PgBackendStatus array */
+		pgstat_bestart_final();
 
 		/* close the transaction we started above */
 		CommitTransactionCommand();
@@ -997,7 +1017,7 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		 */
 		if (!bootstrap)
 		{
-			pgstat_bestart();
+			pgstat_bestart_final();
 			CommitTransactionCommand();
 		}
 		return;
@@ -1197,9 +1217,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	if ((flags & INIT_PG_LOAD_SESSION_LIBS) != 0)
 		process_session_preload_libraries();
 
-	/* report this backend in the PgBackendStatus array */
+	/* fill in the remainder of this entry in the PgBackendStatus array */
 	if (!bootstrap)
-		pgstat_bestart();
+		pgstat_bestart_final();
 
 	/* close the transaction we started above */
 	if (!bootstrap)