[1/3,v2] opensm SA DB dump/restore: added option to load SA DB once

Commit Message

Yevgeny Kliteynik Nov. 4, 2009, 11 a.m. UTC

None

Patch

diff --git a/opensm/include/opensm/osm_subnet.h b/opensm/include/opensm/osm_subnet.h
index 0302f91..871a833 100644
--- a/opensm/include/opensm/osm_subnet.h
+++ b/opensm/include/opensm/osm_subnet.h
@@ -200,6 +200,7 @@  typedef struct osm_subn_opt {
 	char *ids_guid_file;
 	char *guid_routing_order_file;
 	char *sa_db_file;
+	boolean_t sa_db_load_once;
 	boolean_t do_mesh_analysis;
 	boolean_t exit_on_fatal;
 	boolean_t honor_guid2lid_file;
@@ -411,6 +412,10 @@  typedef struct osm_subn_opt {
 *	sa_db_file
 *		Name of the SA database file.
 *
+*	sa_db_load_once
+*		When TRUE causes sa_db_file to be loaded only at the
+*		first master sweep.
+*
 *	exit_on_fatal
 *		If TRUE (default) - SM will exit on fatal subnet initialization
 *		issues.
diff --git a/opensm/opensm/osm_sa.c b/opensm/opensm/osm_sa.c
index 2db8ba2..e44eab4 100644
--- a/opensm/opensm/osm_sa.c
+++ b/opensm/opensm/osm_sa.c
@@ -912,6 +912,12 @@  int osm_sa_db_file_load(osm_opensm_t * p_osm)
 		return 0;
 	}

+	if (p_osm->subn.opt.sa_db_load_once && !p_osm->subn.first_time_master_sweep) {
+		OSM_LOG(&p_osm->log, OSM_LOG_VERBOSE,
+			"Not first sweep - skip SA DB restore\n");
+		return 0;
+	}
+
 	file = fopen(file_name, "r");
 	if (!file) {
 		OSM_LOG(&p_osm->log, OSM_LOG_ERROR | OSM_LOG_SYS, "ERR 4C02: "
@@ -920,6 +926,10 @@  int osm_sa_db_file_load(osm_opensm_t * p_osm)
 		return -1;
 	}

+	OSM_LOG(&p_osm->log, OSM_LOG_VERBOSE,
+		"Restoring SA DB from file \'%s\'\n",
+		file_name);
+
 	lineno = 0;

 	while (fgets(line, sizeof(line) - 1, file) != NULL) {
@@ -1096,7 +1106,15 @@  int osm_sa_db_file_load(osm_opensm_t * p_osm)
 		}
 	}

-	if (!rereg_clients)
+	/*
+	 * If restoring SA DB is required only once, SM should go
+	 * into the usual mode right after that, which means that
+	 * client re-registration should be required even after
+	 * the restore - there is a chance that OSM died right after
+	 * some MCMember joined MCast group, and his membership
+	 * didn't make it into the SA DB file.
+	 */
+	if (!p_osm->subn.opt.sa_db_load_once && !rereg_clients)
 		p_osm->subn.opt.no_clients_rereg = TRUE;

 _error:
diff --git a/opensm/opensm/osm_subnet.c b/opensm/opensm/osm_subnet.c
index cac5e94..b0ffddd 100644
--- a/opensm/opensm/osm_subnet.c
+++ b/opensm/opensm/osm_subnet.c
@@ -348,6 +348,7 @@  static const opt_rec_t opt_tbl[] = {
 	{ "ids_guid_file", OPT_OFFSET(ids_guid_file), opts_parse_charp, NULL, 0 },
 	{ "guid_routing_order_file", OPT_OFFSET(guid_routing_order_file), opts_parse_charp, NULL, 0 },
 	{ "sa_db_file", OPT_OFFSET(sa_db_file), opts_parse_charp, NULL, 0 },
+	{ "sa_db_load_once", OPT_OFFSET(sa_db_load_once), opts_parse_boolean, NULL, 1 },
 	{ "do_mesh_analysis", OPT_OFFSET(do_mesh_analysis), opts_parse_boolean, NULL, 1 },
 	{ "exit_on_fatal", OPT_OFFSET(exit_on_fatal), opts_parse_boolean, NULL, 1 },
 	{ "honor_guid2lid_file", OPT_OFFSET(honor_guid2lid_file), opts_parse_boolean, NULL, 1 },
@@ -746,6 +747,7 @@  void osm_subn_set_default_opt(IN osm_subn_opt_t * p_opt)
 	p_opt->ids_guid_file = NULL;
 	p_opt->guid_routing_order_file = NULL;
 	p_opt->sa_db_file = NULL;
+	p_opt->sa_db_load_once = FALSE;
 	p_opt->do_mesh_analysis = FALSE;
 	p_opt->exit_on_fatal = TRUE;
 	p_opt->enable_quirks = FALSE;
@@ -1446,6 +1448,11 @@  int osm_subn_output_conf(FILE *out, IN osm_subn_opt_t * p_opts)
 		p_opts->sa_db_file ? p_opts->sa_db_file : null_str);

 	fprintf(out,
+		"# If TRUE causes SA database to be loaded only at\n"
+		"# the first master sweep\nsa_db_load_once %s\n\n",
+		p_opts->sa_db_load_once ? "TRUE" : "FALSE");
+
+	fprintf(out,
 		"#\n# HANDOVER - MULTIPLE SMs OPTIONS\n#\n"
 		"# SM priority used for deciding who is the master\n"
 		"# Range goes from 0 (lowest priority) to 15 (highest).\n"