opensm/osm_lid_mgr: use 'first_time_master_sweep' flag

PATCH In review Sasha Khapyorsky 1 participant 5 messages Apr 26, 2010 – May 22, 2010 InfiniBand

Share & tools

Sasha Khapyorsky

author

2010-04-26 10:48 UTC #0 lore raw

PATCH 1/1 opensm/osm_lid_mgr: use 'first_time_master_sweep' flag

Use 'first_time_master_sweep' as initial sweep indication instead of 'coming_out_of_standby'. The last flag will be set only when OpenSM previously was in standby state, this doesn't cover some other cases such as temporary SM port disconnection.

Signed-off-by Sasha Khapyorsky <sashak-smomgflXvOZWk0Htik3J/[email protected]>

---
 opensm/opensm/osm_lid_mgr.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

opensm/opensm/osm_lid_mgr.c +1 -1

index 0fd3b20..84f3508 100644
@@ -304,7 +304,7 @@ static int lid_mgr_init_sweep(IN osm_lid_mgr_t * p_mgr)
 	   info we might have.
 	   Do this only if the honor_guid2lid_file option is FALSE. If not, then
 	   need to honor this file. */
-	if (p_mgr->p_subn->coming_out_of_standby == TRUE) {
+	if (p_mgr->p_subn->first_time_master_sweep == TRUE) {
 		osm_db_clear(p_mgr->p_g2l);
 		if (p_mgr->p_subn->opt.honor_guid2lid_file == FALSE) {
 			OSM_LOG(p_mgr->p_log, OSM_LOG_DEBUG,

Signature · 6 lines

1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Sasha Khapyorsky

author

2010-04-26 12:16 UTC #1 lore raw

PATCH 1/1 opensm/osm_lid_mgr: fix couple of duplicate LIDs bugs

Fix couple of cases where duplicated LID generation is possible:

1) When guid2lid db is reloaded after standby or disconnected SM port state (discovering) it must be validated, so content of used_lids[] array (used as reference during LID assignment) will be consistent with loaded guid2lid db.

2) When port for which LIDs were assigned exists in guid2lid db already its record should be updated due to possibly changed LIDs, LMC, etc..

There still be more potential cases where LIDs could be duplicated. So this patch fixes just part of them. I'm continuing an investigation.

Signed-off-by Sasha Khapyorsky <sashak-smomgflXvOZWk0Htik3J/[email protected]>

---
 opensm/opensm/osm_lid_mgr.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

opensm/opensm/osm_lid_mgr.c +2 -2

index 84f3508..08d54f0 100644
@@ -319,6 +319,7 @@ static int lid_mgr_init_sweep(IN osm_lid_mgr_t * p_mgr)
 					"ERR 0306: "
 					"Error restoring Guid-to-Lid "
 					"persistent database. Ignoring it\n");
+			lid_mgr_validate_db(p_mgr);
 		}
 	}

@@ -710,7 +711,7 @@ static int lid_mgr_get_port_lid(IN osm_lid_mgr_t * p_mgr,
 			/* we still need to send the setting to the target port */
 			lid_changed = 1;
 		}
-		goto Exit;
+		goto NewLidSet;
 	} else
 		OSM_LOG(p_mgr->p_log, OSM_LOG_DEBUG,
 			"0x%016" PRIx64 " has no persistent lid assigned\n",

@@ -764,7 +765,6 @@ NewLidSet:
 	for (lid = *p_min_lid; lid <= *p_max_lid; lid++)
 		p_mgr->used_lids[lid] = 1;
 
-Exit:
 	/* make sure the assigned lids are marked in port_lid_tbl */
 	for (lid = *p_min_lid; lid <= *p_max_lid; lid++)
 		cl_ptr_vector_set(&p_mgr->p_subn->port_lid_tbl, lid, p_port);

Signature · 6 lines

1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Sasha Khapyorsky

author

2010-04-26 13:02 UTC #2 lore raw

PATCH v2 1/1 opensm/osm_lid_mgr: fix couple of duplicate LIDs bugs

Fix couple of cases where duplicated LID generation is possible:

2) When port for which LIDs were assigned exists in guid2lid db already its record should be updated due to possibly changed LIDs, LMC, etc..

There still be more potential cases where LIDs could be duplicated. So this patch fixes just part of them. I'm continuing an investigation.

Signed-off-by Sasha Khapyorsky <sashak-smomgflXvOZWk0Htik3J/[email protected]>

---
 opensm/opensm/osm_lid_mgr.c |   10 +++++-----
 1 files changed, 5 insertions(+), 5 deletions(-)

v2: With guid2lid db reset (osm_db_clear()) clean also user_lids[] array.

opensm/opensm/osm_lid_mgr.c +5 -5

index 84f3508..7da4eb0 100644
@@ -306,11 +306,11 @@ static int lid_mgr_init_sweep(IN osm_lid_mgr_t * p_mgr)
 	   need to honor this file. */
 	if (p_mgr->p_subn->first_time_master_sweep == TRUE) {
 		osm_db_clear(p_mgr->p_g2l);
-		if (p_mgr->p_subn->opt.honor_guid2lid_file == FALSE) {
+		memset(p_mgr->used_lids, 0, sizeof(p_mgr->used_lids));
+		if (p_mgr->p_subn->opt.honor_guid2lid_file == FALSE)
 			OSM_LOG(p_mgr->p_log, OSM_LOG_DEBUG,
 				"Ignore guid2lid file when coming out of standby\n");
-			memset(p_mgr->used_lids, 0, sizeof(p_mgr->used_lids));
-		} else {
+		else {
 			OSM_LOG(p_mgr->p_log, OSM_LOG_DEBUG,
 				"Honor current guid2lid file when coming out "
 				"of standby\n");

@@ -319,6 +319,7 @@ static int lid_mgr_init_sweep(IN osm_lid_mgr_t * p_mgr)
 					"ERR 0306: "
 					"Error restoring Guid-to-Lid "
 					"persistent database. Ignoring it\n");
+			lid_mgr_validate_db(p_mgr);
 		}
 	}

@@ -710,7 +711,7 @@ static int lid_mgr_get_port_lid(IN osm_lid_mgr_t * p_mgr,
 			/* we still need to send the setting to the target port */
 			lid_changed = 1;
 		}
-		goto Exit;
+		goto NewLidSet;
 	} else
 		OSM_LOG(p_mgr->p_log, OSM_LOG_DEBUG,
 			"0x%016" PRIx64 " has no persistent lid assigned\n",

@@ -764,7 +765,6 @@ NewLidSet:
 	for (lid = *p_min_lid; lid <= *p_max_lid; lid++)
 		p_mgr->used_lids[lid] = 1;
 
-Exit:
 	/* make sure the assigned lids are marked in port_lid_tbl */
 	for (lid = *p_min_lid; lid <= *p_max_lid; lid++)
 		cl_ptr_vector_set(&p_mgr->p_subn->port_lid_tbl, lid, p_port);

Signature · 6 lines

1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Sasha Khapyorsky

author

2010-05-22 13:09 UTC #3 lore raw

In reply to Sasha Khapyorsky

Quoted 16 lines · Sasha Khapyorsky

Use 'first_time_master_sweep' as initial sweep indication instead of 'coming_out_of_standby'. The last flag will be set only when OpenSM previously was in standby state, this doesn't cover some other cases such as temporary SM port disconnection.
Signed-off-by Sasha Khapyorsky <sashak-smomgflXvOZWk0Htik3J/[email protected]>
---
 opensm/opensm/osm_lid_mgr.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)
opensm/opensm/osm_lid_mgr.c +0 -0
index 0fd3b20..84f3508 100644

opensm/opensm/osm_lid_mgr.c static int lid_mgr_init_sweep(IN osm_lid_mgr_t * p_mgr) · line 307

Quoted 5 lines

opensm/opensm/osm_lid_mgr.c +1 -1

@@ -304,7 +304,7 @@ static int lid_mgr_init_sweep(IN osm_lid_mgr_t * p_mgr)
 	   info we might have.
 	   Do this only if the honor_guid2lid_file option is FALSE. If not, then
 	   need to honor this file. */
-	if (p_mgr->p_subn->coming_out_of_standby == TRUE) {
+	if (p_mgr->p_subn->first_time_master_sweep == TRUE) {

Actually this changes the current behavior. Flag 'coming_out_of_standby' is not set on first initial sweep and 'first_time_master_sweep' is. So I'm reverting this patch yet up to more cleanup will be performed.

Sasha

Quoted 6 lines

opensm/opensm/osm_lid_mgr.c +0 -0

 		osm_db_clear(p_mgr->p_g2l);
 		if (p_mgr->p_subn->opt.honor_guid2lid_file == FALSE) {
 			OSM_LOG(p_mgr->p_log, OSM_LOG_DEBUG,

Signature · 1 line

1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

Sasha Khapyorsky

author

2010-05-22 13:16 UTC #4 lore raw

PATCH 1/1 opensm/osm_lid_mgr: revert 'coming_out_of_standby' replacement patch

This reverts the patch where 'coming_out_of_standby' flag was replaced by 'first_time_master_sweep'. It is probably a good idea in general to merge those, but right now it will change the default lid manager behavior, since it will ignore guid2lid file in initial sweep.

Signed-off-by Sasha Khapyorsky <sashak-smomgflXvOZWk0Htik3J/[email protected]>

---
 opensm/opensm/osm_lid_mgr.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

opensm/opensm/osm_lid_mgr.c +1 -1

index 7da4eb0..97b1de6 100644
@@ -304,7 +304,7 @@ static int lid_mgr_init_sweep(IN osm_lid_mgr_t * p_mgr)
 	   info we might have.
 	   Do this only if the honor_guid2lid_file option is FALSE. If not, then
 	   need to honor this file. */
-	if (p_mgr->p_subn->first_time_master_sweep == TRUE) {
+	if (p_mgr->p_subn->coming_out_of_standby == TRUE) {
 		osm_db_clear(p_mgr->p_g2l);
 		memset(p_mgr->used_lids, 0, sizeof(p_mgr->used_lids));
 		if (p_mgr->p_subn->opt.honor_guid2lid_file == FALSE)

Signature · 6 lines

1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html