opensm/osmeventplugin: added couple of events to monitor SM

PATCH Superseded Yevgeny Kliteynik 2 participants 3 messages Jan 21, 2010 – Jun 1, 2010 2 messages not in the archive InfiniBand

lore

Share & tools

lore

Yevgeny Kliteynik

author

2010-01-21 16:04 UTC #0 lore raw

PATCH 1/1 opensm/osmeventplugin: added couple of events to monitor SM

Hi Sasha,

I've added a couple of new events that allow event plug-in to see what SM is doing, when it is sweeping and when it updates dump files:

OSM_EVENT_ID_L_SWEEP_STARTED,
OSM_EVENT_ID_L_SWEEP_DONE,
OSM_EVENT_ID_H_SWEEP_STARTED,
OSM_EVENT_ID_H_SWEEP_DONE,
OSM_EVENT_ID_REROUTE_DONE,
OSM_EVENT_ID_ENTERING_STANDBY,
OSM_EVENT_ID_SM_PORT_DOWN,
OSM_EVENT_ID_SA_DB_DUMPED

The last event is reported when SA DB was actually dumped. I'm thinking of similar optimization for guid2lid file - it doesn't have to be dumped at the end of each heavy sweep, as many heavy sweeps don't really happen because of nodes appearing/disappearing.

Stay tuned... :)

Signed-off-by Yevgeny Kliteynik <[email protected]>

---
 opensm/include/opensm/osm_event_plugin.h   |   10 +++++++++-
 opensm/opensm/osm_state_mgr.c              |   19 ++++++++++++++++++-
 opensm/osmeventplugin/src/osmeventplugin.c |   24 ++++++++++++++++++++++++
 3 files changed, 51 insertions(+), 2 deletions(-)

opensm/include/opensm/osm_event_plugin.h +9 -1

index 33d1920..f5a57d7 100644
@@ -72,7 +72,15 @@ typedef enum {
 	OSM_EVENT_ID_PORT_SELECT,
 	OSM_EVENT_ID_TRAP,
 	OSM_EVENT_ID_SUBNET_UP,
-	OSM_EVENT_ID_MAX
+	OSM_EVENT_ID_MAX,
+	OSM_EVENT_ID_L_SWEEP_STARTED,
+	OSM_EVENT_ID_L_SWEEP_DONE,
+	OSM_EVENT_ID_H_SWEEP_STARTED,
+	OSM_EVENT_ID_H_SWEEP_DONE,
+	OSM_EVENT_ID_REROUTE_DONE,
+	OSM_EVENT_ID_ENTERING_STANDBY,
+	OSM_EVENT_ID_SM_PORT_DOWN,
+	OSM_EVENT_ID_SA_DB_DUMPED
 } osm_epi_event_id_t;
 
 typedef struct osm_epi_port_id {

opensm/opensm/osm_state_mgr.c +18 -1

index e43463f..7e64f37 100644
@@ -1076,6 +1076,9 @@ static void do_sweep(osm_sm_t * sm)
 	    sm->p_subn->sm_state != IB_SMINFO_STATE_DISCOVERING)
 		return;
 
+	osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_L_SWEEP_STARTED, NULL);
+
 	if (sm->p_subn->coming_out_of_standby)
 		/*
 		 * Need to force re-write of sm_base_lid to all ports

@@ -1111,6 +1114,8 @@ static void do_sweep(osm_sm_t * sm)
 				osm_sa_db_file_dump(sm->p_subn->p_osm);
 			OSM_LOG_MSG_BOX(sm->p_log, OSM_LOG_VERBOSE,
 					"LIGHT SWEEP COMPLETE");
+			osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_L_SWEEP_DONE, NULL);
 			return;
 		}
 	}

@@ -1151,6 +1156,8 @@ static void do_sweep(osm_sm_t * sm)
 		if (!sm->p_subn->subnet_initialization_error) {
 			OSM_LOG_MSG_BOX(sm->p_log, OSM_LOG_VERBOSE,
 					"REROUTE COMPLETE");
+			osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_REROUTE_DONE, NULL);
 			return;
 		}
 	}

@@ -1158,6 +1165,9 @@ static void do_sweep(osm_sm_t * sm)
 	/* go to heavy sweep */
 repeat_discovery:
 
+	osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_H_SWEEP_STARTED, NULL);
+
 	/* First of all - unset all flags */
 	sm->p_subn->force_heavy_sweep = FALSE;
 	sm->p_subn->force_reroute = FALSE;

@@ -1185,6 +1195,8 @@ repeat_discovery:
 
 		/* Move to DISCOVERING state */
 		osm_sm_state_mgr_process(sm, OSM_SM_SIGNAL_DISCOVER);
+		osm_opensm_report_event(sm->p_subn->p_osm,
+					OSM_EVENT_ID_SM_PORT_DOWN, NULL);
 		return;
 	}

@@ -1205,6 +1217,8 @@ repeat_discovery:
 				"ENTERING STANDBY STATE");
 		/* notify master SM about us */
 		osm_send_trap144(sm, 0);
+		osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_ENTERING_STANDBY, NULL);
 		return;
 	}

@@ -1375,7 +1389,10 @@ repeat_discovery:
 
 		if (osm_log_is_active(sm->p_log, OSM_LOG_VERBOSE) ||
 		    sm->p_subn->opt.sa_db_dump)
-			osm_sa_db_file_dump(sm->p_subn->p_osm);
+			if (!osm_sa_db_file_dump(sm->p_subn->p_osm))
+				osm_opensm_report_event(sm->p_subn->p_osm,
+					OSM_EVENT_ID_SA_DB_DUMPED, NULL);
+
 	}
 
 	/*

opensm/osmeventplugin/src/osmeventplugin.c +24 -0

index b4d9ce9..5029be2 100644
@@ -176,6 +176,30 @@ static void report(void *_log, osm_epi_event_id_t event_id, void *event_data)
 	case OSM_EVENT_ID_SUBNET_UP:
 		fprintf(log->log_file, "Subnet up reported\n");
 		break;
+	case OSM_EVENT_ID_L_SWEEP_STARTED:
+		fprintf(log->log_file, "Light sweep started\n");
+		break;
+	case OSM_EVENT_ID_L_SWEEP_DONE:
+		fprintf(log->log_file, "Light sweep completed\n");
+		break;
+	case OSM_EVENT_ID_H_SWEEP_STARTED:
+		fprintf(log->log_file, "Heavy sweep started\n");
+		break;
+	case OSM_EVENT_ID_H_SWEEP_DONE:
+		fprintf(log->log_file, "Heavy sweep completed\n");
+		break;
+	case OSM_EVENT_ID_REROUTE_DONE:
+		fprintf(log->log_file, "Re-route completed\n");
+		break;
+	case OSM_EVENT_ID_ENTERING_STANDBY:
+		fprintf(log->log_file, "Entering stand-by state\n");
+		break;
+	case OSM_EVENT_ID_SM_PORT_DOWN:
+		fprintf(log->log_file, "SM port is down\n");
+		break;
+	case OSM_EVENT_ID_SA_DB_DUMPED:
+		fprintf(log->log_file, "SA DB dump file updated\n");
+		break;
 	case OSM_EVENT_ID_MAX:
 	default:
 		osm_log(log->osmlog, OSM_LOG_ERROR,

Signature · 6 lines

1.5.1.4

--
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

A message that is not in the archive (sent off-list or not yet received): 4B587AFA.9020102-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org

Yevgeny Kliteynik

author

2010-04-07 09:20 UTC #2 lore raw

PATCH v2 1/1 opensm/osmeventplugin: added couple of events to monitor SM

Hi Sasha,

I've added a couple of new events that allow event plug-in to see what SM is doing, when it is sweeping and when it updates dump files:

Signed-off-by Yevgeny Kliteynik <[email protected]>

---

Changes from V1:
- added reporting OSM_EVENT_ID_H_SWEEP_DONE event
- rebased to latest master

 opensm/include/opensm/osm_event_plugin.h   |   10 +++++++++-
 opensm/opensm/osm_state_mgr.c              |   22 +++++++++++++++++++++-
 opensm/osmeventplugin/src/osmeventplugin.c |   24 ++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 2 deletions(-)

opensm/include/opensm/osm_event_plugin.h +9 -1

index 33d1920..f5a57d7 100644
@@ -72,7 +72,15 @@ typedef enum {
 	OSM_EVENT_ID_PORT_SELECT,
 	OSM_EVENT_ID_TRAP,
 	OSM_EVENT_ID_SUBNET_UP,
-	OSM_EVENT_ID_MAX
+	OSM_EVENT_ID_MAX,
+	OSM_EVENT_ID_L_SWEEP_STARTED,
+	OSM_EVENT_ID_L_SWEEP_DONE,
+	OSM_EVENT_ID_H_SWEEP_STARTED,
+	OSM_EVENT_ID_H_SWEEP_DONE,
+	OSM_EVENT_ID_REROUTE_DONE,
+	OSM_EVENT_ID_ENTERING_STANDBY,
+	OSM_EVENT_ID_SM_PORT_DOWN,
+	OSM_EVENT_ID_SA_DB_DUMPED
 } osm_epi_event_id_t;
 
 typedef struct osm_epi_port_id {

opensm/opensm/osm_state_mgr.c +21 -1

index e43463f..d5dff14 100644
@@ -1076,6 +1076,9 @@ static void do_sweep(osm_sm_t * sm)
 	    sm->p_subn->sm_state != IB_SMINFO_STATE_DISCOVERING)
 		return;
 
+	osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_L_SWEEP_STARTED, NULL);
+
 	if (sm->p_subn->coming_out_of_standby)
 		/*
 		 * Need to force re-write of sm_base_lid to all ports

@@ -1111,6 +1114,8 @@ static void do_sweep(osm_sm_t * sm)
 				osm_sa_db_file_dump(sm->p_subn->p_osm);
 			OSM_LOG_MSG_BOX(sm->p_log, OSM_LOG_VERBOSE,
 					"LIGHT SWEEP COMPLETE");
+			osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_L_SWEEP_DONE, NULL);
 			return;
 		}
 	}

@@ -1151,6 +1156,8 @@ static void do_sweep(osm_sm_t * sm)
 		if (!sm->p_subn->subnet_initialization_error) {
 			OSM_LOG_MSG_BOX(sm->p_log, OSM_LOG_VERBOSE,
 					"REROUTE COMPLETE");
+			osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_REROUTE_DONE, NULL);
 			return;
 		}
 	}

@@ -1158,6 +1165,9 @@ static void do_sweep(osm_sm_t * sm)
 	/* go to heavy sweep */
 repeat_discovery:
 
+	osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_H_SWEEP_STARTED, NULL);
+
 	/* First of all - unset all flags */
 	sm->p_subn->force_heavy_sweep = FALSE;
 	sm->p_subn->force_reroute = FALSE;

@@ -1185,6 +1195,8 @@ repeat_discovery:
 
 		/* Move to DISCOVERING state */
 		osm_sm_state_mgr_process(sm, OSM_SM_SIGNAL_DISCOVER);
+		osm_opensm_report_event(sm->p_subn->p_osm,
+					OSM_EVENT_ID_SM_PORT_DOWN, NULL);
 		return;
 	}

@@ -1205,6 +1217,8 @@ repeat_discovery:
 				"ENTERING STANDBY STATE");
 		/* notify master SM about us */
 		osm_send_trap144(sm, 0);
+		osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_ENTERING_STANDBY, NULL);
 		return;
 	}

@@ -1212,6 +1226,9 @@ repeat_discovery:
 	if (sm->p_subn->force_heavy_sweep)
 		goto repeat_discovery;
 
+	osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_H_SWEEP_DONE, NULL);
+
 	OSM_LOG_MSG_BOX(sm->p_log, OSM_LOG_VERBOSE, "HEAVY SWEEP COMPLETE");
 
 	/* If we are MASTER - get the highest remote_sm, and

@@ -1375,7 +1392,10 @@ repeat_discovery:
 
 		if (osm_log_is_active(sm->p_log, OSM_LOG_VERBOSE) ||
 		    sm->p_subn->opt.sa_db_dump)
-			osm_sa_db_file_dump(sm->p_subn->p_osm);
+			if (!osm_sa_db_file_dump(sm->p_subn->p_osm))
+				osm_opensm_report_event(sm->p_subn->p_osm,
+					OSM_EVENT_ID_SA_DB_DUMPED, NULL);
+
 	}
 
 	/*

opensm/osmeventplugin/src/osmeventplugin.c +24 -0

index b4d9ce9..5029be2 100644
@@ -176,6 +176,30 @@ static void report(void *_log, osm_epi_event_id_t event_id, void *event_data)
 	case OSM_EVENT_ID_SUBNET_UP:
 		fprintf(log->log_file, "Subnet up reported\n");
 		break;
+	case OSM_EVENT_ID_L_SWEEP_STARTED:
+		fprintf(log->log_file, "Light sweep started\n");
+		break;
+	case OSM_EVENT_ID_L_SWEEP_DONE:
+		fprintf(log->log_file, "Light sweep completed\n");
+		break;
+	case OSM_EVENT_ID_H_SWEEP_STARTED:
+		fprintf(log->log_file, "Heavy sweep started\n");
+		break;
+	case OSM_EVENT_ID_H_SWEEP_DONE:
+		fprintf(log->log_file, "Heavy sweep completed\n");
+		break;
+	case OSM_EVENT_ID_REROUTE_DONE:
+		fprintf(log->log_file, "Re-route completed\n");
+		break;
+	case OSM_EVENT_ID_ENTERING_STANDBY:
+		fprintf(log->log_file, "Entering stand-by state\n");
+		break;
+	case OSM_EVENT_ID_SM_PORT_DOWN:
+		fprintf(log->log_file, "SM port is down\n");
+		break;
+	case OSM_EVENT_ID_SA_DB_DUMPED:
+		fprintf(log->log_file, "SA DB dump file updated\n");
+		break;
 	case OSM_EVENT_ID_MAX:
 	default:
 		osm_log(log->osmlog, OSM_LOG_ERROR,

Signature · 7 lines

1.5.1.4


--
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

A message that is not in the archive (sent off-list or not yet received): 4BBC4E4B.7080705-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org

Sasha Khapyorsky

2010-06-01 18:37 UTC #4 lore raw

Hi Yevgeny,

Quoted 14 lines · Yevgeny Kliteynik

I've added a couple of new events that allow event plug-in to see what SM is doing, when it is sweeping and when it updates dump files:
OSM_EVENT_ID_L_SWEEP_STARTED,
OSM_EVENT_ID_L_SWEEP_DONE,
OSM_EVENT_ID_H_SWEEP_STARTED,
OSM_EVENT_ID_H_SWEEP_DONE,
OSM_EVENT_ID_REROUTE_DONE,
OSM_EVENT_ID_ENTERING_STANDBY,
OSM_EVENT_ID_SM_PORT_DOWN,
OSM_EVENT_ID_SA_DB_DUMPED

Quoted 5 lines

The last event is reported when SA DB was actually dumped. I'm thinking of similar optimization for guid2lid file - it doesn't have to be dumped at the end of each heavy sweep, as many heavy sweeps don't really happen because of nodes appearing/disappearing.

I don't think that having a lot of events and spamming OpenSM core code with osm_opensm_report_event() calls were an original goals. The plugin interface is done so that it has full access to OpenSM internal data structures, etc.. So only *really* important things (such as SUBNET UP) will be transferred as events.

Also when sending the patch like this it would be really nice to have some description about why this and that events are needed, where this will be used, etc..

Sasha

Quoted 160 lines

Signed-off-by Yevgeny Kliteynik <[email protected]>

---

Changes from V1:
- added reporting OSM_EVENT_ID_H_SWEEP_DONE event
- rebased to latest master

 opensm/include/opensm/osm_event_plugin.h   |   10 +++++++++-
 opensm/opensm/osm_state_mgr.c              |   22 +++++++++++++++++++++-
 opensm/osmeventplugin/src/osmeventplugin.c |   24 ++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 2 deletions(-)

opensm/include/opensm/osm_event_plugin.h +9 -1

index 33d1920..f5a57d7 100644
@@ -72,7 +72,15 @@ typedef enum {
 	OSM_EVENT_ID_PORT_SELECT,
 	OSM_EVENT_ID_TRAP,
 	OSM_EVENT_ID_SUBNET_UP,
-	OSM_EVENT_ID_MAX
+	OSM_EVENT_ID_MAX,
+	OSM_EVENT_ID_L_SWEEP_STARTED,
+	OSM_EVENT_ID_L_SWEEP_DONE,
+	OSM_EVENT_ID_H_SWEEP_STARTED,
+	OSM_EVENT_ID_H_SWEEP_DONE,
+	OSM_EVENT_ID_REROUTE_DONE,
+	OSM_EVENT_ID_ENTERING_STANDBY,
+	OSM_EVENT_ID_SM_PORT_DOWN,
+	OSM_EVENT_ID_SA_DB_DUMPED
 } osm_epi_event_id_t;
 
 typedef struct osm_epi_port_id {

opensm/opensm/osm_state_mgr.c +21 -1

index e43463f..d5dff14 100644
@@ -1076,6 +1076,9 @@ static void do_sweep(osm_sm_t * sm)
 	    sm->p_subn->sm_state != IB_SMINFO_STATE_DISCOVERING)
 		return;
 
+	osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_L_SWEEP_STARTED, NULL);
+
 	if (sm->p_subn->coming_out_of_standby)
 		/*
 		 * Need to force re-write of sm_base_lid to all ports

@@ -1111,6 +1114,8 @@ static void do_sweep(osm_sm_t * sm)
 				osm_sa_db_file_dump(sm->p_subn->p_osm);
 			OSM_LOG_MSG_BOX(sm->p_log, OSM_LOG_VERBOSE,
 					"LIGHT SWEEP COMPLETE");
+			osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_L_SWEEP_DONE, NULL);
 			return;
 		}
 	}

@@ -1151,6 +1156,8 @@ static void do_sweep(osm_sm_t * sm)
 		if (!sm->p_subn->subnet_initialization_error) {
 			OSM_LOG_MSG_BOX(sm->p_log, OSM_LOG_VERBOSE,
 					"REROUTE COMPLETE");
+			osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_REROUTE_DONE, NULL);
 			return;
 		}
 	}

@@ -1158,6 +1165,9 @@ static void do_sweep(osm_sm_t * sm)
 	/* go to heavy sweep */
 repeat_discovery:
 
+	osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_H_SWEEP_STARTED, NULL);
+
 	/* First of all - unset all flags */
 	sm->p_subn->force_heavy_sweep = FALSE;
 	sm->p_subn->force_reroute = FALSE;

@@ -1185,6 +1195,8 @@ repeat_discovery:
 
 		/* Move to DISCOVERING state */
 		osm_sm_state_mgr_process(sm, OSM_SM_SIGNAL_DISCOVER);
+		osm_opensm_report_event(sm->p_subn->p_osm,
+					OSM_EVENT_ID_SM_PORT_DOWN, NULL);
 		return;
 	}

@@ -1205,6 +1217,8 @@ repeat_discovery:
 				"ENTERING STANDBY STATE");
 		/* notify master SM about us */
 		osm_send_trap144(sm, 0);
+		osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_ENTERING_STANDBY, NULL);
 		return;
 	}

@@ -1212,6 +1226,9 @@ repeat_discovery:
 	if (sm->p_subn->force_heavy_sweep)
 		goto repeat_discovery;
 
+	osm_opensm_report_event(sm->p_subn->p_osm,
+				OSM_EVENT_ID_H_SWEEP_DONE, NULL);
+
 	OSM_LOG_MSG_BOX(sm->p_log, OSM_LOG_VERBOSE, "HEAVY SWEEP COMPLETE");
 
 	/* If we are MASTER - get the highest remote_sm, and

@@ -1375,7 +1392,10 @@ repeat_discovery:
 
 		if (osm_log_is_active(sm->p_log, OSM_LOG_VERBOSE) ||
 		    sm->p_subn->opt.sa_db_dump)
-			osm_sa_db_file_dump(sm->p_subn->p_osm);
+			if (!osm_sa_db_file_dump(sm->p_subn->p_osm))
+				osm_opensm_report_event(sm->p_subn->p_osm,
+					OSM_EVENT_ID_SA_DB_DUMPED, NULL);
+
 	}
 
 	/*

opensm/osmeventplugin/src/osmeventplugin.c +24 -0

index b4d9ce9..5029be2 100644
@@ -176,6 +176,30 @@ static void report(void *_log, osm_epi_event_id_t event_id, void *event_data)
 	case OSM_EVENT_ID_SUBNET_UP:
 		fprintf(log->log_file, "Subnet up reported\n");
 		break;
+	case OSM_EVENT_ID_L_SWEEP_STARTED:
+		fprintf(log->log_file, "Light sweep started\n");
+		break;
+	case OSM_EVENT_ID_L_SWEEP_DONE:
+		fprintf(log->log_file, "Light sweep completed\n");
+		break;
+	case OSM_EVENT_ID_H_SWEEP_STARTED:
+		fprintf(log->log_file, "Heavy sweep started\n");
+		break;
+	case OSM_EVENT_ID_H_SWEEP_DONE:
+		fprintf(log->log_file, "Heavy sweep completed\n");
+		break;
+	case OSM_EVENT_ID_REROUTE_DONE:
+		fprintf(log->log_file, "Re-route completed\n");
+		break;
+	case OSM_EVENT_ID_ENTERING_STANDBY:
+		fprintf(log->log_file, "Entering stand-by state\n");
+		break;
+	case OSM_EVENT_ID_SM_PORT_DOWN:
+		fprintf(log->log_file, "SM port is down\n");
+		break;
+	case OSM_EVENT_ID_SA_DB_DUMPED:
+		fprintf(log->log_file, "SA DB dump file updated\n");
+		break;
 	case OSM_EVENT_ID_MAX:
 	default:
 		osm_log(log->osmlog, OSM_LOG_ERROR,

Signature · 7 lines

1.5.1.4


--
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

--
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