DAPL v2.0: scm, ucm: MPI spawn test on oversubcribed server taking excessive time to complete

Commit Message

Arlin Davis Oct. 22, 2010, 8:59 p.m. UTC

None

Patch

diff --git a/dapl/openib_scm/cm.c b/dapl/openib_scm/cm.c
index 56d4c73..f82d0ff 100644
--- a/dapl/openib_scm/cm.c
+++ b/dapl/openib_scm/cm.c
@@ -463,10 +463,8 @@  DAT_RETURN dapli_socket_disconnect(dp_ib_cm_handle_t cm_ptr)
 		return DAT_SUCCESS;
 	}
 	cm_ptr->state = DCM_DISCONNECTED;
-	dapl_os_unlock(&cm_ptr->lock);
-	
-	/* send disc date, close socket, schedule destroy */
 	send(cm_ptr->socket, (char *)&disc_data, sizeof(disc_data), 0);
+	dapl_os_unlock(&cm_ptr->lock);
 
 	/* disconnect events for RC's only */
 	if (cm_ptr->ep->param.ep_attr.service_type == DAT_SERVICE_TYPE_RC) {
@@ -1812,7 +1810,13 @@  void cr_thread(void *arg)
 						dapl_os_unlock(&cr->lock);
 						dapli_socket_disconnect(cr);
 						break;
+					case DCM_DISCONNECTED:
+						cr->state = DCM_FREE;
+						dapl_os_unlock(&cr->lock);
+						break;
 					default:
+						if (ret == DAPL_FD_ERROR)
+							cr->state = DCM_FREE;
 						dapl_os_unlock(&cr->lock);
 						break;
 					}
diff --git a/dapl/openib_ucm/cm.c b/dapl/openib_ucm/cm.c
index 3a518c3..0fe5e2e 100644
--- a/dapl/openib_ucm/cm.c
+++ b/dapl/openib_ucm/cm.c
@@ -544,8 +544,9 @@  retry:
 		msg = (ib_cm_msg_t*) (uintptr_t) wc[i].wr_id;
 
 		dapl_dbg_log(DAPL_DBG_TYPE_CM, 
-			     " ucm_recv: wc status=%d, ln=%d id=%p sqp=%x\n", 
-			     wc[i].status, wc[i].byte_len, 
+			     " ucm_recv: stat=%d op=%s ln=%d id=%p sqp=%x\n",
+			     wc[i].status, dapl_cm_op_str(ntohs(msg->op)),
+			     wc[i].byte_len,
 			     (void*)wc[i].wr_id, wc[i].src_qp);
 
 		/* validate CM message, version */
@@ -609,7 +610,7 @@  static int ucm_send(ib_hca_transport_t *tp, ib_cm_msg_t *msg, DAT_PVOID p_data,
         sge.addr = (uintptr_t)smsg;
 
 	dapl_dbg_log(DAPL_DBG_TYPE_CM, 
-		" ucm_send: op %s ln %d lid %x c_qpn %x rport %s\n", 
+		" ucm_send: op %s ln %d lid %x c_qpn %x rport %x\n",
 		dapl_cm_op_str(ntohs(smsg->op)), 
 		sge.length, htons(smsg->daddr.ib.lid), 
 		htonl(smsg->dqpn), htons(smsg->dport));
@@ -818,7 +819,7 @@  static void ucm_disconnect_final(dp_ib_cm_handle_t cm)
 		return;
 
 	dapl_os_lock(&cm->lock);
-	if (cm->state == DCM_DISCONNECTED) {
+	if ((cm->state == DCM_DISCONNECTED) || (cm->state == DCM_FREE)) {
 		dapl_os_unlock(&cm->lock);
 		return;
 	}