The Mac appears to have problems with the keepalive support - once keepalive starts, the memory footprint soars. So disable keepalive on the Mac

config/opal_check_os_flavors.m4

@@ -57,6 +57,12 @@ AC_DEFUN([OPAL_CHECK_OS_FLAVORS],
                        [$opal_have_solaris],
                        [Whether or not we have solaris])
 
+    AS_IF([test "$opal_found_apple" = "yes"],
+          [opal_have_mac=1], [opal_have_mac=0])
+    AC_DEFINE_UNQUOTED([OPAL_HAVE_MAC],
+                       [$opal_have_mac],
+                       [Whether or not we are on a Mac])
+    
     # check for sockaddr_in (a good sign we have TCP)
     AC_CHECK_HEADERS([netdb.h netinet/in.h netinet/tcp.h])
     AC_CHECK_TYPES([struct sockaddr_in], 

orte/mca/oob/tcp/oob_tcp_common.c

@@ -72,7 +72,7 @@
 /**
  * Set socket buffering
  */
-
+#if defined(SO_KEEPALIVE) && !OPAL_HAVE_MAC
 static void set_keepalive(int sd)
 {
     int option;
@@ -146,6 +146,7 @@ static void set_keepalive(int sd)
     }
 #endif  // TCP_KEEPCNT
 }
+#endif //SO_KEEPALIVE
 
 void orte_oob_tcp_set_socket_options(int sd)
 {
@@ -181,7 +182,7 @@ void orte_oob_tcp_set_socket_options(int sd)
                             opal_socket_errno);
     }
 #endif
-#if defined(SO_KEEPALIVE)
+#if defined(SO_KEEPALIVE) && !OPAL_HAVE_MAC
     if (0 < mca_oob_tcp_component.keepalive_time) {
         set_keepalive(sd);
     }

orte/mca/oob/tcp/oob_tcp_component.c

@@ -404,7 +404,7 @@ static int tcp_component_register(void)
                                           &mca_oob_tcp_component.disable_ipv6_family);
 #endif
 
-
+#if !OPAL_HAVE_MAC
     mca_oob_tcp_component.keepalive_time = 10;
     (void)mca_base_component_var_register(component, "keepalive_time",
                                           "Idle time in seconds before starting to send keepalives (num <= 0 ----> disable keepalive)",
@@ -427,7 +427,8 @@ static int tcp_component_register(void)
                                           OPAL_INFO_LVL_9,
                                           MCA_BASE_VAR_SCOPE_READONLY,
                                           &mca_oob_tcp_component.keepalive_probes);
-
+#endif
+    
     mca_oob_tcp_component.retry_delay = 0;
     (void)mca_base_component_var_register(component, "retry_delay",
                                           "Time (in sec) to wait before trying to connect to peer again",