>> I assume that both of you have seen the reply from Aleksej Saushev,
>> who seems to be the bloke looking after the port of OpenMPI to the
>> NetBSD platform.
>>
>>
>> Aleksej suggested some mods he had partially looked at, in
>>
>> opal/util/if.c
>
> Nope - didn't see anything like that :-/
Aah, just realised that that portion of Aleksej's comments were in
an offlist posting.
It'll be interesting to compare which files Jeff thinks the munging
needs to be done in.
> Since none of us (to my knowledge) have ever looked at NetBSD (in
> fact, I never heard of it before), I would not be surprised to find
> that there are going to be problems encountered in such a port.
> There always are.
I have not had a chance to start looking at this in earnest myself
yet but I include the relevant info here, in case experience with
porting to those platforms you have heard of suggests something
obvious.
==
OpenMPI uses incorrect way to access network interface information,
what works for FreeBSD (by an accident) doesn't work for NetBSD,
we should rewrite respective parts of opal/util/if.c file to use BSD API,
that is getifaddrs(3) even when walking over IPv4 addresses.
My old "draft" (which is simply pointer to that part) is below,
I don't remember which OpenMPI version it is based on, I hope that you
find the place yourself. If not, ask or wait. I do hope to find some
time for OpenMPI next week after I finish reworking Fortran support in
pkgsrc. Stay tuned.
--- opal/util/if.c.orig 2009-03-18 18:42:39.000000000 +0300
+++ opal/util/if.c 2009-03-21 22:14:44.000000000 +0300
@@ -164,6 +164,135 @@
false, false, (int)false, &sd);
do_not_resolve = OPAL_INT_TO_BOOL(sd);
+#if defined( __NetBSD__) || defined(__OpenBSD__) || defined(__FreeBSD__)
+/* || defined(__386BSD__) || defined(__bsdi__) || defined(__APPLE__) */
+/* || defined(__linux__) */
+
+ {
+ struct ifaddrs **ifadd_list;
+ struct ifaddrs *cur_ifaddrs;
+ struct sockaddr_in6* sin_addr;
+
+ /*
+ * the manpage claims that getifaddrs() allocates the memory,
+ * and freeifaddrs() is later used to release the allocated memory.
+ * however, without this malloc the call to getifaddrs() segfaults
+ */
+ ifadd_list = (struct ifaddrs **) malloc(sizeof(struct ifaddrs*));
+
+ /* create the linked list of ifaddrs structs */
+ if(getifaddrs(ifadd_list) < 0) {
+ opal_output(0, "opal_ifinit: getifaddrs() failed with
error=%d\n",
+ errno);
+ return OPAL_ERROR;
+ }
+
+ for(cur_ifaddrs = *ifadd_list; NULL != cur_ifaddrs;
+ cur_ifaddrs = cur_ifaddrs->ifa_next) {
+
+ opal_if_t intf;
+ opal_if_t *intf_ptr;
+ struct in6_addr a6;
+
+ /* skip non-ipv6 interface addresses */
+ if(AF_INET6 != cur_ifaddrs->ifa_addr->sa_family) {
+#if 0
+ printf("skipping non-ipv6 interface %s.\n",
cur_ifaddrs->ifa_name);
+#endif
+ continue;
+ }
+
+ /* skip interface if it is down (IFF_UP not set) */
+ if(0 == (cur_ifaddrs->ifa_flags & IFF_UP)) {
+#if 0
+ printf("skipping non-up interface %s.\n",
cur_ifaddrs->ifa_name);
+#endif
+ continue;
+ }
+
+ /* skip interface if it is a loopback device (IFF_LOOPBACK
set) */
+ /* or if it is a point-to-point interface */
+ /* TODO: do we really skip p2p? */
+ if(0 != (cur_ifaddrs->ifa_flags & IFF_LOOPBACK)
+ || 0!= (cur_ifaddrs->ifa_flags & IFF_POINTOPOINT)) {
+#if 0
+ printf("skipping loopback interface %s.\n",
cur_ifaddrs->ifa_name);
+#endif
+ continue;
+ }
+
+ sin_addr = (struct sockaddr_in6 *) cur_ifaddrs->ifa_addr;
+
+ /*
+ * skip IPv6 address starting with fe80:, as this is supposed
to be
+ * link-local scope. sockaddr_in6->sin6_scope_id doesn't
always work
+ * TODO: test whether scope id is set to a sensible value on
+ * linux and/or bsd (including osx)
+ *
+ * MacOSX: fe80::... has a scope of 0, but ifconfig -a shows
+ * a scope of 4 on that particular machine,
+ * so the scope returned by getifaddrs() isn't working properly
+ */
+
+ if((IN6_IS_ADDR_LINKLOCAL (&sin_addr->sin6_addr))) {
+#if 0
+ printf("skipping link-local ipv6 address on interface \
+ %s with scope %d.\n",
+ cur_ifaddrs->ifa_name, sin_addr->sin6_scope_id);
+#endif
+ continue;
+ }
+
+ OMPI_DEBUG_ZERO(intf);
+ OBJ_CONSTRUCT(&intf, opal_list_item_t);
+#if 0
+ char *addr_name = (char *) malloc(48*sizeof(char));
+ inet_ntop(AF_INET6, &sin_addr->sin6_addr, addr_name,
48*sizeof(char));
+ opal_output(0, "ipv6 capable interface %s discovered, address
%s.\n",
+ cur_ifaddrs->ifa_name, addr_name);
+ free(addr_name);
+#endif
+
+ /* fill values into the opal_if_t */
+ memcpy(&a6, &(sin_addr->sin6_addr), sizeof(struct in6_addr));
+
+ strncpy(intf.if_name, cur_ifaddrs->ifa_name, IF_NAMESIZE);
+ intf.if_index = opal_list_get_size(&opal_if_list) + 1;
+ ((struct sockaddr_in6*) &intf.if_addr)->sin6_addr = a6;
+ ((struct sockaddr_in6*) &intf.if_addr)->sin6_family = AF_INET6;
+
+ /* since every scope != 0 is ignored, we just set the scope
to 0 */
+ ((struct sockaddr_in6*) &intf.if_addr)->sin6_scope_id = 0;
+
+ /*
+ * hardcoded netmask, adrian says that's ok
+ */
+ intf.if_mask = 64;
+ intf.if_flags = cur_ifaddrs->ifa_flags;
+
+ /*
+ * FIXME: figure out how to gain access to the kernel index
+ * (or create our own), getifaddrs() does not contain such
+ * data
+ */
+
+ intf.if_kernel_index = (uint16_t)
if_nametoindex(cur_ifaddrs->ifa_name);
+
+ intf_ptr = (opal_if_t*) malloc(sizeof(opal_if_t));
+ OMPI_DEBUG_ZERO(*intf_ptr);
+ if(NULL == intf_ptr) {
+ opal_output(0, "opal_ifinit: unable to allocate %lu
bytes\n",
+ sizeof(opal_if_t));
+ OBJ_DESTRUCT(&intf);
+ return OPAL_ERR_OUT_OF_RESOURCE;
+ }
+ memcpy(intf_ptr, &intf, sizeof(intf));
+ opal_list_append(&opal_if_list, (opal_list_item_t*) intf_ptr);
+ OBJ_DESTRUCT(&intf);
+ } /* of for loop over ifaddrs list */
+
+ }
+#else
/* create the internet socket to test off */
/*
Change AF_INET to AF_UNSPEC (or AF_INET6) and everything will fail.
@@ -358,6 +487,9 @@
}
free(ifconf.ifc_req);
close(sd);
+#endif /* bsd, macosx */
+
+
#if OPAL_WANT_IPV6
#ifdef __linux__ /* Linux does not have SIOCGL*, so parse
/proc/net/if_inet6 instead */
==
--
Kevin M. Buckley Room: CO327
School of Engineering and Phone: +64 4 463 5971
Computer Science
Victoria University of Wellington
New Zealand
