What will happen when you run this in a TCP-based networked environment?
I.e., won't the TCP BTL then publish the 127.x.x.x address in the modex, and
then other peers will think "oh, that's on the same subnet as me, so therefore
I should be able to communicate with that endpoint over my 127.x.x.x address",
right?
I agree that it's a bit weird that we are excluding the loopback interfaces
inside the logic, but the problem is that we really only want loopback IP
addresses to communicate with peers on the same server. That kind of
restriction is not well exposed through the if_include/exclude MCA vars.
We basically have the same problem with IP bridge interfaces (e.g., to VMs on
the same server). Meaning: yes, if you just compare IP address+subnet, two
peers may be ruled to be "reachable". But in reality, they may *not* be
reachable (especially when you start talking about the private subnets of
127.x.x.x/8, 10.x.x.x/8, 192.168.x.x/24, ...etc.).
> On Sep 21, 2016, at 7:59 AM, George Bosilca <bosi...@icl.utk.edu> wrote:
>
> The current code in the TCP BTL prevents local execution on a laptop not
> exposing a public IP address, by unconditionally disqualifying all interfaces
> with local addresses. This is not done based on MCA parameters but instead is
> done deep inside the IP matching logic, independent of what the user
> specified in the corresponding MCA parameters (if_include and/or if_exclude).
>
> Instead, I propose we exclude the local interface only via the exclude MCA
> (both IPv4 and IPv6 local addresses are already in the default if_exclude),
> and remove all the code that prevents local addresses. I propose the
> following patch (local addresses are accepted via the second if because
> opal_net_samenetwork returns true).
>
> If no complaints by Friday morning, I will push the code.
>
> Thanks,
> George.
>
>
>
> diff --git a/opal/mca/btl/tcp/btl_tcp_proc.c b/opal/mca/btl/tcp/btl_tcp_proc.c
> index a727a43..f7decc4 100644
> --- a/opal/mca/btl/tcp/btl_tcp_proc.c
> +++ b/opal/mca/btl/tcp/btl_tcp_proc.c
> @@ -541,9 +541,9 @@ int mca_btl_tcp_proc_insert( mca_btl_tcp_proc_t* btl_proc,
> }
>
>
> - for(i=0; i<proc_data->num_local_interfaces; ++i) {
> + for( i = 0; i < proc_data->num_local_interfaces; ++i ) {
> mca_btl_tcp_interface_t* local_interface =
> proc_data->local_interfaces[i];
> - for(j=0; j<proc_data->num_peer_interfaces; ++j) {
> + for( j = 0; j < proc_data->num_peer_interfaces; ++j ) {
>
> /* initially, assume no connection is possible */
> proc_data->weights[i][j] = CQ_NO_CONNECTION;
> @@ -552,19 +552,8 @@ int mca_btl_tcp_proc_insert( mca_btl_tcp_proc_t*
> btl_proc,
> if(NULL != proc_data->local_interfaces[i]->ipv4_address &&
> NULL != peer_interfaces[j]->ipv4_address) {
>
> - /* check for loopback */
> - if ((opal_net_islocalhost((struct sockaddr
> *)local_interface->ipv4_address) &&
> - !opal_net_islocalhost((struct sockaddr
> *)peer_interfaces[j]->ipv4_address)) ||
> - (opal_net_islocalhost((struct sockaddr
> *)peer_interfaces[j]->ipv4_address) &&
> - !opal_net_islocalhost((struct sockaddr
> *)local_interface->ipv4_address)) ||
> - (opal_net_islocalhost((struct sockaddr
> *)local_interface->ipv4_address) &&
> - !opal_ifislocal(proc_hostname))) {
> -
> - /* No connection is possible on these interfaces */
> -
> - /* check for RFC1918 */
> - } else if(opal_net_addr_isipv4public((struct sockaddr*)
> local_interface->ipv4_address) &&
> - opal_net_addr_isipv4public((struct sockaddr*)
> peer_interfaces[j]->ipv4_address)) {
> + if(opal_net_addr_isipv4public((struct sockaddr*)
> local_interface->ipv4_address) &&
> + opal_net_addr_isipv4public((struct sockaddr*)
> peer_interfaces[j]->ipv4_address)) {
> if(opal_net_samenetwork((struct sockaddr*)
> local_interface->ipv4_address,
> (struct sockaddr*)
> peer_interfaces[j]->ipv4_address,
> local_interface->ipv4_netmask)) {
> @@ -574,17 +563,16 @@ int mca_btl_tcp_proc_insert( mca_btl_tcp_proc_t*
> btl_proc,
> }
> proc_data->best_addr[i][j] =
> peer_interfaces[j]->ipv4_endpoint_addr;
> continue;
> + }
> + if(opal_net_samenetwork((struct sockaddr*)
> local_interface->ipv4_address,
> + (struct sockaddr*)
> peer_interfaces[j]->ipv4_address,
> + local_interface->ipv4_netmask)) {
> + proc_data->weights[i][j] = CQ_PRIVATE_SAME_NETWORK;
> } else {
> - if(opal_net_samenetwork((struct sockaddr*)
> local_interface->ipv4_address,
> - (struct sockaddr*)
> peer_interfaces[j]->ipv4_address,
> - local_interface->ipv4_netmask)) {
> - proc_data->weights[i][j] = CQ_PRIVATE_SAME_NETWORK;
> - } else {
> - proc_data->weights[i][j] =
> CQ_PRIVATE_DIFFERENT_NETWORK;
> - }
> - proc_data->best_addr[i][j] =
> peer_interfaces[j]->ipv4_endpoint_addr;
> - continue;
> + proc_data->weights[i][j] = CQ_PRIVATE_DIFFERENT_NETWORK;
> }
> + proc_data->best_addr[i][j] =
> peer_interfaces[j]->ipv4_endpoint_addr;
> + continue;
> }
>
> /* check state of ipv6 address pair - ipv6 is always public,
> @@ -593,19 +581,9 @@ int mca_btl_tcp_proc_insert( mca_btl_tcp_proc_t*
> btl_proc,
> if(NULL != local_interface->ipv6_address &&
> NULL != peer_interfaces[j]->ipv6_address) {
>
> - /* check for loopback */
> - if ((opal_net_islocalhost((struct sockaddr
> *)local_interface->ipv6_address) &&
> - !opal_net_islocalhost((struct sockaddr
> *)peer_interfaces[j]->ipv6_address)) ||
> - (opal_net_islocalhost((struct sockaddr
> *)peer_interfaces[j]->ipv6_address) &&
> - !opal_net_islocalhost((struct sockaddr
> *)local_interface->ipv6_address)) ||
> - (opal_net_islocalhost((struct sockaddr
> *)local_interface->ipv6_address) &&
> - !opal_ifislocal(proc_hostname))) {
> -
> - /* No connection is possible on these interfaces */
> -
> - } else if(opal_net_samenetwork((struct sockaddr*)
> local_interface->ipv6_address,
> - (struct sockaddr*)
> peer_interfaces[j]->ipv6_address,
> -
> local_interface->ipv6_netmask)) {
> + if(opal_net_samenetwork((struct sockaddr*)
> local_interface->ipv6_address,
> + (struct sockaddr*)
> peer_interfaces[j]->ipv6_address,
> + local_interface->ipv6_netmask)) {
> proc_data->weights[i][j] = CQ_PUBLIC_SAME_NETWORK;
> } else {
> proc_data->weights[i][j] = CQ_PUBLIC_DIFFERENT_NETWORK;
>
> _______________________________________________
> devel mailing list
> devel@lists.open-mpi.org
> https://rfd.newmexicoconsortium.org/mailman/listinfo/devel
--
Jeff Squyres
jsquy...@cisco.com
For corporate legal information go to:
http://www.cisco.com/web/about/doing_business/legal/cri/
_______________________________________________
devel mailing list
devel@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/devel
