Re: AF_VSOCK loopback

2016-11-14 Thread Stefan Hajnoczi
On Fri, Nov 11, 2016 at 02:14:44PM +, Jorgen S. Hansen wrote: > Hi Stefan, > > All datagram communication in VMCI based AF_VSOCK is going through the host - > also for loopback communication. The only difference wrt loopback is that the > VMCI queue pairs implementing the shared queues for

Re: AF_VSOCK loopback

2016-11-11 Thread Jorgen S. Hansen
: Stefan Hajnoczi <stefa...@redhat.com> Sent: Thursday, November 10, 2016 3:43 PM To: Jorgen S. Hansen Cc: cav...@redhat.com; netdev@vger.kernel.org Subject: AF_VSOCK loopback Hi Jorgen, Cathy Avery found that the AF_VSOCK VMCI transport does loopback inside the guest (but not on th

Re: AF_VSOCK loopback

2016-11-10 Thread Cathy Avery
I had trouble with loopback on the esx host. Using the nc-vsock ( AF_VSOCK 56 ) the server and the client connected but they both terminated without error when I attempted to send characters over. It might be due to something other than vsock. I haven't pursued it yet. On 11/10/2016 09:43 AM,

AF_VSOCK loopback

2016-11-10 Thread Stefan Hajnoczi
Hi Jorgen, Cathy Avery found that the AF_VSOCK VMCI transport does loopback inside the guest (but not on the host?). The virtio transport currently does no loopback. The loopback scenario I'm thinking of is where process A listens on port 1234 and process B on the same machine connects to port