[libfabric-users] connection-less send/recv with verbs

[Maurizio Drocco]

> Now the problem is that, with the following code:
> ========================================
> ret = fi_send(ep, tx_buf, 32, NULL, to, ctx);
> assert(!ret);
> while(true) {
> 	ret = fi_cq_read(cq, &comp, 1);
> 	/*…*/
> }
> ========================================
> no completion event is ever found in the queue (always return FI_EAGAIN).
> 
> With gdb, I noticed that the functions used by fi_send and fi_cq_read are, respectively:
> - fi_ibv_rdm_send
> - fi_ibv_rdm_tagged_cq_read
> 
> Do you think there can be some other issue related to modes/capabilities?

Let me add a bit that could help to understand.
I ran some basic tests on the two infiniband clusters I have access to.

The following libfabric test completes successfully:
fi_pingpong -p verbs -e rdm & fi_pingpong -p verbs -e rdm localhost

Whereas the following fabtests test just stalls on the first call to fi_cq_read (in the very same manner as my code):
fi_rdm_pingpong -p verbs & fi_rdm_pingpong -p verbs localhost

I am getting confused :)

Maurizio

---
Maurizio Drocco
PhD Candidate
University of Torino, department of Computer Science
Via Pessinetto 12, 10149 Torino - Italy