Wasn't quite sure how to reply to Roy's e-mail since I was unsubscribed before, but saw it was recent so wanted to chime in.

I have this exact same problem.  What I find interesting is that in my case, where I call irecv() from a number of other ranks directly, but with any_tag:

    world.irecv(1, mpi::any_tag, data);

I only have issues when there are more processes than those I am listening to.  I find this to be especially odd.  The issue seems like the second receive (after the data count) is picking up a separate ISend's count.  I'm still looking into what the issue could be...

Thanks,

Walt