On 28 June 2013 14:23, Michael R. Hines <mrhi...@linux.vnet.ibm.com> wrote: >> I assume from the PACKED annotations (do we really need both, >> incidentally) that this is shared with either the guest or >> with another instance of QEMU. Are there definitely no >> endianness issues to deal with here? > > > I have ntohl()/htonl() on the protocol headers, but I did not > add them for the data portions of the protocol. > > > Is endianess for the data a big issue when you are assume the migration > is happening across identical CPU architectures?
Well: * is that a reasonable assumption? (why?) * if you try this on some setup where it's not true, do we fail helpfully or obscurely? This is really just my usual "all the world is not an x86" nudge; I don't know enough about rdma to be able to say what the right thing in this particular case is. -- PMM