Hi Sinan, On 20/09/2017 18:29, Sinan Kaya wrote: > On 9/20/2017 12:11 PM, Alex Williamson wrote: >> My impression is that the issue would be inefficiency. There should be >> nothing functionally wrong with a read request less than MPS, but we're >> not "filling" the TLP as much as the topology allows. Is that your >> understanding as well, Sinan? > > That's my understanding as well. It would be a performance hit to use a > value less than MPS. > > Thank you for your explanations. best Regards Eric