I certainly have nothing to contribute in terms of implementation details (you all know best). I will happily test and provide numbers though. I guess it was just one of those (out of the box) corner cases where NFSv3 > NFSv4.2 that I thought was worth highlighting. For now, I probably have no other option but to use NFSv3 for any high latency clients that require lots of concurrency as future changes to the server side per client slot count logic is unlikely to make its way into this generation of Linux distros (e.g. RHEL8). Daire On Mon, 21 Feb 2022 at 07:59, NeilBrown <neilb@xxxxxxx> wrote: > > On Sat, 19 Feb 2022, Trond Myklebust wrote: > > On Sat, 2022-02-19 at 11:43 +1100, NeilBrown wrote: > > > On Sat, 19 Feb 2022, Chuck Lever III wrote: > > > > > > > > For the Linux NFS server, there is an enhancement request open > > > > in this area: > > > > > > > > https://bugzilla.linux-nfs.org/show_bug.cgi?id=375 > > > > > > > > If there are any relevant design notes or performance results, > > > > that would be the place to put them. > > > > > > I wonder if I have a login there.. > > > > > > > If you're having trouble setting one up, then let me know. I should be > > able to help. > > Thanks. I couldn't find any evidence in email history of ever having > one, so I tried creating one and it went completely smoothly. :-) > > NeilBrown
