Please don't reply to lustre-devel. Instead, comment in Bugzilla by using the following link: https://bugzilla.lustre.org/show_bug.cgi?id=11089
(In reply to comment #17) > The proc is organized as this > > +- nid --> stats... > | > + exp#1 --> stats... > | > + exp#2 --> stats... > > So it would avoid both situation you mentioned earlier with a little more > memory > consumed for each NID. We considered it is worthwhile unless concrete numbers > on > its weakness of scaling. > Aha, so you want to destroy the export proc stats when the export disappears, but _also_ keep a running total of per-nid stats, which lives for the life of the server. Is that right? (I'm happier about that because it doesn't burn memory every time a client restarts.) Also, FYI, we're putting proc through a fairly major overhaul to deal with bug 10866, so we should wait for the dust to settle there before trying to land this. _______________________________________________ Lustre-devel mailing list [email protected] https://mail.clusterfs.com/mailman/listinfo/lustre-devel
