On Sat, Apr 15, 2006 at 08:31:18AM -0600, David Wilk wrote: > I've got a test server with OpenBSD-3.8 on it (GENERIC except with > RAIDFRAME support) and considering the hardware, it does pretty well > with NFS performance. However, I've noticed that when under heavy NFS > load, it becomes nearly unresponsive. Shell sessions take 2-6 seconds > to respond, and top updates stretch out for several seconds as well. > > Is this normal behavior (trading latency for throughput)? or is there > something else going on?
i've got a ppro/200 that has an old ami(4) and provides NFS/NIS for the LAN. if i try to beat the living hell out of it, yeah, things slow up, but that is only when i'm running some kind of benchmark or purposefully throwing a bunch of dd(1)s at it, etc. i find that running the IO load locally to the server makes it less responsive to the entire LAN , while running the IO load from an NFS client tends to just make local actions on that client suffer (what i would expect) under just normal use circumstances, no, nothing freaky. i usually do random find/grep/cp operations to/from the NFS partition for whatever reason during the day and those don't hurt any clients' performance. the times i am actually logged into the NFS server i don't notice nastiness when doing some big NFS xfers, but i don't log in to it much either. -- jared [ openbsd 3.9-current GENERIC ( mar 15 ) // i386 ]
