NFS on ZFS pure SSD pool

[Garrett Wollman]

<<On Wed, 28 Aug 2013 19:48:29 -0400 (EDT), Rick Macklem <rmacklem at uoguelph.ca> said:

> You should get your users to do their mounts over flaky WiFi links
> and such, in order to make better use of the cache;-)

We don't support NFS use by such clients -- it's purely for compute
cluster type applications.  Anything that can use AFS is supposed to
use AFS.

> By the way Garrett, what do you have kern.ipc.nmbclusters set to,
> since cache entries will use mbuf clusters normally.

I have it at 2**20, which is actually only important because it causes
kern.ipc.nmbjumbop to be set as a side effect.  We also set maxusers
(to match the new calculation in 10-current) so that other kernel data
structures will be sized appropriately.

This server's pretty idle right now:

36907/150098/187005 mbufs in use (current/cache/total)
948/22794/23742/1048576 mbuf clusters in use (current/cache/total/max)
0/4352 mbuf+clusters out of packet secondary zone in use (current/cache)
24583/36548/61131/524288 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/262144 9k jumbo clusters in use (current/cache/total/max)
0/0/0/131072 16k jumbo clusters in use (current/cache/total/max)
109454K/229304K/338759K bytes allocated to network (current/cache/total)

On a machine without jumbo frames, it looks like this:

10829/230836/241665 mbufs in use (current/cache/total)
8268/93146/101414/1048576 mbuf clusters in use (current/cache/total/max)
8190/80641 mbuf+clusters out of packet secondary zone in use (current/cache)
0/1993/1993/524288 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/262144 9k jumbo clusters in use (current/cache/total/max)
0/0/0/131072 16k jumbo clusters in use (current/cache/total/max)
19243K/251973K/271216K bytes allocated to network (current/cache/total)

-GAWollman