zfs home directories best practice

[Graham Allan]

On 4/3/2013 6:56 PM, Rick Macklem wrote:
>>
> Well, there isn't any limit to the # of exported file systems afaik,
> but updating a large /etc/exports file takes quite a bit of time and
> when you use mountd (the default) for this, you can have problems.
> (You either have a period of time when no client can get response
>   from the server or a period of time when I/O fails because the
>   file system isn't re-exported yet.)
>
> If you choose this approach, you should look seriously at using
> nfse (on sourceforge) instead of mountd.

That's an interesting-looking project though I'm beginning to think that 
unless there's some serious downside to the "one big filesystem", I 
should just defer the per-user filesystems for the system after this 
one. As you remind me below, I'll probably have other issues to chase 
down besides that one (performance as well as making the jump to NFSv4...)

> You might also want to contact Garrett Wollman w.r.t. the NFS
> server patch(es) and setup he is using, since he has been
> working through performance issues (relatively successfully
> now, as I understand) for a fairly large NFS/ZFS server.
> You should be able to find a thread discussing this on
> freebsd-fs or freebsd-current.

I found the thread "NFS server bottlenecks" on freebsd-hackers, which 
has a lot of interesting reading, and then also "NFS DRC size" on 
freebsd-fs. We might dig into some of that material (eg DRC-related 
patches) though I probably need to spend more time on basics first 
(kernel parameters, number of nfsd threads, etc).

Thanks for the pointers,

Graham
--