Subject: Re: Efficiency of nfsiod
To: Jonathan Stone <jonathan@DSG.Stanford.EDU>
From: Gordon W. Ross <email@example.com>
Date: 11/11/1998 00:41:29
Jonathan Stone writes:
> The point was to look at sharing that same vmspace/pmap (and avoid the
> pmap_activate() costs) for processes like nfs_iod(), yet give them
> back `a vmspace of their own' if/when they return to userland.
> That was a noticeable-to-users win on NFS servers, back when SunOS did
> it. seems like it'd be the same for us too. yes?
Yes, that provides a noticable performance improvement when
one has processes stuck in the kernel for a while (nfsiod).
The sun3 and sun3x pmap modules use the "empty context" trick,
which allows delaying the actual allocation of an MMU context
until a process touches a user-space address. Just FYI.