Subject: Re: mp->mnt_vnodelist change
To: Andrew Reilly <email@example.com>
From: Reinoud Zandijk <firstname.lastname@example.org>
Date: 10/19/2006 13:33:33
On Thu, Oct 19, 2006 at 03:40:20PM +1000, Andrew Reilly wrote:
> On Thu, 19 Oct 2006 00:01:53 +0200
> Reinoud Zandijk <email@example.com> wrote:
> > The syncfs syncer uses a different set of lists but yes, it too has the
> > same problem with the lists.
> I've never looked at the code, but I would have thought that
> there would be some sort of block-sorting/elevator-algorithm step
> in between "this list of blocks need to go to disk" and "disk
> drive: seek to xyz; write blocks nnn to nnn+m". Isn't there?
> If there is, then this reversal probably doesn't matter much, if
> all it does is pessimize an in-memory sort.
Well there is some sort of disc queue sorting going on at the disc
interface driver level but thats a peep-hole optimalisation that only works
for some sanity when accessed by multiple processes and asynchronous writes
from one processes.
For synchronous writes this peep-hole optimalisation is not relevant since
it will wait for each write to complete before it issues a new one.