On Thu, Apr 24, 2008 at 10:59 PM, Soeren Sandmann <sandmann@daimi.au.dk> wrote:
[...]
Instead of a specific system call for "multistat" it would be interesting
to look at syslets. I'm not sure what the current state of that work is,
the last reference I find is http://lkml.org/lkml/2007/12/6/336 and more
interestingly http://lkml.org/lkml/2008/1/9/327
I guess it would be difficult to get close to the optimal disk schedule by
using syslets; if a directory contains 1000 files that would require 1000
syslets and a good I/O scheduler - that's unlikely to be feasible.
I've added Zach Brown to Cc because he authored the last syslet patchset.
--
Carl Henrik
--