Ihnen, David <[EMAIL PROTECTED]> writes on 23 August 2000 at 09:57:43 -0700
> > And you also noticed both the number of forks, and the number of
> > filesystem synchs (and hence actual physical disk IO) required in this
> > process, I guess.
>
> Correct me if I'm wrong, but I believe that on any unix system, the file
> system cache allows process B to access data written by process A regardless
> of whether or not a physical disk synchronization has taken place. The
> actual write-to-disk is unimportant, as the file cache already knows what
> that file contains. It would be wasteful to access the disk for data
> already in cache, where it was put by process A's write.
I believe that to be true; but when the process does an fsync, it is
blocked until the write to disk has been reported complete.
--
Photos: http://dd-b.lighthunters.net/ Minicon: http://www.mnstf.org/minicon
Bookworms: http://ouroboros.demesne.com/ SF: http://www.dd-b.net/dd-b
David Dyer-Bennet / Welcome to the future! / [EMAIL PROTECTED]
