"A month of sundays ago John Kodis wrote:"
> On Tue, 2 May 2000, Bruce Janson wrote:
>
> > Which popular/essential/useful user-level Linux applications
> > break when atime is disabled (say, pegged to zero)?
>
> You could eliminate most of the performance penalty by stealing an
> idea that was used successfully on VMS: rather than simply pegging
> atime to zero, provide an atime granularity mount option. With an
> atime granularity of, say, 3600 (one hour), an atime update would only
> be performed if not doing so would result in an atime value that was
> in error by more than an hour. This limits atime updates to at most
> one per hour per file.
Eh? Yes, it reduces the number of atime changes by a factor equal
to the average number of times a file is looked at per hour, given
that it is looked at all.
But it doesn't clump the changes together, so it's useless for spundown
disks. To get clumping, you'd have to keep all the new atimes grouped
at hour points too. So you'd have to save 'em up until the next hour
point.
What happens on readonly fs's, by the way?
Peter
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun May 07 2000 - 21:00:10 EST