> Larry McVoy wrote:
>
> > THINK. You guys aren't THINKING. It is very FRUSTRATING.
> >
> > If you have 200 small files and you have to go get 200 inodes and 200 blocks
> > to read them in, the inodes and the blocks aren't next to each other, that's
> > 400 disk transactions instead of 1. THINK. PLEASE. This is the third time
> > I've gone over this point.
>
> And if you have 200 small files spread about in a pseudo-tarball of 4000 files?
> Or say your tarballs only cover 200 files at a time, you have 200 files spread
> through 20 pseudo-tarballs?
This seems to be turning into a rehash of the argument over paging versus
overlaying. Paging does an okay job of keeping code around when it is
probably going to be useful soon, and doesn't require much thought to use.
Overlaying can do a superb job of keeping just the code you're going to
need real soon, but using it takes lots of thought and measurement by
people who know how to think about it. Likewise, those 200 small files
may have been selected and packed into that tarball because the designer
*knows* that they are related and that many subsets will be wanted all
together, and that they are not usefully related to any other files he's
aware of. The question is, then, how hard is it going to be to do good
selections? Is it worth the bother, or should we just let a
general-purpose filesystem continue to do an okay job?
-- Mark H. Wood, Lead System Programmer mwood@IUPUI.Edu Specializing in unusual perspectives for more than twenty years.
- 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/