Re: [tor-dev] Comparing Stem, metrics-lib, and zoossh

What you could try, though, is extend Zoossh to parse tarballs rather than directories. This is more than 2 times faster in metrics-lib, and it doesn't clutter your hard disk with thousands or millions of tiny files.

For what it's worth processing tarballs rather than flat files made a huge difference for Stem as well (tempted to say it was a 5x improvement). Since you care so much about Zoossh's speed this could be a great way to make it even faster. :)