I would really like to see expire gone
Kai Henningsen
kaih at khms.westfalen.de
Mon Jan 27 07:11:00 UTC 2003
rra at stanford.edu (Russ Allbery) wrote on 26.01.03 in <yld6mjn3hh.fsf at windlord.stanford.edu>:
> bill davidsen <davidsen at tmr.com> writes:
>
> > If you mean that it takes that time using sleepycat but faster disk,
> > then clearly the db itself isn't the bottleneck (ie. CPU usage). Clearly
> > any database is going to depend on disk speed to some extent, sure as
> > hell dbz does.
>
> No, the problem is that Sleepcat will go to disk *way* more than our
> current history implementation does. You'll get some of that time back if
> you turn off fsync (at the cost of reliability, since our current history
> implementation does fsync occasionally), but not all of it. Our current
> history implementation is specifically designed to minimize disk access by
> holding horking huge tables in memory, and does mostly work.
Though at least newer versions of Sleepycat (2.x is approximately stone
age) have loads of knobs you can turn to tune it. I'd not dismiss it based
on an obviously untuned 2.x test alone. (2 hours on 100k records on a big
fast sun? That's what, 14 records per second? That doesn't sound quite
like what I'm accustomed to even with default parameters.)
Maybe that was rebuild with full locking?
MfG Kai
More information about the inn-workers
mailing list