Peter Zijlstra <[EMAIL PROTECTED]> said:
I'm still torn between CLOCK-Pro and CART.
CLOCK-Pro is still vulnerable to the cyclic scan use case, since at that
time all pages will have equal distance.
I was recently testing CLOCK-Pro for the entry cache in OpenLDAP, with this
cyclic scan case. I've set it aside for now, but if anyone is interested in
playing with a user-level version as opposed to these kernel adaptations, an
early version of mine is at
http://www.openldap.org/its/index.cgi/Software%20Enhancements?id=4807
I found that although it managed to allow some cached pages to be reused, it
also forced several full sweeps of the clock in each scan. Overall it
performed more slowly than regular CLOCK due to these extra sweeps. (In our
case, moving the hands required some expensive lock manipulation. Possibly if
I found a better locking strategy there the performance cost would come down.)
--
-- Howard Chu
Chief Architect, Symas Corp. http://www.symas.com
Director, Highland Sun http://highlandsun.com/hyc
OpenLDAP Core Team http://www.openldap.org/project/
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
