Arnd, in your observations about 2.6, you mentioned that the I/O request lock is a problem.
Does 2.6 and earlier releases queue behind a single lock at some point? I have noticied both in 2.4.7 and 2.4.19 there is a limit to the amount of I/O I, which is a fraction of the real device throughput capacity. We have a lot of people testing with up to 128 volumes in a LPAR and I was wondering what impact one would expect. ===== Jim Sibley Implementor of Linux on zSeries in the beautiful Silicon Valley "Computer are useless.They can only give answers." Pablo Picasso __________________________________ Do you Yahoo!? Yahoo! SiteBuilder - Free, easy-to-use web site design software http://sitebuilder.yahoo.com
