On Sun, Mar 23, 2008 at 07:27:10PM -0700, James G. Sack (jim) wrote:
While there may be plenty of gotchas to worry about, and a long time between now and a reliable implementation, I think you may be a little too quick to dismiss it. In (perhaps only?) my imagination, it may in fact, be so much better at (say) caching functionality, or versatile at dealing with (or redefining) ordering, that new paradigms may pop out of it -- who can forsee?
I get exactly this behavior just by adding a lot of RAM to an recent Linux system. Plus, if something needs that RAM for another purpose, stuff can get flushed out to disk and the RAM used for something else. So far, most of the hype I've seen over it seems to suggest the people don't understand how the existing buffer cache works. I'm not saying things can't be better, but people seem to be comparing it with something much poorer than how things are already being done. David -- [email protected] http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
