henry@utzoo.uucp (Henry Spencer) (07/11/89)
In article <1989Jul9.043700.11769@ddsw1.MCS.COM> karl@ddsw1.MCS.COM (Karl Denninger) writes: >>... the fastest system I've >>tried (I haven't been able to try TMNN). > >TMNN is supposed to be killer-fast, but unfortunately it breaks EVERYTHING... Unless Eric has really revised the visible file structures a lot, TMNN is probably not *quite* as fast as C News, but the difference should not be huge. He's borrowed a lot of ideas from us (including some that we, in the end, didn't implement!) and had some of his own too. Unfortunately, we too hear that it's not very compatible any more. Although there are some less-than-instantaneous preliminaries, once our relaynews gets rolling, it's fundamentally impossible to beat it by very much: on a reasonable machine, it is mostly system-call bound, and it works hard at avoiding unnecessary system calls. (This is not to say that you can't come up with circumstances where it's not as quick as it could be -- we know one or two ourselves, and are considering doing something about them -- but they're pretty unusual.) -- $10 million equals 18 PM | Henry Spencer at U of Toronto Zoology (Pentagon-Minutes). -Tom Neff | uunet!attcan!utzoo!henry henry@zoo.toronto.edu