On 05/20/2011 09:51 AM, Stephan von Krawczynski wrote: > Forgive my ignorance Jeff, but it is obvious to anyone having used glusterfs > for months or years that the guys have a serious software design issue. No, it is not. I've been using and watching its development for years, I know its code far better than you ever could, and I disagree. That's one counterexample disproving "anyone" right there. Don't try to bluff me with risible appeals to non-existent authority. > If you > look at the "tuning" options configurable in glusterfs you should notice that > most of them are just an outcome of not being able to find a working i.e. best > solution for a problem. cache-timeout? thread-count? quick-read? > stat-prefetch? Are you seriously saying that modularity and tuning parameters are bad? Do you even know how many tuning options other filesystems such as ext4 or XFS have, or how many times they've iterated through different internal algorithms to address various issues (especially scaling)? The features you name are *all* configurable because some people need to make different tradeoffs - often performance vs. resource consumption or consistency - in their deployments. They can't just be "one size fits all" values, and the Gluster developers are wise to allow this flexibility. I'm not going to engage you further on this Stephan, as long as you demonstrate such complete ignorance of the issues involved and seem interested in nothing but insulting those you should be thanking. If GlusterFS is so bad, go away. Good luck with the alternatives, which I know just as well and which are even more painful to deal with. When you're capable of contributing constructively, your opinions will gain some weight.
