Ingo, I am so glad you posted here!

I wanted to say I've been using the -tip tree for over a year, with great success for my desktop, and my laptop.
Many of the problems listed here? They never seem to occur with -tip kernels. It's my hope that it gets more exposure.

I know some of the patches have made it back into the mainline kernel, any idea when they all will be merged?

Also one thing I've noticed, but it seems not to be part of the discussion is the choice of files systems, I was under the impression that scheduling was abstracted away from the file systems?

More so in the non-tip kernels, I've seen major differences in behavior between ones I've tested, usually with XFS performing best for IO, and BFS having wildly different behaviors depending on the workload, and ext3 just kinda sucking in general, but consistently sucking.

Reading this makes me so nostalgic for byte magazine, they on occasion would right the most awesome, and in depth articles about processors. They did not just regurgitate the companies white paper, and glossy marketing copy.

Kinda scary, everyone is looking old, looking to the mirror, oh, me too.

You know you are right, I bet it is a Markov chain....