I can't believe they figured it out first. That was the thought going through my head back in mid-December after several weeks of 12-hour days debugging why this cluster was slow. This was probably the most intense performance analysis I'd done since Inktank. Half-forgotten superstitions from the 90s about appeasing SCSI gods flitted through my consciousness. The 90s? Man, I'm getting old. We were about two-thirds of the way through the work that would let us start over at the beginning. Speakin...