"My day job is PostgreSQL DBA. [...] transaction logs, which must be fsync()'ed often to guarantee consistency, and enable crash recovery, reside on a smaller, dedicated filesystem from the rest of my database's disk footprint. If I didn't do that, at every checkpoint, my performance would measurably fall. I learned this lesson the hard way, at an old job, where my postgres clusters lived on a SAN — it wasn't just my db instances that were being adversely affected by this IO storm. It was everything else that lived on the filer, too."