We moseyed on down to the server in question to take a look at it. One thing stood out immediately, CPU was pegged out at 100% but SQL itself didn’t actually seem to be doing anything, transactionssecond was on the floor. Unfortunately this happened a while back and I didn’t think to capture any graphs or metrics at the time so you’re just going to have to take my word for this.
After looking into a few different things, the mention of spinlock contention came up. I’ll be honest here, actual spinlock contention is rare and is something that I’ve seen cause an issue only a handful of times so it’s something that I don’t generally get to until I’ve ruled out just about everything else.
David’s scenario was on an older patch of SQL Server and it was fixed later. It’s a good reminder to keep those servers patched.