I've got a long, long list of interesting questions. And I blog frightfully slowly :-)
So... why don't I start blogging more of the questions? Someone else may very well be able to springboard from one of my questions to a *really* astounding answer! Maybe. I hope my questions are that good anyway :-)
Sometimes the questions come to me as a form of L'esprit de L'escalier - not something I wish I'd said but a question I wish I had asked.
So it is with my question: "Whither SQL Server Backup Buffers?"
Yesterday (or maybe really early this morning) I posed the question: "Whence SQL Server Backup Buffers?"
Here's what I noticed: 'Target server memory' 33553968 hadn't been achieved. 'Total server memory' during the backup was 14947794. Of that 4194496 was allocated to memoryclerk_backup.
When the backup was cancelled, the memoryclerk_backup allocation was simply returned to the OS.
Why not give it to free memory? It should have been nice, contiguous chunks of memory addresses. The server was far from reaching target server memory. The server wasn't under memory pressure. This is what it looks like right now... and it would have looked nearly the same right after the backup was cancelled.
-If 'max server memory' wasn't being overridden by a more reasonable target (because max server memory is 120 GB on a 32GB VM), would the behavior still be the same before reaching target? I bet it would be.
-Is this behavior specific to not having reached target? Or when reaching target would backup buffers be allocated, potentially triggering a shrink of the bpool, then returned to the OS afterward requiring the bpool to grow again?
-What other allocations are returned directly to the OS rather than given back to the memory manager to add to free memory? I bet CLR does this, too. Really large query plans? Nah, I bet they go back into the memory manager's free memory.
-Does this make a big deal? I bet it could. Especially if a system is prone to develop persistent foreign memory among its NUMA nodes. In most cases, it probably wouldn't matter.
Maybe I'll get around to testing some of this. But it probably won't be for a while.