Do you have any opinion on the idea of having exponential back-off on re-trying failed metric scrapes to reduce log-spam in case of problems?

If it's an idea you're open to I can look at cooking up a patch to support it if my initial PoC of this scraper works out.

CloudNative-PG's built-in scraper, which I currently use, doesn't do this either. But log-spam is a real problem with it if there's a mistake in a query. So it's something I'd like to see if I can implement here if I adopt this scraper.