[dns-operations] prefetching and thundering herds

[Mark Delany]

On 15Jul20, Tony Finch allegedly wrote:
> I'm wondering if the stub caches catch the queries that would otherwise
> cause a prefetch, so instead of a newly hot cache in the recursive server,
> the stubs encounter a high latency refill.

I can see how this would disadvantage client queries as they always see the resolution
delay at TTL expiration.

But in terms of thundering herds, it's still seem no worse than if none of the stub
resolvers cached.

However, I can see how if the choice is between stub caches which "smear" TTL (regardless
of mechanism) and stubs which don't "smear", the smearers are probably a little nicer to
recursive resolvers which incur high costs queuing duplicate queries.

But then I have to wonder, is there a fundamental reason why recursive resolvers perform
non-linearly as the arrival rate of identical queries increases?


Mark.