On 11/4/21 7:51 PM, Huang, Ying wrote:
Let's also try to do it with the existing node_demotion[] dataTo avoid cache ping-pong, I guess some kind of per-CPU data structure
structure before we go adding more.
may be more suitable for interleaving among multiple nodes.
It would probably be better to just find something that's more
read-heavy. Like, instead of keeping a strict round-robin, just
randomly select one of the notes to which you can round-robin.
That will scale naturally without having to worry about caching or fancy
per-cpu data structures.