Another virtual threads migration story: ReentrantReadWriteLock

[Alan Bateman]

On 29/01/2025 16:58, Matthew Swift wrote:
> :
>
> Given that scaling IO to millions of concurrent IO bound tasks was one 
> of the key motivations for vthreads, it seems a bit surprising to me 
> that a basic concurrency building block of many applications is 
> constrained to 64K concurrent accesses. Are you aware of this 
> limitation and its implications?

There was some brief discussion about this in the past, but I think 
mostly in the context of Phaser rather than RRWL. The "configuration 
change" usage where a huge number of concurrent threads hold the read 
lock to exclude a rare config change is a good motivation to look at 
this. I've created JDK-8349031 [1] to track it.

-Alan

[1] https://bugs.openjdk.org/browse/JDK-8349031