[asveikau]

I had a similar reaction. It's not rust that makes this faster. It's the algorithm chosen. The rust part is an attention grabbing headline.

However I could see an argument that rust or another higher level language makes it easier for someone to experiment with a new algorithm and iterate faster on those ideas.

[viraptor]

It's not just attention grabbing. So far, almost all rust development I've seen has been in drivers. Getting something as core as scheduler replaced is a very interesting event.

[asveikau]

I remember replacing the Linux scheduler in an undergraduate class. It's probably changed since those days but I don't think it's that hard. Doing a good job is probably very hard though.

[viraptor]

I don't mean that it's particularly hard, but rather that it's using new interfaces which haven't been exposed yet, AFAIK. Scheduler itself + bpf is there from what I've seen, but likely other things too.

[asveikau]

But isn't exposing a C interface to Rust very easy? In either direction...

[viraptor]

1:1, calling the original functions - sure. Building a good usable interface - that's harder.