Hippolyte Barraud

> Memory registration is also interesting, but in practice, it has to be done when the executor comes online. After there are requests flowing it gets very hard, for reasons...

Thanks for reporting the issue @inevity. I'll try to reproduce this weekend and I'll bisect the log to find the culprit if I can. There are fewer users of the...

It just so happens that I'm dealing with a similar issue with some Glommio app myself. My case is slightly different but ends up being essentially the same. I am...

@duarten your example works because you use the stack for storage. Try to make this work with a stream, and you'll realize you can't always do that. I'm looking for...

> (To be clear, I'm not pushing back on anything, I'm just trying to understand the issue. As you see, I don't have a lot of experience with the lower...

Thanks @duarten you definitely say it better than I do 😅 > Until then, named futures seem like a good approach. Maybe we can introduce a macro that will generate...

> this violates the preempt timer agreement How does it? The agreement encompasses two things on a best-effort basis: * We will schedule IO on that (moving) interval, and *...

For reference, this PR is motivated by the fact that I have an app that consistently panics at the following assertion: https://github.com/DataDog/glommio/blob/69fd84b347ef5965d7930352a540c875f6431a66/glommio/src/sys/uring.rs#L1719-L1722

Hey @dignifiedquire! Can you post an example I can compile on my end to reproduce?

Oh, I see what's going on. The issue is that this symbol you don't have access to itself wraps the stream you provide us. Instead, you should treat it like...