[bicolao]

fuse probably isn't a good example here because you still have to enter kernel space if i'm not mistaken, then out again to the fs driver in userspace then probably back to kernel space (block driver). fuse has many upsides, but I don't think performance is one of them.

[viega]

Well, you still have to enter the kernel to actually queue an OS-level thread w/ a futex. The kernel supporting being able to move stuff to userland sure doesn't guarantee better performance-- the main opportunity from that perspective is minimizing how often you cross the boundary.

You're 100% right that there are plenty of other considerations, often positive for lifting things out, like minimization of ring 0 attack surface.