lundman

Cool, as someone still working with that code (a little bit still remains) thanks for your work :)

Can't comment on the original macos version, or zevo version, but you will not lose a pool by "just unplugging it" or rebooting without export.

\o/

Alas, didn't quite work. Turns out DPC's are not allowed to wait, so the first condvar we hit in zio makes us die :)

Looks like I started 2017/02/08

Ah that looks interesting. I will research that once I leave SF

Just a matter of cherry-picking it in. I'll get around it it soon

Just a hobby, working on it because I want to :)

I tried that way first, but because it called the callback at different level, and ZFS grabs a mutex, it just died. Which why I changed it to spawn a taskq to wait for the callback to come back, then tell ZFS about it. So it is async right now, I'm just not happy it has to create yet another taskq to handle it, for each IO request.