Jens Axboe

Got that one, thanks!

Sure, we can certainly do that. Remind me next week if I don't get to it, gone this week.

@isilence Can you take a look?

Can confirm I see the same here as you report. I added a bunch of debugging and all the masking is done correctly, and both sqpoll and io-wq workers end...

I don't think the library can handle this. The kernel scheduler doesn't seem to spread the love if the mask has isolated cpus in it, and things like io-wq only...

In case I wasn't clear, this isn't a io_uring bug, and nobody has reported any issues with isolcpus before. In other words, this is all news to me and others....

I like making the cancel bits consistent, and it's a separate patch so good like that. Made a few comments on the other patch.

Nick, can you address the comments from last week? I'd like to cut 2.4 soon, and it would be a shame to do that without adding these bits.

@dankamongmen ping on the above...

I finally gave up waiting on OP and pulled this, fixing up my complaints after the fact.