Re: [RFC PATCH 0/3 v3] futex/sched: introduce FUTEX_SWAP operation

Hi Jim, thank you for your interest! While FUTEX_SWAP seems to be a nonstarter, there is a discussion off-list on how to approach the larger problem of userspace scheduling. A full userspace scheduling patchset is likely to take some time to shape out, but the "core" patches of wait/wake/swap are

Re: [RFC PATCH 0/3 v3] futex/sched: introduce FUTEX_SWAP operation

I'm not well versed in this part of the kernel (ok, any part, really), but I wanted to chime in from a user perspective that I'm very interested in this functionality. We (Rob + Ryan + I, cc'd) are currently developing the second generation of the Shadow simulator , whic

Re: [RFC PATCH 0/3 v3] futex/sched: introduce FUTEX_SWAP operation

Hi Thomas, Ingo! Do you have any comments/suggestions/objections here? FUTEX_SWAP seems to be quite useful for fast task context switching, and several teams at Google would like to see this capability upstreamed. Thanks, Peter On Wed, Jun 24, 2020 at 11:53 AM Peter Oskolkov wrote: > > From: Pe

[RFC PATCH 0/3 v3] futex/sched: introduce FUTEX_SWAP operation

From: Peter Oskolkov This is an RFC! As Paul Turner presented at LPC in 2013 ... - pdf: http://pdxplumbers.osuosl.org/2013/ocw//system/presentations/1653/original/LPC%20-%20User%20Threading.pdf - video: https://www.youtube.com/watch?v=KXuZi9aeGTw ... Google has developed an M:N userspace threa