On 4/22/22 6:52 AM, Hao Xu wrote: > Hi Avi, > ? 4/13/22 6:33 PM, Avi Kivity ??: >> Unfortunately, only ideas, no patches. But at least the first seems very easy. >> >> >> - IORING_OP_MEMCPY_IMMEDIATE - copy some payload included in the op itself (1-8 bytes) to a user memory location specified by the op. >> >> >> Linked to another op, this can generate an in-memory notification useful for busy-waiters or the UMWAIT instruction >> >> >> This would be useful for Seastar, which looks at a timer-managed memory location to check when to break computation loops. >> >> >> - IORING_OP_MEMCPY - asynchronously copy memory >> >> >> Some CPUs include a DMA engine, and io_uring is a perfect interface to exercise it. It may be difficult to find space for two iovecs though. > > I have a question about the 'DMA' here, do you mean DMA device for > memory copy? My understanding is you want async memcpy so that the > cpu can relax when the specific hardware is doing memory copy. the > thing is for cases like busy waiting or UMAIT, the length of the memory > to be copied is usually small(otherwise we don't use busy waiting or > UMAIT, right?). Then making it async by io_uring's iowq may introduce > much more overhead(the context switch). Nothing fast should use io-wq. But not sure why you think this would need it, as long as you can start the operation in a sane fashion and get notified when done, why would it need io-wq? -- Jens Axboe
