On 26/03/19 14:18, Stefan Hajnoczi wrote: > Hi Sergio, > Here are the forgotten event loop optimizations I mentioned: > > https://github.com/stefanha/qemu/commits/event-loop-optimizations > > The goal was to eliminate or reorder syscalls so that useful work (like > executing BHs) occurs as soon as possible after an event is detected. > > I remember that these optimizations only shave off a handful of > microseconds, so they aren't a huge win. They do become attractive on > fast SSDs with <10us read/write latency. > > These optimizations are aggressive and there is a possibility of > introducing regressions. > > If you have time to pick up this work, try benchmarking each commit > individually so performance changes are attributed individually. > There's no need to send them together in a single patch series, the > changes are quite independent.
Another thing to consider is IOCB_CMD_POLL, and replacing poll() with io_getevents(min_nr=1, nr=1). If more than one event is ready, it can be read directly from the ring buffer. Maybe we can even remove the little-tested epoll() path in favor of this one. Paolo
