Messages in this thread | | | Subject | Re: [PATCH v3] io_uring: reduce latency by reissueing the operation | From | Jens Axboe <> | Date | Mon, 21 Jun 2021 14:05:24 -0600 |
| |
On 6/21/21 1:22 PM, Olivier Langlois wrote: > It is quite frequent that when an operation fails and returns EAGAIN, > the data becomes available between that failure and the call to > vfs_poll() done by io_arm_poll_handler(). > > Detecting the situation and reissuing the operation is much faster > than going ahead and push the operation to the io-wq.
This now looks pretty good to me. I know you had some data associated with this, would be great to include it in the commit message.
-- Jens Axboe
| |