On Wed, Sep 13, 2017 at 02:40:00PM +0300, Adrian Hunter wrote: > Non-CQE blk-mq showed a 3% decrease in sequential read performance. This > seemed to be coming from the inferior latency of running work items compared > with a dedicated thread. Hacking blk-mq workqueue to be unbound reduced the > performance degradation from 3% to 1%.
Can you start a discussion on just this on the linux-block lists?