Hello, On Thu, Aug 15, 2019 at 04:46:23PM +0200, Jan Kara wrote: > Although I would note that here you take effort not to recycle bdi->id so > that you don't flush wrong devices while in patch 4 you take pretty lax > approach to feeding garbage into the writeback system. So these two don't > quite match to me... So, I was trying to avoid systemic errors where the wrong thing can be triggered repeatedly. A wrong flush once in a blue moon shouldn't be a big problem but if they can be triggered consistently by some pathological behavior, it's an a lot bigger problem. Thanks. -- tejun
