On 2020-06-22 19:28, Kiwoong Kim wrote: > If you could get the information, Many would exploit it for their respective purposes. > But, it's important for the information to contain accurate timestamps when the driver > hooks it, if you're trying to figure out something wrong. > > As for scaling DVFS knobs to boost UFS throughput, locating in the ufs driver is more > Beneficial because SoC vendors have their own power domains and thus lead to make > different way of what to scale up to boost. If it's populated in block layer, there is > no way to introduce boosting per SoC. Thanks for the clarification. Unfortunately we do not yet have an API for sharing information between I/O schedulers and block drivers ... Bart.
