On Fri, Sep 22, 2017 at 3:30 PM, Adrian Hunter <adrian.hunter@xxxxxxxxx> wrote: > On 21/09/17 12:47, Ulf Hansson wrote: >> I asume the goal of adding this option is to enable us to move slowly >> forward. In general that might be a good idea, however for this >> particular case I am not sure. >> >> The main reason is simply that I find it unlikely that people and >> distributions will actually go in and change the default value, so in >> the end we will just be adding new code, which isn't really going to >> be much tested. That's what happened in scsi case. > > The argument that no one is going to test anyway so we shouldn't give them > the opportunity, is not a sustainable vision for the future. Instead we > should reach out to relevant stakeholders and get them to do their testing > with blk-mq first. We *could* simply invert the option then. Default it to "y" and only leave it as a debugging aid so that people can set it to "n" if they want to test with MQ disabled. This is also simple to revert by a oneliner just removing "default y" if there are problems with it. Yours, Linus Walleij
