James, > I was hoping the HPB guys would do this. Yes, that would be great. Easier to validate for someone with access to the hardware in question. > Agreed, that was my initial proposed solution: get rid of the write > buffer optimzation now to fix the API abuse and see if we can add it > back in a more acceptable form later. Doesn't matter to me whether we back out the 2.0 stuff or mark it as broken. I merely objected to reverting all of HPB since I don't think that would solve anything. But obviously we'll need a patch to fix 5.15 ASAP... -- Martin K. Petersen Oracle Linux Engineering
