On 4/16/19 2:59 PM, Yang Shi wrote:
On 4/16/19 2:22 PM, Dave Hansen wrote:In Keith's code, I don't think we differentiated. We let any node
Keith Busch had a set of patches to let you specify the demotion orderDoes this mean any remote node? Or just DRAM to PMEM, but remote PMEM
via sysfs for fun. The rules we came up with were:
1. Pages keep no history of where they have been
2. Each node can only demote to one other node
might be ok?
demote to any other node you want, as long as it follows the cycle rule.