On Tue, 14 Jan 2025 at 20:12, Joanne Koong <joannelkoong@xxxxxxxxx> wrote: > If we copy the cache page, do we not have the same issue with needing > an rb tree to track writeback state since writeback on the original > folio would be immediately cleared? Writeback would not be cleared in that case. The copy would be to guarantee that the page can be migrated. Starting migration for an under-writeback page would need some new mechanism, because currently that's not possible. But I realize now that even though write-through does not involve PG_writeback, doing splice will result in those cache pages being referenced for an indefinite amount of time, which can deny migration. Ugh. Same as page reading, this exists today. Thanks, Miklos
