> Yes, it's the same problem that copy-on-read has. We can serialize I/O > requests, if necessary, in order to prevent them racing with each other.
My current patchset have a big dedup_lock co mutex. I'll replace it with the overlapping request solution. > Where do you see an issue - do you think the refcount manipulations > you're doing for dedup might conflict with internal snapshots? Ok, Anyway it seems to pass the savevm tests. Benoît