Am 27.06.2019 um 17:42 hat Alberto Garcia geschrieben: > On Thu 27 Jun 2019 05:38:56 PM CEST, Alberto Garcia wrote: > >> I would consider 64k cluster/8k subcluster as too extreme for me. > > I forgot to add: this 64k/8k ratio is only with my current prototype. > > In practice if we go with the 128-bit L2 entries we would have 64 > subclusters per cluster, or 32 if we want to have a separate > QCOW_OFLAG_ZERO for each subcluster (would we need this?).
Yes, I think we'd want to have a separate zero flag for each subcluster. Otherwise, when writing to a zero cluster, you'd have to COW the whole supercluster again. And you'd have to fall back to explicit writes of a zeroed buffer rather than using efficient operations more often. Kevin
