Every tiered index search() call does an internal conversion to padded dataset first.
One solution is to make the owning storage of tiered index padded. New vectors as part of the initial build or extend can still accept standard datasets but can internally be copied into the padded storage.
During search, tiered index currently calls "attach_dataset" (not directly but through a helper called convert_standard_to_padded_index). We are planning to remove these helpers and the "attach_dataset" shortly in favor of update_dataset.
Every tiered index search() call does an internal conversion to padded dataset first.
One solution is to make the owning storage of tiered index padded. New vectors as part of the initial build or extend can still accept standard datasets but can internally be copied into the padded storage.
During search, tiered index currently calls "attach_dataset" (not directly but through a helper called convert_standard_to_padded_index). We are planning to remove these helpers and the "attach_dataset" shortly in favor of update_dataset.