On 10/30/07, Arnd Bergmann <arnd@xxxxxxxx> wrote: > This make me curious, why would t13 want to invent a new command when > there is already the erase command from CFA? > > It's not exactly the same, but close enough that the proposed BIO_HINT_RELEASE > should probably be mapped to CFA_ERASE (0xc0) on drives that support it: > http://t13.org/Documents/UploadedDocuments/technical/d97116r1.pdf > I'm not sure about the background. However, it's definitely a sign that passing the deleted block info to the flash-based storage is useful. Anyway, BIO_HINT_RELEASE could destroy the content of the blocks after being passed to the device. I think that other bio should not be reordered accross that hint (just like barrier). Dongjun - To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html