David Woodhouse wrote: > Can we get away with representing discards as 'writes without buffers'? That seems like a very good idea. They have the same requirements as writes w.r.t. barriers and merges/discards. I can imagine situations where a filesystem wants discards to work with barrier requests in exactly the same way as writes. -- Jamie -- 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