David Woodhouse wrote: > On Tue, 2008-08-12 at 19:04 +0100, Jamie Lokier wrote: > > David Woodhouse wrote: > > > Anything else I need to address before you pull the tree? Any comment on > > > the BLKDISCARD ioctl? I've left that one using the non-barrier version > > > since it's waiting for it anyway, and shouldn't be happening > > > concurrently with anything else. > > > > What makes you think a userspace filesystem or database wouldn't call > > BLKDISCARD concurrently with anything else? > > The BLKDISCARD ioctl is synchronous -- I haven't done an aio version of > it. Issuing a write to the same sectors before it finishes would be kind > of silly. You're right, as long as it's not aio, there's no way to sensibly order it with concurrent writes; I take it back. (Aside: You would issue writes to *different* sectors before BLKDISCARD, and they must be done in that order. That is how you implement journalling.) -- 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
