On Tue, Jun 15, 2010 at 08:55:38PM +1000, Nick Piggin wrote: > > What I do in fsblock is to maintain a block-nr sorted tree of dirty > blocks. This works nicely because fsblock dirty state is properly > synchronized with page dirty state. So writeout can just walk this in > order and it provides pretty optimal submission pattern of any > interleavings of data and metadata. No need for buffer boundary or > hacks like that. (needs some intelligence for delalloc, though). I think worrying about indirect blocks really doesn't matter much these days. For one thing extent based filesystems have a lot less of these, and second for a journaling filesystem we only need to log modification to the indirect blocks and not actually write them back in place during the sync. At least for XFS the actual writeback can happen a lot later, as part of the ordered list of delwri buffers. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>