I think I might split incoming requests into two heaps. The first heap would be synchronous requests such as reads and syncs that someone in userspace is blocking on. The second is background I/O like writeback and readahead. The same distinction that CFQ completely makes. Anyway, I plan to give the first heap strict priority over the second. But anyway yeah, I'm into this more for learning how to interface with the APIs in question and write kernel code in general. Good performance is a secondary objective. _______________________________________________ Kernelnewbies mailing list Kernelnewbies@xxxxxxxxxxxxxxxxx http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
