OK, it looks like the problem is fixed for me in both the stock 2.6.35 and +iofix provided by Brian Rogers. There's still [kdmflush] and a bunch of other programs causing a lot of I/O wait (according to top and iotop), but the system is MUCH more responsive. Usually when the problem occurred, the HDD light would go solid for several moments before I could use my system again. Now, the pause is brief, much less than two seconds if it ceases being responsive at all. I mentioned earlier that the problem still occurred shortly after boot, but that was the HDD light I was referring to, not the perceived responsiveness of the system. So for me, the solution is to upgrade to 2.6.35.
OK, it looks like the problem is fixed for me in both the stock 2.6.35 and +iofix provided by Brian Rogers. There's still [kdmflush] and a bunch of other programs causing a lot of I/O wait (according to top and iotop), but the system is MUCH more responsive. Usually when the problem occurred, the HDD light would go solid for several moments before I could use my system again. Now, the pause is brief, much less than two seconds if it ceases being responsive at all. I mentioned earlier that the problem still occurred shortly after boot, but that was the HDD light I was referring to, not the perceived responsiveness of the system. So for me, the solution is to upgrade to 2.6.35.