On Tuesday May 2, bert.hubert@xxxxxxxxxxxxx wrote: > On Mon, May 01, 2006 at 03:30:19PM +1000, NeilBrown wrote: > > When a md array has been idle (no writes) for 20msecs it is marked as > > 'clean'. This delay turns out to be too short for some real > > workloads. So increase it to 200msec (the time to update the metadata > > should be a tiny fraction of that) and make it sysfs-configurable. > > What does this mean, 'too short'? What happens in that case, backing block > devices are still busy writing? When making this configurable, the help text > better explain what the trade offs are. "too short" means that the update happens often enough to cause a noticeable performance degradation. In an application writes steadily very 21msecs (or maybe 30msecs) then there will be 2 superblock writes and 1 application write every 21msecs, and this causes enough disk io to close the app down. - I guess all the updates fill up the 21msec space. With a larger delay - 200msec - you could still get bad situations e.g. with the app writing every 210msecs. However 2 superblock updates plus one app write is a much smaller fraction of 200msecs, so there shouldn't be as many problems. Yes, a more detailed explanation should go in Documentation/md.txt NeilBrown - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
