On Fri, Oct 19, 2012 at 12:36:00PM -0700, Tejun Heo wrote: > Hello, Vivek. > > On Fri, Oct 19, 2012 at 11:00:11AM -0400, Vivek Goyal wrote: > > > That way we can stick to the usual stats facility. > > > > So how does this help? Because it is a monotonically increasing value > > we can use per cpu stats without extra locking? Or somthing else? > > It's generally much simpler to expose dumb increasing counters. You > don't have to worry about mismatching decrements (for whatever reason, > percpu or segmented counters), so unless there's a pretty good reason > to deviate, why deviate?
I really can't think of a reason to deviate. I was just curious of advantages. I think it does make sense to not get into decrement business and let user space subtract two values and figure out how much IO from the group is throttled. Thanks Vivek -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
