I see no reason why atime updates can't be postponed until some moment other metadata has to be flushed, or once a minute, whatever comes first. The exactness of atime might suffer, but nobody will notice. That said, I agree the noatime mount option covers most needs.
Naah, only the dispatcher should in the kernel. The ordering of the processor queue (scheduler) can be delegated to a process outside the kernel.
Come on, this shape is almost common knowledge. Anyone can see this frequently on Discovery Channel or National Geographic Channel.
You've been avoiding Bushes for too long. They're all shaved nowadays.
I see no reason why atime updates can't be postponed until some moment other metadata has to be flushed, or once a minute, whatever comes first.
The exactness of atime might suffer, but nobody will notice.
That said, I agree the noatime mount option covers most needs.