Re: [RFC][PATCH] iowait statistics

[Martin J. Bligh]

>> This appears to be global across all cpu's. Maybe nr_iowait_tasks
>> should be accounted on a per-cpu basis, where
> 
> While your proposal should work, somehow I doubt it's worth
> the complexity. It's just a statistic to help sysadmins ;)

Depends how often you're going to end up bouncing that cacheline 
around ... do you do this for every IO?

M.