Messages in this thread | | | Date | Fri, 16 Aug 2013 17:13:39 +0200 | From | Oleg Nesterov <> | Subject | Re: proc/stat: idle goes backward |
| |
On 08/16, Frederic Weisbecker wrote: > > On Fri, Aug 16, 2013 at 04:47:04PM +0200, Oleg Nesterov wrote: > > > > Questions: > > > > - Any other reason why it can be non-monotonic? > > > > - Should we fix this or should we document that userspace > > should handle this itself? > > > > IOW, is this is bug or not? > > I don't know if we want to fix it (I personally think we should because it is not the > first time I hear complains about this) but if we do, here is a possible fix: > > https://lkml.org/lkml/2013/8/8/638
Thanks! it is not easy to read the patches on lkml.org and I do not understand this code enough. But it seems that this should address my concerns, including the "even ignoring drivers/cpuidle/".
Except, I am not sure that these changes handle the case when nr_iowait() change in between.
Are you going to resend?
Oleg.
| |