Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-07 Thread Minchan Kim
Hi Andrew, On Tue, Mar 07, 2017 at 02:43:38PM -0800, Andrew Morton wrote: > On Tue, 7 Mar 2017 11:05:45 +0100 Michal Hocko wrote: > > > On Fri 03-03-17 16:10:27, Andrew Morton wrote: > > > On Thu, 2 Mar 2017 17:30:54 +0100 Michal Hocko wrote: > > > > > >

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-07 Thread Minchan Kim
Hi Andrew, On Tue, Mar 07, 2017 at 02:43:38PM -0800, Andrew Morton wrote: > On Tue, 7 Mar 2017 11:05:45 +0100 Michal Hocko wrote: > > > On Fri 03-03-17 16:10:27, Andrew Morton wrote: > > > On Thu, 2 Mar 2017 17:30:54 +0100 Michal Hocko wrote: > > > > > > > > It's not that I think you're

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-07 Thread Andrew Morton
On Tue, 7 Mar 2017 11:05:45 +0100 Michal Hocko wrote: > On Fri 03-03-17 16:10:27, Andrew Morton wrote: > > On Thu, 2 Mar 2017 17:30:54 +0100 Michal Hocko wrote: > > > > > > It's not that I think you're wrong: it *is* an implementation detail. > > > > But

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-07 Thread Andrew Morton
On Tue, 7 Mar 2017 11:05:45 +0100 Michal Hocko wrote: > On Fri 03-03-17 16:10:27, Andrew Morton wrote: > > On Thu, 2 Mar 2017 17:30:54 +0100 Michal Hocko wrote: > > > > > > It's not that I think you're wrong: it *is* an implementation detail. > > > > But we take a bit of incoherency from

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-07 Thread Michal Hocko
On Fri 03-03-17 16:10:27, Andrew Morton wrote: > On Thu, 2 Mar 2017 17:30:54 +0100 Michal Hocko wrote: > > > > It's not that I think you're wrong: it *is* an implementation detail. > > > But we take a bit of incoherency from batching all over the place, so > > > it's a little

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-07 Thread Michal Hocko
On Fri 03-03-17 16:10:27, Andrew Morton wrote: > On Thu, 2 Mar 2017 17:30:54 +0100 Michal Hocko wrote: > > > > It's not that I think you're wrong: it *is* an implementation detail. > > > But we take a bit of incoherency from batching all over the place, so > > > it's a little odd to take a stand

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-03 Thread Andrew Morton
On Thu, 2 Mar 2017 17:30:54 +0100 Michal Hocko wrote: > > It's not that I think you're wrong: it *is* an implementation detail. > > But we take a bit of incoherency from batching all over the place, so > > it's a little odd to take a stand over this particular instance of it >

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-03 Thread Andrew Morton
On Thu, 2 Mar 2017 17:30:54 +0100 Michal Hocko wrote: > > It's not that I think you're wrong: it *is* an implementation detail. > > But we take a bit of incoherency from batching all over the place, so > > it's a little odd to take a stand over this particular instance of it > > - whether

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-02 Thread Michal Hocko
On Thu 02-03-17 09:01:01, Johannes Weiner wrote: > On Wed, Mar 01, 2017 at 07:57:35PM +0100, Michal Hocko wrote: > > On Wed 01-03-17 13:31:49, Johannes Weiner wrote: [...] > > > The error when reading a specific smaps should be completely ok. > > > > > > In numbers: even if your process is

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-02 Thread Michal Hocko
On Thu 02-03-17 09:01:01, Johannes Weiner wrote: > On Wed, Mar 01, 2017 at 07:57:35PM +0100, Michal Hocko wrote: > > On Wed 01-03-17 13:31:49, Johannes Weiner wrote: [...] > > > The error when reading a specific smaps should be completely ok. > > > > > > In numbers: even if your process is

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-02 Thread Johannes Weiner
On Wed, Mar 01, 2017 at 07:57:35PM +0100, Michal Hocko wrote: > On Wed 01-03-17 13:31:49, Johannes Weiner wrote: > > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > > @@ -474,7 +474,7 @@ static int madvise_free_single_vma(struct > > > vm_area_struct *vma, > > >

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-02 Thread Johannes Weiner
On Wed, Mar 01, 2017 at 07:57:35PM +0100, Michal Hocko wrote: > On Wed 01-03-17 13:31:49, Johannes Weiner wrote: > > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > > @@ -474,7 +474,7 @@ static int madvise_free_single_vma(struct > > > vm_area_struct *vma, > > >

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Minchan Kim
On Wed, Mar 01, 2017 at 07:57:35PM +0100, Michal Hocko wrote: > On Wed 01-03-17 13:31:49, Johannes Weiner wrote: > > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > > > show MADV_FREE pages info of each vma in smaps. The interface

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Minchan Kim
On Wed, Mar 01, 2017 at 07:57:35PM +0100, Michal Hocko wrote: > On Wed 01-03-17 13:31:49, Johannes Weiner wrote: > > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > > > show MADV_FREE pages info of each vma in smaps. The interface

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Shaohua Li
On Wed, Mar 01, 2017 at 06:49:56PM +0100, Michal Hocko wrote: > On Wed 01-03-17 09:37:10, Shaohua Li wrote: > > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > > > show MADV_FREE pages info of each vma in smaps. The interface is

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Shaohua Li
On Wed, Mar 01, 2017 at 06:49:56PM +0100, Michal Hocko wrote: > On Wed 01-03-17 09:37:10, Shaohua Li wrote: > > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > > > show MADV_FREE pages info of each vma in smaps. The interface is

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Johannes Weiner
On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > show MADV_FREE pages info of each vma in smaps. The interface is for > > diganose or monitoring purpose, userspace could use it to understand > > what happens in the application. Since

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Johannes Weiner
On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > show MADV_FREE pages info of each vma in smaps. The interface is for > > diganose or monitoring purpose, userspace could use it to understand > > what happens in the application. Since

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Michal Hocko
On Wed 01-03-17 13:31:49, Johannes Weiner wrote: > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > > show MADV_FREE pages info of each vma in smaps. The interface is for > > > diganose or monitoring purpose, userspace could use it

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Michal Hocko
On Wed 01-03-17 13:31:49, Johannes Weiner wrote: > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > > show MADV_FREE pages info of each vma in smaps. The interface is for > > > diganose or monitoring purpose, userspace could use it

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Shaohua Li
On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > show MADV_FREE pages info of each vma in smaps. The interface is for > > diganose or monitoring purpose, userspace could use it to understand > > what happens in the application. Since

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Shaohua Li
On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > show MADV_FREE pages info of each vma in smaps. The interface is for > > diganose or monitoring purpose, userspace could use it to understand > > what happens in the application. Since

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Michal Hocko
On Wed 01-03-17 09:37:10, Shaohua Li wrote: > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > > show MADV_FREE pages info of each vma in smaps. The interface is for > > > diganose or monitoring purpose, userspace could use it to

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Michal Hocko
On Wed 01-03-17 09:37:10, Shaohua Li wrote: > On Wed, Mar 01, 2017 at 02:36:24PM +0100, Michal Hocko wrote: > > On Fri 24-02-17 13:31:49, Shaohua Li wrote: > > > show MADV_FREE pages info of each vma in smaps. The interface is for > > > diganose or monitoring purpose, userspace could use it to

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Michal Hocko
On Fri 24-02-17 13:31:49, Shaohua Li wrote: > show MADV_FREE pages info of each vma in smaps. The interface is for > diganose or monitoring purpose, userspace could use it to understand > what happens in the application. Since userspace could dirty MADV_FREE > pages without notice from kernel,

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-03-01 Thread Michal Hocko
On Fri 24-02-17 13:31:49, Shaohua Li wrote: > show MADV_FREE pages info of each vma in smaps. The interface is for > diganose or monitoring purpose, userspace could use it to understand > what happens in the application. Since userspace could dirty MADV_FREE > pages without notice from kernel,

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-02-27 Thread Hillf Danton
On February 25, 2017 5:32 AM Shaohua Li wrote: > > show MADV_FREE pages info of each vma in smaps. The interface is for > diganose or monitoring purpose, userspace could use it to understand > what happens in the application. Since userspace could dirty MADV_FREE > pages without notice from

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-02-27 Thread Hillf Danton
On February 25, 2017 5:32 AM Shaohua Li wrote: > > show MADV_FREE pages info of each vma in smaps. The interface is for > diganose or monitoring purpose, userspace could use it to understand > what happens in the application. Since userspace could dirty MADV_FREE > pages without notice from

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-02-27 Thread Michal Hocko
On Fri 24-02-17 13:31:49, Shaohua Li wrote: > show MADV_FREE pages info of each vma in smaps. The interface is for > diganose or monitoring purpose, userspace could use it to understand > what happens in the application. Since userspace could dirty MADV_FREE > pages without notice from kernel,

Re: [PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-02-27 Thread Michal Hocko
On Fri 24-02-17 13:31:49, Shaohua Li wrote: > show MADV_FREE pages info of each vma in smaps. The interface is for > diganose or monitoring purpose, userspace could use it to understand > what happens in the application. Since userspace could dirty MADV_FREE > pages without notice from kernel,

[PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-02-24 Thread Shaohua Li
show MADV_FREE pages info of each vma in smaps. The interface is for diganose or monitoring purpose, userspace could use it to understand what happens in the application. Since userspace could dirty MADV_FREE pages without notice from kernel, this interface is the only place we can get accurate

[PATCH V5 6/6] proc: show MADV_FREE pages info in smaps

2017-02-24 Thread Shaohua Li
show MADV_FREE pages info of each vma in smaps. The interface is for diganose or monitoring purpose, userspace could use it to understand what happens in the application. Since userspace could dirty MADV_FREE pages without notice from kernel, this interface is the only place we can get accurate