Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On (02/19/16 10:39), Joonsoo Kim wrote: [..] > > not sure if it's worth mentioning in the comment, but the other > > concern here is the performance impact of an extra function call, > > I believe. otherwise, Joonsoo would just do: > > It's very natural thing so I'm not sure it is worth

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On (02/19/16 10:39), Joonsoo Kim wrote: [..] > > not sure if it's worth mentioning in the comment, but the other > > concern here is the performance impact of an extra function call, > > I believe. otherwise, Joonsoo would just do: > > It's very natural thing so I'm not sure it is worth

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Fri, 19 Feb 2016 10:39:10 +0900 Joonsoo Kim wrote: > > not sure if it's worth mentioning in the comment, but the other > > concern here is the performance impact of an extra function call, > > I believe. otherwise, Joonsoo would just do: > > It's very natural thing so

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Fri, 19 Feb 2016 10:39:10 +0900 Joonsoo Kim wrote: > > not sure if it's worth mentioning in the comment, but the other > > concern here is the performance impact of an extra function call, > > I believe. otherwise, Joonsoo would just do: > > It's very natural thing so I'm not sure it is

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

2016-02-19 9:34 GMT+09:00 Sergey Senozhatsky : > On (02/18/16 09:29), Steven Rostedt wrote: >> > diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h >> > index 534249c..fd6d9a5 100644 >> > --- a/include/linux/page_ref.h >> > +++

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

2016-02-19 9:34 GMT+09:00 Sergey Senozhatsky : > On (02/18/16 09:29), Steven Rostedt wrote: >> > diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h >> > index 534249c..fd6d9a5 100644 >> > --- a/include/linux/page_ref.h >> > +++ b/include/linux/page_ref.h >> > @@ -1,6 +1,54 @@ >> >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

2016-02-18 23:29 GMT+09:00 Steven Rostedt : > On Mon, 15 Feb 2016 12:04:50 +0900 > js1...@gmail.com wrote: > > >> diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h >> index 534249c..fd6d9a5 100644 >> --- a/include/linux/page_ref.h >> +++

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

2016-02-18 23:29 GMT+09:00 Steven Rostedt : > On Mon, 15 Feb 2016 12:04:50 +0900 > js1...@gmail.com wrote: > > >> diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h >> index 534249c..fd6d9a5 100644 >> --- a/include/linux/page_ref.h >> +++ b/include/linux/page_ref.h >> @@ -1,6 +1,54

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On (02/18/16 09:29), Steven Rostedt wrote: > > diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h > > index 534249c..fd6d9a5 100644 > > --- a/include/linux/page_ref.h > > +++ b/include/linux/page_ref.h > > @@ -1,6 +1,54 @@ > > #include > > #include > > #include > > +#include >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On (02/18/16 09:29), Steven Rostedt wrote: > > diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h > > index 534249c..fd6d9a5 100644 > > --- a/include/linux/page_ref.h > > +++ b/include/linux/page_ref.h > > @@ -1,6 +1,54 @@ > > #include > > #include > > #include > > +#include >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, 15 Feb 2016 12:04:50 +0900 js1...@gmail.com wrote: > diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h > index 534249c..fd6d9a5 100644 > --- a/include/linux/page_ref.h > +++ b/include/linux/page_ref.h > @@ -1,6 +1,54 @@ > #include > #include > #include > +#include >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, 15 Feb 2016 12:04:50 +0900 js1...@gmail.com wrote: > diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h > index 534249c..fd6d9a5 100644 > --- a/include/linux/page_ref.h > +++ b/include/linux/page_ref.h > @@ -1,6 +1,54 @@ > #include > #include > #include > +#include >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Thu, 18 Feb 2016 16:46:08 +0900 Joonsoo Kim wrote: > 2016-02-16 10:16 GMT+09:00 Steven Rostedt : > > On Tue, 16 Feb 2016 09:47:20 +0900 > > Joonsoo Kim wrote: > > > >> > They return true when CONFIG_TRACEPOINTS is configured in

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Thu, 18 Feb 2016 16:46:08 +0900 Joonsoo Kim wrote: > 2016-02-16 10:16 GMT+09:00 Steven Rostedt : > > On Tue, 16 Feb 2016 09:47:20 +0900 > > Joonsoo Kim wrote: > > > >> > They return true when CONFIG_TRACEPOINTS is configured in and the > >> > tracepoint is enabled, and false otherwise. >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

2016-02-16 10:16 GMT+09:00 Steven Rostedt : > On Tue, 16 Feb 2016 09:47:20 +0900 > Joonsoo Kim wrote: > >> > They return true when CONFIG_TRACEPOINTS is configured in and the >> > tracepoint is enabled, and false otherwise. >> >> This implementation is

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

2016-02-16 10:16 GMT+09:00 Steven Rostedt : > On Tue, 16 Feb 2016 09:47:20 +0900 > Joonsoo Kim wrote: > >> > They return true when CONFIG_TRACEPOINTS is configured in and the >> > tracepoint is enabled, and false otherwise. >> >> This implementation is what you proposed before. Please refer below

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Tue, 16 Feb 2016 09:47:20 +0900 Joonsoo Kim wrote: > > They return true when CONFIG_TRACEPOINTS is configured in and the > > tracepoint is enabled, and false otherwise. > > This implementation is what you proposed before. Please refer below > link and source. > >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Tue, 16 Feb 2016 09:47:20 +0900 Joonsoo Kim wrote: > > They return true when CONFIG_TRACEPOINTS is configured in and the > > tracepoint is enabled, and false otherwise. > > This implementation is what you proposed before. Please refer below > link and source. > >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, Feb 15, 2016 at 11:07:41AM -0500, Steven Rostedt wrote: > On Mon, 15 Feb 2016 12:04:50 +0900 > js1...@gmail.com wrote: > > > From: Joonsoo Kim > > > > CMA allocation should be guaranteed to succeed by definition, but, > > unfortunately, it would be failed

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, Feb 15, 2016 at 11:07:41AM -0500, Steven Rostedt wrote: > On Mon, 15 Feb 2016 12:04:50 +0900 > js1...@gmail.com wrote: > > > From: Joonsoo Kim > > > > CMA allocation should be guaranteed to succeed by definition, but, > > unfortunately, it would be failed sometimes. It is hard to track

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, 15 Feb 2016 12:04:50 +0900 js1...@gmail.com wrote: > From: Joonsoo Kim > > CMA allocation should be guaranteed to succeed by definition, but, > unfortunately, it would be failed sometimes. It is hard to track down > the problem, because it is related to page

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, 15 Feb 2016 12:04:50 +0900 js1...@gmail.com wrote: > From: Joonsoo Kim > > CMA allocation should be guaranteed to succeed by definition, but, > unfortunately, it would be failed sometimes. It is hard to track down > the problem, because it is related to page reference manipulation and >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

2016-02-15 14:28 GMT+09:00 Sergey Senozhatsky : > On (02/15/16 14:08), Sergey Senozhatsky wrote: >> >> will this compile with !CONFIG_TRACEPOINTS config? >> Yes, even if !CONFIG_TRACEPOINTS, it is compiled well. > uh.. sorry, was composed in email client. seems

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

2016-02-15 14:28 GMT+09:00 Sergey Senozhatsky : > On (02/15/16 14:08), Sergey Senozhatsky wrote: >> >> will this compile with !CONFIG_TRACEPOINTS config? >> Yes, even if !CONFIG_TRACEPOINTS, it is compiled well. > uh.. sorry, was composed in email client. seems the correct way to do it is > >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On (02/15/16 14:08), Sergey Senozhatsky wrote: > > will this compile with !CONFIG_TRACEPOINTS config? > uh.. sorry, was composed in email client. seems the correct way to do it is +#if defined CONFIG_DEBUG_PAGE_REF && defined CONFIG_TRACEPOINTS #include #define

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On (02/15/16 14:08), Sergey Senozhatsky wrote: > > will this compile with !CONFIG_TRACEPOINTS config? > uh.. sorry, was composed in email client. seems the correct way to do it is +#if defined CONFIG_DEBUG_PAGE_REF && defined CONFIG_TRACEPOINTS #include #define

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

Hello Joonsoo, On (02/15/16 12:04), js1...@gmail.com wrote: [..] > <...>-9018 [004]92.678375: page_ref_set: pfn=0x17ac9 flags=0x0 > count=1 mapcount=0 mapping=(nil) mt=4 val=1 > <...>-9018 [004]92.678378: kernel_stack: > => get_page_from_freelist (81176659) > =>

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

Hello Joonsoo, On (02/15/16 12:04), js1...@gmail.com wrote: [..] > <...>-9018 [004]92.678375: page_ref_set: pfn=0x17ac9 flags=0x0 > count=1 mapcount=0 mapping=(nil) mt=4 val=1 > <...>-9018 [004]92.678378: kernel_stack: > => get_page_from_freelist (81176659) > =>

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Wed, Dec 09, 2015 at 10:36:48PM -0500, Steven Rostedt wrote: > On Thu, 10 Dec 2015 11:50:15 +0900 > Joonsoo Kim wrote: > > > Output of cpu 3, 7 are mixed and it's not easy to analyze it. > > > > I think that it'd be better not to sort stack trace. How do > > you think about it? Could you fix

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Thu, 10 Dec 2015 11:50:15 +0900 Joonsoo Kim wrote: > Output of cpu 3, 7 are mixed and it's not easy to analyze it. > > I think that it'd be better not to sort stack trace. How do > you think about it? Could you fix it, please? It may not be that easy to fix because of the sorting algorithm.

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Wed, Dec 09, 2015 at 03:01:54PM -0500, Steven Rostedt wrote: > On Thu, 3 Dec 2015 13:16:58 +0900 > Joonsoo Kim wrote: > > > On Tue, Nov 24, 2015 at 10:45:28AM +0900, Joonsoo Kim wrote: > > > On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > > > > On Mon, 23 Nov 2015 17:28:05

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Thu, 3 Dec 2015 13:16:58 +0900 Joonsoo Kim wrote: > On Tue, Nov 24, 2015 at 10:45:28AM +0900, Joonsoo Kim wrote: > > On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > > > On Mon, 23 Nov 2015 17:28:05 +0900 > > > Joonsoo Kim wrote: > > > > > > > On Fri, Nov 20, 2015 at

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Thu, 10 Dec 2015 11:50:15 +0900 Joonsoo Kim wrote: > Output of cpu 3, 7 are mixed and it's not easy to analyze it. > > I think that it'd be better not to sort stack trace. How do > you think about it? Could you fix it, please? It may not be that easy to fix because

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Wed, Dec 09, 2015 at 10:36:48PM -0500, Steven Rostedt wrote: > On Thu, 10 Dec 2015 11:50:15 +0900 > Joonsoo Kim wrote: > > > Output of cpu 3, 7 are mixed and it's not easy to analyze it. > > > > I think that it'd be better not to sort stack trace. How do > > you think

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Wed, Dec 09, 2015 at 03:01:54PM -0500, Steven Rostedt wrote: > On Thu, 3 Dec 2015 13:16:58 +0900 > Joonsoo Kim wrote: > > > On Tue, Nov 24, 2015 at 10:45:28AM +0900, Joonsoo Kim wrote: > > > On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > > > > On

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Thu, 3 Dec 2015 13:16:58 +0900 Joonsoo Kim wrote: > On Tue, Nov 24, 2015 at 10:45:28AM +0900, Joonsoo Kim wrote: > > On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > > > On Mon, 23 Nov 2015 17:28:05 +0900 > > > Joonsoo Kim

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Tue, Nov 24, 2015 at 10:45:28AM +0900, Joonsoo Kim wrote: > On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > > On Mon, 23 Nov 2015 17:28:05 +0900 > > Joonsoo Kim wrote: > > > > > On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > > > > On Fri, 20 Nov 2015

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Tue, Nov 24, 2015 at 10:45:28AM +0900, Joonsoo Kim wrote: > On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > > On Mon, 23 Nov 2015 17:28:05 +0900 > > Joonsoo Kim wrote: > > > > > On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > > > >

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > On Mon, 23 Nov 2015 17:28:05 +0900 > Joonsoo Kim wrote: > > > On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > > > On Fri, 20 Nov 2015 15:33:25 +0900 > > > Joonsoo Kim wrote: > > > > > > > > > > Steven, is it

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > On Mon, 23 Nov 2015 17:28:05 +0900 > Joonsoo Kim wrote: > > > On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > > > On Fri, 20 Nov 2015 15:33:25 +0900 > > > Joonsoo Kim wrote: > > > > > > > > > > Steven, is it

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, 23 Nov 2015 17:28:05 +0900 Joonsoo Kim wrote: > On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > > On Fri, 20 Nov 2015 15:33:25 +0900 > > Joonsoo Kim wrote: > > > > > > > Steven, is it possible to add tracepoint to inlined fucntion such as > > > get_page() in

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > On Fri, 20 Nov 2015 15:33:25 +0900 > Joonsoo Kim wrote: > > > > Steven, is it possible to add tracepoint to inlined fucntion such as > > get_page() in include/linux/mm.h? > > I highly recommend against it. The tracepoint code

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > On Fri, 20 Nov 2015 15:33:25 +0900 > Joonsoo Kim wrote: > > > > Steven, is it possible to add tracepoint to inlined fucntion such as > > get_page() in include/linux/mm.h? > > I highly recommend against

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, 23 Nov 2015 17:28:05 +0900 Joonsoo Kim wrote: > On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > > On Fri, 20 Nov 2015 15:33:25 +0900 > > Joonsoo Kim wrote: > > > > > > > Steven, is it possible to add tracepoint to

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > On Mon, 23 Nov 2015 17:28:05 +0900 > Joonsoo Kim wrote: > > > On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > > > On Fri, 20 Nov 2015 15:33:25 +0900 > > > Joonsoo Kim

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, Nov 23, 2015 at 09:26:04AM -0500, Steven Rostedt wrote: > On Mon, 23 Nov 2015 17:28:05 +0900 > Joonsoo Kim wrote: > > > On Fri, Nov 20, 2015 at 11:42:25AM -0500, Steven Rostedt wrote: > > > On Fri, 20 Nov 2015 15:33:25 +0900 > > > Joonsoo Kim

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Fri, 20 Nov 2015 15:33:25 +0900 Joonsoo Kim wrote: > Steven, is it possible to add tracepoint to inlined fucntion such as > get_page() in include/linux/mm.h? I highly recommend against it. The tracepoint code adds a bit of bloat, and if you inline it, you add that bloat to every use case.

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Fri, 20 Nov 2015 15:33:25 +0900 Joonsoo Kim wrote: > Steven, is it possible to add tracepoint to inlined fucntion such as > get_page() in include/linux/mm.h? I highly recommend against it. The tracepoint code adds a bit of bloat, and if you inline it, you add that

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

Ccing Steven. Hello, On Wed, Nov 18, 2015 at 04:34:30PM +0100, Vlastimil Babka wrote: > On 11/09/2015 08:23 AM, Joonsoo Kim wrote: > > CMA allocation should be guaranteed to succeed by definition, but, > > unfortunately, it would be failed sometimes. It is hard to track down > > the problem,

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

Ccing Steven. Hello, On Wed, Nov 18, 2015 at 04:34:30PM +0100, Vlastimil Babka wrote: > On 11/09/2015 08:23 AM, Joonsoo Kim wrote: > > CMA allocation should be guaranteed to succeed by definition, but, > > unfortunately, it would be failed sometimes. It is hard to track down > > the problem,

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Wed, Nov 18, 2015 at 04:34:30PM +0100, Vlastimil Babka wrote: > On 11/09/2015 08:23 AM, Joonsoo Kim wrote: > > CMA allocation should be guaranteed to succeed by definition, but, > > unfortunately, it would be failed sometimes. It is hard to track down > > the problem, because it is related to

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On 11/09/2015 08:23 AM, Joonsoo Kim wrote: > CMA allocation should be guaranteed to succeed by definition, but, > unfortunately, it would be failed sometimes. It is hard to track down > the problem, because it is related to page reference manipulation and > we don't have any facility to analyze

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On 11/09/2015 08:23 AM, Joonsoo Kim wrote: > CMA allocation should be guaranteed to succeed by definition, but, > unfortunately, it would be failed sometimes. It is hard to track down > the problem, because it is related to page reference manipulation and > we don't have any facility to analyze

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Wed, Nov 18, 2015 at 04:34:30PM +0100, Vlastimil Babka wrote: > On 11/09/2015 08:23 AM, Joonsoo Kim wrote: > > CMA allocation should be guaranteed to succeed by definition, but, > > unfortunately, it would be failed sometimes. It is hard to track down > > the problem, because it is related to

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, Nov 09 2015, Joonsoo Kim wrote: > CMA allocation should be guaranteed to succeed by definition, Uh? That’s a peculiar statement. Which is to say that it’s not true. > but, > unfortunately, it would be failed sometimes. It is hard to track down > the problem, because it is related to

Re: [PATCH 2/2] mm/page_ref: add tracepoint to track down page reference manipulation

On Mon, Nov 09 2015, Joonsoo Kim wrote: > CMA allocation should be guaranteed to succeed by definition, Uh? That’s a peculiar statement. Which is to say that it’s not true. > but, > unfortunately, it would be failed sometimes. It is hard to track down > the problem, because it is related to