Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath

From	Dave Hansen <dave.hansen@intel.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath
Date	2016-07-27 19:30 +0200
Message-ID	<rZAOB-2kF-3@gated-at.bofh.it> (permalink)
References	<rZyjM-F9-5@gated-at.bofh.it> <rZyjM-F9-11@gated-at.bofh.it> <rZyWu-19P-29@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On 07/27/2016 08:23 AM, Steven Rostedt wrote:
>> > +
>> > +	trace_mm_slowpath_end(page);
>> > +
> I'm thinking you only need one tracepoint, and use function_graph
> tracer for the length of the function call.
> 
>  # cd /sys/kernel/debug/tracing
>  # echo __alloc_pages_nodemask > set_ftrace_filter
>  # echo function_graph > current_tracer
>  # echo 1 > events/kmem/trace_mm_slowpath/enable

I hesitate to endorse using the function_graph tracer for this kind of
stuff.  Tracepoints offer some level of stability in naming, and the
compiler won't ever make them go away.   While __alloc_pages_nodemask is
probably more stable than most things, there's no guarantee that it will
be there.

BTW, what's the overhead of the function graph tracer if the filter is
set up to be really restrictive like above?  Is the overhead really just
limited to that one function?

Thread

[PATCH 0/2] New tracepoints for slowpath and memory compaction Janani Ravichandran <janani.rvchndrn@gmail.com> - 2016-07-27 16:50 +0200
  [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Janani Ravichandran <janani.rvchndrn@gmail.com> - 2016-07-27 16:50 +0200
    Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Steven Rostedt <rostedt@goodmis.org> - 2016-07-27 17:30 +0200
      Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Dave Hansen <dave.hansen@intel.com> - 2016-07-27 19:30 +0200
        Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Steven Rostedt <rostedt@goodmis.org> - 2016-07-27 19:40 +0200
      Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Janani Ravichandran <janani.rvchndrn@gmail.com> - 2016-07-28 22:20 +0200
        Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Steven Rostedt <rostedt@goodmis.org> - 2016-08-04 17:30 +0200
          Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Janani Ravichandran <janani.rvchndrn@gmail.com> - 2016-08-05 18:20 +0200
            Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Steven Rostedt <rostedt@goodmis.org> - 2016-08-05 18:40 +0200
              Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Janani Ravichandran <janani.rvchndrn@gmail.com> - 2016-08-07 12:40 +0200
    Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Michal Hocko <mhocko@kernel.org> - 2016-07-27 18:40 +0200
      Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Rik van Riel <riel@surriel.com> - 2016-07-27 20:20 +0200
        Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Steven Rostedt <rostedt@goodmis.org> - 2016-07-27 20:30 +0200
        Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Michal Hocko <mhocko@kernel.org> - 2016-07-27 20:50 +0200
          Re: [PATCH 1/2] mm: page_alloc.c: Add tracepoints for slowpath Rik van Riel <riel@surriel.com> - 2016-07-27 21:00 +0200
  [PATCH 2/2] mm: compaction.c: Add/Modify direct compaction  tracepoints Janani Ravichandran <janani.rvchndrn@gmail.com> - 2016-07-27 17:00 +0200
    Re: [PATCH 2/2] mm: compaction.c: Add/Modify direct compaction  tracepoints Steven Rostedt <rostedt@goodmis.org> - 2016-07-27 17:30 +0200
    Re: [PATCH 2/2] mm: compaction.c: Add/Modify direct compaction  tracepoints Vlastimil Babka <vbabka@suse.cz> - 2016-08-01 15:30 +0200
      Re: [PATCH 2/2] mm: compaction.c: Add/Modify direct compaction tracepoints Janani Ravichandran <janani.rvchndrn@gmail.com> - 2016-08-07 14:40 +0200

csiph-web