Re: [RFC 1/2] docs: ftrace: Clarify the RAM impact of buffer_size_kb

[Steven Rostedt]

On Wed, 13 Nov 2019 11:32:36 -0500
"Frank A. Cancio Bello" <frank@xxxxxxxxxxxxxxxxxxxxxx> wrote:

> The current text could mislead the user into believing that the number
> of pages allocated by each CPU ring buffer is calculated by the round
> up of the division: buffer_size_kb / PAGE_SIZE.
> 
> Clarify that the number of pages allocated is the round up of the
> division: buffer_size_kb / (PAGE_SIZE - BUF_PAGE_HDR_SIZE). Add an
> example that shows how the number of pages allocated could be off by
> 5 pages more compared with how the current text suggests it should be.
> 
> Suggested-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Frank A. Cancio Bello <frank@xxxxxxxxxxxxxxxxxxxxxx>
> ---
>  Documentation/trace/ftrace.rst | 13 +++++++++++--
>  1 file changed, 11 insertions(+), 2 deletions(-)
> 
> diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
> index e3060eedb22d..ec2c4eff95a6 100644
> --- a/Documentation/trace/ftrace.rst
> +++ b/Documentation/trace/ftrace.rst
> @@ -188,8 +188,17 @@ of ftrace. Here is a list of some of the key files:
>  	If the last page allocated has room for more bytes
>  	than requested, the rest of the page will be used,
>  	making the actual allocation bigger than requested or shown.
> -	( Note, the size may not be a multiple of the page size
> -	due to buffer management meta-data. )

The above is not untrue ;-)

> +
> +        The number of pages allocated for each CPU buffer may not
> +        be the same than the round up of the division:
> +        buffer_size_kb / PAGE_SIZE. This is because part of each page is
> +        used to store a page header with metadata. E.g. with
> +        buffer_size_kb=4096 (kilobytes), a PAGE_SIZE=4096 bytes and a
> +        BUF_PAGE_HDR_SIZE=16 bytes (BUF_PAGE_HDR_SIZE is the size of the
> +        page header with metadata) the number of pages allocated for each
> +        CPU buffer is 1029, not 1024. The formula for calculating the
> +        number of pages allocated for each CPU buffer is the round up of:
> +        buffer_size_kb / (PAGE_SIZE - BUF_PAGE_HDR_SIZE).

I have no problem with this patch, but the concern of documenting the
implementation here, which will most likely not be updated if the
implementation is ever changed, which is why I was vague to begin with.

But it may never be changed as that code has been like that for a
decade now.

-- Steve


>  
>  	Buffer sizes for individual CPUs may vary
>  	(see "per_cpu/cpu0/buffer_size_kb" below), and if they do