Re: [PATCH] ring-buffer/Documentation: Add documentation on buffer_percent file

[Steven Rostedt]

Jon,

I was about to ask if you can take this through your tree, but then I did a
self edit :-p

On Tue, 26 Dec 2023 12:35:25 -0500
Steven Rostedt <rostedt@xxxxxxxxxxx> wrote:

> From: "Steven Rostedt (Google)" <rostedt@xxxxxxxxxxx>
> 
> When the buffer_percent file was added to the kernel, the documentation
> should have been updated to document what that file does.
> 
> Fixes: 03329f9939781 ("tracing: Add tracefs file buffer_percentage")
> Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
> ---
>  Documentation/trace/ftrace.rst | 15 +++++++++++++++
>  1 file changed, 15 insertions(+)
> 
> diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
> index 933e7efb9f1b..16eabb00fa55 100644
> --- a/Documentation/trace/ftrace.rst
> +++ b/Documentation/trace/ftrace.rst
> @@ -180,6 +180,21 @@ of ftrace. Here is a list of some of the key files:
>  	Only active when the file contains a number greater than 0.
>  	(in microseconds)
>  
> +  buffer_percent:
> +
> +	This is the water-mark for how much the ring buffer needs to be filled
> +	before a waiter is woken up. That is, if an application call a

							"calls"

> +	blocking read syscall on one of the per_cpu trace_pipe_raw files, it
> +	will block until the given amount of data specified by buffer_percent
> +	is in the ring buffer before it wakes the reader up. This also
> +	controls how splice system calls are blocked on this file.

		"the splice system"

> +
> +	0   - means to wake up as soon as there is any data in the ring buffer.
> +	50  - means to wake up when roughly half of the ring buffer sub-buffers
> +	      are full.
> +	100 - means to block until the ring buffer is totally full and is
> +	      about to start overwriting the older data.
> +
>    buffer_size_kb:
>  
>  	This sets or displays the number of kilobytes each CPU

Will send a v2.

-- Steve