Re: [PATCH 13/15] small_traces: Add config option to shrink trace events.

[David Sharp]

I considered that, and I generally thing it's a good idea. However, I
also want to use this switch to shrink individual tracepoint event
structures.

eg: sched switch is a high frequency event and it is 68 bytes (60
after these patches)

Can you suggest a syntax for TRACE_EVENT, DECLARE_EVENT_CLASS, etc,
that could express the two versions and produce the right code?

I'm worried about adding even further complexity to the TRACE_EVENT
macros. I could add TRACE_EVENT_SMALL that takes two versions of
TP_STRUCT__entry, TP_fast_assign, and TP_printk each, but then this
will need to be permuted with your TP_CONDITIONAL patches as well.

Thanks,
d#

On Fri, Dec 3, 2010 at 5:56 PM, Steven Rostedt <rostedt@xxxxxxxxxxx> wrote:
> [ Added Frederic on Cc ]
>
> I rather have this as a run time option than a compile time.
>
> You could use two different trace event structures. The normal one and a
> "compact" one. Add to the "trace_options" and when it is set the traces
> are compact.
>
> -- Steve
>
>
> On Fri, 2010-12-03 at 16:13 -0800, David Sharp wrote:
>> This option will remove several fields from trace events to reduce the
>> payload size. Under heavy load, events can be produced faster than they
>> can possibly be written to disk or sent on the network. Shrinking the
>> payload size will enable fitting more traces in the ring buffer, which
>> therefore enables tracing for longer periods, at the cost of losing some
>> relatively unimportant details.
>>
>> Google-Bug-Id: 3224547
>>
>> Signed-off-by: David Sharp <dhsharp@xxxxxxxxxx>
>> ---
>> Âkernel/trace/Kconfig | Â 12 ++++++++++++
>> Â1 files changed, 12 insertions(+), 0 deletions(-)
>>
>> diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
>> index ea37e2f..9c24fe5 100644
>> --- a/kernel/trace/Kconfig
>> +++ b/kernel/trace/Kconfig
>> @@ -403,6 +403,18 @@ config FUNCTION_PROFILER
>>
>> Â Â Â Â If in doubt, say N.
>>
>> +config SMALL_TRACES
>> + Â Â bool "Shrink trace events"
>> + Â Â default n
>> + Â Â help
>> + Â Â Â Minimize the size of trace events. Omits fields from trace event
>> + Â Â Â header like preempt_count, and lock_depth. Chooses smaller
>> + Â Â Â alternative event structures. Shrinking the payload size enables
>> + Â Â Â fitting more traces in the ring buffer, which enables tracing for
>> + Â Â Â longer periods when the buffer can not be read as fast as it is
>> + Â Â Â filled, at the cost of losing some details.
>> +
>> +
>> Âconfig FTRACE_MCOUNT_RECORD
>> Â Â Â def_bool y
>> Â Â Â depends on DYNAMIC_FTRACE
>
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/