[ltt-dev] Flight-recording mode

[Mathieu Desnoyers]

* Gerlando Falauto (gerlando.falauto at keymile.com) wrote:
> Hi all,
>
> after a little experimenting with LTTng 0.x on kernel 2.6.33,
> I am doing some further investigation on LTTng 2.x on kernel 3.0.
>
> I am still missing something though on both versions though.
> I would assume that in /pure/ flight-recording mode, everything would be  
> buffered by LTTng on kernel side.
>
> Here's what I am doing on LTTng 2.x:
>
> # lttng create trace
> Spawning a session daemon
> Session trace created.
> Traces will be written in /root/lttng-traces/trace-19700101-000039
>
> # lttng enable-channel myc -k --overwrite --subbuf-size=4096  
> --num-subbuffers=4
> Channel enabled myc for session trace
>
> # lttng enable-event sched_switch,sched_wakeup -k -c myc
> Kernel event sched_switch created in channel myc
> Kernel event sched_wakeup created in channel myc
>
> # lttng start
> Tracing started for session trace
>
> However, I still get files which are constantly, unreasonably growing in  
> my /root/lttng-traces/trace-19700101-000039
> I also tried enabling the channel *after* enabling the events, but with  
> the same end result.
>
> How can I make sure that only the latest N seconds of traces will be  
> saved? The answer should be flight-recording mode, but how do I really  
> do it?

I discussed this with David this morning, and we'll need to enhance
ltt-sessiond in lttng-tools to ensure it does not send the streams to
the consumer daemon upon trace start for overwrite mode channels, but
just on trace stop. This is lacking currently.

Thanks for reporting this!

Mathieu

>
> Thanks!
> Gerlando
>
> _______________________________________________
> ltt-dev mailing list
> ltt-dev at lists.casi.polymtl.ca
> http://lists.casi.polymtl.ca/cgi-bin/mailman/listinfo/ltt-dev
>

-- 
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com