Interoperability of LTTng and LTTV with SystemTAP

[Jose R. Santos]

Mathieu Desnoyers wrote:

>Hi,
>
>I just had a discussion with Frank Ch. Eigler from the SystemTAP team on the
>topic "how can the tools cooperate well together".
>
>SystemTAP is especially made for running user defined scripts at specific points
>in the kernel. I has the ability to add/remove scripts and instrumentation
>dynamically from a running kernel.
>
>LTTng is a kernel tracer designed to have the minimum impact on the system while
>having a design solid enough that it can trace NMI handlers (no locking). It
>supports native C types and alignment. It can register new instrumentation sites
>from dynamically loaded modules on-the-fly.
>
>LTTV is a modular text/graphical trace analysis tool. You can think of it as
>framework offered for plugins to interact together to show information. Simple
>plugins can show generically some information (detailed event list, for
>instance), while more sophisticated plugins can show a particular representation
>of the system (each process state (user mode, system call, interrupted,
>in trap, ...) evolving through time).
>
>While the SystemTAP project focus on pre-processing of the information, LTT
>focus on raw data copy (limiting the impact at probe site) at the cost of more
>data to be transferred and analysed afterward.
>
>I think that both approaches are complementary. I am trying to see where
>integrated analysis of pre-processed and post-processed information could be
>interesting, but I'm sure there are areas where it is.
>
>If you have application ideas, feel free to express yourself.
>  
>

We have a team that is working on implementing a kernel event trace tool 
using Systemtap.  The project does not have a post-processor and I think 
it would be really cool to create a program that converts the Systemtap 
trace output into something the other visualizers can use.  The first 
one that came to mind was LTTV.  While the overhead right now is quite 
high compared to LTTing, the target of this trace utility is for 
situations were parching a kernel is not an option.  We now have several 
trace hooks implemented and expect to release the code to the mailing 
list with in the next couple of days.

We plan on investing a significant portion of our time next year 
addressing some of the performance issues but performance will probably 
not be as fast as LTTing.  Designing a common set of trace hooks for 
both the Systemtap and LTTing implementations will help people move 
between one and the other with out a significant learning curve.  As 
long as the visualizer can handle both trace formats, I believe that 
both projects can complement each other.

-JRS