The LTTng tracer : A Low Impact Performance and Behavior Monitor for GNU/Linux.

Efficient tracing of system-wide execution, allowing integrated analysis of both kernel space and user space, is something difficult to achieve. The following article will present you a new tracer core, Linux Trace Toolkit Next Generation (LTTng), that has taken over the previous version known as "LTT". It has the same goals of low system disturbance and architecture independance while being fully reentrant, scalable, precise, extensible, modular and easy to use. For instance, LTTng allows tracepoints in NMI code, multiple simultaneous traces and a flight recorder mode. LTTng reuses and enhances the existing LTT instrumentation and RelayFS.

This paper will focus on the approaches taken by LTTng to fulfill these goals. It will present the modular architecture of the project. It will then explain how NMI reentrancy requires atomic operations for writing and RCU lists for tracing behavior control. It will show how these techniques are inherently scalable to multiprocessor systems. Then, time precision limitations in the kernel will be discussed, followed by an explanation of LTTng's own monotonic timestamps motives.

In addition, the template based code generator for architecture agnostic trace format will be presented. The approach taken to allow nested types, variable fields and dynamic alignment of data in the trace buffers will be revealed. It will show the mechanisms deployed to facilitate use and extension of this tool by adding custom instrumentation and analysis involving kernel, libraries and user space programs.

It will also introduce LTTng's trace analyzer and graphical viewer counterpart: Linux Trace Toolkit Viewer (LTTV). The latter implements extensible analysis of the trace information through collaborating text and graphical plugins (see http://ltt.polymtl.ca). It can simultaneously display multiple multi-GBytes traces of multi-processor systems.