LTTng Live trace reading how-to Julien Desfossez September 27th, 2013 This document presents a summary on how to use the live trace reading feature introduced in LTTng 2.4. For the details about the protocol, please refer to the live-reading-protocol.txt document. Live trace reading refers to the feature of reading the trace while it is being recorded. In order to do that, the trace must be streamed a relay even if the viewer is running on the same machine as the tracer. So, the first thing to do is to start a lttng-relayd process. It can be anywhere on the network (including localhost) as long as the sessiond/consumerd and the viewer can communicate with it over TCP/IP. $ lttng-relayd -d Then, we can create a session configured for streaming with the new --live parameter. $ lttng create --live 1000000 -U net://localhost The --live parameter activates a session-wide timer (usec) that is responsible for checking at a user-defined rate if new data is available. If there is new data, it is flushed automatically, otherwise a beacon is sent to the relayd to inform it that the stream is currently empty and the viewer can ignore this stream up to a certain point in time. Once the session is created, the user can activate events as usual. In order to view the live trace, the viewer must implement the live-reading protocol. As of now, Babeltrace[1] and LTTngTop[2] implement the protocol. [1] git://git.efficios.com/babeltrace.git [2] git://git.lttng.org/lttngtop.git