| 摘要 |
A system and method for tracing a clustered application are disclosed. A server system hosts the clustered application, and an instance tracer manages a shared memory segment for one or more nodes within an instance of each process of the clustered application. The instance tracer is adapted to serialize trace information for each of the one or more nodes and write the trace information directly to the shared memory segment according to a common time sequence. Preferably, the shared memory segment is arranged as a rollbuffer, and the trace information is written to the rollbuffer as a trace entry in sequential writer entries until a reader entry on the rollbuffer is reached.
|
