Totalview® for HPC User Guide : PART II Debugging Tools and Tasks : Chapter 15 Debugging Strategies for Parallel Applications : General Parallel Debugging Tips : Breakpoints, Stepping, and Program Execution
Breakpoints, Stepping, and Program Execution
Setting Breakpoint Behavior
When you’re debugging message-passing and other multi-process programs, it is usually easier to understand the program’s behavior if you change the default stopping action of breakpoints and barrier breakpoints. By default, when one process in a multi-process program hits a breakpoint, TotalView stops all other processes.
To change the default stopping action of breakpoints and barrier breakpoints, you can set debugger preferences. The online Help contains information on these preference. These preferences tell TotalView whether to continue to run when a process or thread hits the breakpoint.
These options affect only the default behavior. You can choose a behavior for a breakpoint by setting the breakpoint properties in the File > Preferences Action Points Page. See "Setting Breakpoints for Multiple Processes".
Synchronizing Processes
TotalView has two features that make it easier to get all of the processes in a multi-process program synchronized and executing a line of code. Process barrier breakpoints and the process hold/release features work together to help you control the execution of your processes. See "Setting Barrier Points".
The Process Window Group > Run To command is a special stepping command. It lets you run a group of processes to a selected source line or instruction. See Stepping (Part I)” on page 521.
Using Group Commands
Group commands are often more useful than process commands.
It is often more useful to use the Group > Go command to restart the whole application instead of the Process > Go command.
CLI: dfocus g dgo
Abbreviation: G
You would then use the Group > Halt command instead of Process > Halt to stop execution.
CLI: dfocus g dhalt
Abbreviation: H
The group-level single-stepping commands such as Group > Step and Group > Next let you single-step a group of processes in a parallel. See Stepping (Part I)” on page 521.
CLI: dfocus g dstep
Abbreviation: S
dfocus g dnext
Abbreviation: N
Stepping at Process Level
If you use a process-level single-stepping command in a multi-process program, TotalView may appear to hang (it continuously displays the watch cursor). If you single-step a process over a statement that can’t complete without allowing another process to run, and that process is stopped, the stepping process appears to hang. This can occur, for example, when you try to single-step a process over a communication operation that cannot complete without the participation of another process. When this happens, you can abort the single-step operation by selecting Cancel in the Waiting for Command to Complete Window that TotalView displays. As an alternative, consider using a group-level single-step command.
CLI: Type Ctrl+C
NOTE >> Rogue Wave receives many bug reports on hung processes, usually because one process is waiting for another. Using the Group debugging commands almost always solves this problem.