Making root cause analysis feasible for large code bases: a solution approach for a climate model

TL;DR

This paper introduces a scalable approach to root cause analysis in large code bases like the CESM climate model, enabling developers to trace output discrepancies to their sources efficiently.

Contribution

The work presents a novel technique combining graph analysis, program slicing, and ranking to reduce the search space for root cause analysis in large-scale scientific codes.

Findings

Effective reduction of search space for root cause analysis.

Successful identification of error sources in CESM simulations.

Improved debugging efficiency for large scientific code bases.

Abstract

For large-scale simulation codes with huge and complex code bases, where bit-for-bit comparisons are too restrictive, finding the source of statistically significant discrepancies (e.g., from a previous version, alternative hardware or supporting software stack) in output is non-trivial at best. Although there are many tools for program comprehension through debugging or slicing, few (if any) scale to a model as large as the Community Earth System Model (CESM; trademarked), which consists of more than 1.5 million lines of Fortran code. Currently for the CESM, we can easily determine whether a discrepancy exists in the output using a by now well-established statistical consistency testing tool. However, this tool provides no information as to the possible cause of the detected discrepancy, leaving developers in a seemingly impossible (and frustrating) situation. Therefore, our aim in this work is to provide the tools to enable developers to trace a problem detected through the CESM output to its source. To this end, our strategy is to reduce the search space for the root cause(s) to a tractable size via a series of techniques that include creating a directed graph of internal CESM variables, extracting a subgraph (using a form of hybrid program slicing), partitioning into communities, and ranking nodes by centrality. Runtime variable sampling then becomes feasible in this reduced search space. We demonstrate the utility of this process on multiple examples of CESM simulation output by illustrating how sampling can be performed as part of an efficient parallel iterative refinement procedure to locate error sources, including sensitivity to CPU instructions. By providing CESM developers with tools to identify and understand the reason for statistically distinct output, we have positively impacted the CESM software development cycle and, in particular, its focus on quality assurance.