and by Intel and Microsoft under the Universal Parallel Computing Research Center (UPCRC) AtomTracker: A Comprehensive Approach to Atomic Region Inference and Violation Detection*This work was supported in part by the National Science Foundation under grant CNS 0720593

A particularly insidious type of concurrency bug is atomicity violations. While there has been substantial work on automatic detection of atomicity violations, each existing technique has focused on a certain type of atomic region. To address this limitation, this paper presents AtomTracker, a comprehensive approach to atomic region inference and violation detection. AtomTracker is the first scheme to (1) automatically infer generic atomic regions (not limited by issues such as the number of variables accessed, the number of instructions included, or the type of code construct the region is embedded in) and (2) automatically detect violations of them at runtime with negligible execution overhead. AtomTracker provides novel algorithms to infer generic atomic regions and to detect atomicity violations of them. Moreover, we present a hardware implementation of the violation detection algorithm that leverages cache coherence state transitions in a multiprocessor. In our evaluation, we take eight atomicity violation bugs from real-world codes like Apache, MySql, and Mozilla, and show that AtomTracker detects them all. In addition, AtomTracker automatically infers all of the atomic regions in a set of microbenchmarks accurately. Finally, we also show that the hardware implementation induces a negligible execution time overhead of 0.2-4.0% and, therefore, enables AtomTracker to find atomicity violations on-the-fly in production runs. 2010 IEEE.

AtomTracker: A Comprehensive Approach to Atomic Region Inference and Violation Detection*This work was supported in part by the National Science Foundation under grant CNS 0720593, and by Intel and Microsoft under the Universal Parallel Computing Research Center (UPCRC) Conference Paper