University of Belgrade
Department for Computer Science

PLATO

Programming languages and tools

Jasper: An extensible benchmarking framework for JVM data serializers

Motivation

Data serialization is part of many cloud-native services. It appears in service-boundary payloads, in-memory and persistent caches, message processing, checkpointed state, and data-preparation workflows. Serializer choice affects CPU time, payload size, object allocation, startup behavior, and process memory footprint. These costs become particularly visible in cloud deployments because application instances are replicated, restarted, and scaled under resource limits. Existing serializer benchmarks typically focus on isolated microbenchmarks, making it difficult to assess how serialization choices affect memory behavior and end-to-end application performance.

Jasper

Jasper addresses this gap by combining correctness and robustness testing, serializer microbenchmarks, POSIX-level memory-operation baselines, and cloud-native macrobenchmarks based on web API and NLP workloads. It provides built-in adapters for widely used JVM serializers and an extensible workload generator, a command-line client, and a web dashboard for reproducible local and remote experiments. Its extension-oriented architecture allows researchers to add custom serializers and workloads and compare serialization technologies across different experimental conditions.


Download

Jasper is free and open-sourced, and can be found on GitHub (Ristović, 2025a) and Zenodo (Ristović and Vujošević, 2025b).

Acknowledgements

Jasper is developed as part of the research collaboration between the Faculty of Mathematics and Oracle LLC. More information about the applicability of Jasper can be found in the accompanying GraalDoss publication (Ristović et al., 2026b) and the related PhD Thesis (Ristović, 2026a).

References

  • Ristović, Ivan: JASPER: Cloud-Native Java Serializer Performance Evaluation fRamework. rlhttps://github.com/ivan-ristovic/jasper, 2025a.
  • Ristović, Ivan, Vujošević, Janičić, Milena: JASPER: Cloud-Native JVM Serializer Performance Evaluation Framework. Zenodo, 2025b. https://doi.org/10.5281/zenodo.16535566
  • Ivan Ristović: Direct Data-Snapshotting and Snapshot Sharing Across Cloud-Native Applications. Doctoral Dissertation, Faculty of Mathematics, University of Belgrade, 2026a.
  • Ivan Ristović, Vojin Jovanović, Peter Hofer, Milena Vujošević Janičić: GraalDoss: Direct Object Snapshotting and Sharing for Cloud-Native Applications. Future Generation Computer Systems, 108375, 2026b. https://doi.org/10.1016/j.future.2026.108375