Implementing Cold-Start Reduction Techniques on Globus Compute
Resumo
This work addresses the cold-start delay issue within Globus Compute, a FaaS solution aimed at scientific workflows. We introduce the Warm-Start Engine, a novel engine for the system which integrates two techniques: an increase in the keepalive time of resources and a new task assignment algorithm. To validate our approach, we conducted a comparative performance analysis of the original system against two new versions, one with only the extended keepalive time and another with both modifications. The results demonstrate that the Warm-Start Engine reduces total workflow execution times by up to 62% and improves individual function execution times by as much as 82%, when compared to the baseline Globus Compute implementation.
Referências
Basu Roy, R., Patel, T., Liew, R., Babuji, Y. N., Chard, R., and Tiwari, D. (2023). ProPack: Executing Concurrent Serverless Functions Faster and Cheaper. In Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing, HPDC ’23, page 211–224, New York, NY, USA. Association for Computing Machinery.
Bauer, A., Gonthier, M., Pan, H., Chard, R., Grzenda, D., Straesser, M., Pauloski, J. G., Kamatar, A., Baughman, M., Hudson, N., Foster, I., and Chard, K. (2024a). An Empirical Investigation of Container Building Strategies and Warm Times to Reduce Cold Starts in Scientific Computing Serverless Functions. In 2024 IEEE 20th International Conference on e-Science (e-Science), pages 1–10.
Bauer, A., Pan, H., Chard, R., Babuji, Y., Bryan, J., Tiwari, D., Foster, I., and Chard, K. (2024b). The globus compute dataset: An open function-as-a-service dataset from the edge to the cloud. Future Generation Computer Systems, 153:558–574.
Bermbach, D., Karakaya, A.-S., and Buchholz, S. (2020). Using application knowledge to reduce cold starts in FaaS services. In Proceedings of the 35th Annual ACM Symposium on Applied Computing, SAC ’20, page 134–143, New York, NY, USA. Association for Computing Machinery.
Castro, P., Ishakian, V., Muthusamy, V., and Slominski, A. (2019). The rise of serverless computing. Commun. ACM, 62(12):44–54.
Chard, R., Babuji, Y., Li, Z., Skluzacek, T., Woodard, A., Blaiszik, B., Foster, I., and Chard, K. (2020). FuncX: A Federated Function Serving Fabric for Science. In Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing, HPDC ’20, page 65–76. Association for Computing Machinery.
Conover, W. J. (1999). Practical Nonparametric Statistics. Wiley.
Ebrahimi, A., Ghobaei-Arani, M., and Saboohi, H. (2024). Cold start latency mitigation mechanisms in serverless computing: Taxonomy, review, and future directions. Journal of Systems Architecture, 151:103115.
Fireman, D., Silva, P., Pereira, T. E., Mafra, L., and Valadares, D. (2024). Prebaking runtime environments to improve the FaaS cold start latency. Future Generation Computer Systems, 155:287–299.
Liu, X., Wen, J., Chen, Z., Li, D., Chen, J., Liu, Y., Wang, H., and Jin, X. (2023). FaaSLight: General Application-level Cold-start Latency Optimization for Functionas-a-Service in Serverless Computing. ACM Trans. Softw. Eng. Methodol., 32(5).
Bauer, A., Gonthier, M., Pan, H., Chard, R., Grzenda, D., Straesser, M., Pauloski, J. G., Kamatar, A., Baughman, M., Hudson, N., Foster, I., and Chard, K. (2024a). An Empirical Investigation of Container Building Strategies and Warm Times to Reduce Cold Starts in Scientific Computing Serverless Functions. In 2024 IEEE 20th International Conference on e-Science (e-Science), pages 1–10.
Bauer, A., Pan, H., Chard, R., Babuji, Y., Bryan, J., Tiwari, D., Foster, I., and Chard, K. (2024b). The globus compute dataset: An open function-as-a-service dataset from the edge to the cloud. Future Generation Computer Systems, 153:558–574.
Bermbach, D., Karakaya, A.-S., and Buchholz, S. (2020). Using application knowledge to reduce cold starts in FaaS services. In Proceedings of the 35th Annual ACM Symposium on Applied Computing, SAC ’20, page 134–143, New York, NY, USA. Association for Computing Machinery.
Castro, P., Ishakian, V., Muthusamy, V., and Slominski, A. (2019). The rise of serverless computing. Commun. ACM, 62(12):44–54.
Chard, R., Babuji, Y., Li, Z., Skluzacek, T., Woodard, A., Blaiszik, B., Foster, I., and Chard, K. (2020). FuncX: A Federated Function Serving Fabric for Science. In Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing, HPDC ’20, page 65–76. Association for Computing Machinery.
Conover, W. J. (1999). Practical Nonparametric Statistics. Wiley.
Ebrahimi, A., Ghobaei-Arani, M., and Saboohi, H. (2024). Cold start latency mitigation mechanisms in serverless computing: Taxonomy, review, and future directions. Journal of Systems Architecture, 151:103115.
Fireman, D., Silva, P., Pereira, T. E., Mafra, L., and Valadares, D. (2024). Prebaking runtime environments to improve the FaaS cold start latency. Future Generation Computer Systems, 155:287–299.
Liu, X., Wen, J., Chen, Z., Li, D., Chen, J., Liu, Y., Wang, H., and Jin, X. (2023). FaaSLight: General Application-level Cold-start Latency Optimization for Functionas-a-Service in Serverless Computing. ACM Trans. Softw. Eng. Methodol., 32(5).
Publicado
28/10/2025
Como Citar
LEMBO, João Gabriel; GOLDMAN, Alfredo.
Implementing Cold-Start Reduction Techniques on Globus Compute. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 26. , 2025, Bonito/MS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 229-241.
DOI: https://doi.org/10.5753/sscad.2025.16692.
