Assessing the Computational Impact of Handlespace Management in Lightweight Reliable Server Pooling Architectures
AUTHORS
Lukas Steinbauer,Institute of Computer Engineering, Vienna University of Technology (TU Wien), Austria
Anna-Maria Vogel,Department of Information Technology, Graz University of Technology, Austria
Florian Neubauer,Department of Distributed Systems, Johannes Kepler University Linz, Austria
ABSTRACT
Ensuring the uninterrupted availability of services has become increasingly vital in today's Internet-driven applications. To address this demand, the Reliable Server Pooling (RSerPool) framework, currently undergoing standardization by the Internet Engineering Task Force (IETF), offers a robust and lightweight solution for server redundancy and seamless session failover. Distinguished by its minimal computational and memory overhead, RSerPool is particularly well-suited for deployment in resource-constrained environments, including embedded systems and network edge devices. While earlier research has examined the general behavior and performance characteristics of RSerPool in specific application scenarios, such as Voice-over-IP, e-commerce platforms, and distributed computing systems—there remains a critical lack of comprehensive analysis focusing on the overhead introduced by handlespace management. This paper seeks to fill that gap by providing a detailed evaluation of the computational and structural performance of the pool maintenance subsystem, a core component of the RSerPool architecture. The study begins by presenting a clear overview of the RSerPool framework, including its protocol stack, operational principles, and policy-driven mechanisms for server selection. Subsequently, we introduce an efficient handlespace structure based on red-black trees and examine its behavior through both controlled simulations and real-world experimental setups. Performance metrics such as registration throughput, re-registration frequency, timer management efficiency, and handle resolution scalability are measured and analyzed. The results demonstrate that the proposed handlespace management approach exhibits excellent performance even under high-load conditions. Thus, the findings affirm RSerPool’s viability for deployment in systems requiring high availability and low maintenance overhead, especially within limited-resource environments.
KEYWORDS
Reliable server pooling, Handlespace management, Microbenchmarking, Controlled simulation, Policy-agnostic abstraction
REFERENCES
[1] T. Dreibholz, “Overview and evaluation of the pool maintenance overhead in reliable server pooling systems,” International Journal of Hybrid Information Technology, vol.1, no.2, pp.17–32, (2008)
[2] R. R. Stewart, Q. Xie, M. Stillman, and M. Tüxen, “Endpoint handlespace redundancy protocol (ENRP),” RFC 5353, IETF, (2008)
[3] S. Zhao, X. Zhang, P. Cao, and X. Wang, “Robust and efficient edge server placement and scheduling policies,” IEEE Transactions on Cloud Computing, vol.9, no.4, pp.1093–1106, (2021)
[4] T. Lähderanta, T. Leppänen, L. Ruha, et al., “Capacitated edge server placement for fog computing,” Journal of Systems Architecture, vol.98, pp.22–35, (2019)
[5] Y. C. Hu, M. Patel, D. Sabella, N. Sprecher, and V. Young, “Mobile edge computing: A key technology towards 5G,” ETSI White Paper, no.11, (2015)
[6] X. Sun and N. Ansari, “EdgeIoT: Mobile edge computing for the Internet of Things,” IEEE Communications Magazine, vol.54, no.12, pp.22–29, (2016)
[7] S. Xiang and A. Nirwan, “Latency-aware workload offloading in the cloudlet network,” IEEE Communications Letters, vol.21, no.7, pp.1481–1484, (2017)
[8] C. Sonmez, A. Ozgovde, and C. Ersoy, “Fuzzy workload orchestration for edge computing,” IEEE Transactions on Network and Service Management, vol.16, no.2, pp.769–782, (2019)
[9] T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein, Introduction to Algorithms, 3rd ed., MIT Press, (2009)
[10] S. Hanke, “The performance of concurrent red black tree algorithms,” Institut für Informatik Report, Universität Salzburg, (1999)
[11] T. Dreibholz, F. Zahid, A. Taherkordi, and E. G. Gran, “Mobile edge as part of the multi-cloud ecosystem: A performance study,” in Proc. Euromicro PDP, pp.50–57, (2019)
[12] L. Bounif and D. E. Zegour, “AVL and Red Black Tree as a Single Balanced Tree,” International Journal of Applied Computer Science & Mathematics, vol.10, no.2, pp.72–77, (2016)
[13] A. Reiser and J. Alonso, “Hybrid replication: State-machine-based and deferred-update replication,” Distributed Computing, vol.22, no.2, pp.89–109, (2009)
[14] S. Rajan, A. Rathi, and S. Sivaguru, “A survey on middleware for high availability,” International Journal of Computer Applications, vol.97, no.11, pp.30–37, (2014)
[15] H. Zhou and J. Xu, “Adaptive server assignment for cloud-hosted applications under dynamic workloads,” Journal of Network and Computer Applications, vol.98, pp.25–35, (2017)
[16] A. Alkaff, H. Nishiyama, N. Kato, and Y. Shimizu, “Context-aware service provisioning in mobile cloud computing,” IEEE Transactions on Services Computing, vol.10, no.6, pp.790–801, (2017)
[17] M. Tüxen and R. Stewart, “Engineering considerations for SCTP applications,” Computer Communications, vol.30, no.10, pp.2210–2220, (2007)
[18] J. Bi, Z. Zhu, R. Tian, and Q. Wang, “ADN: Application-driven dynamic network for high performance computing,” Future Generation Computer Systems, vol.88, pp.262–273, (2018)
[19] M. Aazam and E. N. Huh, “Fog computing and smart gateway-based communication for cloud of things,” Future Generation Computer Systems, vol.74, pp.111–118, (2017)
[20] A. Prokopec, N. Bronson, P. Bagwell, and M. Odersky, “Concurrent tries with efficient non-blocking snapshots,” ACM SIGPLAN Notices, vol.47, no.8, pp.151–160, (2012)
[21] M. Moir, D. Nussbaum, O. Shalev, and N. Shavit, “Using elimination to implement scalable and lock-free FIFO queues,” Journal of Parallel and Distributed Computing, vol.68, no.7, pp.809–821, (2008)
[22] R. Bhatia and S. Sharma, “Performance analysis of failover strategies in hybrid cloud environments,” Cluster Computing, vol.24, no.1, pp.113–130, (2021)