Generalizing QoS-Aware Memory Bandwidth Allocation to Multi-Socket Cloud Servers
2021 (English)In: 2021 Ieee 14Th International Conference On Cloud Computing (Cloud 2021) / [ed] Ardagna, CA Chang, C Daminai, E Ranjan, R Wang, Z Ward, R Zhang, J Zhang, W, Institute of Electrical and Electronics Engineers (IEEE) , 2021, p. 551-557Conference paper, Published paper (Refereed)
Abstract [en]
Although the problem of QoS-aware resource allocation is not new, novel hardware-based resource allocation mechanisms have recently become available in commodity cloud servers and enabled a new generation of QoS-aware resource allocation approaches. Unfortunately, to the best of our knowledge, existing proposals are by design tailored to single-socket architectures only. In many warehouse scale data centers, dual-socket (or even larger) machines already constitute the largest share of hosts. This paper presents the full design and implementation of BALM, a QoS-aware memory bandwidth allocation technique for multi-socket architectures. BALM combines commodity bandwidth allocation mechanisms originally designed for single-socket with a novel adaptive cross-socket page migration scheme. Our evaluation with a large and dynamic set of real applications co-located on a dual-socket machine shows that BALM can overcome the efficiency limitations of state-of-the-art. BALM delivers substantial throughput gains to bandwidth-intensive best-effort applications, while ensuring marginal SID violation windows to latency-critical applications.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2021. p. 551-557
Series
IEEE International Conference on Cloud Computing, ISSN 2159-6182
Keywords [en]
QoS-aware resource allocation, Cloud computing, Multi-socket systems
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-309298DOI: 10.1109/CLOUD53861.2021.00071ISI: 000749430800059Scopus ID: 2-s2.0-85119378639OAI: oai:DiVA.org:kth-309298DiVA, id: diva2:1641284
Conference
IEEE 14th International Conference on Cloud Computing (CLOUD), SEP 05-10, 2021, ELECTR NETWORK, Chicago, IL, USA
Note
QC 20220301
Part of proceedings ISBN: 978-1-6654-0060-2
2022-03-012022-03-012023-03-06Bibliographically approved