TY - GEN
T1 - Semeru
T2 - 14th USENIX Symposium on Operating Systems Design and Implementation,OSDI 2020
AU - Wang, Chenxi
AU - Ma, Haoran
AU - Liu, Shi
AU - Li, Yuanqi
AU - Ruan, Zhenyuan
AU - Nguyen, Khanh
AU - Bond, Michael D.
AU - Netravali, Ravi
AU - Kim, Miryung
AU - Xu, Guoqing Harry
N1 - Funding Information:
We thank the OSDI reviewers for their valuable and thorough comments. We are grateful to our shepherd Yiying Zhang for her feedback, helping us improve the paper substantially. This work is supported by NSF grants CCF-1253703, CCF-1629126, CNS-1703598, CCF-1723773, CNS-1763172, CCF-1764077, CNS-1907352, CNS-1901510, CNS-1943621, CNS-2007737, CNS-2006437, and ONR grants N00014-16-1-2913 and N00014-18-1-2037, and a grant from the Alexander von Humboldt Foundation.
Publisher Copyright:
© 2020 Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020. All rights reserved.
PY - 2020
Y1 - 2020
N2 - Resource-disaggregated architectures have risen in popularity for large datacenters. However, prior disaggregation systems are designed for native applications; in addition, all of them require applications to possess excellent locality to be efficiently executed. In contrast, programs written in managed languages are subject to periodic garbage collection (GC), which is a typical graph workload with poor locality. Although most datacenter applications are written in managed languages, current systems are far from delivering acceptable performance for these applications. This paper presents Semeru, a distributed JVM that can dramatically improve the performance of managed cloud applications in a memory-disaggregated environment. Its design possesses three major innovations: (1) a universal Java heap, which provides a unified abstraction of virtual memory across CPU and memory servers and allows any legacy program to run without modifications; (2) a distributed GC, which offloads object tracing to memory servers so that tracing is performed closer to data; and (3) a swap system in the OS kernel that works with the runtime to swap page data efficiently. An evaluation of Semeru on a set of widely-deployed systems shows very promising results.
AB - Resource-disaggregated architectures have risen in popularity for large datacenters. However, prior disaggregation systems are designed for native applications; in addition, all of them require applications to possess excellent locality to be efficiently executed. In contrast, programs written in managed languages are subject to periodic garbage collection (GC), which is a typical graph workload with poor locality. Although most datacenter applications are written in managed languages, current systems are far from delivering acceptable performance for these applications. This paper presents Semeru, a distributed JVM that can dramatically improve the performance of managed cloud applications in a memory-disaggregated environment. Its design possesses three major innovations: (1) a universal Java heap, which provides a unified abstraction of virtual memory across CPU and memory servers and allows any legacy program to run without modifications; (2) a distributed GC, which offloads object tracing to memory servers so that tracing is performed closer to data; and (3) a swap system in the OS kernel that works with the runtime to swap page data efficiently. An evaluation of Semeru on a set of widely-deployed systems shows very promising results.
UR - http://www.scopus.com/inward/record.url?scp=85096777483&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096777483&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85096777483
T3 - Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020
SP - 261
EP - 280
BT - Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020
PB - USENIX Association
Y2 - 4 November 2020 through 6 November 2020
ER -