Zamanian, Erfan and Shun, Julian and Binnig, Carsten and Kraska, Tim (2020):
Chiller: Contention-Centric Transaction Execution and Data Partitioning for Modern Networks.
In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, pp. 511-526,
ACM, SIGMOD/PODS '20: International Conference on Management of Data, virtual Conference, 14.-19.06, ISBN 9781450367356,
DOI: 10.1145/3318464.3389724,
[Conference or Workshop Item]
Abstract
Distributed transactions on high-overhead TCP/IP-based networks were conventionally considered to be prohibitively expensive and thus were avoided at all costs. To that end, the primary goal of almost any existing partitioning scheme is to minimize the number of cross-partition transactions. However, with the new generation of fast RDMA-enabled networks, this assumption is no longer valid. In fact, recent work has shown that distributed databases can scale even when the majority of transactions are cross-partition. In this paper, we first make the case that the new bottleneck which hinders truly scalable transaction processing in modern RDMA-enabled databases is data contention, and that optimizing for data contention leads to different partitioning layouts than optimizing for the number of distributed transactions. We then present Chiller, a new approach to data partitioning and transaction execution, which aims to minimize data contention for both local and distributed transactions. Finally, we evaluate Chiller using various workloads, and show that our partitioning and execution strategy outperforms traditional partitioning techniques which try to avoid distributed transactions, by up to a factor of 2.
Item Type: | Conference or Workshop Item |
---|---|
Erschienen: | 2020 |
Creators: | Zamanian, Erfan and Shun, Julian and Binnig, Carsten and Kraska, Tim |
Title: | Chiller: Contention-Centric Transaction Execution and Data Partitioning for Modern Networks |
Language: | German |
Abstract: | Distributed transactions on high-overhead TCP/IP-based networks were conventionally considered to be prohibitively expensive and thus were avoided at all costs. To that end, the primary goal of almost any existing partitioning scheme is to minimize the number of cross-partition transactions. However, with the new generation of fast RDMA-enabled networks, this assumption is no longer valid. In fact, recent work has shown that distributed databases can scale even when the majority of transactions are cross-partition. In this paper, we first make the case that the new bottleneck which hinders truly scalable transaction processing in modern RDMA-enabled databases is data contention, and that optimizing for data contention leads to different partitioning layouts than optimizing for the number of distributed transactions. We then present Chiller, a new approach to data partitioning and transaction execution, which aims to minimize data contention for both local and distributed transactions. Finally, we evaluate Chiller using various workloads, and show that our partitioning and execution strategy outperforms traditional partitioning techniques which try to avoid distributed transactions, by up to a factor of 2. |
Title of Book: | Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data |
Publisher: | ACM |
ISBN: | 9781450367356 |
Uncontrolled Keywords: | dm |
Divisions: | 20 Department of Computer Science 20 Department of Computer Science > Data Management |
Event Title: | SIGMOD/PODS '20: International Conference on Management of Data |
Event Location: | virtual Conference |
Event Dates: | 14.-19.06 |
Date Deposited: | 14 Dec 2020 09:28 |
DOI: | 10.1145/3318464.3389724 |
Official URL: | https://doi.org/10.1145/3318464.3389724 |
Export: | |
Suche nach Titel in: | TUfind oder in Google |
![]() |
Send an inquiry |
Options (only for editors)
![]() |
Show editorial Details |