Flexible Resource Allocation for Relational Database-as-a-Service

被引：3

作者：

Arora, Pankaj ^{[1
]}

Chaudhuri, Surajit ^{[1
]}

Das, Sudipto ^{[3
]}

Dong, Junfeng ^{[1
]}

George, Cyril ^{[1
]}

Kalhan, Ajay ^{[1
]}

Konig, Arnd Christian ^{[1
]}

Lang, Willis ^{[1
]}

Li, Changsong ^{[1
]}

Li, Feng ^{[4
]}

Liu, Jiaqi ^{[1
]}

Maas, Lukas M. ^{[1
]}

Mata, Akshay ^{[1
]}

Menache, Ishai ^{[1
]}

Moeller, Justin ^{[1
]}

Narasayya, Vivek ^{[1
]}

Olma, Matthaios ^{[1
]}

Oslake, Morgan

Rezai, Elnaz ^{[2
]}

Shan, Yi ^{[1
]}

Syamala, Manoj ^{[1
]}

Xu, Shize ^{[5
]}

Zois, Vasileios ^{[1
]}

机构：

[1] Microsoft Corp, Redmond, WA 98052 USA

[2] Amazon, Chennai, Tamil Nadu, India

[3] Amazon Web Serv, Seattle, WA USA

[4] Meta Platforms Inc, Cambridge, MA USA

[5] Stripe Inc, Dublin, Ireland

来源：

PROCEEDINGS OF THE VLDB ENDOWMENT | 2023年 / 16卷 / 13期

关键词：

OPTIMIZATION;

D O I：

10.14778/3625054.3625058

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Oversubscription is an essential cost management strategy for cloud database providers, and its importance is magnified by the emerging paradigm of serverless databases. In contrast to general purpose techniques used for oversubscription in hypervisors, operating systems and cluster managers, we develop techniques that leverage our understanding of how DBMSs use resources and how resource allocations impact database performance. Our techniques are designed to flexibly redistribute resources across database tenants at the node and cluster levels with low overhead. We have implemented our techniques in a commercial cloud database service: Azure SQL Database. Experiments using microbenchmarks, industry-standard benchmarks and real-world resource usage traces show that using our approach, it is possible to tightly control the impact on database performance even with a relatively high degree of oversubscription.

引用

页码：4202 / 4215

页数：14

共 57 条

[1]

AWS, 2023, Amazon Aurora

[2]

AWS, 2021, Amazon Aurora Serverless

[3]

Banerjee Ishan, 2014, Memory Overcommitment in the ESX Server

[4]

Baset Salman Abdul, 2012, ICE HOT

[5] Fully dynamic bin packing revisited [J].

Berndt, Sebastian ;

Jansen, Klaus ;

Klein, Kim-Manuel .

MATHEMATICAL PROGRAMMING, 2020, 179 (1-2) :109-155

[6]

Clark C, 2005, USENIX ASSOCIATION PROCEEDINGS OF THE 2ND SYMPOSIUM ON NETWORKED SYSTEMS DESIGN & IMPLEMENTATION (NSDI '05), P273

[7] Resource Central: Understanding and Predicting Workloads for Improved Resource Management in Large Cloud Platforms [J].

Cortez, Eli ;

Bonde, Anand ;

Muzio, Alexandre ;

Russinovich, Mark ;

Fontoura, Marcus ;

Bianchini, Ricardo .

PROCEEDINGS OF THE TWENTY-SIXTH ACM SYMPOSIUM ON OPERATING SYSTEMS PRINCIPLES (SOSP '17), 2017, :153-167

[8]

Curino Carlo, 2011, SIGMOD, P313, DOI DOI 10.1145/1989323.1989357

[9] Automatically Indexing Millions of Databases in Microsoft Azure SQL Database [J].

Das, Sudipto ;

Grbic, Miroslav ;

Ilic, Igor ;

Jovandic, Isidora ;

Jovanovic, Andrija ;

Narasayya, Vivek R. ;

Radulovic, Miodrag ;

Stikic, Maja ;

Xu, Gaoxiang ;

Chaudhuri, Surajit .

SIGMOD '19: PROCEEDINGS OF THE 2019 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2019, :666-679

[10] CPU Sharing Techniques for Performance Isolation in Multi-tenant Relational Database-as-a-Service [J].

Das, Sudipto ;

Narasayya, Vivek R. ;

Li, Feng ;

Syamala, Manoj .

PROCEEDINGS OF THE VLDB ENDOWMENT, 2013, 7 (01) :37-48

← 1 2 3 4 5 6 →