Avocado: A Secure In-Memory Distributed Storage System

被引:0
|
作者
Bailleu, Maurice [1 ]
Giantsidi, Dimitra [1 ]
Gavrielatos, Vasilis [1 ]
Quoc, Do Le [2 ,4 ]
Nagarajan, Vijay [1 ]
Bhatotia, Pramod [1 ,3 ]
机构
[1] Univ Edinburgh, Edinburgh, Midlothian, Scotland
[2] Huawei Res, Munich, Germany
[3] Tech Univ Munich, Munich, Germany
[4] Tech Univ Dresden, Dresden, Germany
关键词
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We introduce Avocado, a secure in-memory distributed storage system that provides strong security, fault-tolerance, consistency (linearizability) and performance for untrusted cloud environments. Avocado achieves these properties based on TEEs, which, however, are primarily designed for securing limited physical memory (enclave) within a single-node system. Avocado overcomes this limitation by extending the trust of a secure single-node enclave to the distributed environment over an untrusted network, while ensuring that replicas are kept consistent and fault-tolerant in a malicious environment. To achieve these goals, we design and implementAvocado underpinning on the cross-layer contributions involving the network stack, the replication protocol, scalable trust establishment, and memory management. Avocado is practical: In comparison to BFT, Avocado provides confidentiality with fewer replicas and is significantly faster -4.5x to 65x for YCSB read and write heavy workloads, respectively.
引用
收藏
页码:285 / 301
页数:17
相关论文
共 50 条
  • [1] Performance Optimization of In-Memory File System in Distributed Storage System
    Li, Zhaowei
    Yan, Yunlong
    Mo, Jintao
    Wen, Zhaocong
    Wu, Junmin
    [J]. 2017 INTERNATIONAL CONFERENCE ON NETWORKING, ARCHITECTURE, AND STORAGE (NAS), 2017, : 280 - 281
  • [2] NYNN: An In-memory Distributed Storage System for Massive Graph Analysis
    Ran, Panfeng
    Zhou, Wei
    Han, Jizhong
    [J]. 2015 SEVENTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE (ICACI), 2015, : 383 - 389
  • [3] Secure In-memory Key-Value Storage with SGX
    Kim, Taehoon
    Park, Joongun
    Woo, Jaewook
    Jeon, Seungheun
    Huh, Jaehyuk
    [J]. PROCEEDINGS OF THE 2018 ACM SYMPOSIUM ON CLOUD COMPUTING (SOCC '18), 2018, : 507 - 507
  • [4] Memory Management for Billions of Small Objects in a Distributed In-Memory Storage
    Klein, Florian
    Beineke, Kevin
    Schoettner, Michael
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING (CLUSTER), 2014, : 113 - 122
  • [5] DITA: A Distributed In-Memory Trajectory Analytics System
    Shang, Zeyuan
    Li, Guoliang
    Bao, Zhifeng
    [J]. SIGMOD'18: PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2018, : 1681 - 1684
  • [6] In-memory, distributed content-based recommender system
    Simon Dooms
    Pieter Audenaert
    Jan Fostier
    Toon De Pessemier
    Luc Martens
    [J]. Journal of Intelligent Information Systems, 2014, 42 : 645 - 669
  • [7] Implementation of Distributed In-Memory Moving Objects Management System
    Lee, H.
    Kwak, Y.
    Song, S.
    [J]. ADVANCED SCIENCE LETTERS, 2017, 23 (10) : 10361 - 10365
  • [8] Optimizing Pipelined Execution for Distributed In-Memory OLAP System
    Wang, Li
    Zhang, Lei
    Yu, Chengcheng
    Zhou, Aoying
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2014, 2014, 8505 : 204 - 216
  • [9] In-memory, distributed content-based recommender system
    Dooms, Simon
    Audenaert, Pieter
    Fostier, Jan
    De Pessemier, Toon
    Martens, Luc
    [J]. JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2014, 42 (03) : 645 - 669
  • [10] SharkDB:An In-Memory Storage System for Massive Trajectory Data
    Wang, Haozhou
    Zheng, Kai
    Zhou, Xiaofang
    Sadiq, Shazia
    [J]. SIGMOD'15: PROCEEDINGS OF THE 2015 ACM SIGMOD INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2015, : 1099 - 1104