Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/135837
Title: IN-MEMORY LARGE SCALE DATA MANAGEMENT AND PROCESSING
Authors: ZHANG HAO
Keywords: In-Memory Databases, Distributed Systems, RDMA Networking, Big Data, Distributed Shared Memory, Virtual Memory Management
Issue Date: 17-Jan-2017
Source: ZHANG HAO (2017-01-17). IN-MEMORY LARGE SCALE DATA MANAGEMENT AND PROCESSING. ScholarBank@NUS Repository.
Abstract: Growing main memory capacity has fueled the development of in-memory big data management and processing. In this thesis, we first give a survey on the important memory technology and a wide range of in-memory systems. We then propose a unified in-memory big data management system -- MemepiC, which integrates both online data query and data analytics functionality, by efficiently utilizing the memory hierarchy and exploring RDMA technique. What's more, to extend the capacity of in-memory systems, we design a user-space virtual memory management mechanism (UVMM), which takes advantage of the efficiency of OS VMM in utilizing the hardware, and the abundance of application semantics in the user-space design. Finally, we introduce the Globally Addressable Memory (GAM) that abstracts the memory from a cluster of servers as a shared memory space based on RDMA network. Our approaches are evaluated via extensive experiments, showing its superior performance compared with existing works.
URI: http://scholarbank.nus.edu.sg/handle/10635/135837
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ZhangH.pdf5.58 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

59
checked on Jan 13, 2018

Download(s)

72
checked on Jan 13, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.