Download Mid-term Presentation

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

File Allocation Table wikipedia , lookup

Computer security wikipedia , lookup

Lustre (file system) wikipedia , lookup

Asynchronous I/O wikipedia , lookup

Clusterpoint wikipedia , lookup

OneDrive wikipedia , lookup

XFS wikipedia , lookup

Files-11 wikipedia , lookup

File locking wikipedia , lookup

Concurrency control wikipedia , lookup

Computer file wikipedia , lookup

Object storage wikipedia , lookup

Transcript
Cloud Storage Systems
A Survey
Presented By
Nitya Shankaran
Ritika Sharma
Motivation
 Important to know how our data is being stored.
 Need to know how your data can be stored efficiently in the
cloud i.e. choosing the right kind of storage.
 Currently not much research is carried out on this topic.
 Need for a clear classification of different cloud storage
systems.
 Recent security issue:
Dropbox - deduplication of files
Goals
 Analyzing different types of storage that cloud systems provide.
- Object storage
- Block storage
- Relational Database storage (RDS)
- Distributed File systems etc.
 Research on architecture of different cloud storage systems.
- Amazon S3 (Object storage)
- Google File System (Distributed File System Storage)
- HDFS (Distributed File System Storage)
- Microsoft SQL Azure (Relational Database Storage)
 Performance Analysis and Evaluation of each system.
Related Work
 Palankar, M., Onibokun, A., Iamnitchi, A., and Ripeanu, M.
2007. Amazon S3 for Science Grids: a Viable Solution?. 4th
USENIX Symposium on Networked Systems, Design &
Implementation (NSDI'07), April 2007.
 Amazon Web Services: Overview of Security Processes
http://s3.amazonaws.com/aws_blog/AWS_Security_Whitepaper_2008.
pdf
 Ghemawat,S., Gobioff, H., and Shun-Tak Leung. The Google
File System 2003
 Konstantin Shvachko, Hairong Kuang, Sanjay Radia, Robert
Chansler. The Hadoop Distributed File System
 Chappell David, Oct 2008. Introducing the Azure Services
Platform, Microsoft Corporation
Performance Analysis and
Evaluation










Reliability
Scalability
Data Durability
Throughput of write requests
Availability rate
Data access performance
- Downloading
- Uploading
Concurrent Access
Load balancing
Security Issues
Cost
Timeline
 17th Oct : Project Proposal
 23rd Oct - 29th Oct : Research the architecture of Microsoft
SQL Azure (Nitya) and Amazon S3 (Ritika)
 30th Oct - 8th Nov : Performance Analysis and Evaluation of
the above systems
 9th Nov - 16th Nov : Research the architecture of Google
File System (Nitya) and HDFS (Ritika)
 17th - 26th Nov : Performance Analysis and Evaluation of the
above systems
 27th Nov - 4th Dec : Comparison of all systems and Final
Report
Thank you!