Fall 2010   CSCE 689-601   Special Topics on Frontiers in Storage Systems

Location and Hours:

Monday, Wednesday, Friday, 3:00pm-3:50pm

Location: FRAN 153.

Instructor:

Prof. Anxiao (Andrew) Jiang, 309B Bright Building. Email: ajiang@cse.tamu.edu

Office hours: 4:00-5:00pm on Fridays.

Course Description:

Data storage is a very fast developing area in computer systems. With the wide adoption of flash memories, storage systems are undergoing a fundamental transition from magnetic-based mass storage to flash-based mass storage. Frontiers in storage systems – including new infrastructures of storage systems/networks, file systems and coding theories – are actively explored by both industry and academia. This course introduces the basic principles underlying storage systems and their state-of-the-art developments. Students are expected to get a comprehensive understanding of the numerous research directions, and explore novel ideas.

Course Materials:

Reading materials and slides.

Grading and Requirements:

Grading is based on homework (30%), presentation of papers in class (30%), and a final  project (40%). There  are no exams.

Homework:

1. Homework assignment one: Sort the papers in the reading list based on your preference for presentations, and email the sorted list to me by 11:59pm, Sunday, September 26.

2. Homework assignment two: Sort the papers in the reading list based on your preference for presentations, and email the sorted list to me by 11:59pm, Sunday, October 10.

    (The papers are shown in the "Syllabus" table below.)  

3. Homework assignment three: Prepare a question for the talk on 11/05/2010, "Network attached storage architecture," and get the answer. Email me your question and answer by 11:59pm on Friday, 11/05/2010.

4. Homework assignment four: Prepare a question for the talk on 11/08/2010, "Storage Area Network Extension Solutions and Their Performance Assessment," and get the answer. Email me your question and answer by 11:59pm on Monday, 11/08/2010.

5. Homework assignment five: Prepare a question for the talk on 12/01/2010, "Server-storage virtualization: integration and load balancing in data centers," and get the answer. Email me your question and answer by 11:59pm on Monday, 12/01/2010.

Paper Presentation Requirements:

For a paper, a student first gives a five-minute mini presentation. Your goal is to help the audience understand the paper within five minutes. Questions will be asked after the mini presentation. Then, the student gives a 30-minute detailed presentation, which will again be followed by questions from the audience. Your goal is to help the audience have a detailed and clear understanding of the paper.

Slides are required for both the mini presentation and the detailed presentation. Email me the slides one day before the presentation.

Project:

(1) Choose to write either a research paper or a review paper.

(2)  Students should send me (via email) a brief description of the project by November 19, 2010. The final paper is due (by email) on December 6, 2010.

Syllabus:
 
Date Lectures Reading
08/30/2010 Monday Overview. Introduction to Flash Memories. [Slides] 1. Wiki page on flash memory

2. Flash Memory Cells -- An Overview

3. Algorithms and Data Structures for Flash Memories

09/01/2010 Wednesday Introduction to Flash Memories. [Slides]  
09/03/2010 Friday Introduction to Flash Memories. Emerging memory technologies [Slides] 1. Wiki page on phase-change memory (PCM)
09/06/2010 Monday Emerging memory technologies [Slides]  
09/08/2010 Wednesday Memory hierarchy and disk storage.  [Slides]  
09/10/2010 Friday Constrained coding for magnetic/optical storage technologies.  [Chapter 1 of "An Introduction to Coding for Constrained Systems" by Brian H. Marcus, Ron. M. Roth and Paul H. Siegel]  
09/13/2010 Monday Information and coding theory.  [Slides]  
09/15/2010 Wednesday Self study.  
09/17/2010 Friday Information and coding theory.  [Slides]  
09/20/2010 Monday Information and coding theory.  [Slides]  
09/22/2010 Wednesday Information and coding theory.  [Slides]  
09/24/2010 Friday Data movement in NAND flash memories.  [Slides] 1. Storage coding for wear leveling in flash memories.

2. Data movement in flash memories.

3. Data movement and aggregation in flash memories.

09/27/2010 Monday Data movement in NAND flash memories.  [Slides]  
09/29/2010 Wednesday Codes for rewriting data in flash memories. 1. How to reuse a "write-once" memory.
10/01/2010 Friday Codes for rewriting data in flash memories. 1. Universal rewriting in constrained memories.

2. Position modulation code for rewriting write-once memories.

3. On the capacity of permanent memory.

10/04/2010 Monday Presentation by Viacheslav Fedorov: (1) David Woodhouse, JFFS: The journaling flash file system, Ottawa Linux Symposium, July 2001.

[Short Introduction in PPT]   [Short Introduction in PDF]   [Full Presentation in PPT]   [Full Presentation in PDF]

10/06/2010 Wednesday Presentation by Mingqu Yue: (2) Hui Dai, Michael Neufeld and Richard Han, ELF: An Efficient Log-structured Flash File System for Micro Sensor Nodes, in Proc. 2nd International Conference on Embedded Networked Sensor Systems, pp. 176-187, 2004.

[Short Introduction in PPT]   [Short Introduction in PDF]   [Full Presentation in PPT]   [Full Presentation in PDF]

 
10/08/2010 Friday Presentation by Chien-an Lai: (3) Jen-Wei Hsieh, Tei-Wei Kuo and Li-Pin Chang, Efficient identification of hot data for flash memory storage systems. In ACM Transactions on Storage, vol. 2, no. 1, pp. 22-40, 2006.

[Short Introduction in PPT]    [Full Presentation in PPT]

 
10/11/2010 Monday Presentation by Xiangnan Xu: (4) Song Lin, Demetrios Zeinalipour-Yazti, Vana Kalogeraki, Dimitrios Gunopulos and Walid A. Najjar. Efficient indexing data structures for flash-based sensor devices. In ACM Transactions on Storage, vol. 2, no. 4, pp. 468-503, Nov. 2006.

[Short Introduction in PPT] [Short Introduction in PDF] [Full Presentation in PPT] [Full Presentation in PDF]

 

 
10/13/2010 Wednesday Presentation by Yongle Wang: (5) Gaurav Mathur, Peter Desnoyers, Deepak Ganesan and Prashant Shenoy. Ultra-low power data storage for sensor networks. In Proc. the 5th International Conference on Information Processing in Sensor Networks (IPSN), Nashville, Tennessee, April 2006.

[Short Introduction in PPT]  [Full Presentation in PPT]

 

 

10/15/2010 Friday Presentation by Chia-chun Lin: (6) Andrew Birrell, Michael Isard, Chuck Thacker and Ted Wobber. A design for high-performance flash disks. In Operating Systems Review, 41(2), April 2007, pages 88-93.

[Short Introduction in PPT]  [Full Presentation in PPT]

 

 

10/18/2010 Monday Presentation by Shirin Shirvani: (7) Suman Nath and Aman Kansal, FlashDB: Dynamic self-tuning database for NAND flash, in Proc. 6th International Conference on Information Processing in Sensor Networks (IPSN), pp. 410-419, 2007.

[Short Introduction in PPT]  [Full Presentation in PPT]

 
10/20/2010 Wednesday Presentation by Reena Panda: (8) Andreas Lachenmann, Pedro Jose Marron, Matthias Gauger, Daniel Minder, Olga Saukh and Kurt Rothermel. Removing the memory limitations of sensor networks with flash-based virtual memory. In Proc. EuroSys'07, Lisboa, Portugal, March 2007.

[Short Introduction in PPT]  [Short Introduction in PDF]  [Full Presentation in PPT]  [Full Presentation in PDF]

 
10/22/2010 Friday Presentation by Qing Li: (9) Yuan-Hao Chang, Jen-Wei Hsieh and Tei-Wei Kuo, Endurance enhancement of flash-memory storage systems: An efficient static wear leveling design, Proc. DAC 2007, pp.212--217, San Diege, CA, June 2007.

[Introduction and Presentation in PDF]

 
10/25/2010 Monday Presentation by Elangovan Kembanur Natarajan: (10) Hyojun Kim and Seongjun Ahn, BPLRU: A buffer management scheme for improving random writes in flash storage, FAST'08.

[Short Introduction in PPT] [Short Introduction in PDF] [Full Presentation in PPT]  [Full Presentation in PDF]

 
10/27/2010 Wednesday Presentation by Shuhan Xu: (11) David Roberts, Taeho Kgil, Trevor Mudge, Integrating NAND flash devices onto servers, in Communications of the ACM, vol. 52 , no. 4, pp. 98-106, 2009. 

[Introduction and Presentation in PPT]  [Introduction and Presentation in PDF]

 
10/29/2010 Friday Presentation by Sangwhan Moon: (12) Feng Chen, David A. Koufaty, and Xiaodong Zhang, Understanding intrinsic characteristics and system implications of flash memory based solid state drives, in Proceedings of the eleventh international joint conference on Measurement and modeling of computer systems (SIGMETRICS/Performance), Seattle, WA, pp. 181-192, June 2009.

[Introduction and Presentation in PPT]  [Introduction and Presentationo in PDF]

 
11/01/2010 Monday Presentation by Viacheslav Fedorov: U. Manber, Finding Similar Files in a Large File System, Technical Report, University of Arizona, 1993.

[Short Introduction in PPT]  [Full Presentation in PPT]

 
11/03/2010 Wednesday Presentation by Mingqu Yue: F. Chang et al., Bigtable: A Distributed Storage System for Structured Data, ACM Transactions on Computer Systems, 2008.

[Introduction and Presentation in PPT]  [Introduction and Presentation in PDF]

 
11/05/2010 Friday Presentation by Chien-an Lai: G. Gibson and R. Meter, Network attached storage architecture, in Communications of the ACM, 2000.

[Short Introduction in PPT] [Full Presentation in PPT]

 
11/08/2010 Monday Presentation by Xiangnan Xu: R. Telikepalli, T. Drwiega, and J. Yan, Storage Area Network Extension Solutions and Their Performance Assessment, in IEEE Communications Magazine, 2004.

[Short Introduction in PPT] [Short Introduction in PDF] [Full Presentation in PPT] [Full Presentation in PDF]

 
11/10/2010 Wednesday Presentation by Yongle Wang: A. Chervenak, V. Vellanki, and Z. Kurmas, Protecting File Systems: A Survey of Backup Techniques, Proc. Joint NASA and IEEE Mass Storage Conference, 1998.

[Short Introduction in PPT] [Full Presentation in PPT]

 
11/12/2010 Friday Presentation by Chia-chun Lin: B. Zhu, K. Li and H. Patterson, Avoiding the Disk Bottleneck in the Data Domain Deduplication File System, in Proc. 6th USENIX Conference on File and Storage Technologies (FAST), 2008.

[Short Introduction in PPT] [Full Presentation in PPT]

 
11/15/2010 Monday Presentation by Shirin Shirvani: J. Ousterhout et al., The Case for RAMClouds: Scalable High-Performance Storage Entirely in DRAM, Proc. SOSP, 2009.

[Short Introduction in PDF]  [Full Presentation in PDF]

 
11/17/2010 Wednesday Presentation by Reena Panda: G. Burr et al., Overview of Candidate Device Technologies for Storage-Class Memory, in IBM Journal of Research and Development, 2008.

[Short Introduction in PPT]  [Short Introduction in PDF]  [Full Presentation in PPT]  [Full Presentation in PDF]

 
11/19/2010 Friday Presentation by Qing Li: M. Armbrust et al., Above the Clouds: A Berkeley View of Cloud Computing, Technical Report, U.C. Berkeley, 2009.

[Introduction and Presentation in PPT]

 
11/22/2010 Monday Presentation by Elangovan Kembanur Natarajan: D. Andersen et al., FAWN: A Fast Array of Wimpy Nodes, in Proc. SOSP, 2009.

[Short Introduction in PPTX] [Short Introduction in PDF] [Full Presentation in PPTX] [Full Presentation in PDF]

 
11/24/2010 Wednesday No class due to Thanksgiving.  
11/26/2010 Friday No class due to Thanksgiving.  
11/29/2010 Monday Presentation by Shuhan Xu: Sang-Won Lee and Bongki Moon, Design of Flash-based DBMS: An In-page Logging Approach, Proc. of ACM SIGMOD 2007.

[Introduction and Presentation in PPT] [Introduction and Presentation in PDF]

 
12/01/2010 Wednesday Presentation by Sangwhan Moon: A. Singh, M. Korupolu, and D. Mohapatra, Server-storage virtualization: integration and load balancing in data centers, in Proc. ACM/IEEE conference on Supercomputing, 2008. [Introduction and Presentation in PDF]
12/03/2010 Friday No class.  
12/06/2010 Monday No class. Final project due by email at 11:59pm.