- Attribute-Based Naming - file management using both user supplied file attributes plus attributes based on context analysis.
- Database I/O - optimizing database performance
- Data Center Observatory (DCO) - A working data center and a research vehicle for the study of data center automation and efficiency.
- DiskSim - an efficient, accurate, highly-configurable disk system simulator.
- Expressive Storage Interface - increasing the flow of information between storage devices and system software to increase performance, reliability, and make data more manageable.
- Fates Database Storage - exploiting information available at each level of the database memory hierarchy offers efficient execution and optimized data layout to improve performance.
- Survivable Storage (PASIS) - decentralized storage systems whose availability and security policies can survive component failures and successful malicious attacks
- Self-Securing Devices - systems with security functionality equally distributed among physically distinct system components
- Self-Securing Storage - storage devices that prevent successful intruders from undetectably tampering with or permanently deleting stored data
- Self-* Storage - a new storage architecture that integrates automated management functions and simplifies the human administrative task. Self*-systems are self configuring, self-organizing, self-managing, etc.
- Workload Characterization - traffic
modeling of storage workloads for evaluating system design.
- Abacus - explores the effective use of cluster resources for distributed applications
- Attribute-Based Learning Environments (ABLE) - a method of classifying the properties of existing files and predicting the properties of new files when they are created.
- Active Disks - remote execution for network-attached storage
- Active Storage Networks - storage and filesystem functionality able to migrate to the most appropriate location in the system (e.g. client, router, NASD)
- Batchactive Scheduling - combining batch and interactive characteristics to exploit the inherent speculation in common application scenarios
- Castellan - administrative interfaces for managing distributed intrusion detection.
- Continuous Data Reorganization - A two-tiered software architecture for cleanly and extensibly combining heuristics developed for adapting on-disk data layouts to expected and observed workload characteristics.
- DIXtrac - automated disk drive characterization
- Freeblock Scheduling - a new disk scheduling approach that can increase media bandwidth utilization by 10X
- MEMS-Based Storage - a new technology for non-volatile storage technology merging magnetic recording material and thousands of recording heads to provide 1-10 GB of storage in under 1 square cm
- Network Attached Secure Disks (NASD) - devices, networking, security protocols, file systems and storage management for network-attached storage
- PARIS - A general approach to the identification and characterization of robustness faults within applications by the analysis of the source program
- RAID - novel architectures and rapid prototyping for redundant disk arrays
- RAIDframe - rapid prototyping for disk arrays
- SIO - file system interfaces and support mechanisms for I/O-intensive parallel applications
- Transparent Informed Prefetching (TIP) - an aggressive method of prefetching and caching informed by application disclosure in local and remote file systems
- Internet Video - resource reservation
and video prefetching for internet video server clusters in digital
libraries
WELCOME
The Parallel Data Lab at Carnegie Mellon University is academia's premiere storage systems research center. An interdisciplinary group, its 40-50 members come mainly from the Computer Science and ECE Departments. We also have a lot of friends in industry who generously provide us with advice, and some of the funding and equipment necessary to carry out our research.
BRIEF RESEARCH OVERVIEW
Our research addresses a broad spectrum of storage-related challenges, including storage security, emerging technologies, disk characterization and modeling, efficient storage access, storage networking, and network-attached storage clusters.
CURRENT PROJECTS:
RECENT PROJECTS:
CONTACTS
,
PDL Director
(412) 268-1297
, PDL Executive Director
(412) 268-5485
(412) 268-5890
,
PDL Administrative Manager
(412) 268-6716
Mailing Address:
Computer Science Department
School of Computer Science
Carnegie Mellon University
5000 Forbes Avenue - CIC 2209
Pittsburgh, PA 15213-3891
FIND US
Most PDL offices are now located in the CIC Building on campus.
PDL's Visitor Information page.
The School of Computer Science's extensive
list of directions on how
to get to CMU from just about anywhere.
More directions to find CMU and the Dept. of ECE.