|
The NUCAR Army Publications General Information Conferences Research Projects |
|
Home |
IO Workload Characterization
| Research Students: Yijian Wang |
Recent Participants:
Melaku Teshome Hua Huang |
Faculty: David Kaeli |
Project Summary:
This project is supported by the CenSSIS Engineering
Research Center. The project explores how to expose additional parallelism
in data parallel applications by carefully partitioning data files across
multiple disk. This work targets Beowulf clusters and attempts to obtain
parallelism in both processing and I/O access. We are investigating both
static (compile time) and profile-guided approaches to data partitioning.
We are also involved with working with IO Integrity, a startup based
in Medway, MA, developing a smart IO caching device.
In past joint research
between EMC Corporation, I-Tech and NUCAR we investigated new tracing
tools for the I/O domain. These tools allow unlimited length traces
of SCSI bus activity to be captured in real time.
We are working on a new tracing tool able to capture multiple streams
of I/O concurrently, and have used this tool to capture several
large IO traces of synthetic, as well as real, workloads. We are using these
traces to investigate new architectural features in the I/O domain.
This project will also study the characteristics of a number of datamining
applications, hosted in an Oracle database.
Related information can be found at:
NFSTrace at Princeton University code
DFSTrace at CMU code
SRS Kernel Event Trace Facility at UMN
IO Tracing at University of Kentucky
Disk Trace at USM
WRL Tracing Facility at DEC
IO Tracing at HP
Windows I/O Tracing Package at Berkeley
Musketeers at Purdue University
CHARISMA at Dartmouth College
Pablo I/O Trace Environment at UIUC
Parallel I/O Archive
TNF tool at Sun
GlancePlus and Glance Plus Pak at HP
Win-eXpoae-I/O at Shetef Solution Ltd.
SystemI/O at Systar Inc.
Oracle Trace at Oracle
DFSMS Optimizer-I/O Summary Trace Facility at IBM
Sql power I/O statistics Analyzer at Sql Power