Cluster:LLK Poster Structure

Abstract

Network latency continues to be a bottleneck for many computational science applications on Beowulf clusters. Using open source tools, we develop technology for making nanosecond precision measurements between timing points within the 2.6 Linux kernel. Using this technology, in conjunction with low-level and application benchmarks, we establish that there is significant network latency in the kernel and identify its origin. Lastly, we survey software-based latency reduction technologies and make recommendations based on our measurements. (original)

Keywords:

The Problem

Survey/Current State of Affairs

• Light, detail in #Measurement_(Techniques).
• Include dead ends here.
• List of approaches.

Places to look:

• Beowulf archives
• ACM
• IEEE
• Citeseer
• Google Scholar
• tp_timer
• NIST

Design (of the Experiment, Methodology)

Measurement (Techniques)

• TCP/IP stack time point placement
• tp_timer
• high res timing w/counters

Verification and Validation

• Verification is the demonstration that the model is logically correct and follows from the physical and mathematical laws used. For a computer simulation, verification shows that the specifications are fulfilled and that the model will run on the computer system as specified.

• Validation is the demonstration that the model correctly predicts the phenomena modeled. This ensures that the model is based on good scientific methods and principles.

(Analysis) Tools

• /proc -> database
• PHP/gnuplot visualization

Benchmarks

• netpipe (low level)
• MrBayes (high level)

Results (of the Experiment)

(tabular, incl. test environment)

References

• source documents
• bibtex/latex