Difference between revisions of "Cluster:LLK Poster Structure"

From Earlham CS Department
Jump to navigation Jump to search
(Benchmarks)
Line 10: Line 10:
  
 
===Survey/Current State of Affairs===
 
===Survey/Current State of Affairs===
 +
* Light, detail in [[#Measurement Techniques]].
 +
* Include dead ends here.
 +
* List of approaches.
 +
 
Places to look:
 
Places to look:
 
* Beowulf archives
 
* Beowulf archives
Line 17: Line 21:
 
* Google Scholar
 
* Google Scholar
  
==Methodology==
+
==Design (of the Experiment, Methodology)==
 
===Measurement (Techniques)===
 
===Measurement (Techniques)===
 
* TCP/IP stack time point placement
 
* TCP/IP stack time point placement
Line 33: Line 37:
 
* MrBayes (high level)
 
* MrBayes (high level)
  
==Test Results==
+
==Results (of the Experiment)==
 
(tabular, incl. test environment)
 
(tabular, incl. test environment)
  
==Summary/Discussion/Conclusions==
+
==Analysis (Summary/Discussion/Conclusions)==
  
 
==Future Work==
 
==Future Work==
  
 
==References==
 
==References==

Revision as of 11:47, 28 January 2006

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

Overview

Motivation

Survey/Current State of Affairs

Places to look:

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

Design (of the Experiment, Methodology)

Measurement (Techniques)

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

Verification and Validation

(Analysis) Tools

  • /proc -> database
  • PHP/gnuplot visualization

Benchmarks

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

Results (of the Experiment)

(tabular, incl. test environment)

Analysis (Summary/Discussion/Conclusions)

Future Work

References