Save up to 30% on Elsevier print and eBooks with free shipping. No promo code needed.
Save up to 30% on print and eBooks.
Problem-solving in High Performance Computing
A Situational Awareness Approach with Linux
1st Edition - September 1, 2015
Author: Igor Ljubuncic
Language: English
Paperback ISBN:9780128010198
9 7 8 - 0 - 1 2 - 8 0 1 0 1 9 - 8
eBook ISBN:9780128010648
9 7 8 - 0 - 1 2 - 8 0 1 0 6 4 - 8
Problem-Solving in High Performance Computing: A Situational Awareness Approach with Linux focuses on understanding giant computing grids as cohesive systems. Unlike other ti…Read more
Purchase options
LIMITED OFFER
Save 50% on book bundles
Immediately download your ebook while waiting for your print delivery. No promo code is needed.
Problem-Solving in High Performance Computing: A Situational Awareness Approach with Linux focuses on understanding giant computing grids as cohesive systems. Unlike other titles on general problem-solving or system administration, this book offers a cohesive approach to complex, layered environments, highlighting the difference between standalone system troubleshooting and complex problem-solving in large, mission critical environments, and addressing the pitfalls of information overload, micro, and macro symptoms, also including methods for managing problems in large computing ecosystems.
The authors offer perspective gained from years of developing Intel-based systems that lead the industry in the number of hosts, software tools, and licenses used in chip design. The book offers unique, real-life examples that emphasize the magnitude and operational complexity of high performance computer systems.
Provides insider perspectives on challenges in high performance environments with thousands of servers, millions of cores, distributed data centers, and petabytes of shared data
Covers analysis, troubleshooting, and system optimization, from initial diagnostics to deep dives into kernel crash dumps
Presents macro principles that appeal to a wide range of users and various real-life, complex problems
Includes examples from 24/7 mission-critical environments with specific HPC operational constraints
Professional system administrators, power users and developers, engineers, and solutions architects.
Dedication
Preface
Acknowledgments
Introduction: data center and high-end computing
Chapter 1: Do you have a problem?
Abstract
Identification of a problem
Problem definition
Problem reproduction
Cause and effect
Conclusions
Chapter 2: The investigation begins
Abstract
Isolating the problem
Comparison to a healthy system and known references
Linear versus nonlinear response to changes
Conclusions
Chapter 3: Basic investigation
Abstract
Profile the system status
Process accounting
Statistics to your aid
Conclusions
Chapter 4: A deeper look into the system
Abstract
Working with /proc
Examine kernel tunables
Conclusions
Chapter 5: Getting geeky – tracing and debugging applications
Abstract
Working with strace and ltrace
Working with perf
Working with Gdb
Chapter 6: Getting very geeky – application and kernel cores, kernel debugger
Abstract
Collecting application cores
Collecting kernel cores (Kdump)
Crash analysis (crash)
Kernel debugger
Conclusion
Chapter 7: Problem solution
Abstract
What to do with collected data
Chapter 8: Monitoring and prevention
Abstract
Which data to monitor
How to monitor and analyze trends
How to respond to trends
Configuration auditing
System data collection utilities
Conclusion
Chapter 9: Make your environment safer, more robust
Abstract
Version control
Configuration management
The correct way of introducing changes into the environment
Conclusion
Chapter 10: Fine-tuning the system performance
Abstract
Log size and log rotation
Filesystem tuning
The sysfs filesystem
Proc and sys together
Conclusion
Chapter 11: Piecing it all together
Abstract
Top-down approach
Methodologies used
Tools used
From simple to complicated
Operational constraints
Smart practices
Conclusion
Subject Index
No. of pages: 320
Language: English
Edition: 1
Published: September 1, 2015
Imprint: Morgan Kaufmann
Paperback ISBN: 9780128010198
eBook ISBN: 9780128010648
IL
Igor Ljubuncic
Igor Ljubuncic is a Principal Engineer with Rackspace, a managed cloud company. Previously, Igor has worked as an OS architect within Intel's IT Engineering Computing business group, exploring and developing solutions for a large, global high-performance Linux environment that supports Intel's chip design. Igor has twelve years of experience in the hi-tech industry, first as a physicist and lately in various engineering roles, with a strong focus on data-driven methodologies. To date, Igor has had fifteen patents accepted for filing with the US PTO, emphasizing on data center technologies, scheduling, and Internet of Things. He has authored several open-source projects and technical books, numerous articles accepted for publication in leading technical journals and magazines, and presented at prestigious international conferences. In his free time, Igor writes car reviews, fantasy books and manages his Linux-oriented blog, dedoimedo.com, which garners close to a million views from loyal readers every month.
Affiliations and expertise
Igor Ljubuncic is a Principal Engineer with Rackspace, a managed cloud company
Read Problem-solving in High Performance Computing on ScienceDirect