Skip to content

Solving Enterprise Applications Performance Puzzles Queuing Models to the Rescue

ISBN-10: 1118061578

ISBN-13: 9781118061572

Edition: 2012

Authors: Leonid Grinshpan

List price: $63.50
Blue ribbon 30 day, 100% satisfaction guarantee!
what's this?
Rush Rewards U
Members Receive:
Carrot Coin icon
XP icon
You have reached 400 XP and carrot coins. That is the daily max!

Description:

Poorly performing enterprise applications are the weakest links in corporations management chains causing delays and disruptions of critical business functions. This groundbreaking book frames enterprise application performance engineering not as an art but as applied science built on model-based methodological foundation. The book introduces queuing models of enterprise application that visualize, demystify, explain, and solve system performance issues. Analysis of the models discovers and clarifies not obvious connections and correlations among workloads, hardware architecture, and software parameters.
Customers also bought

Book details

List price: $63.50
Copyright year: 2012
Publisher: John Wiley & Sons, Limited
Publication date: 3/6/2012
Binding: Paperback
Pages: 232
Size: 6.00" wide x 9.25" long x 0.50" tall
Weight: 0.792
Language: English

Acknowledgments
Preface
Queuing Networks as Applications Models
Enterprise Applications-What Do They Have in Common?
Key Performance Indicator-Transaction Time
What Is Application Tuning and Sizing?
Queuing Models of Enterprise Application
Transaction Response Time and Transaction Profile
Network of Highways as an Analogy of the Queuing Model
Take Away from the Chapter
Building and Solving Application Models
Building Models
Hardware Specification
Model Topology
A Model's Input Data
Model Calibration
Essentials of Queuing Networks Theory
Solving Models
Interpretation of Modeling Results
Hardware Utilization
Server Queue Length, Transaction Time, System Throughput
Take Away from the Chapter
Workload Characterization and Transaction Profiling
What Is Application Workload?
Workload Characterization
Transaction Rate and User Think Time
Think Time Model
Take Away from the Think Time Model
Workload Deviations
"Garbage in, Garbage out" Models
Realistic Workload
Users' Redistribution
Changing Number of Users
Transaction Rate Variation
Take Away from "Garbage in, Garbage out" Models
Number of Application Users
User Concurrency Model
Take Away from User Concurrency Model
Business Process Analysis
Mining Transactional Data from Production Applications
Profiling Transactions Using Operating System Monitors and Utilities
Application Log Files
Transaction Monitors
Take Away from the Chapter
Servers, CPUs, and Other Building Blocks of Application Scalability
Application Scalability
Bottleneck Identification
CPU Bottleneck
CPU Bottleneck Models
CPU Bottleneck Identification
Additional CPUs
Additional Servers
Faster CPUs
Take Away from the CPU Bottleneck Model
I/O Bottleneck
I/O Bottleneck Models
I/O Bottleneck Identification
Additional Disks
Faster Disks
Take Away from the I/O Bottleneck Model
Take Away from the Chapter
Operating System Overhead
Components of an Operating System
Operating System Overhead
System Time Models
Impact of System Overhead on Transaction Time
Impact of System Overhead on Hardware Utilization
Take Away from the Chapter
Software Bottlenecks
What Is a Software Bottleneck?
Memory Bottleneck
Memory Bottleneck Models
Preset Upper Memory Limit
Paging Effect
Take Away from the Memory Bottleneck Model
Thread Optimization
Thread Optimization Models
Thread Bottleneck Identification
Correlation Among Transaction Time, CPU Utilization, and the Number of Threads
Optimal Number of Threads
Take Away from Thread Optimization Model
Other Causes of Software Bottlenecks
Transaction Affinity
Connections to Database; User Sessions
Limited Wait Time and Limited Wait Space
Software Locks
Take Away from the Chapter
Performance and Capacity of Virtual Systems
What Is Virtualization?
Hardware Virtualization
Non-Virtualized Hosts
Virtualized Hosts
Queuing Theory Explains It All
Virtualized Hosts Sizing After Lesson Learned
Methodology of Virtual Machines Sizing
Take Away from the Chapter
Model-Based Application Sizing: Say Good-Bye to Guessing
Why Model-Based Sizing?
A Model's Input Data
Workload and Expected Transaction Time
How to Obtain a Transaction Profile
Hardware Platform
Mapping a System into a Model
Model Deliverables and What-If Scenarios
Take Away from the Chapter
Modeling Different Application Configurations
Geographical Distribution of Users
Remote Office Models
Users' Locations
Network Latency
Take Away from Remote Office Models
Accounting for the Time on End-User Computers
Remote Terminal Services
Cross-Platform Modeling
Load Balancing and Server Farms
Transaction Parallel Processing Models
Concurrent Transaction Processing by a Few Servers
Concurrent Transaction Processing by the Same Server
Take Away from Transaction Parallel Processing Models
Take Away from the Chapter
Glossary
References
Index