book

IBM Power Systems Performance Guide: Implementing and Optimizing

Name: IBM Power Systems Performance Guide: Implementing and Optimizing
ISBN: 0738437662

by Dino Quintero, Sebastien Chabrolles, Chi Hui Chen, Murali Dhandapani, Talor Holloway, Chandrakant Jadhav, Sae Kee Kim, Sijo Kurian, Bharath Raj, Ronan Resende, Bjorn Roden, Niranjan Srinivasan, Richard Wale, William Zanatta, Zhi Zhang

February 2013

Intermediate to advanced

372 pages

11h 50m

English

IBM Redbooks

Read now

Unlock full access

Front cover
Notices
Trademarks
Preface
The team who wrote this bookNow you can become a published author, too!Comments welcomeStay connected to IBM Redbooks
Chapter 1. IBM Power Systems and performance tuning
1.1 Introduction1.2 IBM Power Systems1.3 Overview of this publication1.4 Regarding performance
Chapter 2. Hardware implementation and LPAR planning
2.1 Hardware migration considerations2.2 Performance consequences for processor and memory placement2.2.1 Power Systems and NUMA effect2.2.2 PowerVM logical partitioning and NUMA2.2.3 Verifying processor memory placement2.2.4 Optimizing the LPAR resource placement2.2.5 Conclusion of processor and memory placement2.3 Performance consequences for I/O mapping and adapter placement2.3.1 POWER 740 8205-E6B logical data flow2.3.2 POWER 740 8205-E6C logical data flow2.3.3 Differences between the 8205-E6B and 8205-E6C2.3.4 POWER 770 9117-MMC logical data flow2.3.5 POWER 770 9117-MMD logical data flow2.3.6 Expansion units2.3.7 Conclusions2.4 Continuous availability with CHARM2.4.1 Hot add or upgrade2.4.2 Hot repair2.4.3 Prepare for Hot Repair or Upgrade utility2.4.4 System hardware configurations2.5 Power management
Chapter 3. IBM Power Systems virtualization
3.1 Optimal logical partition (LPAR) sizing3.2 Active Memory Expansion3.2.1 POWER7+ compression accelerator3.2.2 Sizing with the active memory expansion planning tool3.2.3 Suitable workloads3.2.4 Deployment3.2.5 Tunables3.2.6 Monitoring3.2.7 Oracle batch scenario3.2.8 Oracle OLTP scenario3.2.9 Using amepat to suggest the correct LPAR size3.2.10 Expectations of AME3.3 Active Memory Sharing (AMS)3.4 Active Memory Deduplication (AMD)3.5 Virtual I/O Server (VIOS) sizing3.5.1 VIOS processor assignment3.5.2 VIOS memory assignment3.5.3 Number of VIOS3.5.4 VIOS updates and drivers3.6 Using Virtual SCSI, Shared Storage Pools and N-Port Virtualization3.6.1 Virtual SCSI3.6.2 Shared storage pools3.6.3 N_Port Virtualization3.6.4 Conclusion3.7 Optimal Shared Ethernet Adapter configuration3.7.1 SEA failover scenario3.7.2 SEA load sharing scenario3.7.3 NIB with an SEA scenario3.7.4 NIB with SEA, VLANs and multiple V-switches3.7.5 Etherchannel configuration for NIB3.7.6 VIO IP address assignment3.7.7 Adapter choices3.7.8 SEA conclusion3.7.9 Measuring latency3.7.10 Tuning the hypervisor LAN3.7.11 Dealing with dropped packets on the hypervisor network3.7.12 Tunables3.8 PowerVM virtualization stack configuration with 10 Gbit3.9 AIX Workload Partition implications, performance and suggestions3.9.1 Consolidation scenario3.9.2 WPAR storage3.10 LPAR suspend and resume best practices
Chapter 4. Optimization of an IBM AIX operating system
4.1 Processor folding, Active System Optimizer, and simultaneous multithreading4.1.1 Active System Optimizer4.1.2 Simultaneous multithreading (SMT)4.1.3 Processor folding4.1.4 Scaled throughput4.2 Memory4.2.1 AIX vmo settings4.2.2 Paging space4.2.3 One TB segment aliasing4.2.4 Multiple page size support4.3 I/O device tuning4.3.1 I/O chain overview4.3.2 Disk device tuning4.3.3 Pbuf on AIX disk devices4.3.4 Multipathing drivers4.3.5 Adapter tuning4.4 AIX LVM and file systems4.4.1 Data layout4.4.2 LVM best practice4.4.3 File system best practice4.4.4 The filemon utility4.4.5 Scenario with SAP and DB24.5 Network4.5.1 Network tuning on 10 G-E4.5.2 Interrupt coalescing4.5.3 10-G adapter throughput scenario4.5.4 Link aggregation4.5.5 Network latency scenario4.5.6 DNS and IPv4 settings4.5.7 Performance impact due to DNS lookups4.5.8 TCP retransmissions4.5.9 tcp_fastlo4.5.10 MTU size, jumbo frames, and performance
Chapter 5. Testing the environment
5.1 Understand your environment5.1.1 Operating system consistency5.1.2 Operating system tunable consistency5.1.3 Size that matters5.1.4 Application requirements5.1.5 Different workloads require different analysis5.1.6 Tests are valuable5.2 Testing the environment5.2.1 Planning the tests5.2.2 The testing cycle5.2.3 Start and end of tests5.3 Testing components5.3.1 Testing the processor5.3.2 Testing the memory5.3.3 Testing disk storage5.3.4 Testing the network5.4 Understanding processor utilization5.4.1 Processor utilization5.4.2 POWER7 processor utilization reporting5.4.3 Small workload example5.4.4 Heavy workload example5.4.5 Processor utilization reporting in power saving modes5.4.6 A common pitfall of shared LPAR processor utilization5.5 Memory utilization5.5.1 How much memory is free (dedicated memory partitions)5.5.2 Active memory sharing partition monitoring5.5.3 Active memory expansion partition monitoring5.5.4 Paging space utilization5.5.5 Memory size simulation with rmss5.5.6 Memory leaks5.6 Disk storage bottleneck identification5.6.1 Performance metrics5.6.2 Additional workload and performance implications5.6.3 Operating system - AIX5.6.4 Virtual I/O Server5.6.5 SAN switch5.6.6 External storage5.7 Network utilization5.7.1 Network statistics5.7.2 Network buffers5.7.3 Virtual I/O Server networking monitoring5.7.4 AIX client network monitoring5.8 Performance analysis at the CEC5.9 VIOS performance advisor tool and the part command5.9.1 Running the VIOS performance advisor in monitoring mode5.9.2 Running the VIOS performance advisor in post processing mode5.9.3 Viewing the report5.10 Workload management
Chapter 6. Application optimization
6.1 Optimizing applications with AIX features6.1.1 Improving application memory affinity with AIX RSETs6.1.2 IBM AIX Dynamic System Optimizer6.2 Application side tuning6.2.1 C/C++ applications6.2.2 Java applications6.2.3 Java Performance Advisor6.3 IBM Java Support Assistant6.3.1 IBM Monitoring and Diagnostic Tools for Java - Memory Analyzer6.3.2 Other useful performance advisors and analyzers
Appendix A. Performance monitoring tools and what they are telling us
NMONlpar2rrdTrace tools and PerfPMR

Appendix B. New commands and new commands flags
amepatlsconf
Appendix C. Workloads
IBM WebSphere Message BrokerOracle SwingBenchSelf-developed C/C++ application
Related publications
IBM RedbooksOnline resourcesHelp from IBM
Back cover

Overview

This IBM® Redbooks® publication addresses performance tuning topics to help leverage the virtualization strengths of the POWER® platform to solve clients’ system resource utilization challenges, and maximize system throughput and capacity. We examine the performance monitoring tools, utilities, documentation, and other resources available to help technical teams provide optimized business solutions and support for applications running on IBM POWER systems’ virtualized environments.

The book offers application performance examples deployed on IBM Power Systems™ utilizing performance monitoring tools to leverage the comprehensive set of POWER virtualization features: Logical Partitions (LPARs), micro-partitioning, active memory sharing, workload partitions, and more. We provide a well-defined and documented performance tuning model in a POWER system virtualized environment to help you plan a foundation for scaling, capacity, and optimization
.
This book targets technical professionals (technical consultants, technical support staff, IT Architects, and IT Specialists) responsible for providing solutions and support on IBM POWER systems, including performance tuning.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 0738437662Purchase book

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills