[ Previous | Next | Table of Contents | Index | Library Home | Legal | Search ]

Performance Management Guide

Table of Contents

About This Book

  • Who Should Use This Book
  • Highlighting
  • ISO 9000
  • Related Publications
  • Trademarks

    • Chapter 1. Performance Concepts

  • How Fast is That Computer?
  • Understanding the Workload
  • Industry-Standard Benchmarks: A Risky Shortcut
  • Performance Objectives
  • Program Execution Dynamics
  • Hardware Hierarchy
  • Fixed Disks
  • Real Memory
  • Translation Lookaside Buffer (TLB)
  • Caches
  • Pipeline and Registers
  • Software Hierarchy
  • Executable Programs
  • Interrupt Handlers
  • Waiting Threads
  • Dispatchable Threads
  • Currently Dispatched Threads
  • Current Instructions
  • System Dynamics
  • Classes of Workload
  • Introducing the Performance-Tuning Process
  • Identifying the Workloads
  • Setting Objectives
  • Identifying Critical Resources
  • CPU
  • Memory
  • Disk Space
  • Network Access
  • Minimizing Critical-Resource Requirements
  • Using the Appropriate Resource
  • Reducing the Requirement for the Critical Resource
  • Structuring for Parallel Use of Resources
  • Reflecting Priorities in Resource Allocation
  • Repeating the Tuning Steps
  • Applying Additional Resources
  • Performance Benchmarking
  • Related Information

    • Chapter 2. Resource Management Overview

  • Performance Overview of the CPU Scheduler
  • Thread Support
  • Processes and Threads
  • Process and Thread Priority
  • Scheduling Policy for Threads
  • Scheduler Run Queue
  • Scheduler CPU Time Slice
  • Mode Switching
  • User Mode
  • Kernel Mode
  • Mode Switches
  • Performance Overview of the Virtual Memory Manager (VMM)
  • Real-Memory Management
  • Free List
  • Persistent versus Working Segments
  • Computational versus File Memory
  • Page Replacement
  • Repaging
  • VMM Thresholds
  • VMM Memory Load Control Facility
  • Memory Load Control Algorithm
  • Allocation and Reclamation of Paging Space Slots
  • Late Allocation Algorithm
  • Early Allocation Algorithm
  • Deferred Allocation Algorithm
  • Performance Overview of Fixed-Disk Storage Management
  • Sequential-Access Read Ahead
  • Write Behind
  • Memory Mapped Files and Write Behind
  • Disk-I/O Pacing

    • Chapter 3. Introduction to Multiprocessing

  • Symmetrical Multiprocessor (SMP) Concepts and Architecture
  • Types of Multiprocessing
  • Shared Nothing MP (pure cluster)
  • Shared Disks MP
  • Shared Memory Cluster (SMC)
  • Shared Memory MP
  • Symmetrical versus Asymmetrical Multiprocessors
  • Asymmetrical Multiprocessors
  • Symmetrical Multiprocessors
  • Multiprocessors
  • Parallelizing an Application
  • Data Serialization
  • Types of Locks
  • AIX Version 4 Simple Locks
  • AIX Version 4 Complex Locks
  • Lock Granularity
  • Locking Overhead
  • Waiting for Locks
  • Cache Coherency
  • Processor Affinity and Binding
  • Memory and Bus Contention
  • SMP Performance Issues
  • Workload Concurrency
  • Throughput
  • Response Time
  • SMP Workloads
  • Workload Multiprocessability
  • Multiprocessor Throughput Scalability
  • Multiprocessor Response Time
  • SMP Thread Scheduling
  • Default Scheduler Processing of Migrated Workloads
  • Scheduling Algorithm Variables
  • Thread Tuning
  • Thread Environment Variables
  • SPINLOOPTIME=n
  • YIELDLOOPTIME=n
  • AIXTHREAD_SCOPE={P|S}
  • AIXTHREAD_GUARDPAGES=n
  • MALLOCMULTIHEAP={considersize,heaps:n}
  • Variables for Process-Wide Contention Scope
  • Thread Debug Options
  • Thread Tuning Summary
  • SMP Tools
  • The bindprocessor Command
  • Considerations
  • The lockstat Command
  • The schedtune -s Command

    • Chapter 4. Planning and Implementing for Performance

  • Identifying the Components of the Workload
  • Documenting Performance Requirements
  • Estimating the Resource Requirements of the Workload
  • Measuring Workload Resources
  • Measuring a Complete Workload on a Dedicated System
  • Measuring a Complete Workload on a Production System
  • Measuring a Partial Workload on a Production System
  • Measuring an Individual Program
  • Estimating Resources Required by a New Program
  • Transforming Program-Level Estimates to Workload Estimates
  • Designing and Implementing Efficient Programs
  • CPU-Limited Programs
  • Design and Coding for Effective Use of Caches
  • Registers and Pipeline
  • Cache and TLBs
  • Effective Use of Preprocessors and the Compilers
  • Levels of Optimization
  • No Optimization
  • -O or -O2
  • -O3
  • Compiling for Specific Hardware Platforms (-qarch, -qtune)
  • C Options for string.h Subroutine Performance
  • C and C++ Coding Style for Best Performance
  • Compiler Execution Time
  • Memory-Limited Programs
  • Structuring of Pageable Code
  • Structuring of Pageable Data
  • Misuse of Pinned Storage
  • Using Performance-Related Installation Guidelines
  • Operating System Preinstallation Guidelines
  • CPU Preinstallation Guidelines
  • Memory Preinstallation Guidelines
  • Disk Preinstallation Guidelines
  • Placement and Sizes of Paging Spaces
  • Performance Implications of Disk Mirroring
  • Performance Implications of Mirrored Striped LVs
  • Communications Preinstallation Guidelines

    • Chapter 5. System Monitoring and Initial Performance Diagnosis

  • The Case for Continuous Performance Monitoring
  • Using the vmstat, iostat, netstat, and sar Commands
  • Using the topas Monitor
  • Using the Performance Diagnostic Tool
  • Using the Performance Toolbox
  • Recording with the Performance Agent
  • Determining the Kind of Performance Problem Reported
  • A Particular Program Runs Slowly
  • Everything Runs Slowly at a Particular Time of Day
  • Everything Runs Slowly at Unpredictable Times
  • Everything That an Individual User Runs is Slow
  • A Number of LAN-Connected Systems Slow Down Simultaneously
  • Everything on a Particular Service or Device Slows Down at Times
  • Identifying the Performance-Limiting Resource
  • Determining the Limiting Factor for a Single Program
  • Determining Whether the Problem is Related to Disk or Memory
  • Managing Workload

    • Chapter 6. Monitoring and Tuning CPU Use

  • Monitoring CPU Use
  • The vmstat Command (CPU)
  • The iostat Command
  • The sar Command
  • Real-time sampling and display
  • Display previously captured data
  • System activity accounting via cron daemon
  • The xmperf Program
  • Using the time Command to Measure CPU Use
  • time and timex Cautions
  • Identifying CPU-Intensive Programs
  • Using the ps Command
  • CPU Intensive
  • CPU Time Ratio
  • The THREAD Option
  • Using the acctcom Command
  • Using the tprof Program to Analyze Programs for CPU Use
  • A tprof Example
  • Offline Processing with the tprof Command
  • Using the pprof Command to Measure CPU usage of Kernel Threads
  • Detecting Instruction Emulation with the emstat Tool
  • Restructuring Executable Programs with the fdpr Program
  • Controlling Contention for the CPU
  • Controlling the Priority of User Processes
  • Running a Command with the nice Command
  • Setting a Fixed Priority with the setpri Subroutine
  • Displaying Process Priority with the ps Command
  • Modifying the Priority with the renice Command
  • Clarification of the nice and renice Command Syntax
  • Tuning the Thread-Priority-Value Calculation
  • Priority Calculation
  • Tuning with the schedtune Command
  • Example of a Priority Calculation
  • Modifying the Scheduler Time Slice with the schedtune Command
  • CPU-Efficient User ID Administration (The mkpasswd Command)

    • Chapter 7. Monitoring and Tuning Memory Use

  • Determining How Much Memory Is Being Used
  • The vmstat Command (Memory)
  • The vmstat -I Command
  • The vmstat -s Command
  • The ps Command
  • The svmon Command
  • How Much Memory is in Use
  • Who is Using Memory?
  • Detailed Information on a Specific Segment ID
  • List of Top Memory Usage of Segments
  • Correlating svmon and vmstat Outputs
  • Correlating svmon and ps Outputs
  • Calculating the Minimum Memory Requirement of a Program
  • Finding Memory-Leaking Programs
  • Assessing Memory Requirements Through the rmss Command
  • Two Styles of Using rmss
  • Using rmss to Change the Memory Size and Exit
  • Using rmss to Run a Command over a Range of Memory Sizes
  • Interpreting rmss Results
  • Report Generated for the foo Program
  • Report for a 16 MB Remote Copy
  • Hints for Using the -s, -f, -d, -n, and -o Flags
  • Guidelines to Consider When Running the rmss Command
  • Tuning VMM Memory Load Control with the schedtune Command
  • Memory Load Control Tuning
  • The h Parameter
  • The p Parameter
  • The m Parameter
  • The w Parameter
  • The e Parameter
  • Tuning VMM Page Replacement with the vmtune Command
  • Choosing minfree and maxfree Settings
  • Tuning Memory Pools
  • Tuning lrubucket to Reduce Memory Scanning Overhead
  • Choosing minperm and maxperm Settings
  • Placing a Hard Limit on Persistent File Cache with strict_maxperm
  • Tuning Paging-Space Thresholds
  • Choosing npswarn and npskill Settings
  • Tuning the fork() Retry Interval Parameter with schedtune
  • Choosing a Page Space Allocation Method
  • Late Page Space Allocation
  • Early Page Space Allocation
  • Deferred Page Space Allocation
  • Choosing between LPSA and DPSA with the vmtune Command
  • Looking at Paging Space and Virtual Memory
  • Using Shared Memory
  • Extended Shared Memory (EXTSHM)

    • Chapter 8. Monitoring and Tuning Disk I/O Use

  • Monitoring Disk I/O
  • Building a Pre-Tuning Baseline
  • Wait I/O Time Reporting
  • Method Used in AIX 4.3.2 and Earlier
  • Method Used in AIX 4.3.3 and Later
  • Assessing Disk Performance with the iostat Command
  • TTY Report
  • CPU Report
  • Drive Report
  • Assessing Disk Performance with the vmstat Command
  • Assessing Disk Performance with the sar Command
  • Assessing Logical Volume Fragmentation with the lslv Command
  • Assessing Physical Placement of Data with the lslv Command
  • Assessing File Placement with the fileplace Command
  • Space Efficiency and Sequentiality
  • Assessing Paging Space I/O with the vmstat Command
  • Assessing Overall Disk I/O with the vmstat Command
  • Detailed I/O Analysis with the filemon Command
  • Global Reports of the filemon Command
  • Detailed Reports of the filemon Command
  • Guidelines for Using the filemon Command
  • Summary for Monitoring Disk I/O
  • Changing File System Attributes that Affect Performance
  • File-System Fragment Size
  • Compression
  • Changing Logical Volume Attributes That Affect Performance
  • Position on Physical Volume
  • Range of Physical Volumes
  • Maximum Number of Physical Volumes to Use for Allocation
  • Mirror Write Consistency
  • Allocate Each Logical Partition Copy on a Separate PV
  • Relocate the Logical Volume During Reorganization?
  • Scheduling Policy for Reading/Writing Logical Partition Copies
  • Enable Write Verify
  • Striping Size
  • Physical Volume Considerations
  • Volume Group Recommendations
  • Performance Impacts of Mirroring rootvg
  • Reorganizing Logical Volumes
  • Recommendations for Best Performance
  • Recommendations for Highest Availability
  • Reorganizing File Systems
  • Reorganizing a File System
  • Defragmenting a File System
  • Reorganizing JFS Log and Log Logical Volumes
  • Creating Log Logical Volumes
  • Tuning with vmtune
  • Sequential Read-Ahead
  • VMM Write-Behind
  • Sequential Write-Behind
  • Random Write-Behind
  • Tuning File Syncs
  • Miscellaneous I/O Tuning Parameters
  • numfsbufs
  • lvm_bufcnt
  • hd_pbuf_cnt
  • pd_npages
  • v_pinshm
  • fsbufwaitcnt and psbufwaitcnt
  • Using Disk-I/O Pacing
  • Example
  • Tuning Logical Volume Striping
  • Designing a Striped Logical Volume
  • Tuning for Striped Logical Volume I/O
  • Mirrored Striped Logical Volume Performance Implications
  • Tuning Asynchronous Disk I/O
  • Tuning Direct I/O
  • Performance of Direct I/O Reads
  • Performance of Direct I/O Writes
  • Performance Example
  • Summary
  • Using Raw Disk I/O
  • Using sync/fsync Calls
  • Setting SCSI-Adapter and Disk-Device Queue Limits
  • Non-IBM Disk Drive
  • Non-IBM Disk Array
  • Expanding the Configuration
  • Using RAID
  • RAID Levels and Their Performance Implications
  • RAID 0 - For Performance
  • RAID 1 - For Availability/Good Read Response Time
  • RAID 2 - Rarely Used
  • RAID 3 - For CAD/CAM, Sequential Access to Large Files
  • RAID 4 - Less Used (Parity Volume Bottleneck)
  • RAID 5 - High Availability and Fewer Writes Than Reads
  • RAID 6 - Seldom Used
  • RAID 7 - A Definition of 3rd Parties
  • RAID 10 - RAID-0+1
  • Summary of RAID Levels
  • RAID Performance Summary
  • Using SSA
  • Guidelines for Improving SSA Performance
  • Using Fast Write Cache

    • Chapter 9. Monitoring and Tuning Communications I/O Use

  • UDP and TCP/IP Performance Overview
  • Communication Subsystem Memory (mbuf) Management
  • Socket Layer
  • Send Flow
  • Receive Flow
  • Socket Creation
  • Ephemeral Ports
  • Relative Level of Function in UDP and TCP
  • UDP Layer
  • TCP Layer
  • IP Layer
  • Send Flow
  • Receive Flow
  • Demux Layer
  • Send Flow
  • Receive Flow
  • LAN Adapters and Device Drivers
  • Send Flow
  • Receive Flow
  • Analyzing Network Performance
  • The ping Command
  • The ftp Command
  • The netstat Command
  • Using the netstat Command
  • The netpmon Command
  • Using netpmon
  • Global Reports of netpmon
  • Detailed Reports of netpmon
  • Limitations of netpmon
  • The traceroute Command
  • Successful traceroute Examples
  • Failed traceroute Examples
  • The iptrace daemon, and the ipreport and ipfilter Commands
  • Adapter Statistics
  • The entstat Command
  • The tokstat Command
  • The fddistat Command
  • The atmstat Command
  • The no Command
  • Tuning TCP and UDP Performance
  • Overall Recommendations
  • Maximizing Throughput
  • Minimizing Memory
  • Adapter Transmit and Receive Queue Tuning
  • Transmit Queues
  • Receive Queues
  • Device-Specific Buffers
  • When to Increase the Receive/Transmit Queue Parameters
  • Commands to Query and Change the Queue Parameters
  • How to See the Settings
  • How to Change the Parameters
  • Tuning MCA and PCI Adapters
  • Enabling Thread Usage on LAN Adapters (dog threads)
  • Tuning TCP Maximum Segment Size
  • Local Network
  • Remote Network
  • UDP Socket Buffer Tuning
  • udp_sendspace
  • udp_recvspace
  • TCP Socket Buffer Tuning
  • tcp_sendspace
  • tcp_recvspace
  • rfc1323
  • sb_max
  • Interface-Specific Network Options (ISNO)
  • IP Protocol Performance Tuning Recommendations
  • Ethernet Performance Tuning Recommendations
  • Token-Ring (4 MB) Performance Tuning Recommendations
  • Token-Ring (16 MB) Performance Tuning Recommendations
  • FDDI Performance Tuning Recommendations
  • ATM Performance Tuning Recommendations
  • SOCC Performance Tuning Recommendations
  • HIPPI Performance Tuning Recommendations
  • Tuning mbuf Pool Performance
  • Overview of the mbuf Management Facility
  • Tuning Network Memory
  • Tuning Asynchronous Connections for High-Speed Transfers
  • Async Port Tuning Techniques
  • Shell Script fastport.sh for Fast File Transfers
  • Tuning Name Resolution
  • Improving telnetd/rlogind Performance
  • Tuning the SP Network
  • SP Switch Statistics
  • The estat Command
  • The vdidlxxxx Commands
  • SP System-Specific Tuning Recommendations
  • Managing Tunable SP Parameters
  • Initial Settings of SP Tunable Parameters
  • Tuning the SP Network for Specific Workloads

    • Chapter 10. Monitoring and Tuning NFS Use

  • NFS Overview
  • NFS Version 3
  • Write Throughput
  • Read Throughput
  • Reduced Requests for File Attributes
  • Efficient Use of High Bandwidth Network Technology
  • Reduced Directory "Lookup" Requests
  • Changes Since AIX 4.2.1
  • Changes in AIX 4.3
  • Analyzing NFS Performance
  • The nfsstat Command
  • RPC Statistics
  • NFS Server Information
  • NFS Client Information
  • The netpmon Command
  • The nfso Command
  • NFS References
  • List of Network File System (NFS) Files
  • List of NFS Commands
  • List of NFS Daemons
  • Tuning for NFS Performance
  • How Many biod and nfsd Daemons Are Needed?
  • Choosing Initial Numbers of nfsd and biod daemons
  • Tuning the Numbers of nfsd and biod daemons
  • Performance Implications of Hard or Soft NFS Mounts
  • Other mount Options That Affect Performance
  • The rsize and wsize Options
  • Disabling Unused NFS ACL Support
  • Tune Retransmissions
  • Tuning to Avoid Retransmits
  • Dropped Packets
  • Packets Dropped by the Client
  • Packets Dropped by the Server
  • Dropped Packets On the Network
  • Tuning the NFS File-Attribute Cache
  • Tuning for Maximum Caching of NFS Data
  • Cache File System (CacheFS)
  • CacheFS Benefits
  • What CacheFS Does Not Do
  • Configuring CacheFS
  • Tuning Other Layers to Improve NFS Performance
  • Increasing NFS Socket Buffer Size
  • NFS Server Disk Configuration
  • Misuses of NFS That Affect Performance
  • NFS Tuning Checklist

    • Chapter 11. Monitoring and Tuning Java

  • What is Java?
  • Why Java?
  • Java Performance Guidelines
  • Monitoring Java
  • Tuning Java

    • Chapter 12. Analyzing Performance with the Trace Facility

  • Understanding the Trace Facility
  • Implementation
  • Limiting the Amount of Trace Data Collected
  • Starting and Controlling Trace
  • Formatting Trace Data
  • Viewing Trace Data
  • Example of Trace Facility Use
  • Obtaining a Sample Trace File
  • Formatting the Sample Trace
  • Reading a Trace Report
  • Filtering of the Trace Report
  • Starting and Controlling Trace from the Command Line
  • Controlling Trace in Subcommand Mode
  • Controlling Trace by Commands
  • Starting and Controlling Trace from a Program
  • Controlling Trace with Trace Subroutine Calls
  • Controlling Trace with ioctl() Calls
  • Using the trcrpt Command to Format a Report
  • Formatting a Report on the Same System
  • Formatting a Report on a Different System
  • Formatting a Report from trace -C Output
  • Adding New Trace Events
  • Possible Forms of a Trace Event Record
  • Trace Channels
  • Macros for Recording Trace Events
  • Use of Event IDs
  • Examples of Coding and Formatting Events
  • Syntax for Stanzas in the Trace Format File

    • Chapter 13. Using Performance Diagnostic Tool (PDT)

  • Structure of PDT
  • Scope of PDT Analysis
  • Analyzing the PDT Report
  • Header
  • Alerts
  • Upward and Downward Trends
  • System Health
  • Summary
  • Installing and Enabling PDT
  • Customizing PDT
  • Changing the PDT Report Recipient and Severity Level
  • PDT Severity Levels
  • Severity 1 Problems
  • Severity 2 Problems
  • Severity 3 Messages
  • Obtaining a PDT Report on Demand
  • Modifying the List of Files Monitored by PDT
  • Modifying the List of Hosts That PDT Monitors
  • Changing the Historical-Record Retention Period
  • Modifying the Collection, Retention, and Reporting Times
  • Modifying the Thresholds
  • PDT Error Reporting
  • Uninstalling PDT
  • Responding to PDT Report Messages

    • Chapter 14. Reporting Performance Problems

  • Measuring the Baseline
  • Reporting a Performance Problem
  • What is a Performance Problem?
  • Performance Problem Description
  • Reporting the Problem
  • Using the Problem-Analysis Data Collected

    • Chapter 15. Application Tuning

  • Profiling
  • Timing Commands
  • The prof Command
  • The gprof Command
  • The gprof Implementation
  • The tprof Command
  • Source Level Profiling with tprof
  • Reports That the tprof Command Generates
  • Compiler Optimization Techniques
  • Compiling with Optimization (-O, -O2, -O3, -qstrict, -qhot, -qipa)
  • Recommendations
  • When to Compile without Optimization
  • Compiling for Specific Hardware Platforms (-qarch, -qtune)
  • Recommendations
  • Compiling for Floating-Point Performance (-qfloat)
  • Recommendations
  • Specifying Cache Sizes (-qcache)
  • Expanding Procedure Calls Inline (-Q)
  • When to Use Dynamic Linking and Static Linking
  • Determining If Nonshared Libraries Help Performance
  • Specifying the Link Order to Reduce Paging for Large Programs
  • Calling the BLAS and ESSL Libraries
  • Profile Directed Feedback (PDF)
  • The fdpr Command
  • Optimizing Preprocessors for FORTRAN and C
  • Code-Optimization Techniques
  • Mapped Files

    • Appendix A. Monitoring and Tuning Commands and Subroutines

  • Performance Reporting and Analysis Commands
  • Performance Tuning Commands
  • Performance-Related Subroutines

    • Appendix B. Efficient Use of the ld Command

  • Rebindable Executable Programs
  • Prebound Subroutine Libraries
  • Examples

    • Appendix C. Accessing the Processor Timer

  • POWER-based-Architecture-Unique Timer Access
  • Assembler Routines to Access the POWER Timer Registers
  • C Subroutine to Supply the Time in Seconds
  • Accessing Timer Registers in POWER-based Systems
  • Example of the second Subroutine

    • Appendix D. Determining CPU Speed

    Appendix E. National Language Support: Locale versus Speed

  • Programming Considerations
  • Some Simplifying Rules
  • Setting the Locale

    • Appendix F. Performance Tuning with AIX Fast Connect For Windows and OS/2

  • Monitoring AIX Fast Connect
  • Tuning AIX Fast Connect

    • Appendix G. Summary of Tunable Parameters

  • Environment Variables
  • Thread Support Tunable Parameters
  • Miscellaneous Tunable Parameters
  • Kernel Tunable Parameters
  • Scheduler Tunable Parameters
  • Memory Load Control Tunable Parameters
  • Virtual Memory Manager and File System Tunable Parameters
  • Asynchronous I/O Tunable Parameters
  • Logical Volume Manager Tunable Parameters
  • Disk and Disk Adapter Tunable Parameters
  • Interprocess Communication Tunable Parameters
  • Network Tunable Parameters
  • Network Option Tunable Parameters
  • arpqsize
  • arpt_killc
  • arptab_bsiz
  • arptab_nb
  • bcastping
  • clean_partial_conns
  • delayack
  • delayackports
  • directed_broadcast
  • extendednetstats
  • fasttimo
  • icmpaddressmask
  • ie5_old_multicast_mapping
  • ifsize
  • inet_stack_size
  • ipforwarding
  • ipfragttl
  • ipignoreredirects
  • ipqmaxlen
  • ipsendredirects
  • ipsrcrouteforward
  • ipsrcrouterecv
  • ipsrcroutesend
  • ip6_defttl
  • ip6_prune
  • ip6forwarding
  • ip6srcrouteforward
  • llsleep_timeout
  • main_if6
  • main_site6
  • maxmbuf
  • maxnip6q
  • maxttl
  • MTU
  • multi_homed
  • nbc_limit
  • nbc_max_cache
  • nbc_min_cache
  • nbc_pseg (AIX 4.3.3 and later)
  • nbc_pseg_limit (AIX 4.3.3 and later)
  • ndpqsize
  • ndpt_down
  • ndpt_keep
  • ndpt_mmaxtries
  • ndpt_probe
  • ndpt_reachable
  • ndpt_retrans
  • ndpt_umaxtries
  • net_malloc_police
  • nonlocsrcroute
  • pmtu_default_age
  • pmtu_rediscover_interval
  • rec_que_size
  • rfc1122addrchk
  • rfc1323
  • route_expire
  • routerevalidate
  • rto_high
  • rto_length
  • rto_limit
  • rto_low
  • sack (AIX 4.3.3 and later)
  • sb_max
  • send_file_duration
  • site6_index
  • sockthresh
  • somaxconn
  • subnetsarelocal
  • tcp_ephemeral_high
  • tcp_ephemeral_low
  • tcp_keepidle
  • tcp_keepinit
  • tcp_keepintvl
  • tcp_mssdflt
  • tcp_ndebug
  • tcp_nodelay
  • tcp_pmtu_discover
  • tcp_recvspace
  • tcp_sendspace
  • tcp_timewait
  • tcp_ttl
  • thewall
  • threads
  • udp_ephemeral_high
  • udp_ephemeral_low
  • udp_pmtu_discover
  • udp_recvspace
  • udp_sendspace
  • udp_ttl
  • udpcksum
  • use_isno (AIX 4.3.3 and later)
  • xmt_que_size
  • NFS Option Tunable Parameters
  • biod Count
  • nfs_allow_all_signals
  • nfs_device_specific_bufs (AIX 4.2.1 and later)
  • nfs_duplicate_cache_size (AIX 4.1, Version 4.2.0)
  • nfs_dynamic_retrans (AIX 4.1 and later)
  • nfs_gather_threshold
  • nfs_iopace_pages (AIX 4.1)
  • nfs_max_connections
  • nfs_max_read_size (AIX 4.3.1 and later)
  • nfs_max_threads (AIX 4.2.1 and later)
  • nfs_max_write_size (AIX 4.3.1 and later)
  • nfs_repeat_messages (AIX Version 4)
  • nfs_rfc1323 (AIX 4.3)
  • nfs_server_base_priority (AIX 4.1 and later)
  • nfs_server_clread (AIX 4.2.1 and later)
  • nfs_setattr_error (AIX 4.2.1 and later)
  • nfs_socketsize (AIX 4.1 and later)
  • nfs_tcp_duplicate_cache_size (AIX 4.2.1 and later)
  • nfs_tcp_socketsize (AIX 4.2.1 and later)
  • nfs_udp_duplicate_cache_size (AIX 4.2.1 and later)
  • nfs_use_reserved_ports (AIX 4.2.1 and later)
  • nsfd Count
  • portcheck
  • udpchecksum
  • Streams Tunable Attributes
  • lowthresh
  • medthresh
  • nstrpush
  • psebufcalls
  • psecache
  • pseintrstack
  • psetimers
  • strctlsz
  • strmsgsz
  • strthresh
  • strturncnt

    • Appendix H. Notices

    Index

    [ Previous | Next | Table of Contents | Index | Library Home | Legal | Search ]