Oracle Audio Technologies A86828-01 System Throughput, Wait Time

What is Performance Tuning?

1-4 Oracle HTTP Server powered by Apache Performance Guide

In parallel processing with multiple resources, more resources are available to the

tasks. Each independent task executes immediately using its own resource: no wait

time is involved.

System Throughput

System throughput is the amount of work accomplished in a given amount of time.

You can increase throughput by:

■Reducing service time

■Reducing overall response time by increasing the amount of scarce resources

available. For example, if the system is CPU bound, and you can add more

CPUs.

Wait Time

While the service time for a task may stay the same, wait time will lengthen with

increased contention. If many users are waiting for a service that takes one second,

the tenth user must wait 9 seconds. Figure 1–2 shows the relationship between wait

time and resource conten tion.

Figure 1–2 Wait time rising with increased contention for a resource

Contents

Main Page Contents Send Us Your Comments Preface 1 Performance Overview 2 Monitoring Your Web Server 3 Sizing and Configuration 4 Optimizing HTTP Server Performance 5 Optimizing Apache JServ Page Page Send Us Your Comments i Page Preface Audience Assumptions Conventions Oracle Services and Support Oracle Support Services Page Page Performance Overview Performance Terms What is Performance Tuning? Response Time System Throughput Wait Time Critical Resources Effects of Excessive Demand Adjustments to Relieve Problems Setting Performance Targets Setting User Expectations Evaluating Performance Performance Methodology Factors in Improving Performance Architecture Monitoring Your Web Server Monitoring Processor Use Using the sar Utility (AIX, HP-UX, Intel Solaris) Report CPU Utilization Using the top Utility Monitoring the Web Server Using the mod_status Utility your_domain.com Interpreting Server Status Information Customizing the Server Status display Logging Server Statistics to a File Page Monitoring JServ Processes Page Page Sizing and Configuration Sizing your Hardware and Resources Understanding Concurrent Users and User Population Understanding Concurrent Users and User Population Note: The MaxClients setting in your httpd.conf file limits the Table 31 Concurrent executing users Determining CPU Requirements Secure Sockets Layer Impact on CPU Requirements Determining Memory Requirements Memory for Non-HTTP Server Software and Operating System HTTP Server Memory Requirements JServ Memory Requirements Determining Java Heap Size Servlet and OracleJSP pages Memory Requirements Number of JServ Processes Page Page Optimizing HTTP Server Performance TCP Tuning TCP Tuning Table 42 Tuning HP-UX for Performance Benchmarking Table 43 Tru64 TCP/IP Tunables Linux Tunables Raising Network Limits on Linux Systems for 2.1.100 or greater Tuning a Running System Tuning the Default and Maximum Size Tuning at Compile Time Setting TCP parameters Increasing TCP Connection Table Access Speed Specifying Retention time for Connection Table entries Increasing the Handshake Queue Length Changing the Data Transmission Rate Changing the Data Transfer Window Size MaxClients SSL Session Caching Impact of Logging Access Logging HostNameLookups Error logging HTTP/1.1 Persistent Connections Shorter Response Times Reduction in Server Workload httpd Process Availability FIN_WAIT_2 Apache Versions Optimizing Apache JServ JServ Overview Optimizing Servlet Performance Loading Servlet Classes Pre-Loading with JSPs Automatic Class Reloading Load Balancing Configuring the JServ processes Modifying jserv.conf to distribute the load Distribution of JServ Requests Using Single Thread Model Servlets What is OracleJSP? OracleJSP Page Performance Tuning Impact of Session Management Developer Mode Buffering Enhancing OracleJSP Performance Caching database connections Page Index A C D E L M O P R T U W Z