HP Hewlett Packard Server 5992 4859 User Manual

HP OSMS: Tomcat Sizing Guide for HP  
ProLiant c-Class Blade Servers  
HP Part Number: 5992-4859  
Published: May 2008  
Edition: 1.0  
Download from Www.Somanuals.com. All Manuals Search And Download.  
Table of Contents  
Table of Contents  
3
Download from Www.Somanuals.com. All Manuals Search And Download.  
4
Download from Www.Somanuals.com. All Manuals Search And Download.  
List of Figures  
5
Download from Www.Somanuals.com. All Manuals Search And Download.  
6
Download from Www.Somanuals.com. All Manuals Search And Download.  
8
Download from Www.Somanuals.com. All Manuals Search And Download.  
Introduction  
HP Open Source Middleware Stacks (OSMS) offer building block applications, such as the Web  
Server; technical blueprints, and documents such as this Tomcat Sizing Guide which describes  
the maximum workload that HP ProLiant c-Class Blade Servers are capable of supporting; and  
consulting services to speed the successful implementation of an open source strategy.  
Executive Summary  
The HP Open Source Integrated Portfolio (HP OSIP) comprises a range of products and services  
designed to verify that customers can successfully realize the cost and feature benefits of adopting  
open source software in their IT environments. HP Open Source foundation components include  
the base components of an open source-based ecosystem. HP servers and storage are validated  
to run the Linux operating system together with the supported commercial Linux distribution.  
The results published in this document were achieved using the Apache benchmarking tool and  
Apche JMeter for each of the HP ProLiant c-Class Blade Servers. Various test configurations and  
test environments were used and documented to provide readers an opportunity to understand  
the testing methodology.  
Intended Audience  
The intended audience for this document is anyone who is interested in determining the Tomcat  
user connection workload that can be supported on a given HP ProLiant c-Class Blade Server  
and details for deploying a hardware environment based on the Tomcat environment requirements  
of certain applications.  
Scope and Purpose  
This document presents the results of a series of benchmark tests performed using the Apache  
Benchmarking tool and Apache JMeter. The tests were conducted running a Tomcat application  
server to evaluate system performance when running a web application under a heavy load. The  
following HP ProLiant servers were used in this test: BL460c, BL480c, and BL465c. The benchmark  
data provided in this sizing guide can assist customers in determining which HP Proliant c-Class  
Blade Server meets their Tomcat server requirements along with how-to information for  
configuring the HP Proliant c-Class Blade Server and storage in a specific production environment.  
HP provides quality assurance from extensive integration testing with open source software and  
HP hardware so that you can confidently deploy the complete stack. Once you have completed  
a successful evaluation, you have the flexibility to “do it yourself” or get assistance from HP to  
incorporate open source stacks into your existing IT infrastructure.  
HP Services  
HP Open Source Consulting Services can help you build and integrate open source and commercial  
software across multiple operating system (OS) environments. Additionally, HP Open Source  
Support Services provide industry leading technical support for all the products HP sells,  
including hardware, operating systems, and open source middleware.  
To learn more about HP Open Source Consulting and Support Services, contact your local HP  
sales representative or visit the HP Business and IT Services website at:  
For the location of the nearest sales office, call:  
In the United States: +1 800 637 7740  
In Canada: +1 905 206 4725  
In Japan: +81 3 3331 6111  
In Latin America: +1 305 267 4220  
Introduction  
9
Download from Www.Somanuals.com. All Manuals Search And Download.  
         
In Australia/New Zealand: +61 3 9272 2895  
In Asia Pacific: +8522 599 7777  
In Europe/Africa/Middle East: +41 22 780 81 11  
10  
Download from Www.Somanuals.com. All Manuals Search And Download.  
Typographic Conventions  
This document uses the following typographic conventions.  
Command  
ComputerOut  
Ctrl-x  
A command name or qualified command phrase.  
Text displayed by the computer.  
A key sequence. A sequence such as Ctrl-x indicates that  
you must hold down the key labeled Ctrl while you press  
another key or button.  
ENVIRONVAR  
The name of an environment variable, for example, PATH.  
[ERRORNAME]  
The name of an error, usually returned in the errno  
variable.  
Key  
The name of a keyboard key. Return and Enter both refer  
to the same key.  
Term  
UserInput  
The defined use of an important word or phrase.  
Commands and other text that you type.  
VARIABLE  
The name of a placeholder in a command, function, or  
other syntax display that you replace with an actual value.  
\ (continuation character) A backslash (\) at the end of a line of code (such as a  
command) indicates that the following line of code is  
contiguous, and you must not insert a line break. This  
convention facilitates the typesetting of long lines of code  
examples on a printed page. If you cut and paste sample  
code from this publication, ensure that you remove  
backslash characters at line endings.  
...  
The preceding element can be repeated an arbitrary number  
of times.  
|
Separates items in a list of choices.  
Publishing History  
The document publishing date and part number indicate the current edition of the document.  
The publishing date changes when a new edition is printed. Minor changes might be made  
without changing the publishing date. The document part number changes only when extensive  
changes are made. Document updates might be issued between editions to correct errors or  
document product changes. For the latest version of this document online, see the HP Technical  
Documentation website at:  
Manufacturing Part  
Number  
Supported OS  
Edition  
Number  
Publication Date  
5992-4859  
Red Hat Enterprise Linux 5 AS Update 1  
(RHEL5ASu1)  
1
May 2008  
HP Encourages Your Comments  
HP encourages your comments concerning this document. We are committed to providing  
documentation that meets your needs. Send any errors found, suggestions for improvement, or  
compliments to:  
Include the document title, manufacturing part number, and any comment, error found, or  
suggestion for improvement you have concerning this document.  
Introduction  
11  
Download from Www.Somanuals.com. All Manuals Search And Download.  
     
Hardware Test Environment  
This benchmark was performed within an HP BladeSystem c-Class blade enclosure with enhanced  
backplane using C-GbE2 Network interconnect switches. Table 1 lists the specifications of the  
hardware test environment.  
Table 1 Test Hardware Environment  
Hardware  
BL460c  
BL465c  
BL480c  
CPU  
(2) Quad-Core Intel® Xeon® (2) Dual-Core AMD  
(2) Quad-Core Intel® Xeon®  
processor X5365 (3.0  
Opteron™ processor 2218 (2.6 processor X5365 (3.0  
GHz/4MB L2 cache per core) GHz/1MB L2 cache per core) GHz/4MB L2 cache per core)  
Memory  
16GB (8x2GB PC2-5300 DDR2) 14GB (6x2GB+ 2x1GB  
PC2-5300 DDR2)  
24GB (12x2GB PC2-5300  
DDR2)  
Disk Storage  
2 x 73GB SAS Smart Array  
2 x 73GB SAS Smart Array  
4 x 73GB SAS Smart Array  
E200i controller with Battery E200i controller with Battery P400i controller with Battery  
Backed Write Cache (BBWC) Backed Write Cache (BBWC) Backed Write Cache (BBWC)  
File System  
Partitioning  
(ext3 – no LVM):  
Disk0: /, /boot, swap  
(ext3 – no LVM):  
Disk0: /, /boot, swap  
(ext3 – no LVM):  
Disk0: /, /boot, swap  
Operating System RHEL5 AS u1 SMP kernel  
(2.6.18-53.el5) with errata  
updates  
RHEL5 AS u1 SMP kernel  
(2.6.18-53.el5) with errata  
updates  
RHEL5 AS u1 SMP kernel  
(2.6.18-53.el5) with errata  
updates  
During the test, the server and configuration that were used as the client where ab and JMeter  
were run is as follows:  
Machine Model: HP ProLiant BL460c  
CPU: (1)Dual-Core Intel® Xeon® processor X5160  
(3.0GHz/4MB L2 cache per core)  
Memory: 2GB  
OS: RHEL5 AS u1  
Tomcat Installation  
The Tomcat software is available on the Apache Software Foundation website. The file to  
download for Linux servers is apache-tomcat-6.0.14.tar.gzfile. The following provides  
the steps for installing and configuring Tomcat.  
NOTE: Prior to installing Apache Tomcat, please verify that JDK is installed and configured  
on the system.  
1. Unzip the *.gzfile to the dictionary where you want to install tomcat.  
In the example that follows, the directory used is /usr/local/apache-tomcat.  
2. To start Tomcat, enter the command:  
# /usr/local/apache-tomcat/bin/startup.sh  
The following messages display:  
Using CATALINA_BASE: /usr/local/apache-tomcat  
Using CATALINA_HOME: /usr/local/apache-tomcat  
Using CATALINA_TMPDIR: /usr/local/apache-tomcat/temp  
Using JRE_HOME: /usr/local/jdk  
3. Verify the Tomcat installation by launching a browser and navigating to the following URL:  
http://<YOUR_TOMCAT_SERVER_IP>:8080/  
The Tomcat web page displays as shown in Figure 1.  
12  
Download from Www.Somanuals.com. All Manuals Search And Download.  
     
Figure 1 Tomcat Successful Installation Verification  
NOTE: If the iptables firewall is enabled in the system, the Tomcat server can not be  
accessed from other machines.  
4. If necessary, stop Tomcat by entering the following command:  
# /usr/local/apache-tomcat/bin/shutdown.sh  
The following messages display:  
Using CATALINA_BASE: /usr/local/apache-tomcat  
Using CATALINA_HOME: /usr/local/apache-tomcat  
Using CATALINA_TMPDIR: /usr/local/apache-tomcat/temp  
Using JRE_HOME: /usr/local/jdk  
Tomcat Configuration  
Setting JVM Options for Tomcat  
Edit the /usr/local/apache-tomcat/bin/catalina.shfile and add the JVM options to  
the JAVA_OPTSenvironment variable. Table 2 lists the JVM options that need to be added to the  
catalina.shconfiguration file.  
Table 2 JVM Configuration  
JVM Option  
-Xmx  
Value  
4g  
Description  
The maximum Java heap size.  
The initial Java heap size.  
-Xms  
4g  
-Xmn  
1g  
The size of young generation.  
To use parallel garbage collection for scavenges.  
The initial size of permanent generation.  
-XX:+UseParallelGC  
-XX:PermSize  
50m  
Tomcat Configuration  
13  
Download from Www.Somanuals.com. All Manuals Search And Download.  
       
Setting Tomcat Connector Attributes  
Edit the /usr/local/apache-tomcat/conf/server.xmlfile and add the attributes listed  
in Table 3 to the Connector element. The following example shows the element in the xml file  
after the connector attributes are added.  
<Connector port="8080" protocol="HTTP/1.1"  
maxThreads="3000" acceptCount="200" ...  
Table 3 Tomcat Configuration  
Attribute  
Value  
Description  
maxThreads  
3000  
The maximum number of request processing threads to be created by this  
connector, which therefore determines the maximum number of simultaneous  
requests that can be handled. If not specified, the default value for this attribute  
is 40. If an executor is associated with this connector, this attribute is ignored  
and the connector executes tasks using the executor rather than an internal  
thread pool.  
acceptCount  
2000  
500  
The maximum queue length for incoming connection requests when all  
possible request processing threads are in use. Any requests received when  
the queue is full are refused. The default value is 10.  
minSpareThreads  
The number of request processing threads that are created when this connector  
is first started. The connector also verifies that it has the specified number of  
idle processing threads available. This attribute should be set to a value smaller  
than that set for maxThreads. The default value is 4.  
maxSpareThreads  
enableLookups  
2000  
false  
The maximum number of unused request processing threads that are allowed  
to exist until the thread pool starts stopping the unnecessary threads. The  
default value is 50.  
Set to “true” if you want calls to request.getRemoteHost() to perform DNS  
lookups in order to return the actual host name of the remote client. Set to  
“false” to skip the DNS lookup and return the IP address in String form instead  
(thereby improving performance). By default, DNS lookups are enabled.  
Static Web Page Benchmark  
This section provides information on running static web page benchmark on BL460c, BL480c  
and BL465c servers. The Apache Benchmarking tool was used on web pages of different sizes  
to generate two types of data: 1) the number of requests (recorded per second) and 2) the response  
time (recorded in milliseconds). A basic analysis of these results is also included with this data  
to assist you in understanding the benchmark results.  
Benchmark Software  
The Apache HTTP Benchmarking Tool is a command line (ab) benchmarking tool that is bundled  
with the standard Apache package to benchmark Hypertext Transfer Protocol (HTTP) Web  
servers. It is a free and open source software that is distributed under the Apache license. It can  
simulate large numbers of connections to perform a series of requests against given pages in  
applications on the HTTP web server. The tool then provides performance statistics, in particular  
data about the number of requests per second which the server is capable of serving and the  
average response time for all requests.  
Table 4 Main ab Options  
Main ab  
Option  
Value  
Description  
-c  
Varies from 100 to 2500.  
Number of multiple requests to perform at one time, such as  
concurrent connections.  
-n  
100 times the number of  
concurrent connections.  
Number of requests to perform for the benchmarking session  
14  
Download from Www.Somanuals.com. All Manuals Search And Download.  
         
For more information about ab, see the following web site:  
Benchmark Results  
In the static web page testing, several web pages were used with different sizes that varied from  
5KB to 200KB. For each web page, ab was run with a varying number of concurrent connections  
and total requests to determine the maximum requests per second and the maximum response  
time for 80% of the fastest requests. For this test, the concurrent connections varied in number  
from 100 to 2500 and the total number of requests was set to 100 times the number of concurrent  
connections.  
The benchmark results for the testing are presented in the following sections and show the  
maximum number of requests per second and maximum response time for 80% of the fastest  
requests that each system can handle, depending on the number of concurrent connections and  
the size of pages.  
The following tables show that, with regard to requests per second, having more connections  
can negatively impact the value for small size pages like the 5KB page but have little influence  
for bigger size pages. In regard to response time, when the number of concurrent connections is  
larger, so is the response time. For relatively small pages such as a 5KB size page, both the HP  
ProLiant BL460c and BL480c servers, configured with 2 Quad-Core processors, can handle more  
than 10,000 requests per second even with 2500 concurrent connections. However, the HP ProLiant  
BL465c server, configured with 2 Dual-Core Opteron processors, can process fewer requests. For  
pages over 30KB, the number of requests that all three servers can handle per second is stable  
and does not vary as user connections are increased.  
HP Proliant BL460c Server  
The HP ProLiant BL460c server has features that are equal to standard 1U rack-mount servers.  
The two-processor, dual-core or quad-core ProLiant BL460c combines power-efficient compute  
power, and high density with expanded memory and I/O for maximum performance. The  
ProLiant c7000 enclosure supports up to 16 BL460c server blades, two more servers than the IBM  
BladeCenter, and each BL460c supports double the memory capacity of the HS21 server without  
an expansion blade. The Proliant BL460c now comes with dual-core and quad-core Intel® Xeon®  
processors, DDR2 fully buffered DIMMs, Serial Attached SCSI (SAS) or Serial ATA (SATA), hard  
drives, and support of multi-function NICs and multiple I/O cards. The BL460c provides a  
performance system ideal for the full range of scale-out applications. In this small form factor,  
the BL460c includes more features to enable high-availability, such as hot plug hard drives,  
mirrored memory, online spare memory, memory interleaving, embedded RAID capability, and  
enhanced remote Lights-Out management. Table 5 provides the benchmark results that were  
obtained using a ProLiant BL460c server configured with two Quad-Core Intel® Xeon® processors  
running at 3.0GHz.  
Table 5 Static Web Page Test Results for the HP ProLiant BL460c Server  
User Connections  
5K  
30K  
resp time req/sec resp time req/sec  
80K  
200K  
req/sec  
resp time req/sec resp time  
100  
200  
18886.63  
17643.76  
17230.17  
15180.41  
14174.95  
12617.91  
6
3769.51  
3770.53  
3773.20  
3766.08  
3772.20  
3731.98  
26  
1426.88  
1427.35  
1425.38  
1424.56  
1423.59  
1421.59  
76  
572.57  
572.96  
572.50  
571.31  
570.14  
569.16  
189  
9
51  
115  
328  
500  
10  
12  
69  
123  
64  
467  
1448  
3008  
4139  
5217  
1000  
1500  
2000  
321  
337  
545  
1033  
1622  
2139  
Static Web Page Benchmark  
15  
Download from Www.Somanuals.com. All Manuals Search And Download.  
     
Figure 2 Static Web Page Test Results for the HP ProLiant BL460c Server - Requests per Second  
Figure 3 Static Web Page Test Results for the HP ProLiant BL460c Server - Average Response Time  
HP Proliant BL465c Server  
The HP ProLiant BL465c server is a two-way server blade designed for maximum compute  
density and power efficiencies. The small form factor accommodates two blades in each slot  
allowing for 16 servers in a standard 6u enclosure. Each CPU is a 95 Watt version of the Dual-Core  
AMD Opteron 2000 series processor, which gives the equivalent of four processing units per  
server. Up to 32GB of PC2-5300 DIMMs running at 667MHz is supported. Internal storage consists  
of two small form factor disk drives, either SAS or SATA attached to the integrated Smart Array  
E200i RAID controller with 64MB cache supporting RAID 0, 1. An optional StorageWorks SB40c  
storage blade provides connectivity to additional storage, supporting RAID 5, and ADG. The  
benchmark results in Table 6 were obtained with a ProLiant BL465c server configured with two  
Dual-Core Opteron processors running at 2.6 GHz.  
Table 6 Static Web Page Test Results for the HP ProLiant BL465c Server  
User Connections  
5K  
30K  
resp time req/sec resp time req/sec  
80K  
200K  
req/sec  
9482.27  
9280.24  
8297.94  
8185.66  
resp time req/sec resp time  
100  
200  
12  
12  
12  
14  
3762.61  
3767.93  
3773.08  
3753.01  
26  
1425.04  
1426.18  
1414.36  
1409.57  
73  
572.85  
572.62  
572.30  
567.19  
185  
52  
115  
268  
624  
329  
500  
63  
1348  
2959  
1000  
120  
16  
Download from Www.Somanuals.com. All Manuals Search And Download.  
       
Table 6 Static Web Page Test Results for the HP ProLiant BL465c Server (continued)  
User Connections  
5K  
30K  
resp time req/sec resp time req/sec  
80K  
200K  
req/sec  
6958.18  
5993.03  
resp time req/sec resp time  
1500  
2000  
21  
22  
3721.44  
3680.87  
122  
362  
1405.94  
1370.03  
1466  
1554  
564.29  
564.67  
4101  
4849  
Figure 4 Static Web Page Test Results for the HP ProLiant BL465c Server - Requests per Second  
Figure 5 Static Web Page Test Results for the HP ProLiant BL465c Server - Average Response Time  
HP Proliant BL480c Server  
The HP ProLiant BL480c server is a 2-way server blade designed for maximum performance and  
scalability. The ProLiant BL480c server can support two Quad-Core Inter Xeon processors, which  
gives the equivalent of eight processing units per server. Up to 48GB (PC2-5300 DDR2, 667 MHz)  
of memory is supported. Each full-height blade has a Smart Array P400i Controller that supports  
four hot-swap SCSI disks in a RAID configuration. An optional dual-port Fiber Channel adapter  
provides connectivity to HP and third-party storage area networks (SANs). The benchmark  
results in Table 7 were obtained with a BL480c server configured with two Quad-Core Inter Xeon  
processors running at 3.0 GHz.  
Static Web Page Benchmark  
17  
Download from Www.Somanuals.com. All Manuals Search And Download.  
     
Table 7 Static Web Page Test Results for the HP ProLiant BL480c Server  
User Connections  
5K  
30K  
resp time req/sec resp time req/sec  
80K  
200K  
req/sec  
resp time req/sec resp time  
100  
200  
19446.04  
18313.09  
16814.04  
15649.88  
14162.79  
13810.74  
13519.09  
5
3770.73  
3768.29  
3768.88  
3766.76  
3768.50  
3768.70  
3718.98  
26  
1426.77  
1426.88  
1425.07  
1425.52  
1424.00  
1416.06  
1412.64  
76  
572.69  
572.84  
572.37  
570.90  
564.46  
568.92  
567.78  
187  
8
54  
115  
333  
500  
10  
20  
56  
117  
130  
65  
461  
1417  
3011  
4108  
4832  
6146  
1000  
1500  
2000  
2500  
320  
339  
551  
581  
1010  
1616  
2223  
2734  
Figure 6 Static Web Page Test Results for the HP ProLiant BL480c Server - Requests per Second  
Figure 7 Static Web Page Test Results for the HP ProLiant BL480c Server - Average Response Time  
Application Scenario Benchmark  
To evaluate the performance of a Tomcat application server, apart from benchmark testing on  
single pages, the scenario testing to simulate operations on an application in the real world is  
another important approach to obtain the maximum number of concurrent users a Tomcat server  
can support in the case of the system response time being met.  
18  
Download from Www.Somanuals.com. All Manuals Search And Download.  
       
JPetStore was used as the test application deployed on the Tomcat Application server. This  
section provides a detailed description of the test scenario for JPetStore and, how to run Apache  
JMeter against the test application. The benchmark data includes the number of requests the  
Tomcat Application server can process per second and the average response time for all requests  
on each ProLiant Blade server.  
JMeter Installation and Configuration  
Apache JMeter is an open source Java desktop application. It is designed to load test functional  
behavior and can be used to measure performance on static and dynamic resources like Servlets,  
Perl scripts, Java Objects, and so on. It can be used to simulate a heavy load on a Tomcat server  
to test its capabilities, and can also make a graphical analysis of performance under concurrent  
load. JMeter version 2.3.1 is used in the following tests. For more information, visit the JMeter  
site located at:  
The steps for installing and configuring JMeter are as follows:  
1. Verify the computing environment meets the JMeter test requirements.  
JMeter requires a fully compliant JVM 1.4 or later. JMeter Version 2.2 and later no longer  
support Java 1.3. Make sure you have the correct version of JRE/JDK installed and set the  
JAVA_HOMEenvironment variable.  
2. Download the latest JMeter version from the website and unzip the file to the directory  
where you want to install JMeter.  
3. To run JMeter in GUI mode, run the jmeterfile in the JMETER_HOME/bin/directory.  
NOTE: You can edit the JMETER_HOME/bin/jmeterfile to modify the JMeter parameters  
or Java Virtual Machine (VM) options. For example, to create the memory consumed by  
JMeter from the default 256MB to 3GB, you can set the following line in the JMeter file:  
HEAP="-Xms3g -Xmx3g -Xmn1g"  
For more detailed information, see the JMeter documentation located at:  
JPetStore Installation and Configuration  
JPetStore is a sample application based on the Struts and iBATIS framework. It is a completely  
rewritten Pet Store application based on Suns original J2EE Pet Store. For more information on  
iBATIS and JPetStore, see:  
JPetStore can be deployed in Tomcat and other Java web servers. It supports MySQL, PostgreSQL  
and other databases. In this document, MySQL is used as the database for JPetStore. Figure 8  
displays the architecture of the test environment.  
Application Scenario Benchmark  
19  
Download from Www.Somanuals.com. All Manuals Search And Download.  
   
Figure 8 Application Scenario Test Environment Architecture  
Before performing the JPetStore installation on the Web server, verify that the following  
installations and configurations have been completed.  
Tomcat has been installed on the Tomcat server node and configured correctly.  
MySQL has been installed and configured on the MySQL server node. Make sure that MySQL  
is running correctly.  
Download the MySQL JDBC Driver file, mysql-connector-java-5.0.4-bin.jar.  
Copy the file to TOMCAT_HOME/libdirectory.  
Perform the following steps to install and configure JPetStore.  
1. Download the latest version of JPetStore from the iTBATIS website.  
2. Unzip the file JPetStore-5.0.zipto the appropriate directory.  
In the JPetStore-5.0/src/ddl/mysqldirectory, locate the following files:  
jpetstore-mysql-schema.sql  
jpetstore-mysql-create-user.sql  
jpetstore-mysql-dataload.sql  
3. On the MySQL node, run the following commands:  
mysql -uroot -p < jpetstore-mysql-schema.sql  
mysql -uroot -p < jpetstore-mysql-dataload.sql  
mysql -uroot -p < jpetstore-mysql-create-user.sql  
4. Copy JPetStore-5.0/build/wars/jpetstore.warfile to the folder  
TOMCAT_HOME/webapps.  
Tomcat automatically deploys the JPetStore application if it is running.  
5. Edit the file  
webapps/jpetstore/WEB-INF/classes/properties/database.propertiesand  
change the default values to the corresponding configurations in the environment:  
Driver=org.gjt.mm.mysql.Driver  
Url=jdbc:mysql://<YOUR_MYSQL_SERVER>:3306/JPETSTORE  
Username=jpetstore  
Password=ibatis9977  
20  
Download from Www.Somanuals.com. All Manuals Search And Download.  
 
Application Scenario Configuration  
A JMeter test plan must be created to simulate the requests sent to the server in the scenario.  
There are two approaches which are generally used to create a test plan: JMeters Proxy and  
Badboy. For JMeter, see the JMeter Reference Manual located at:  
For JMeter's Proxy and recording tests, see the JMeter tutorial located at:  
For Badboy, see the Badboy website located at:  
To simulate a customers shopping behavior, a scenario is created according to the following  
typical visiting steps:  
1. Visit the index page, and then perform a login action.  
2. Look through a kind of fish, and add it to the cart  
3. Perform a search action, select a kind of goods from the search result and add it to the cart.  
4. Switch to the cart page, and update the goods number to the correct number.  
5. Check out and then logout.  
Figure 9 displays a JMeter test plan that was created in accordance with the previously described  
scenario.  
Figure 9 Typical JMeter Test Plan  
Running the Scenario  
Select the Thread Group element in the JMeter tree and increase the Number of Threads (users)  
from the default value to the value you want to test. Next, enter a value in the Loop Count field.  
For instance, if the thread number is 1000, and the loop count is 100, then JMeter creates 1000  
users at the same time and each user repeatedly runs the test plan 100 times. Before starting the  
test, select Summary Report in the tree. While the test is running, you can watch the statistics  
from the page until the end of the test. At the end of the test, a Summary Report is generated,  
similar to the example shown in Figure 10.  
Application Scenario Benchmark  
21  
Download from Www.Somanuals.com. All Manuals Search And Download.  
     
Figure 10 JMeter Summary Report  
Benchmark Results  
Table 8 shows the requests per second and average response time of the scenario described in  
the previous section. The response time is defined as the time it takes the Tomcat server to send  
the object of an HTTP request back to the client. The requests per second is the average request  
number Tomcat is capable of handling (per second) in the particular scenario.  
Table 8 JMeter Application Test Results  
User Connections  
BL460c  
BL465c  
BL480c  
requests/sec  
response time requests/sec  
(min/sec)  
responsetime requests/sec  
(min/sec)  
response  
time  
(min/sec)  
100  
200  
1677.7  
1763.6  
1733.4  
1721.0  
1631.0  
1619.5  
58  
1166.8  
1162.1  
1147.3  
1123.9  
1083.6  
1110.6  
83  
1593.5  
1730.4  
1717.4  
1664.0  
1613.5  
1575.6  
61  
112  
286  
577  
902  
1192  
170  
433  
884  
1356  
1757  
114  
289  
594  
909  
1230  
500  
1000  
1500  
2000  
22  
Download from Www.Somanuals.com. All Manuals Search And Download.  
     
Figure 11 JMeter Application Scenario Test Results – Requests per Second  
Figure 12 JMeter Application Scenario Test Results – Response Time  
Summary  
The performance of the Tomcat Application server is impacted by several factors such as network  
throughput, system processing capability, concurrent user connections, and so on. The data  
shown in this document were obtained under the precondition that network throughput was  
stable. However, it is not generally the case that all users are simultaneously requesting service  
from the application server. Among the different applications, the ratio of concurrent users to  
total users of a certain application is different, but usually varies between 10% and 30%. Another  
difference is the interval between requests of each user. The longer the interval is, the more users  
the Tomcat server can serve. In the benchmark testing described in this document, the interval  
between requests of each user was not considered. Therefore, for applications in the real world,  
the number of concurrent user connections that the Tomcat Application server can process on  
these three-blade servers may be much greater than shown in the document. When there are  
millions of concurrent user connections, the Tomcat cluster and load-balancing technology can  
be considered to scale out the Tomcat environment based on HP ProLiant c-Class Blade servers.  
Summary  
23  
Download from Www.Somanuals.com. All Manuals Search And Download.  
     
Resources  
For additional information on the hardware and software used in the Tomcat tests, see the  
following websites:  
HP Open Source Middleware Stacks (OSMS)  
HP BladeSystem  
Apache Tomcat  
Apache JMeter  
24  
Download from Www.Somanuals.com. All Manuals Search And Download.  
 

Graco Car Seat ISPB004HB User Manual
Gravely Lawn Mower 252M XDZ User Manual
Grizzly Nail Gun T20568 User Manual
Hamilton Beach Coffeemaker Percolator User Manual
Harbor Freight Tools Grinder 93088 User Manual
Harman Stove Company Indoor Fireplace HB 38 DV User Manual
Hasbro Motorized Toy Car 56690 61176 User Manual
Hotpoint Refrigerator FF7190TX User Manual
Hotpoint Washer AQ113D 697 E User Manual
HP Hewlett Packard Toaster 8508A User Manual