
A Principled Technologies test report 3
Red Hat Enterprise Linux 6: Performance advantages with an
open source software stack
Number of DVD
Store Web sites
Number of
simulated users
Performance increase
using LAMP
Figure 2: Performance results, in OPM, for the two solution stacks.
WHAT WE TESTED
About Red Hat Enterprise Linux 6
Red Hat Inc. positions Red Hat Enterprise Linux 6 as a prime competitor to
proprietary operating systems found in enterprise data centers. Red Hat Enterprise
Linux 6 is designed to deliver performance and scalability for both small and large
servers with documented scalability up to 4,096 CPUs and 64 terabytes of RAM. It
provides native support for the majority of the latest and most important enterprise
data center technologies, such as 40Gb Ethernet networking and KVM virtualization as
well as InfiniBand®, FCoE, and iSCSI protocols. Red Hat and its hardware partners are
enabling reliability, availability, serviceability (RAS), and scalability features to help
minimize downtime, increase availability, and protect data. Red Hat includes as part of
its Linux offering tested, open source applications. For more information about Red Hat
Enterprise Linux 6, see http://www.redhat.com/f/pdf/rhel/RHEL6_datasheet.pdf.
About DVD Store Version 2.1
To create our real-world e-commerce workload, we used the DVD Store Version
2.1 (DS2) benchmarking tool. DS2 models an online DVD store, where customers log in,
search for movies, and make purchases. To achieve a good score on this benchmark, the
Web server, database, operating system, and hardware must work together to process
thousands of simultaneous Web requests from dozens of simulated users.
Specifically, the Web server must efficiently control and load-balance network
connections and dispatch customer requests and updates via PHP to the database. The
database must expeditiously service requests, update database records, and maintain
data integrity. The operating system’s role is central to these activities as it oversees all
tasks and must efficiently schedule them on the available CPUs as well as provide
efficient use of the network and disk subsystems.
The DS2 benchmark measures performance in the total number orders per
minute (OPM) that the system could handle. The score depends also on the number of
simulated users connected to the DVD store. To fully stress a specific configuration,
multiple instances of the benchmark run simultaneously. In addition to simulating online
orders, the DS2 workload performs other actions, such as adding new customers, thus
exercising the wide range of database functions typical of e-commerce environments.
The DS2 workload can use several databases, and for this evaluation, we used the open
Kommentare zu diesen Handbüchern