Академический Документы
Профессиональный Документы
Культура Документы
E N V I R O N M E N T
Architecting
Linux
High-Availability
Clusters
By Tau Leng; Jenwei Hsieh, Ph.D.; and Edward Yardumian
PowerSolutions
Heartbeat
Active LVS Server
Heartbeat
Passive LVS
Heartbeat
Application Server
Application Server
Heartbeat
Application Server
PowerSolutions 95
Client Network
Virtual IP
Active LVS
Passive LVS
Application Server 1
Application and Data
Application Server 2
Application and Data
Client Network
Virtual IPs
Active LVS Server
Passive LVS
Private Network
Application Server 1
Application and Data
Application Server 2
Application and Data
Application Server 3
Application and Data
PowerSolutions
Application Server 2
IP Address
Network Name
Application
Advantages
Disadvantages
Mirroring
Shared
Nothing
Shared
Everything
PowerSolutions
Client Network
Server 1
B
A
FC
HBA
FC
HBA
Server 2
B
A
FC
HBA
FC
HBA
FC
HBA
Fibre Channel
Switches
Fabric A
Storage
Processor A
Virtual IPs
Server 4
B
A
Server 3
B
A
FC
HBA
FC
HBA
FC
HBA
Fabric B
Private Network
Storage
Processor B
App
Server 1
Static
Content
Fibre Channel
Storage Enclosure
Passive LVS
App
Server 2
Static
Content
HA IP Cluster 1: Content
App
Server 1
Commerce
Application
App
Server 2
Commerce
Application
App
Server 3
Commerce
Application
App
Server 1
Database
Engine
App
Server 2
Database
Engine
used for the sites catalog and inventory, while the other
node runs the orders database. Although both servers
cannot coprocess the same databases, each server can run
all of the databases simultaneously if one of the two
servers fails.
Support is Growing
Support for high availability and scalable services under
Linux is growing. As these technologies mature, we will
cover more specific implementations and features in
future articles. Presently, Linux is more widely used as
the front end of distributed, multitier configurations for
stateless mode operations, such as load-balanced Web
serving. While the need for high availability and scalability expands far beyond Web farms, the technologies
mentioned in this article provide a good starting point
for advanced solutions to come. As HA implementations
continue their migration from UNIX to Linux, the
number of proven options developed in the UNIX space
will continue to expand for Linux.
Tau Leng (leng_tau@dell.com) is a system engineer in the
Scale Out System Group. His product development responsibilities include cluster product solutions from Dell including
Linux high-performance and high-availability clusters. Tau
earned an M.S. in Computer Science from Utah State
University. Currently he is a Ph.D. candidate in Computer
Science at the University of Houston.
www.dell.com/powersolutions
Edward Yardumian (edward_yardumian@dell.com) is a technologist specializing in distributed systems, cluster computing, and
Internet infrastructure in the Scale Out Systems Group in the
Enterprise Server Products division at Dell. Previously, Ed
was a lead engineer for Dell PowerEdge Clusters.
FOR MORE INFORMATION
SteelEye LifeKeeper:
http://www.steeleye.com/
PowerSolutions 99
100
PowerSolutions