Clusters

• Alternative to symmetric
multiprocessing (SMP)
• Group of interconnected, whole
computers working together as a unified
computing resource
– illusion is one machine
– system can run on its own
 Benefits of Clusters
• Absolute scalability
– Can have dozens of machines each of which is a
multiprocessor
• Incremental scalability
– Add new systems in small increments
• High availability
– Failure of one node does not mean loss of service
• Superior price/performance
– Cluster can be equal or greater computing power
than a single large machine at a much lower cost
Cluster Configurations - Standby
Server, No Shared Disk
Cluster Configurations -
Shared Disk
 Clustering Methods
• Passive standby
• Active secondary
– Separate servers
– Servers connected to disks (one variation is shared
nothing)

– Servers share disks

 CLUSTERING METHODS
Clusterin Description Benefits Limitations
g Method
Passive A secondary server takes over in case Easy to implement High cost because the
Standby of primary server failure secondary server is
unavailable for other
processing tasks
Active A secondary server is also used for Reduced cost because Increased complexity
Standby processing secondary server can
be used for processing

Separate Separate servers have its own disks. High availability High network and server
Servers Data are continuously copied from overhead due to copying
primary to secondary server operations
Servers Servers are cabled to the same disks Reduced network and Usually requires disk
Connected but each server owns its disks. If one server overhead due to mirroring or RAID
to the disks server fails, its disk are taken over by elimination of copying technology to compensate
the other server operations for risk of disk failure
Servers Multiple servers simultaneously Low network and Require lock manager
Share disks share access to disks. server overhead. software. Usually used with
Reduced risk of disk mirroring or RAID
downtime caused by technology
disk failure.
 Clusters
• Separate server
– Each computer is a separate server
– No shared disks
– Need management or scheduling software
– Data must be constantly copied among
systems so each is current
 Clusters
• Server connected to disk(Shared
nothing)
– Reduces communication overhead
– Several servers connected to common disks
– Disks partitioned into volumes
– Each volume owned by a computer
– If computer fails another computer gets
ownership of the volume
 Clusters
• Shared disk
– Multiple computers share the same disks at
the same time
– Each computer has access to all of the
volumes on all of the disks
Cluster computer architecture
 Cluster Computer
Architecture
• Cluster middleware services and functions
– Single entry point : User logs onto cluster rather
than to an individual computer
– Single file hierarchy : user sees a single hierarchy
of file directories under same root directory
– Single control point : A default workstation is used
for cluster management and control
– Single virtual networking : Any node can access
any other point in the cluster, even though the actual
cluster config. consists of multiple interconnected n/ws
– Single memory space
– Single job-management system : cluster job
scheduler
 Cluster Computer
Architecture
• Cluster middleware services and functions
– Single user interface
– Single I/O space: any node can access remote I/O
peripheral without knowledge of its physical location
– Single process space : a uniform process
identification scheme is used
– Checkpointing : this function periodically saves the
process state & intermediate computing results, to
allow rollback recovery after a failure
– Process migration: Enables load balancing
 Clusters Compared to SMP
• SMP is easier to manage and configure
• SMP takes up less space and draws less
power
• Clusters are better for incremental and
absolute scalability
• Clusters are superior in terms of
availability