Clusters

PSDS has been providing advanced clustering solutions since the inception of this leading edge technology.  Our clustering specialties include:
- High-Availability/Failover clustering for the most uptime reliability
- Oracle transaction production clustering for high-volume and mission critical requirements
- OpenVMS Cluster configurations
- Tru64 UNIX TruCluster available server and production server configurations
- Windows 2000 failover clustering
- Tightly-integrated RAID technology
- 1U rack-mount chassis technology that stacks up to 42 systems in a single rack
- InfiniBand, Myrinet, Dolphin, and Gigabit Ethernet technology for high-speed PCI networking and distributed computing
- Many other technologies, including high-performance compilers, TFT rackmount screens, dual motherboard chassis and
other advanced technologies that enable advanced systems clustering
Due to the complex nature of clusters, please contact us for information on available configurations, lead times and pricing.
High-Availability/Failover Clusters
High-availability (also known as Failover) clusters are implemented primarily for the purpose of improving the availability of services which the cluster provides.  They operate by having redundant nodes, which are then used to provide service when system components fail on one or more of the cluster nodes.  The most common size for a High-Availability/Failover cluster is two nodes, which is the minimum requirement to provide redundancy.  High-Availability/Failover cluster implementations attempt to manage the redundancy inherent in a cluster by eliminating single points of failure.  

Load-Balancing Clusters
Load-balancing clusters operate by having all workload come through one or more load-balancing front ends, which then distribute it to a collection of back end servers.  Although they are primarily implemented for improved performance, they commonly include high-availability features as well.  Such a cluster of computers is sometimes referred to as a server farm.   

High-Performance Computing Clusters
High-performance computing clusters are implemented primarily to provide increased performance by splitting a computational task across many different nodes in the cluster and are most commonly used in scientific computing.  Such clusters commonly run custom programs which have been designed to exploit the parallelism available on them.  High-performance clusters are optimized for workloads which require jobs or processes happening on the separate cluster computer nodes to communicate actively during the computation.  These include computations where intermediate results from one nodes calculations will affect future calculations on other nodes
 

PRODUCT SEARCH

Shopping Cart

VirtueMart
Your Cart is currently empty.

Buy Refurbished

Click for Refurbished Servers
  • Lower capital costs
  • Increase current system longevity
  • New product performance doesn't justify purchasing new
  • Low cost hot spares for mission critical systems
  • Compatibility with existing systems is a known entity
  • Familiarity with existing hardware means simplified deployment
  • Reliability is a known factor
  • Immediate availability, especially of spare parts
  • No training costs or learning curves
  • Higher ROI

Lease A Server

On a Budget? Need to Update your Servers?

Lease a Server

Home     About PSDS     Request a Quote     Contact Us     HP Servers     HP Storage    HP-Renew    Services    Specials