Frequently asked questions
If you have questions that may need answering about clustered servers have a look here in our FAQ's.
If you have any more questions submit an FAQ here or call us 0800 4584545.
Definition- What is a clustered server?
- What are the benefits of clustered servers?
- What are clustered servers used for?
- Can clustered servers provide zero downtime for applications?
- What is SQL?
- What are the key features and benefits of cluster hosting?
- What are the typical performance metrics for cluster hosting?
- Who are the target customers for cluster hosting?
- What are the minimum system requirements for cluster hosting?
- What are the preferred system requirements for cluster hosting?
What is a clustered server?
A clustered server is a collection of independent servers that together provide a single, highly available platform for hosting applications.
back to top
What are the benefits of clustered servers?
There are three primary benefits to clustered servers: availability, manageability, and scalability.
back to top
What are clustered servers used for?
Clustered servers provide a highly available platform for mission critical, line of business applications. These typically include database servers (such as Microsoft SQL Server), mail and collaboration servers (such as Exchange Server) and infrastructure servers such as file servers and print servers.
back to top
Can clustered servers provide zero downtime for applications?
No. Clustered servers can dramatically reduce planned and unplanned downtime. However, even with clustered servers, a server could still experience downtime from the following events:
Failover time: If a Server cluster recovers from a server or application failure, or if it is used to move applications from one server to another, the application(s) will be unavailable for a non-zero period of time (typically under a minute).
Failures from which clustered servers can not recover: There are types of failure that clustered servers do not protect against, such as loss of a disk not protected by RAID, loss of power when a UPS is not used, or loss of a site when there is no fast-recovery disaster recovery plan. Most of these can be survived with minimal downtime if precautions are taken in advance.
Server maintenance that requires downtime: Clustered servers can keep applications and data online through many types of server maintenance, but not all (for example: installing a new version of an application which has a new on-disk data format that requires reformatting preexisting data).
back to top
What is SQL?
MySQL Cluster combines the world's most popular open source database with a parallel-server, fault tolerant clustering architecture so you can deliver mission-critical database applications with 99.999% availability.
back to top
What are the key features and benefits of cluster hosting?
High availability - Cost-effectively deliver "5 nines" availability using parallel server architecture with no single point of failure.
Dynamic scalability - Incrementally scale-out your applications as your business needs grow, using commodity hardware.
High performance - Deliver the performance and throughput required to meet the most demanding enterprise applications.
Low cost - Achieve mainframe reliability and scalability using commodity hardware.
back to top
What are the typical performance metrics for cluster hosting?
High Availability - 99.999% (<5 min downtime / year)
Performance:
Response Time 5-10 millisecond (with synchronous replication)
Throughput of 10,000+ replicated transactions/sec on a 2 Node Cluster, with 1 CPU Per Node (minimal configuration)
Throughput of 100,000 replicated transactions/sec on 4 Node Cluster, with 2 CPU Per Node (low-end configuration)
Failover - Sub-second failover enables you to deliver service without interruption
Scalability - Near-linear scalability on preferred system configurations.
For cost-effective scale-out:
Add more storage nodes (8, 16, 32, etc.) per node cluster, or
Add more CPUs (4, 8, etc.) or
Add more Memory (16GB, 32GB, etc.) per storage node
back to top
Who are the target customers for cluster hosting?
Any organisation that is interested in mainframe reliability on cost-effective, commodity hardware and software. Typical customers include telecommunication and financial services companies that need throughput to handle high volumes of transactions. However, clustering is an affordable solution for any company requiring high availability.
Cluster hosting provides a high availability (99.999%) database for the mass market. It does not require specialised hardware or skills and it has a "shared nothing" architecture which does not require any additional infrastructure investments.
back to top
What are the minimum system requirements for cluster hosting?
You can run the whole cluster on a single computer:
OS: Linux (RedHat, SUSE), Solaris, AIX, HP-UX, Mac OS X
CPU: Intel/AMD x86
Memory: 512MB RAM
HDD: 3GB
Network:1+ nodes (Standard Ethernet - TCP/IP)
back to top
What are the preferred system requirements for cluster hosting?
Each Cluster Node:
OS: Linux (RedHat, SUSE), Solaris, AIX, HP-UX, Mac OS X
CPU: 2x Intel Xeon, Intel Itanium, AMD Opteron, Sun SPARC, IBM PowerPC
Memory: 16GB RAM
HDD: 4x 36GB SCSI (RAID 1 Controller)
Network: 1-8 Node clusters (Gigabit Ethernet); 8+ Nodes (Dedicated Cluster Interconnect e.g. SCI)
back to top
