Difference between revisions of "Cluster Computing"

From Teknologisk videncenter
Jump to: navigation, search
m (High Performance Clusters)
m (Diskless nodes)
 
(9 intermediate revisions by the same user not shown)
Line 18: Line 18:
 
|}
 
|}
 
Often you would need a combination of these Clusters in a installation.
 
Often you would need a combination of these Clusters in a installation.
== Storage Clusters ==
+
== Storage Clusters ==  
 
<span id="Storage Clusters"></span>
 
<span id="Storage Clusters"></span>
 +
 +
*RedHat CentOS [[GFS CentOS]]
 +
*[[iSCSI]]´
 +
*[[FreeNAS]]
 +
 
== High Availability Clusters ==
 
== High Availability Clusters ==
 
== Load Balancing Clusters ==
 
== Load Balancing Clusters ==
Line 28: Line 33:
 
=== Grid computing ===
 
=== Grid computing ===
 
For example [http://setiathome.berkeley.edu/ seti@home]
 
For example [http://setiathome.berkeley.edu/ seti@home]
 +
= Examples of cluster solutions =
 +
*[[Redhat cluster computing]]
 +
= OSCAR =
 +
 +
= Diskless nodes =
 +
*[http://web.mst.edu/~vojtat/pegasus/home.htm Pegasus homepage] for ideas to implement a diskless Linux cluster.
 +
*[http://frank.harvard.edu/~coldwell/diskless/ Diskless Linux] by Charles M. "Chip" Coldwell
 +
*[http://www.arl.army.mil/arlreports/2005/ARL-TR-3607.pdf Diskless Linux Cluster how-to] by U.S. Army
 +
*[http://www.redbooks.ibm.com/redpapers/pdfs/redp4238.pdf Building Diskless Nodes] IBM RedBook
 +
 +
= Quorum Disc =
 +
*Windows see [http://support.microsoft.com/kb/280353 Quorum disc]
  
 
= Concepts and abbreviations =
 
= Concepts and abbreviations =
Line 33: Line 50:
 
When a node fails in a cluster, the node is fenced, which means it will be rejected from shared resources.
 
When a node fails in a cluster, the node is fenced, which means it will be rejected from shared resources.
  
= Linux Clustering at Mercantec =
+
=Links=
=== Project: Mercantec Beowulf ===
+
[http://www.openais.org/doku.php OpenAIS]
The goal of the Mercantec Beowulf are to build a scalable cluster for cracking MD5 hashes or some other similar task which are easily distributed among nodes. <br/>
+
[[Category:Network]][[Category:cluster]]
The individual nodes should boot from PXE on the network and automatically enter the cluster.
 

Latest revision as of 15:23, 13 May 2010

See Cluster Computing for a definition Engineering a Beowulf-style Compute Cluster

What is a Cluster

A cluster is a setup of two or more computers - called nodes - that work together to perform a task.

Types of clusters

Basically there are four type of clusters:

Types of clusters
Storage Clusters Shared filesystem among nodes
High Availability Clusters Failover, redundancy
Load Balancing Clusters Distribute Load between two or more nodes
High Performance Clusters Parallel computing, more nodes solving the same problem

Often you would need a combination of these Clusters in a installation.

Storage Clusters

High Availability Clusters

Load Balancing Clusters

Load balancing with Cisco IOS NAT

High Performance Clusters

While there are several systems for cluster computing. OSCAR is very popular.

Grid computing

For example seti@home

Examples of cluster solutions

OSCAR

Diskless nodes

Quorum Disc

Concepts and abbreviations

Fencing

When a node fails in a cluster, the node is fenced, which means it will be rejected from shared resources.

Links

OpenAIS