1 / 11


Clusters. http://ludit.kuleuven.be/hpc/cluster/pressrelease.html http://ludit.kuleuven.be/onderzoek/index.php/Main_Page. Cluster Definition.

Download Presentation


An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.


Presentation Transcript

  1. Clusters http://ludit.kuleuven.be/hpc/cluster/pressrelease.html http://ludit.kuleuven.be/onderzoek/index.php/Main_Page DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  2. Cluster Definition • A computer cluster is a group of loosely coupledcomputers that work together closely so that in many respects they can be viewed as though they are a single computer. • The components of a cluster are commonly, but not always, connected to each other through fast local area networks. • Clusters are usually deployed to improve performance and/or availability over that provided by a single computer, while typically being much more cost-effective than single computers of comparable speed or availability. DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  3. Cluster categories • High-availability (HA) clusters • Load-balancing clusters • Grid computing • (Beowulf computing) DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  4. High-availability (HA) cluster • aca failover cluster • Improve availablity of services • Done with redundant nodes (commonly 2 nodes) • Eliminate single points of failure • Many commercial implementations for many OSses • Free: Linux-HA project DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  5. High-availability (HA) cluster • Minimal 2 nodes • Should one node fail (for a hardware or software problem), the other must acquire the resources being previously managed by the failed node, in order to re-enable access to these resources. This process is known as failover. DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  6. High-availability (HA) cluster • Required hardware components • Two hosts, each with its own local storage device(s) • Shared storage, that can be accessed by each host (or node), such as a SAN or a file server • Some method of interconnection that enables one node to see if the other is dead, and to help coordinate resource access • Interconnections • A serial crossover cable is the simpler (and more reliable) way to ensure proper intracluster communication • An Ethernet crossover cable needs each host's TCP/IP stack to be functional to ensure proper intracluster communication • A shared disk (in advanced setups), usually used for heartbeat only DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  7. High-availability (HA) cluster • Optional but recommended hardware components • Gear to eliminate other single points of failure: • Three Uninterruptible Power Supplies, one for each node and one for the shared storage • Redundant network connections (using dual NICs and dual switches with bonding or trunking software on the server) DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  8. High-availability (HA) cluster • Classification by role symmetry • Active/Passive • One node owns the services, the other one remains inoperative. • Should the primary node fail, the secondary or backup node takes the resources and reactivates the services, while the ex-primary remains in turn inoperative. • This is a configuration where only one node is operative at any point of time. • Active/Active • There is no concept of a primary or backup node: both nodes provide some service, should one of these nodes fail, the other must also take over the failed node's services. DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  9. Load-balancing cluster • 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. • The Linux Virtual Server project provides one commonly used free software package for the Linux OS. DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  10. Grid computing • Grid computing or grid clusters are a technology closely related to cluster computing. The key differences (by definitions which distinguish the two at all) between grids and traditional clusters are that grids connect collections of computers which do not fully trust each other, or which are geographically dispersed. Grids are thus more like a computing utility than like a single computer. In addition, grids typically support more heterogeneous collections than are commonly supported in clusters. • Grid computing is optimized for workloads which consist of many independent jobs or packets of work, which do not have to share data between the jobs during the computation process. Grids serve to manage the allocation of jobs to computers which will perform the work independently of the rest of the grid cluster. Resources such as storage may be shared by all the nodes, but intermediate results of one job do not affect other jobs in progress on other nodes of the grid. DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

  11. Beowulf computing • Beowulf is a design for high-performance parallel computing clusters on inexpensive personal computer hardware. The name comes from the main character in the Old English epic poem Beowulf. • Originally developed by Thomas Sterling and Donald Becker at NASA, Beowulf systems are now deployed worldwide, chiefly in support of scientific computing. • A Beowulf cluster is a group of usually identical PC computers running a Free and Open Source Software (FOSS) Unix-like operating system, such as BSD, Linux or Solaris. They are networked into a small TCP/IP LAN, and have libraries and programs installed which allow processing to be shared among them. • There is no particular piece of software that defines a cluster as a Beowulf. Commonly used parallel processing libraries include MPI (Message Passing Interface) and PVM (Parallel Virtual Machine). Both of these permit the programmer to divide a task among a group of networked computers, and recollect the results of processing. • A common misconception is that arbitrary software will run faster on a Beowulf. Software must be revised to take advantage of the cluster. Specifically, it must perform multiple independent parallel operations that can be distributed among the available processors. DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst

More Related