BasicConcepts - 3 Basic concepts Cloud computing is based...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
3 Basic concepts Cloud computing is based on a large number of ideas and experience accumulated since the Frst electronic computer was used to solve computationally challenging problems. In this chapter we overview concepts in parallel and distributed systems important for understand- ing the basic challenges in the design and use of computer clouds. Cloud computing is intimately tied to parallel and distributed computing. All cloud applications are based on the client-server paradigm with a relatively simple software, a thin-client, running on the user’s machine while the computations are carried out on the cloud. Many cloud applications are data-intensive and use a number of instances which run concurrently. Transaction processing systems, e.g., Web-based services, represent a large class of applications hosted by computing clouds; such applications run multiple instances of the service and require reliable and an in-order delivery of messages. The concepts introduced in this section are very important in practice. Communication protocols which support coordination of distributed processes travel through noisy and unreliable communication channels which may lose messages or deliver duplicate, distorted, or out of order messages. To ensure reliable and in order delivery of messages such protocols stamp each message with a sequence number; in turn, a receiver sends an acknowledgment with its own sequence number to conFrm the receipt of a message. The clocks of a sender and a receiver may not be synchronized thus these sequence numbers act as logical clocks. Timeouts are used to request the retransmission of lost or delayed messages. The concept of consistent cuts and distributed snapshots are at the heart of checkpoint- restart procedures for long-lasting computations. Indeed, many cloud computations are data-intensive and run for extended periods of time on multiple computers in the cloud. Checkpoints are taken periodically in anticipation of the need to restart a software process when one or more systems fail; when a failure occurs the computation is restarted from the last checkpoint rather than from the beginning. Many functions of a computer cloud require information provided by monitors , system components which collect state information from the individual systems. ±or example, controllers for cloud resource management discussed in Chapter 7 require accurate state information; security and reliability can only be implemented using information provided by specialized monitors. Coordination of multiple instances is a critical function of an application controller. 3.1 Parallel computing As demonstrated by nature, the ability to work in parallel as a group represents a very efficient way to reach a common target; the human beings have learned to aggregate them- selves, and to assemble man-made devices in organizations where each entity may have modest ability, but a network of entities can organize themselves to accomplish goals that an individual entity cannot. Thus, we should not be surprised that the thought that indi-
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/15/2012 for the course COP 5611 taught by Professor Staff during the Spring '08 term at University of Central Florida.

Page1 / 27

BasicConcepts - 3 Basic concepts Cloud computing is based...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online