Grid and Cloud Computing Grid ResourceSharing Environment Users

Grid and Cloud Computing

Grid: Resource-Sharing Environment • Users: – 1000 s from 10 s institutions – Well-established communities • Resources: – Computers, data, instruments, storage, applications – Owned/administered by institutions • Applications: data- and compute-intensive processing • Approach: common infrastructure

Grid: Definitions • Definition 1: Infrastructure that provides dependable, consistent, pervasive, and inexpensive access to highend computational capabilities (1998) • Definition 2: A system that coordinates resources not subject to centralized control, using open, generalpurpose protocols to deliver nontrivial Quality of Service (2002)

Grid Computing • Grid computing is the ability to process information by utilizing a collection of networked heterogeneous informationprocessing components (hardware and software), all of which are provisioned from various geographical locations and across organizational boundaries. [5]

Cont. In grid computing the concept of Virtual Organizations (VOs) rises. Which means that all resources were owned by a single organization. Two key outcomes exist in grids: 1. The Open Grid Service Architecture (OGSA) 2. The Globus Toolkit. OGSA means how grids are created and maintained.

Cont. . • The Globus Toolkit is a software middleware package. All that is required is to install and configure Globus and then create all required resources and services. • grid security approach is the Grid Security Infrastructure (GSI) which has been implemented in • the Globus Toolkit

An Example: The Globus Toolkit - Initially developed at Argonne National Lab/University of Chicago and ISI/University of Southern California

How It Started While helping to build/integrate a diverse range of distributed applications, the same problems kept showing up over and over again. – Too hard to keep track of authentication data (ID/password) across institutions – Too hard to monitor system and application status across institutions – Too many ways to submit jobs – Too many ways to store & access files and data – Too many ways to keep track of data – Too easy to leave “dangling” resources lying around (robustness)

grid architecture in a nutshell

Forget Homogeneity! • Trying to force homogeneity on users is futile. Everyone has their own preferences, sometimes even dogma. • The Internet provides the model…

Cloud: just a new name for Grid? • Nevertheless YES: – Problems are the same in clouds and grids – Common need to manage large facilities – Define methods to discover, request and use resources – Implement highly parallel computations Grid Computing, MIERSI, DCC/FCUP 12

Cloud: just a new name for Grid? • YES: – Reduce the cost of computing – Increase reliability – Increase flexibility (third party) Grid Computing, MIERSI, DCC/FCUP 13

Cloud: just a new name for Grid? • NO: – Great increase demand for computing (clusters, high speed networks) – Billions of dollars being spent by Amazon, Google, Microsoft to create real commercial large-scale systems with hundreds of thousands of computers – www. top 500. org shows computers with 100, 000+ cores – Analysis of massive data Grid Computing, MIERSI, DCC/FCUP 14

Clouds: side-by-side comparison with grids Resource management • Compute model – Grids: batch-scheduled (queueing systems) – Clouds: resources shared by all users at the same time (? ? !) in contrast to dedicated resources in queueing systems – Maybe one of the major challenges in clouds: Qo. S! Grid Computing, MIERSI, DCC/FCUP 15

Clouds: side-by-side comparison with grids Resource management • Data model: – Grids: concept of virtual data, replica, metadata catalog, abstract structural representation – Data locality: to achieve good scalability data must be distributed over many computers – Clouds: use map-reduce mechanism like in Google to maintain data locality – Grids: rely on shared file systems (NFS, GPFS, PVFS, Lustre) Grid Computing, MIERSI, DCC/FCUP 16

Clouds: side-by-side comparison with grids Resource management • Virtualization: – Abstraction and encapsulation – Clouds: rely heavily on virtualization – Grids: do not rely on virtualization as much as clouds. One example of use in Grids: Nimbus (previous Virtual Workspace Service) Grid Computing, MIERSI, DCC/FCUP 17

Grid Projects • NAREGI ( National Research Grid Initiative) is a grid project that focuses on the research and development of grid middleware. • The test contains almost 3000 CPUs and is capable of 17 teraflops of processing power, offered from various research institutions throughout Japan. • BOINC is an Open-source software for volunteer computing and grid computing. • BOINC is supported by the National Science Foundation(SETI@home, Climateprediction. net)

Grid vs Cloud 1. Neither grids nor clouds have a commonly accepted definition. 2. Grids are publicly funded and operated, whereas clouds are privately funded and operated. 3. Grids and clouds are instantiations of distributed systems, which is a common feature of them. 4. Grids evolve slowly and clouds evolve fast, and The level of expertise to use a cloud is significantly lower than that of a grids.