There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

"Grid" computing has emerged as an important new field, distinguished from conventional distributed computing by its focus on large-scale resource sharing, innovative applications, and, in some cases, high performance orientation. In this article, the authors define this new field. First, they review the "Grid problem," which is defined as flexible, secure, coordinated resource sharing among dynamic collections of individuals, institutions, and resources--what is referred to as virtual organizations. In such settings, unique authentication, authorization, resource access, resource discovery, and other challenges are encountered. It is this class of problem that is addressed by Grid technologies. Next, the authors present an extensible and open Grid architecture, in which protocols, services, application programming interfaces, and software development kits are categorized according to their roles in enabling resource sharing. The authors describe requirements that they believe any such mechanisms must satisfy and discuss the importance of defining a compact set of intergrid protocols to enable interoperability among different Grid systems. Finally, the authors discuss how Grid technologies relate to other contemporary technologies, including enterprise integration, application service provider, storage service provider, and peer-to-peer computing. They maintain that Grid concepts and technologies complement and have much to contribute to these other approaches.

The Anatomy of the Grid: Enabling Scalable Virtual Organizations

Cloud Computing, the long-held dream of computing as a utility, has the potential to transform a large part of the IT industry, making software even more attractive as a service and shaping the way IT hardware is designed and purchased. Developers with innovative ideas for new Internet services no longer require the large capital outlays in hardware to deploy their service or the human expense to operate it. They need not be concerned about overprovisioning for a service whose popularity does not meet their predictions, thus wasting costly resources, or underprovisioning for one that becomes wildly popular, thus missing potential customers and revenue. Moreover, companies with large batch-oriented tasks can get results as quickly as their programs can scale, since using 1000 servers for one hour costs no more than using one server for 1000 hours. This elasticity of resources, without paying a premium for large scale, is unprecedented in the history of IT. Cloud Computing refers to both the applications delivered as services over the Internet and the hardware and systems software in the datacenters that provide those services. The services themselves have long been referred to as Software as a Service (SaaS). The datacenter hardware and software is what we will call a Cloud. When a Cloud is made available in a pay-as-you-go manner to the general public, we call it a Public Cloud; the service being sold is Utility Computing. We use the term Private Cloud to refer to internal datacenters of a business or other organization, not made available to the general public. Thus, Cloud Computing is the sum of SaaS and Utility Computing, but does not include Private Clouds. People can be users or providers of SaaS, or users or providers of Utility Computing. We focus on SaaS Providers (Cloud Users) and Cloud Providers, which have received less attention than SaaS Users. From a hardware point of view, three aspects are new in Cloud Computing.

/pdf/above-the-clouds-a-berkeley-view-of-cloud-computing-tkj3etim13.pdf

Above the Clouds: A Berkeley View of Cloud Computing

A 2001 IBM manifesto observed that a looming software complexity crisis -caused by applications and environments that number into the tens of millions of lines of code - threatened to halt progress in computing. The manifesto noted the almost impossible difficulty of managing current and planned computing systems, which require integrating several heterogeneous environments into corporate-wide computing systems that extend into the Internet. Autonomic computing, perhaps the most attractive approach to solving this problem, creates systems that can manage themselves when given high-level objectives from administrators. Systems manage themselves according to an administrator's goals. New components integrate as effortlessly as a new cell establishes itself in the human body. These ideas are not science fiction, but elements of the grand challenge to create self-managing computing systems.

The vision of autonomic computing

Large-scale distributed denial of Service (DoS) attacks are an unfortunate everyday reality on the Internet. They are simple to execute and, with the growing size of botnets, more effective than ever. Although much progress has been made in developing techniques to address DoS attacks, no existing solution handles noncacheable, works with the internet model of open access and dynamic routes, and copes with the large numbers of attackers typical of today's botnets. We belive we have created a practical solution.

Withstanding multimillion-node botnets

A network of workstations, harnessed as a single, coherent cluster, offers significant advantages in terms of scalability, cost/performance, incremental growth, and fault tolerance. Effectively extending UNIX semantics from a single node to a cluster requires a level of virtualization for existing UNIX abstractions. Prior efforts to add a level of virtualization in the kernel suffer from many disadvantages, including high cost, implementation complexity, and lack of portability; efforts to virtualize at the user level suffer from restrictions on possible functionality and either lack protection or limited performance. This dissertation examines these problems through the real-world example of GLUnix, a user-level layer providing cluster functionality to a network of workstations.
To overcome the limitations encountered in both kernel-level and user-level approaches to virtualizing UNIX functionality, this dissertation explores how best to support low-cost extension of existing commodity UNIX operating systems. We demonstrate that efficient, protected extension of operating system functionality is possible with little or no change to existing commodity UNIX operating systems. We accomplish this by devising a general-purpose operating system extension method which leverages the concept of interposition to enable trusted, third-party extensions to modify operating system behavior. S scLIC, our prototype of this extension technology, enables extensibility of existing commodity UNIX operating system interfaces with little or no modification to the operating system. S scLIC enables novel system layers, such as GLUnix, to be largely constructed at the user level while at the same time overcoming the limitations associated with completely user-level operating system services. S scLIC downloads extensions into the kernel that provide user-level access to the kernel interfaces necessary to extend UNIX semantics to the cluster. Additionally, S scLIC has been used to implement a security patch, an encryption file system, and a restricted execution environment for untrusted applications.
Introducing general-purpose extensibility to operating systems raises the issue of composability. When multiple extensions, implemented by independent third-party developers, are composed on a single interface, problems can arise with the interaction of those extensions. This dissertation describes this problem, characterizes the sources of many of the conflicts, and presents a number of heuristics which can considerably alleviate the problem of extension conflicts.

Efficient, protected extension of commodity operating systems

: We propose to explore a rendezvous model that has three characteristics: self-organization, heterogeneity, and administrator for friendliness. Not only do we believe that active network techniques have much to offer the overlay, proxy and interposition models that are prevalent in the Internet, but for the most part previous active networks research has not explored models with these characteristics. Our approach builds on our earlier experience with active networks, and specifically the ANTS active network toolkit. We model the network as an Internet-like arrangement of IP routers, some of which are co-located with active nodes that support additional computation in the form of a well-known runtime. We assume this to be ANTS, although our strategies will be applicable to other runtimes too.

RENDEZVOUS: Self-Organizing Services in an Active Network

Software testing is a widely used technique to eliminate defects and improve software quality. Testing is especially useful in the context of large distributed systems, which are notoriously difficult to reason about formally and remain out of reach for many existing analysis tools. A key problem in formulating a test case is identifying scenarios that can be (1) induced by a valid execution of the system under test, and are (2) different from the scenarios exercised by the suite of existing test cases. Today, this is done manually — a developer writes the code for a test case after considering the system implementation and the existing test suite. For a distributed system, this mental effort can be overwhelming since test cases are usually concurrent, involve multiple nodes and numerous message interleavings. Moreover, when coming up with a new test case, the developer usually focuses on the code artifacts and rarely, if ever, thinks about the abstract scenarios that the testing code represents. The goal of our tool, Bandsaw, is to automate test scenario generation for distributed systems by considering the log of system’s test suite executions. Bandsawgenerated scenarios are intended to be converted into test cases by the developer, which can then be run to test the implementation. Bandsaw, therefore, saves the developer the mental effort involved in coming up with a new test case. Test scenarios are also more abstract and simpler than the underlying testing code. These scenarios help developers to more easily reason about their test suites. Bandsaw takes as input a console log file generated by the existing test suite, and outputs a new scenario. By construction, this scenario is (1) different from the ones already encoded in the test suite and (2) plausible — likely to be induced by a valid run of the system. Bandsaw generates scenarios by exploring different interleavings of concurrent events and stitching together previously observed scenarios at those points when the system is likely to be in a common state. The generated scenarios satisfy a set of automatically-mined, key temporal properties that are true of all the existing scenarios. The careful stitching of scenarios and the preservation of the mined properties make the resulting scenarios plausible. buy search search available

/pdf/bandsaw-log-powered-test-scenario-generation-for-distributed-8ir9aypbu7.pdf

Thomas Anderson

Papers

Withstanding multimillion-node botnets

Efficient, protected extension of commodity operating systems

RENDEZVOUS: Self-Organizing Services in an Active Network

Bandsaw: Log-powered test scenario generation for distributed systems

Guest Editors' Introduction: Developing Interconnect Technology