Publications

Abstract not provided.

Abstract not provided.

Traditional parallel programming techniques will suffer rapid deterioration of performance scaling with growing platform size, as the work of coping with increasingly frequent failures dominates over useful computation. To address this challenge, we introduce and simulate a novel software architecture that combines a task dependency graph with a substitution graph. The role of the dependency graph is to limit communication and checkpointing and enhance fault tolerance by allowing graph neighbors to exchange data, while the substitution graph promotes fault oblivious computing by allowing a failed task to be substituted onthe- fly by another task, incurring a quantifiable error. We present optimization formulations for trading off substitution errors and other factors such as available system capacity and low-overlap task partitioning among processors, and demonstrate that these can be approximately solved in real time after some simplifications. Simulation studies of our proposed approach indicate that a substitution network adds considerable resilience and simple enhancements can limit the aggregate substitution errors. © Springer-Verlag 2011.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

CNKemu is a kernel-based system for the 9k variant of the Plan 9 kernel. It is designed to provide transparent binary support for programs compiled for IBM's Compute Node Kernel (CNK) on the Blue Gene series of supercomputers. This support allows users to build applications with the standard Blue Gene toolchain, including C++ and Fortran compilers. While the CNK is not Linux, IBM designed the CNK so that the user interface has much in common with the Linux 2.0 system call interface. The Plan 9 CNK emulator hence provides the foundation of kernel-based Linux system call support on Plan 9. In this paper we discuss cnkemu's implementation and some of its more interesting features, such as the ability to easily intermix Plan 9 and Linux system calls.

The goal of this research was to investigate the potential for employing dynamic, decentralized software architectures to achieve reliability in future high-performance computing platforms. These architectures, inspired by peer-to-peer networks such as botnets that already scale to millions of unreliable nodes, hold promise for enabling scientific applications to run usefully on next-generation exascale platforms ({approx} 10{sup 18} operations per second). Traditional parallel programming techniques suffer rapid deterioration of performance scaling with growing platform size, as the work of coping with increasingly frequent failures dominates over useful computation. Our studies suggest that new architectures, in which failures are treated as ubiquitous and their effects are considered as simply another controllable source of error in a scientific computation, can remove such obstacles to exascale computing for certain applications. We have developed a simulation framework, as well as a preliminary implementation in a large-scale emulation environment, for exploration of these 'fault-oblivious computing' approaches. High-performance computing (HPC) faces a fundamental problem of increasing total component failure rates due to increasing system sizes, which threaten to degrade system reliability to an unusable level by the time the exascale range is reached ({approx} 10{sup 18} operations per second, requiring of order millions of processors). As computer scientists seek a way to scale system software for next-generation exascale machines, it is worth considering peer-to-peer (P2P) architectures that are already capable of supporting 10{sup 6}-10{sup 7} unreliable nodes. Exascale platforms will require a different way of looking at systems and software because the machine will likely not be available in its entirety for a meaningful execution time. Realistic estimates of failure rates range from a few times per day to more than once per hour for these platforms. P2P architectures give us a starting point for crafting applications and system software for exascale. In the context of the Internet, P2P applications (e.g., file sharing, botnets) have already solved this problem for 10{sup 6}-10{sup 7} nodes. Usually based on a fractal distributed hash table structure, these systems have proven robust in practice to constant and unpredictable outages, failures, and even subversion. For example, a recent estimate of botnet turnover (i.e., the number of machines leaving and joining) is about 11% per week. Nonetheless, P2P networks remain effective despite these failures: The Conficker botnet has grown to {approx} 5 x 10{sup 6} peers. Unlike today's system software and applications, those for next-generation exascale machines cannot assume a static structure and, to be scalable over millions of nodes, must be decentralized. P2P architectures achieve both, and provide a promising model for 'fault-oblivious computing'. This project aimed to study the dynamics of P2P networks in the context of a design for exascale systems and applications. Having no single point of failure, the most successful P2P architectures are adaptive and self-organizing. While there has been some previous work applying P2P to message passing, little attention has been previously paid to the tightly coupled exascale domain. Typically, the per-node footprint of P2P systems is small, making them ideal for HPC use. The implementation on each peer node cooperates en masse to 'heal' disruptions rather than relying on a controlling 'master' node. Understanding this cooperative behavior from a complex systems viewpoint is essential to predicting useful environments for the inextricably unreliable exascale platforms of the future. We sought to obtain theoretical insight into the stability and large-scale behavior of candidate architectures, and to work toward leveraging Sandia's Emulytics platform to test promising candidates in a realistic (ultimately {ge} 10{sup 7} nodes) setting. Our primary example applications are drawn from linear algebra: a Jacobi relaxation solver for the heat equation, and the closely related technique of value iteration in optimization. We aimed to apply P2P concepts in designing implementations capable of surviving an unreliable machine of 10{sup 6} nodes.

Tracing system calls makes debugging easy and fast. On Plan 9, traditionally, system call tracing has been implemented with acid. New systems do not always implement all the capabilities needed for Acid, particularly the ability to rewrite the process code space to insert breakpoints. Architecture support libraries are not always available for Acid, or may not work even on a supported architecture. The requirement that Acid's libraries be available can be a problem on systems with a very small memory footprint, such as High Performance Computing systems where every Kbyte counts. Finally, Acid tracing is inconvenient in the presence of forks, which means tracing shell pipelines is particularly troublesome. The strace program available on most Unix systems is far more convenient to use and more capable than Acid for system call tracing. A similar system on Plan 9 can simplify troubleshooting. We have built a system calling tracing capability into the Plan 9 kernel. It has proven to be more convenient than strace in programming effort. One can write a shell script to implement tracing, and the C code to implement an strace equivalent is several orders of magnitude smaller.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

The goal of this research was to combine theoretical and computational approaches to better understand the potential emergent behaviors of large-scale cyber systems, such as networks of {approx} 10{sup 6} computers. The scale and sophistication of modern computer software, hardware, and deployed networked systems have significantly exceeded the computational research community's ability to understand, model, and predict current and future behaviors. This predictive understanding, however, is critical to the development of new approaches for proactively designing new systems or enhancing existing systems with robustness to current and future cyber threats, including distributed malware such as botnets. We have developed preliminary theoretical and modeling capabilities that can ultimately answer questions such as: How would we reboot the Internet if it were taken down? Can we change network protocols to make them more secure without disrupting existing Internet connectivity and traffic flow? We have begun to address these issues by developing new capabilities for understanding and modeling Internet systems at scale. Specifically, we have addressed the need for scalable network simulation by carrying out emulations of a network with {approx} 10{sup 6} virtualized operating system instances on a high-performance computing cluster - a 'virtual Internet'. We have also explored mappings between previously studied emergent behaviors of complex systems and their potential cyber counterparts. Our results provide foundational capabilities for further research toward understanding the effects of complexity in cyber systems, to allow anticipating and thwarting hackers.

Abstract not provided.

In this paper we describe Megatux, a set of tools we are developing for rapid provisioning of millions of virtual machines and controlling and monitoring them, as well as what we've learned from booting one million Linux virtual machines on the Thunderbird (4660 nodes) and 550,000 Linux virtual machines on the Hyperion (1024 nodes) clusters. As might be expected, our tools use hierarchical structures. In contrast to existing HPC systems, our tools do not require perfect hardware; that all systems be booted at the same time; and static configuration files that define the role of each node. While we believe these tools will be useful for future HPC systems, we are using them today to construct botnets. Botnets have been in the news recently, as discoveries of their scale (millions of infected machines for even a single botnet) and their reach (global) and their impact on organizations (devastating in financial costs and time lost to recovery) have become more apparent. A distinguishing feature of botnets is their emergent behavior: fairly simple operational rule sets can result in behavior that cannot be predicted. In general, there is no reducible understanding of how a large network will behave ahead of 'running it'. 'Running it' means observing the actual network in operation or simulating/emulating it. Unfortunately, this behavior is only seen at scale, i.e. when at minimum 10s of thousands of machines are infected. To add to the problem, botnets typically change at least 11% of the machines they are using in any given week, and this changing population is an integral part of their behavior. The use of virtual machines to assist in the forensics of malware is not new to the cyber security world. Reverse engineering techniques often use virtual machines in combination with code debuggers. Nevertheless, this task largely remains a manual process to get past code obfuscation and is inherently slow. As part of our cyber security work at Sandia National Laboratories, we are striving to understand the global network behavior of botnets. We are planning to take existing botnets, as found in the wild, and run them on HPC systems. We have turned to HPC systems to support the creation and operation of millions of Linux virtual machines as a means of observing the interaction of the botnet and other noninfected hosts. We started out using traditional HPC tools, but these tools are designed for a much smaller scale, typically topping out at one to ten thousand machines. HPC programming libraries and tools also assume complete connectivity between all nodes, with the attendant configuration files and data structures to match; this assumption holds up very poorly on systems with millions of nodes.

We report on the work done in the late-start LDRDUsing Emulation and Simulation toUnderstand the Large-Scale Behavior of the Internet. We describe the creation of a researchplatform that emulates many thousands of machines to be used for the study of large-scale inter-net behavior. We describe a proof-of-concept simple attack we performed in this environment.We describe the successful capture of a Storm bot and, from the study of the bot and furtherliterature search, establish large-scale aspects we seek to understand via emulation of Storm onour research platform in possible follow-on work. Finally, we discuss possible future work.3

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.