Phase measurement is required in electronic applications where a synchronous relationship between the signals needs to be preserved. Traditional electronic systems used for time measurement are designed using a classical mixed-signal approach. With the advent of reconfigurable hardware such as field-programmable gate arrays (FPGAs), it is more advantageous for designers to opt for all-digital architecture. Most high-speed serial transceivers of the FPGA circuitry do not ensure the same chip latency after each power cycle, reset cycle, or firmware upgrade. These cause uncertainty of phase relationship between the recovered signals. To address the need to register minute phase shift changes inside an FPGA, we propose a design for phase measurement logic core having resolution and precision in the range of a few picoseconds. The working principle is based on subsample accumulation using systematic sampling over the phase detector signal. The phase measurement logic can operate over a wide range of digital clock frequencies, ranging from a few kilohertz to the maximum frequency that is supported within the FPGA fabric. A mathematical model is developed to illustrate the operating principle of the design. The VLSI architecture is designed for the logic core. We also discussed the procedure of the phase measurement system, the calibration sequence involved, followed by the performance of the design in terms of accuracy, precision, and resolution.

Faster data transmission speed and longer distances are more susceptible to errors. CRC (Cyclic Redundancy Checksum) is an efficient and simple cryptic algorithm has been in use among the software community since very long time to detect malicious changes in transmitted data. Recently hardware engineers are also interested in using it in their forward error detection scheme with low resource consumption overhead for their ultra high-speed data communication. To tap the full potential of CRC algorithm in hardware level, it must be implemented in a hardware friendly manner with proper user constraints. This paper presents a very high throughput low latency VLSI design architecture of CRC-32 with reconfigurable parameters. The high throughput is achieved by using expandable data bus line. While, low latency is made possible by parallelizing the logic implementation. The way this problem is approached is elegantly explained using detailed diagrams and mathematics, such that the readers find it easy to adapt the architecture to any CRC polynomial type/size. The uniqueness of our design lies in its ability to operate on the same clock cycle in which the code word is presented, with results produced in immediately next clock cycle. The effects of variations in design parameters of CRC VLSI design on performance characteristics is studied. Also, we have further extended the scope of utility of this component by modeling test scenarios where our CRC logic core is encapsulated to suit different interface standards and how its efficiency changes with chosen interface. • To tap the full potential of CRC algorithm in hardware level, it must be implemented in a hardware friendly manner with proper user constraints. • The purpose of this work was to develop a CRC design architecture that is fully reconfigurable, got very high throughput and has a single clock latency with data pipelining support. • The effects of variations in design parameters of CRC VLSI design on performance characteristics is studied. • Also, we have further extended the scope of utility of this component by modeling test scenarios where our CRC logic core is encapsulated to suit different interface standards and how its efficiency changes with chosen interface. • The mathematical model discussed is for understanding the operational details of the latency optimized CRC-32 design architecture. It generalizes the architecture to expand data bus width in integral power of 2, and multiplexing of lesser width data lanes into larger width data bus lane.

We present the design and implementation of ENDEAVOUR - a framework for integrated end-to-end disaster recovery (DR) planning. Unlike existing research that provides DR planning within a single layer of the IT stack (e.g. storage controller based replication), ENDEAVOUR can choose technologies and composition of technologies across multiple layers like virtual machines, databases and storage controllers. ENDEAVOUR uses a canonical model of available replication technologies at all layers, explores strategies to compose them, and performs a novel map-search-reduce heuristic to identify the best DR plans for given administrator requirements. We present a detailed analysis of ENDEAVOUR including empirical characterization of various DR technologies, their composition, and a end-to-end case study.

Projection of high dimensional data into a lower dimensional subspace is required for human understanding of the health of an IT infrastructure. Over the past several years, there have been a large number of dimensionality reduction techniques that have been proposed. Their direct application for visualizing system monitoring data is challenged by two factors. First, system monitoring data does not lie in a metric space. Second, system monitoring data is intrinsically iquestmulti-resolutioniquest in that an event may lead to cascaded events (a server going down impacts one or more applications running on the server; a network outage may impact several network dependent components). Lower dimensional representations which do not take into account the intrinsic multi-resolution nature of the monitoring data are thus limited in their utility and challenge human comprehension. In this paper, we exploit the multi-resolution nature of the monitoring data and a 1-of-n representation of event data to construct navigable multi-resolution topology preserving views for visualizing system monitoring data. We also demonstrate the efficacy of the proposed approach using data from a real data center.

Disaster recovery (DR) is an extremely important solution for all organizations. All DR solutions have a myriad of solution specific tweaks, however, each of them have a set of common underlying routine processes/tasks, namely, i) data backup/archive, ii) secondary/offsite replica generation, iii) data migration across storage pools, iv) metadata expiration and v) tape-reclamation. A complete solution needs to judiciously run the above mentioned tasks in the most effective manner. The problem of architecting a balanced schedule considering the constraints of time and bandwidth along with the relative importance of each process/task is a non-trivial one. Designing of schedules is a labor intensive task and often the schedules are far from optimal. In this work we have proposed a solution which automatically generates the most beneficial schedule based on an optimization problem with resource outage risk minimization as the objective and available time and resource capacities as the constraints. The solution is driven by models of the common underlying processes and their relative importance to keep the service up and running.

We consider the problem of routing and dimensioning in a large optical network where traffic is growing over time. A model of traffic in optical network lightpaths is presented. Lightpaths arrive randomly according to a time-varying Poisson process and hold for a random time with a general distribution. We propose a wavelength division multiplexing network that requires no capacity upgrading in a given time period T while allowing the operator to accommodate all the lightpath requests. We obtain an exact solution of the routing and dimensioning problem under an asymptotic regime where both the capacities and the arrival rates are large. For moderate link capacities, we propose a method to dimension the links so that the first lightpath request rejection occurs, with high probability, after the specified time T. This involves the computation of capacity-exhaustion probability $the probability that at least one lightpath request is rejected in the time period (0, T) due to lack of bandwidth/capacity on some link. Computation of the exact capacity-exhaustion probability is possible for a few specific holding time distributions (e.g., exponential). Since this requires large computing resources, it is feasible only for small networks. We propose a method to estimate the capacity-exhaustion probabilities for a large optical network with general holding time distribution based on the results of an asymptotic analysis. We show that this method has a low computational complexity and is quite accurate in the desired range of low capacity-exhaustion probabilities.

In this paper, we consider the problem of dimensioning a large optical wavelength-division multiplexing (WDM) network assuming the traffic is growing over time. Traffic between pairs of nodes is carried through lightpaths which are high-bandwidth end-to-end circuits, occupying a wavelength on each link of the path between two nodes. We are interested in dimensioning the WDM links so that the first lightpath request rejection will occur, with high probability, after a specified period of time T. Here we introduce the concept of capacity exhaustion probability - the probability that at least one lightpath request will be rejected in the time period (0,T) due to lack of bandwidth/capacity on some link. We propose a network dimensioning method based on a traffic growth model which eventually results in a nonlinear optimization problem with cost minimization as the objective and route capacity exhaustion probabilities as the constraints. Computation of exact capacity exhaustion probabilities requires large computing resources and is thus feasible only for small networks. We consider a reduced load approximation for estimating capacity exhaustion probabilities of a wavelength routed network with arbitrary topology and traffic patterns. We show that the estimates are quite accurate and converge to the correct values under a limiting regime in the desired range of low-capacity exhaustion probabilities.

We consider the problem of routing and dimensioning in a large optical network, assuming the traffic is growing over time. In optical networks, traffic is carried through lightpaths and we model the traffic as follows: lightpaths arrive randomly according to a time-varying Poisson process and hold for a random time with a general distribution. We are interested in dimensioning the links so that the first lightpath request rejection occurs, with high probability, after a specified period of time, T, and thus the network requires no capacity upgrading in that time period. We propose a solution based on the absorption probability - the probability that at least one lightpath request is rejected in the time interval (0, T). Computation of exact absorption probability is possible for a few specific holding time distributions (e.g., exponential) and it requires large computing resources. We propose a method which has low computational complexity to approximate the absorption probability for a general holding time distribution based on an asymptotic analysis and we show that it is quite accurate in the desired range of low absorption probabilities.

We introduce a traffic growth model for optical networks with time-varying traffic arrivals assuming the nodes are capable of full wavelength conversion. We propose a network dimensioning method based on the traffic growth model and it eventually results in a nonlinear optimization problem with cost minimization as the objective and route absorption probabilities as the constraints. The absorption probabilities can be obtained from transient analysis of a Markov chain. Computation of exact absorption probabilities requires huge computing resources and is thus feasible only for small networks. We consider a reduced load approximation for estimating absorption probabilities of a wavelength routed network with arbitrary topology and traffic patterns. We show that the approximation method performs very well for optical networks with long-lived lightpaths.

A network dimensioning method allocates appropriate capacities to the links based on the network topology and traffic requirements. We introduce the concept of absorption probability instead of blocking probability which is a more appropriate measure to express the grade of service of an optical network, in many cases. Absorption probability can be obtained from transient analysis of a Markov chain. Computation of exact absorption probabilities requires large computing resources and is thus feasible only for small networks. We present a method to approximate the absorption probability of a wavelength-routed network with arbitrary topology and traffic patterns assuming the nodes have full wavelength conversion capability. We show that the approximation method performs well especially in the desired range of absorption probabilities and it is computationally efficient.