Work stealing for interactive services to meet target latency

A runtime system for interactive Web services

In this chapter, we describe a model-based approach to the analysis of service interactions for web service choreography and their coordinated compositions. The move towards implementing web service choreography requires both design time verification and execution time validation of these service interactions to ensure that service implementations fulfil requirements of multiple interested partners before such compositions and choreographies are deployed for use. The approach employs several formal analysis techniques and perspectives, and applies these to the domain of web service choreographies and the compositional implementations that each role in these choreographies must satisfy. Our approach models the service interaction designs of choreographies (in the form of Message Sequence Charts), the service choreography descriptions (in WS-CDL – the Web Service Choreography Description Language) and the service composition processes (in BPEL4WS – the Business Process Language for Web Services). We translate models between UML and Web service specifications using the Finite State Process algebra notation. Where interactions deviate from choreography rules, the interaction sequences can be shown back to the user of the approach in an easy and accessible way, in the UML form. The described approach is supported by a suite of cooperating tools, formal modelling, simulation, animation and providing verification results from choreographed web service interactions. The tool suite and related papers are available for download at http://www.doc.ic.ac.uk/ltsa/eclipse/wsengineer.

Cloud storage is gaining popularity because features such as pay-as-you-go significantly reduce storage costs. However, the community has not sufficiently explored its contract model and latency characteristics. As LSM-Tree-based key-value stores (LSM stores) become the building block for numerous cloud applications, how cloud storage would impact the performance of key-value accesses is vital. This study reveals the significant latency variances of Amazon Elastic Block Store (EBS) under various I/O pressures, which challenges LSM store read performance on cloud storage. To reduce the corresponding tail latency, we propose Calcspar, a contract-aware LSM store for cloud storage, which efficiently addresses the challenges by regulating the rate of I/O requests to cloud storage and absorbing surplus I/O requests with the data cache. We specifically developed a fluctuation-aware cache to lower the high latency brought on by workload fluctuations. Additionally, we build a congestion-aware IOPS allocator to reduce the impact of LSM store internal operations on read latency. We evaluated Calcspar on EBS with different real-world workloads and compared it to the cutting-edge LSM stores. The results show that Calcspar can significantly reduce tail latency while maintaining regular read and write performance, keeping the 99 th percentile latency under 550μs and reducing average latency by 66%. In addition, Calcspar has lower write prices and average latency compared to Cloud NoSQL services offered by cloud vendors.

Many interactive Web services use the CGI interface for communication with clients. They will dynamically create HTML documents that are presented to the client who then resumes the interaction by submitting data through incorporated form fields. This protocol is difficult to statically type-check if the dynamic documents are created by arbitrary script code using printf-like statements. Previous proposals have suggested using static document templates which trades flexibility for safety. We propose a notion of typed, higher-order templates that simultaneously achieve flexibility and safety. Our type system is based on a flow analysis of which we prove soundness. We present an efficient runtime implementation that respects the semantics of only well-typed programs. This work is fully implemented as part of the system for defining interactive Web services.

In this paper, we present a systematic methodology for designing Reconfigurable Machine Tools (RMTs). The synthesis methodology takes as input a set of functional requirements — a set of process plans and outputs a set of kinematically-viable reconfigurable machine tools that meet the given design specifications. We present a mathematical framework for synthesis of machine tools using a library of building blocks. The framework is rooted in (a) graph theoretic methods of enumeration of alternate structural configurations and (b) screw theory that enables us to manipulate matrix representations of motions to identify appropriate kinematic building blocks. The methodology described in this paper provides a mathematical framework to address dynamic stiffness, and accuracy prediction of the kinematically-viable designs that are generated by the synthesis procedure. This methodology has been implemented in a program, called PREMADE (PRogram for REconfigurable MAchine tool DEsign), and the results are validated against commercial machine tool designs.

A low overhead, fault tolerant and congestion aware routing algorithm for 3D mesh-based Network-on-Chips

Nowadays, organizations are integrating human-computer interaction (HCI) into their information systems. This trend resulted in gathering developers and end-users in different tasks, particularly, the interactive Web services composition (WSC) task. Indeed, to search for solutions that go beyond their individual limited views, an increasing demand of collaboration among users has emerged. However, they are still facing uncomfortable situations especially when they are invited to select the appropriate Web service among functionally similar ones. More support is then needed to provide an effective composition. In this regard, a group recommender system providing the required functionality while considering the users’ preferences, might be highly useful. In this paper, we present a holistic process spanning from capturing users requirements, constructing a global goal model “ColMAP” reflecting their intentions to performing a collaborative, interactive WSC. A step-by-step example illustrates the proposed process. We expect that this approach will pave the way for interactively, collaboratively engineered information systems.

This paper studies cluster load balancing policies and system support for fine-grain network services. Load balancing on a cluster of machines has been studied extensively in the literature, mainly focusing on coarse-grain distributed computation. Fine-grain services introduce additional challenges because system states fluctuate rapidly,for those services and system performance is highly sensitive to various overhead. The main contribution of our work is to identify effective load balancing schemes for fine-grain services through simulations and empirical evaluations on synthetic workload and real traces. Another contribution is the design and implementation of a load balancing system in a Linux cluster that strikes a balance between acquiring enough load information and minimizing system overhead. Our study concludes that: 1) Random polling based load-balancing policies are well-suited for fine-grain network services: 2) A small poll size provides sufficient information for load balancing, while an excessively large poll size may in fact degrade the performance clue to polling overhead; 3) Discarding slow-responding polls can further improve system performance.

A 0.9-1.6-V, 1-MHz, 8-b microcontroller based on the 68HC08 architecture is presented. In addition to standard digital microcontroller functions, the chip features RAM, ROM, phase-locked loop (PLL) clock synthesis, and liquid crystal displays (LCD) drive capabilities operating from the voltage supply range of a single AA or AAA battery. The design used a library of CMOS microcontroller building blocks, converted into a low-voltage technology using unilateral transistors. The design approach was to optimize the conversion strategy for each functional block and to provide new designs when the conversion was insufficient. The chip exceeded specifications with blocks showing full functionality down to 0.7 V.

Standardized and modular microfluidic platform for fast Lab on Chip system development

n/a

A systematic and robust approach to generating complex protein nanomaterials would have broad utility. We develop a hierarchical approach to designing multi-component protein assemblies from two classes of modular building blocks: designed helical repeat proteins (DHRs) and helical bundle oligomers (HBs). We first rigidly fuse DHRs to HBs to generate a large library of oligomeric building blocks. We then generate assemblies with cyclic, dihedral, and point group symmetries from these building blocks using architecture guided rigid helical fusion with new software named WORMS. X-ray crystallography and cryo-electron microscopy characterization show that the hierarchical design approach can accurately generate a wide range of assemblies, including a 43 nm diameter icosahedral nanocage. The computational methods and building block sets described here provide a very general route to de novo designed protein nanomaterials.

Buckling is exploited to design a new class of three-dimensional metamaterials with negative Poisson's ratio. A library of auxetic building blocks is identified and procedures are defined to guide their selection and assembly. The auxetic properties of these materials are demonstrated both through experiments and finite element simulations and exhibit excellent qualitative and quantitative agreement.

One of the key selling points of the next-generation network (NGN) architecture is that it facilitates the rapid deployment of numerous applications onto the same core infrastructure. Before this advantage can be fully realized, however, new methods for traffic estimation are needed to assess the performance impact of new applications and ensure adequate quality of service (QoS). We have created a method to assist network operators with such estimates as part of comprehensive design, capacity planning, or business case analyses. The method identifies the key input parameters that impact traffic, provides a library of application building blocks, assembles them to model new applications quickly, and provides a method for calculating the aggregate signaling and bearer traffic for a given set of applications. In this way, a new network model for each application can be created quickly, and the impact of introducing a new set of applications can be estimated without requiring detailed systems engineering expertise on each aspect of the network.

Dynamic system simulation of small satellite projects