Noah R. Mendelsohn

XML screamer: an integrated approach to high performance XML parsing, validation and deserialization

This paper describes an experimental system in which customized high performance XML parsers are prepared using parser generation and compilation techniques. Parsing is integrated with Schema-based validation and deserialization, and the resulting validating processors are shown to be as fast as or in many cases significantly faster than traditional nonvalidating parsers. High performance is achieved by integration across layers of software that are traditionally separate, by avoiding unnecessary data copying and transformation, and by careful attention to detail in the generated code. The effect of API design on XML performance is also briefly discussed..

Generation of efficient parsers through direct compilation of XML schema grammars

With the widespread adoption of SOAP and Web services, XML-based processing, and parsing of XML documents in particular, is becoming a performance-critical aspect of business computing. In such scenarios, XML is often constrained by an XML Schema grammar, which can be used during parsing to improve performance. Although traditional grammar-based parser generation techniques could be applied to the XML Schema grammar, the expressiveness of XML. Schema does not lend itself well to the generic intermediate representations associated with these approaches. In this paper we present a method for generating efficient parsers by using the schema component model itself as the representation of the grammar. We show that the model supports the full expressive power of the XML Schema, and we present results demonstrating significant performance improvements over existing parsers.

A high-performance interpretive approach to schema-directed parsing

XML delivers key advantages in interoperability due to its flexibility, expressiveness, and platform-neutrality. As XML has become a performance-critical aspect of the next generation of business computing infrastructure, however, it has become increasingly clear that XML parsing often carries a heavy performance penalty, and that current, widely-used parsing technologies are unable to meet the performance demands of an XML-based computing infrastructure. Several efforts have been made to address this performance gap through the use of grammar-based parser generation. While the performance of generated parsers has been significantly improved, adoption of the technology has been hindered by the complexity of compiling and deploying the generated parsers. Through careful analysis of the operations required for parsing and validation, we have devised a set of specialized byte codes, designed for the task of XML parsing and validation. These byte codes are designed to engender the benefits of fine-grained composition of parsing and validation that make existing compiled parsers fast, while being coarse-grained enough to minimize interpreter overhead. This technique of using an interpretive,validating parser balances the need for performance against the requirements of simple tooling and robust scalable infrastructure. Our approach is demonstrated with a specialized schema compiler, used to generate byte codes which in turn drive an interpretive parser. With almost as little tooling and deployment complexity as a traditional interpretive parser, the byte code-driven parser usually demonstrates performance within 20% of the fastest fully compiled solutions.

Reflections on VM/pass-through: a facility for interactive networking

VM/Pass-Through, an interactive networking facility, has gained widespread acceptance within IBM and with IBM customers. Pass-Through allows a single terminal access to many different computers, including those at distant locations. In building Pass-Through, and in observing its growing use, we have had oapnp ortunity to study the practical implications of this facility and of our approach to its design. This paper is divided into two parts. The first, an introduction to Pass-Through networking, describes features of the system, supported configurations, and use of Pass-Through within the IBM Corporation. A brief history of Pass-Throughs development is also provided. In the second part of the paper, Pass-Through is used to motivate a technical discussion of interactive network technology and virtual machine subsystems. Topics covered include appropriate use of the virtual machine environment, choice of routing strategy, and performance considerations. Although the introductory portions of the paper presume no prior knowledge of computer network or operating system technology, the subsequent technical discussions do depend on a basic understanding of these areas.