The high increase in usage of XML in electronic data exchange introduces new challenges for efficient processing of XML data. Applications that heavily use XML need to be able to quickly extract the relevant parts of the XML data, often using the XPath language for addressing XML document parts. High speed execution of XPath requests and queries is therefore becoming a critical requirement in many application domains, including XML databases and event processing. This work explores the potential for accelerating XPath processing in these domains using specialized hardware. This in turn poses the challenges of integrating specialized hardware with general-purpose application code. We present the design decisions behind building an integration layer to bridge between applications and the hardware, and describe our implementation. We discuss the factors that affect the acceleration potential, and show that despite the transmission overheads associated with off-loading XPath processing to the specialized co-processor, significant speedups can be obtained, ranging from modest 11% improvements in the event-processing domain, to over 6x speedup factor in the healthcare domain.

The XML support in relational databases and the SQL/XML language are still relatively new as compared to purely relational databases and traditional SQL. Today, most database users have a strong relational and SQL background. SQL/XML enables users to perform queries and updates across XML and relational data, but many struggle with writing SQL/XML statements or XQuery update expressions. One reason is the novelty of SQL/XML and of the XQuery expressions that must be included. Another problem is that the tree structure of the XML data may be unknown or difficult to understand for the user. Evolving XML Schemas as well as hybrid XML/relational schemas make it even harder to write SQL/XML statements. Also, legacy applications use SQL but may require access to XML data without costly code changes. Motivated by these challenges, we developed a method to generate SQL/XML query and update statements automatically. The input is either a GUI or a regular SQL statement that uses logical data item names irrespective of their actual location in relational or XML columns in the database. The output is a SQL/XML statement that queries or updates relational and XML data as needed to carry out the original user statement. This relieves the user and simplifies schema evolution and integration. We have prototyped and tested the proposed method on top of DB2 9.5.

XML database functionality has been emerging in “XML-only” databases as well as in the major relational database products. Yet, there is no industry standard XML database benchmark to evalu-ate alternative implementations. The research community has proposed several benchmarks which are all useful in their respec-tive scope, such as evaluating XQuery processors. However, they do not aim to evaluate a database system in its entirety and do not represent all relevant characteristics of a real-world XML applica-tion. Often they only define read-only single-user tests on a single XML document. We have developed an application-oriented and domain-specific benchmark called "Transaction Processing over XML " (TPoX). It exercises all aspects of XML databases, includ-ing storage, indexing, logging, transaction processing, and concur-rency control. Based on our analysis of real XML applications, TPoX simulates a financial multi-user workload with XML data conforming to the FIXML standard. In this paper we describe TPoX and present early performance results. We also make its implementation publicly available.

XML parsing is generally known to have poor performance characteristics relative to transactional database processing. Yet, its potentially fatal impact on overall database performance is being underestimated. We report real-word database applications where XML parsing performance is a key obstacle to a successful XML deployment. There is a considerable share of XML database applications which are prone to fail at an early and simple road block: XML parsing. We analyze XML parsing performance and quantify the extra overhead of DTD and schema validation. Comparison with relational database performance shows that the desired response times and transaction rates over XML data can not be achieved without major improvements in XML parsing technology. Thus, we identify research topics which are most promising for XML parser performance in database systems.

The paper surveys performance models for distributed and replicated database systems. Over the last 20 years (1980-2000), a variety of such performance models have been developed and they differ in: (1) which aspects of a real system are or are not captured in the model (e.g., replication, communication, nonuniform data access, etc.); and (2) how these aspects are modeled. We classify the different alternatives and modeling assumptions and discuss their interdependencies and expressiveness for the representation of distributed databases. This leads to a set of building blocks for analytical performance models. To illustrate the work that is surveyed, we select a combination of these proven modeling concepts and give an example of how to compose a balanced analytical model of a replicated database. We use this example to show how to derive meaningful performance values and to discuss the applicability and expressiveness of performance models for distributed and replicated databases. Finally, we compare the analytical results to measurements in a distributed database system.

ADR (Atomic Delayed Replication) is a controllable replication manager implemented on top of commercial distributed relational databases. ADR's goal is to enable various well-defined trade-offs between database coherence, throughput and response time in large database networks, e.g. for telecom applications. By combining a strategy for distributed database design with a specific replication protocol, ADR preserves the ACID properties with a controlled relaxation of coherence between primary and secondary copies. We first discuss formal characteristics of ADR, and present the implementation techniques required to realize these formal characteristics on top of commercial distributed database technology. Then, after reviewing a validated analytical performance model for the approach, we demonstrate its flexibility by summarizing experiences with two industrial ADR applications in telecommunications management, both jointly developed with Philips Laboratories. One is database support for the integrated operation and evolution of Intelligent Network telephone services, where secondary copies are held within a distributed database system optimized for throughput and availability during schema evolution. The other concerns database support for mobile phones in a City-wide DECT setting (Digital Enhanced Cordless Telecommunications), where secondary copies are held in main memory caches outside the DBMS.