Improving the performance of distributed CORBA applications

Mishra, Shivakant; Shi, Nija

doi:10.1109/ipdps.2002.1015514

Cited by 5 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Larger the size of the string, longer it takes to do this. As observed in [5], the main source of performance overhead is marshalling and unmarshalling of function parameters. CORBA-as-needed avoids this marshalling and unmarshalling if the client and the server are running on compatible computing platforms.…”

Section: Performance Resultsmentioning

confidence: 97%

CORBA-as-Needed: A Technique to Construct High Performance CORBA Applications

Dai

Mishra

Hiltunen³

2002

High Performance Computing — HiPC 2002

View full text Add to dashboard Cite

This paper proposes a new optimization technique called CORBA-as-needed to improve the performance of distributed CORBA applications. This technique is based on the observation that in many cases the client and the server of a distributed application run on compatible computing platforms, and do not need the interoperability functionality of CORBA. CORBA-as-needed dynamically determines if the interoperability functionality is needed for a specific application invocation, and bypasses this functionality if it is not needed. Performance measurements from a prototype implementation in omniORB show that CORBA-as-needed achieves a very significant performance improvement. 1 Introduction CORBA [2] has been successfully used in the development of a large number of distributed applications. However, it suffers from an important deficiency. There is a significant performance overhead in using CORBA to construct distributed object applications [3, 4]. Therefore, it is difficult to construct high performance distributed object applications using CORBA. The main source of this performance overhead is the large one-way communication delay incurred by CORBA communication methods, compared to the one-way communication delays of transport-level protocols such as UDP or TCP. We propose a technique called CORBA-as-needed that allows distributed applications to bypass CORBA interoperability functionality whenever the client and the server happen to run on compatible platforms. It allows client server applications to first detect if the interoperability functionality of CORBA is indeed needed for a particular invocation, and bypass it if this functionality is not necessary. In this paper, we present the design, implementation, and performance evaluation of CORBA-as-needed technique in omniORB [1]. We explore four different design alternatives for incorporating CORBA-as-needed in the current CORBA architecture. These design alternatives are called service approach, integration approach, CORBA wrapper approach, and pluggable ORB module approach. These alternatives differ from one another in the exact layer of CORBA architecture where CORBA-as-needed is incorporated. We provide a thorough analysis

show abstract

Section: Performance Resultsmentioning

confidence: 97%

CORBA-as-Needed: A Technique to Construct High Performance CORBA Applications

Dai

Mishra

Hiltunen³

2002

High Performance Computing — HiPC 2002

View full text Add to dashboard Cite

show abstract

“…One such study [48] presents the design and implementation of a Pluggable Fault Tolerant CORBA infrastructure that provides fault tolerance for CORBA applications by utilizing a pluggable protocol framework. Another study [49] proposed a technique called CORBA-as-needed to improve the performance of distributed CORBA applications. It used three design techniques to incorporate CORBA-as-needed in the current CORBA architecture.…”

Section: Corbamentioning

confidence: 99%

CORBA-Based Class Scheduling Framework Using Decorator and Facade Design Patterns

Sermeno,

Orquia

2021

JITC

View full text Add to dashboard Cite

Class scheduling problem has been regarded as one of the most difficult yet important challenges for developers developing timetabling applications. Different algorithms or schemes were devised to address such problems. Yet, considering the growing complexity of the input factors, it contributes to difficulties in maintaining the said system. In order to aid in the development and maintenance of such a system, this paper presents an object-oriented approach to designing a class scheduling paradigm using decorator and facade design patterns with CORBA architecture. This technique was based on the concepts of several existing object-oriented components of Windows GUI platforms. The paradigm designs are expressed using Unified Modeling Language (UML) and illustrated in a Java programming environment. The result of the study is a simplified method for designing an efficient and reusable component for the class scheduling model.

show abstract

“…During the last decade, a considerable amount of standardization [29] and research [30][31][32][33][34] work has been done on CORBA, and some results derived from this work have been incorporated in various ORBs available today, both commercial [35,36] and opensource [37,6,38].…”

Section: Related Workmentioning

confidence: 99%

RTZen: Highly Predictable, Real-Time Java Middleware for Distributed and Embedded Systems

et al. 2005

View full text Add to dashboard Cite

Abstract. Distributed real-time and embedded (DRE) applications possess stringent quality of service (QoS) requirements, such as predictability, latency, and throughput constraints. Real-Time CORBA, an open middleware standard, allows DRE applications to allocate, schedule, and control resources to ensure predictable end-to-end QoS. The Real-Time Specification for Java (RTSJ) has been developed to provide extensions to Java so that it can be used for real-time systems, in order to bring Java's advantages, such as portability and ease of use, to real-time applications. In this paper, we describe RTZen, an implementation of a Real-Time CORBA Object Request Broker (ORB), designed to comply with the restrictions imposed by RTSJ. RTZen is designed to eliminate the unpredictability caused by garbage collection and improper support for thread scheduling through the use of appropriate data structures, threading models, and memory scopes. RTZen's architecture is also designed to hide the complexities of RTSJ related to distributed programming from the application developer. Empirical results show that RTZen is highly predictable and has acceptable performance. RTZen therefore demonstrates that Real-Time CORBA middleware implemented in real-time Java can meet stringent QoS requirements of DRE applications, while supporting safer, easier, cheaper, and faster development in real-time Java.

show abstract

Improving the performance of distributed CORBA applications

Abstract: This paper proposes a new

Cited by 5 publications

References 3 publications

CORBA-as-Needed: A Technique to Construct High Performance CORBA Applications

CORBA-as-Needed: A Technique to Construct High Performance CORBA Applications

CORBA-Based Class Scheduling Framework Using Decorator and Facade Design Patterns

RTZen: Highly Predictable, Real-Time Java Middleware for Distributed and Embedded Systems

Contact Info

Product

Resources

About