ACM Home Page
Please provide us with feedback. Feedback
Isolation points: Creating performance-robust enterprise systems
Full text PdfPdf (622 KB)
Source
ACM Transactions on Autonomous and Adaptive Systems (TAAS) archive
Volume 4 ,  Issue 2  (May 2009) table of contents
Article No. 10  
Year of Publication: 2009
ISSN:1556-4665
Authors
Mohamed S. Mansour  Georgia Institute of Technology
Karsten Schwan  Georgia Institute of Technology
Sameh Abdelaziz  Worldspan, L.P.
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 25,   Downloads (12 Months): 160,   Citation Count: 0
Additional Information:

abstract   references   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1516533.1516534
What is a DOI?

ABSTRACT

This article explores a performance isolation-based approach to creating robust distributed applications. For each application, the approach is to understand the performance dependencies that pervade it and then impose constraints on the possible ‘spread’ of such dependencies through the application. The mechanisms used for this purpose, termed isolation points, are software abstractions inserted at key program locations: (1) in application interfaces, (2) in middleware implementations for making remote requests, and (3) in the system interfaces used by middleware and applications. This article demonstrates the utility of isolation points by using them to implement higher level abstractions that improve the performance-robustness of representative enterprise applications. The I-Queue abstraction uses isolation points to implement performance-robust messaging, targeting the message queues used in distributed enterprise codes. By appropriately orchestrating message dispatching, I-Queue can achieve an improvement of 16--32% in dispatched message locality based on traces obtained from the large-scale e-Pricing® search engine operated by Worldspan L.P.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
Aristotle research group. JABA: Java architecture for bytecode analysis. http://www.cc.gatech.edu/aristotle/Tools/jaba.html. (10/04/04).
 
2
 
3
4
 
5
6
7
 
8
9
 
10
Cai, Z., Chen, Y., Kumar, V., Milojicic, D. S., and Schwan, K. 2007. Automated availability management driven by business policies. In Integr. Netw. Manage. IEEE, 264--273.
 
11
12
13
 
14
15
 
16
17
18
19
 
20
21
 
22
 
23
 
24
Gray, J. 1985. Why do computers stop and what can be done about it? Tech. Rep. TR.85.7, Tandem.
 
25
Gu, W., Eisenhauer, G., Schwan, K., and Vetter, J. S. 1988. Falcon: On-line monitoring and steering of parallel programs. Concurrency: Practice and Experience 10, 9, 699--736.
26
27
 
28
 
29
 
30
 
31
 
32
33
34
 
35
 
36
37
 
38
 
39
Lowekamp, B., Miller, N., Karrer, R., Gross, T., and Steenkiste, P. 2003. Design, implementation, and evaluation of the remos network monitoring system. J. Grid Comput. 1, 1, 75--93.
 
40
 
41
Mansour, M. and Mehalingham, J. 2006. private communication.
 
42
 
43
Mansour, M. S., Schwan, K., and Abdelaziz, S. 2006a. I-Queue: Smart queues for service management. In Proceedings of the 4th International Conference on Service Oriented Computing (ICSOC'06). Lecture Notes in Computer Science. Springer.
 
44
Mansour, M. S., Schwan, K., and Abdelaziz, S. 2006b. I-Queue: Smart queues for service management. Tech. Rep. GIT-CERCS-06-11, CERCS.
45
 
46
 
47
Oster, S., Hastings, S. L., Langella, S., Ervin, D. W., Madduri, R., Kurc, T. M., Siebenlist, F., Foster, I., Shanbhag, K., Covitz, P. A., and Saltz, J. H. 2007. cagrid 1.0: A grid enterprise architecture for cancer research. Proceedings of the 2007 AMIA Annual Symposium.
 
48
Poellabauer, C., Schwan, K., West, R., Ganev, I., Bright, N., and Losik, G. 2000. Flexible user/kernel communication for real-time applications in Elinux. In Proceedings of the Workshop on Real Time Operating Systems and Applications and Second Real Time Linux Workshop (in conjunction with RTSS 2000).
49
50
 
51
 
52
Pyarali, I., Schmidt, D. C., and Cytron, R. 2003. Techniques for enhancing real-time corba quality of service. Proc. IEEE 91, 7, 1070--1085.
 
53
 
54
 
55
 
56
 
57
 
58
 
59
Strom, R., Banavar, G., Chandra, T., Kaplan, M., Miller, K., Mukherjee, B., Sturman, D., and Ward, M. 1998. Gryphon: An information flow based approach to message brokering. In Proceedings of the International Symposium on Software Reliability Engineering (ISSRE'98).
60
 
61
Uthayopas, P., Phaisithbenchapol, S., and Chongbarirux, K. 1998. Building a resources monitoring system for smile beowulf cluster. In Proceeding of the 3rd International Conference/Exhibition on High Performance Computing in Asia-Pacific Region (HPC ASIA'99).
 
62
 
63
 
64
 
65
Yuan, W. and Nahrstedt, K. 2004. Process group management in cross-layer adaptation. In Proceedings of the SPIE/ACM Multimedia Computing and Networking Conference (MMCN'04). 55--68.
 
66

Collaborative Colleagues:
Mohamed S. Mansour: colleagues
Karsten Schwan: colleagues
Sameh Abdelaziz: colleagues