Caching review
Download as pptx, pdf1 like334 views
This document summarizes an article that describes an aspect-oriented approach to caching and compressing web service response messages using a proxy called Tantivy. Tantivy uses caching and compression techniques like hashing and gzip to reduce response times and overhead. It evaluates the performance of this approach through benchmarks measuring throughput and response time with different cache hit ratios and bandwidths. The results showed that Tantivy can substantially improve performance without compromising consistency through caching and compression.
Caching review
- 1. An Aspect-Oriented Approach to Consistency-Preserving Caching and Compression of Web Service Response Messages Wubin Li, Johan Tordsson, and Erik Elmroth Department of Computing Science and HPC2N Ume属a University Ume属a, Sweden {wubin.li, tordsson, elmroth}@cs.umu.se
- 2. Agenda Abstract Motivation AOP Web Services Proposed solution Design and Implementation Experimental Evaluation 2010 IEEE International Conference on Web Services
- 3. Abstract This article describes a tool called Tantity proxy which acts as a middleware layer to improve the throughput of Webservices using Caching and AOP techniques. It also describes the use of compression in order to reduce the size of the soap information over the network. 2010 IEEE International Conference on Web Services
- 4. Motivation Web Services suffer from overhead due to verbose encoding and extensive (de)serialization Reducing response time of costly remote services is a critical challenge No related work for Caching without semantic interpretation Previous work on handling caching transparent ignored the consistency aspect Previous work which provides consistency does not ignores transparency thus requires substancial effor on implementation 2010 IEEE International Conference on Web Services
- 5. AOP Programming methodology for separating crosscutting concerns; Logging Caching Such concern is represented in a unit called Aspect Aspect Unit that provides a functionality with a crosscutting cocern Encapsulates behavior that affects multiple classes Weaving rules Set of rules which indicates in which classes aspects will be applied 2010 IEEE International Conference on Web Services
- 6. AOP 2010 IEEE International Conference on Web Services
- 7. Web Services Web services is method of communication between two eletronic devices In A web service enviroment SOAP provides interoperability between client and Service Communication happens using XML-encoded messages Substantial overhead is induced due to (de)serialization Web Service response caching Previous work on Remote object caching utilizing CORBA, SOAP object, Java RMI This work does not handle Consistency SigSitAccelarator tackles the consistency using Cryptographical hashing 2010 IEEE International Conference on Web Services
- 8. Proposed solution Technologies: Java AspectJ Apache CXF WSTest benchmark suite 2010 IEEE International Conference on Web Services
- 9. Proposed solution Tantivy proxy Cache textual-based data uzing GZIP Layer betweeen client and server side Caching and sending hashed object over network 2010 IEEE International Conference on Web Services
- 10. Proposed solution (server side) 2010 IEEE International Conference on Web Services
- 11. Proposed solution (server-side) 2010 IEEE International Conference on Web Services
- 12. Proposed solution (client side) 2010 IEEE International Conference on Web Services
- 13. Experimental Evaluation(Benchmarking) WSTEst Suite Benchmarking Multi-thread application performing parallel calls simulating real life scenario Reports throughput ( average number of requests performed per second) Reports response time (average time it takes to process a request) 2010 IEEE International Conference on Web Services
- 14. Experimental evaluation(Benchmarking) EchoVoid - sends and receives an empty message. This benchmark performs neither serialization nor deserialization. EchoStruct - receives an array of arbitrary length as input parameter and returns this array. The structures in the array contain one element each of type integer, float, and string. The longer the array, the more work is required in deserialization and re-serialization of the SOAP object to and from XML. EchoList - sends and receives a linked list of any size, where each element in the list consists of the same structure as used in EchoStruct. EchoSynthetic - sends and receives a structure that contains a byte array of varying length. GetOrder - simulates a request for a complete purchase order for an e-commerce service. This benchmark takes three integer input parameters and returns an order object. The order object is a complex structure that include order header information, a customer structure with shipping address and billing address structures, as well as any number of objects. 2010 IEEE International Conference on Web Services
- 15. Experimental evaluation(Results) Time: 600s Bandwith: 5Mb/s, 20 Mb/s, 100 Mb/s Cache-hit Ratio: 0%, 8%, 13% Mix of invocations (20% for each approach) Client Threads: 600 2010 IEEE International Conference on Web Services
- 16. Experimental evaluation(Results) Bandwidth: 5 Mb/s Cache-hit ratio: 0% 2010 IEEE International Conference on Web Services
- 17. Experimental evaluation(Results) Bandwidth: 5 Mb/s Cache-hit ratio: 8% 2010 IEEE International Conference on Web Services
- 18. Experimental evaluation(Results) Bandwidth: 5 Mb/s Cache-hit ratio: 13% 2010 IEEE International Conference on Web Services
- 19. Experimental evaluation(Results) Bandwidth: 100 Mb/s Cache-hit ratio: 8% 2010 IEEE International Conference on Web Services
- 20. Experimental evaluation(Results) Bandwidth: 20 Mb/s Cache-hit ratio: 8% 2010 IEEE International Conference on Web Services
- 21. Experimental evaluation(Results) Bandwidth: 20 Mb/s Cache-hit ratio: 8% 2010 IEEE International Conference on Web Services
- 22. Conclusion Web Services have received substantial attention around the opportunities they provide This paper proposed a new way to address response latency issues performance can be substantially reduced through caching and compression without any compromise to the strict consistency semantics of service response messages Tantivy uses hashing to detect similarity with previous results and sends either hashes of results or compressed results rather than original results Tantivy is the first system that combines the use of hash-based techniques, application object data representation, and data compression techniques with caching of response messages to improve Web Service performance 2010 IEEE International Conference on Web Services
- 23. Future work Web Service cache consistency management protocols would help in avoiding consistency problems and in achieving higher cache-hit ratios. Dinamically compression threshold based on current network conditions Caching sub elements of a SOAP message for frequently exchange a common set of data 2010 IEEE International Conference on Web Services
- 24. Conclusion (reviewer) Good article on avoiding the duplicated payload going over the wire unnecessarily The article descibres similar response objects but it needs to be identical in order to work; The article does not mention how the compressed data plus SHA-1 key is sent back to the Tantivy Client; The article does not show any raw request using the Tantivy Service The proposed solution does not handle very similar bug big payload; 2010 IEEE International Conference on Web Services