Lazy receiver processing (LRP): a network subsystem architecture for server systems
OSDI '96 Proceedings of the second USENIX symposium on Operating systems design and implementation
Improving end-to-end performance of the Web using server volumes and proxy filters
Proceedings of the ACM SIGCOMM '98 conference on Applications, technologies, architectures, and protocols for computer communication
EW 7 Proceedings of the 7th workshop on ACM SIGOPS European workshop: Systems support for worldwide applications
Application specific data replication for edge services
WWW '03 Proceedings of the 12th international conference on World Wide Web
Evaluation of edge caching/offloading for dynamic content delivery
WWW '03 Proceedings of the 12th international conference on World Wide Web
Engineering and hosting adaptive freshness-sensitive web applications on data centers
WWW '03 Proceedings of the 12th international conference on World Wide Web
Lazy Database Replication with Ordering Guarantees
ICDE '04 Proceedings of the 20th International Conference on Data Engineering
Transparent information dissemination
Proceedings of the 5th ACM/IFIP/USENIX international conference on Middleware
GlobeDB: autonomic data replication for web applications
WWW '05 Proceedings of the 14th international conference on World Wide Web
Fine-grained replication and scheduling with freshness and correctness guarantees
VLDB '05 Proceedings of the 31st international conference on Very large data bases
Dynamo: amazon's highly available key-value store
Proceedings of twenty-first ACM SIGOPS symposium on Operating systems principles
Balancing performance and data freshness in web database servers
VLDB '03 Proceedings of the 29th international conference on Very large data bases - Volume 29
Hi-index | 0.00 |
In this work we are focusing on reducing response time and bandwidth requirements for high performance web server. Many researches have been done in order to improve web server performance by modifying the web server architecture. In contrast to these approaches, we take a different point of view, in which we consider the web server performance in OS perspective rather than web server architecture itself. To achieve these purposes we are exploring two different approaches. The first is running web server within OS kernel. We use kHTTPd as our basis for implementation. But it has a several drawbacks such as copying data redundantly, synchronous write, and processing only static data. We propose some techniques to improve these flaws. The second approach is caching dynamic data. Dynamic data can seriously reduce the performance of web servers. Caching dynamic data has been thought difficult to cache because it often change a lot more frequently than static pages and because web server needs to access database to provide service with dynamic data. To this end, we propose a solution for higher performance web service by caching dynamic data using content separation between static and dynamic portions. Benchmark results using WebStone show that our architecture can improve server performance by up to 18 percent and can reduce user's perceived latency significantly.