E. Cohen, H. Kaplan, and U. Zwick. Connection caching. In Proc. 31st Annual ACM Symposium on Theory of Computing. ACM, 1999.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....requests to the same server to re use an existing connection to that server, obviating the TCP connection establishment delay that would otherwise occur. Squid supports persistent connections between client and proxy and between proxy and server. This process is sometimes called connection caching [9], and is a source of difficulty (a) Client re uses persistent connection. b) Second client finds cached data. Figure 3: Transaction timelines showing how persistent connections complicate timing replication. for our task. Consider the case in which client C1 requests resource R1 from ....

E. Cohen, H. Kaplan, and U. Zwick. Connection caching. In Proceedings of the 31st Annual ACM Symposium on Theory of Computing. ACM, 1999.

....the most cormnon example. Maintaining the connection to a web server avoids incurring additional setup delays for future requests to the server. Extending HTTP connections adds an additional management burden on both the client and the server machine that might be managed through cooperation [CKZ99] Delayed Use predictions allow an application to maximize the impact of an action by aggregating dependencies. In TCP, the Nagel algorithm [Nag84] delays transmission of small packets awaiting more data. In the web, there have been several attempts to collect requests for popular pages and ....

Cohen, E., Kaplan, H., and Zwick, U., "Connection Caching", in Proceedings of the 31 st Annual ACM Symposium on Theory of Computing, Atlanta, Georgia, May 1999, pp. 612-621.

....larger number of updates. Note that a search engine keeps hundreds of millions of documents and hence if it receives noti cation of every update instantly, then it could easily get overwhelmed. This is because the number of connections which can be simultaneously kept open is limited [FCD 99, CKZ99] Regardless of the use of algorithm in Section 5, one could still come up with worst case scenarios where search engines get overwhelmed by updates. We have addressed that issue in [GC00] 7 8 Implementation experience We implemented the algorithm outlined in Figure 1 in a system for ....

E. Cohen, H. Kaplan, and U. Zwick. Connection caching. In Proceedings of the ACM Symposium on Theory of Computing, pages 612-621, 1999.

....Connection Caching SUSANNE ALBERS # Lehrstuhl Informatik II Universit at Dortmund 44221 Dortmund, Germany albers ls2.cs. uni dortmund.de Abstract Cohen et al. [5] recently initiated the theoretical study of connection caching in the world wide web. They extensively studied uniform connection caching, where the establishment cost is uniform for all connections [5, 6] They showed that ordinary paging algorithms can be used to derive algorithms for uniform ....

....at Dortmund 44221 Dortmund, Germany albers ls2.cs.uni dortmund.de Abstract Cohen et al. 5] recently initiated the theoretical study of connection caching in the world wide web. They extensively studied uniform connection caching, where the establishment cost is uniform for all connections [5, 6]. They showed that ordinary paging algorithms can be used to derive algorithms for uniform connection caching and analyzed various algorithms such as Belady s rule, LRU and Marking strategies. In particular, in [5] Cohen et al. showed that LRU yields a (2k 1) competitive algorithm, where k is ....

[Article contains additional citation context not shown here]

E. Cohen, H. Kaplan and U. Zwick. Connection caching. In Proc. of the 31st Annual ACM Symposium on Theory of Computing, pages 612-621, 1999.

No context found.

E. Cohen, H. Kaplan, and U. Zwick. Connection caching. In Proc. 31st Annual ACM Symposium on Theory of Computing. ACM, 1999.

....Accommodating a new connection may cause the closing of two existing connections, one at each end. Moreover, a connection closed by one end may be a priority at the other end. Such interactions suggest studying the global behavior of local connection management algorithms. Recently, Cohen et al. [11] proposed a theoretical model for connection caching. Using this model they prove bounds on the competitive ratio of local algorithms such as lru against the optimal offline (not local) algorithm. Acknowledgments We thank Yoav Freund, David Johnson, Yishay Mansour, Jeff Mogul, Balachander ....

E. Cohen, H. Kaplan, and U. Zwick. Connection caching. In Proc. 31st Annual ACM Symposium on Theory of Computing. ACM, 1999.

....(u; v) each one of the endpoints u and v may have to shut down another connection, to make room in its cache for the new connection. A precise de nition of the connection caching model is given in the next section. Preliminary versions of the results contained in this paper appeared in [10], and [11] A fundamental di erence between connection caching and standard caching, is that connectioncaching involves multiple distributed caches that a ect each other. Each open connection is cached by two entities. If one of the entities decides to terminate ( evict ) the connection, the ....

E. Cohen, H. Kaplan, and U. Zwick. Connection caching. In Proc. 31st Annual ACM Symposium on Theory of Computing. ACM, 1999.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC