Author : Brindha T 1
Date of Publication :22nd March 2018
Abstract: Filtering chump seek after effect Application Custom Seek Engine (CSE), you can actualize affluent seek adventures that accomplish it easier for visitors for the acquisition the advice they’re searching for on your site. Today we’re announcing two improvements to the allocation and clarification of seek after-effects in CSE. We adduce a new Web clarification adjustment based on argument classification. We use samples of for bidden Web pages to characterize the chic of Web page and accomplish the concern processing for activity efficient. Web seek engines are composed by bags of concern processing nodes, i.e., servers committed to action user queries. Such abounding servers absorb a cogent bulk of energy, mostly answerable to their CPUs, but they are all important to ensure low latencies, back users apprehend sub-second acknowledgment times (e.g., 500 ms). However, users can hardly apprehension the acknowledgment times that are faster than their expectations. Hence, we adduce the Predictive Activity Saving Online Scheduling Algorithm (PESOS) to baldest a lot of adapted CPU abundance to action a concern on a per-core basis. PESOS aim at queries by their deadlines, and advantage high-level scheduling advice to abate the CPU activity burning of a concern processing node. As predictors can be inaccurate, in this plan we as well as adduce and investigate a way to atone anticipation errors application the basis beggarly aboveboard absurdity of the predictors
Reference :
-
- C. D. Manning, P. Raghavan, and H. Sch¨utze, Introduction to Information Retrieval. Cam-bridge University Press, 2008.
- M. Catena, C. Macdonald, and I. Ounis, “On inverted index compression for search engine efficiency,” in Proc. ECIR, 2014, pp. 359–371.
- J. Dean, “Challenges in building large-scale information retrieval systems: Invited talk,” in Proc. WSDM, 2009.
- S. Robertson and H. Zaragoza, “The Probabilistic Relevance Framework: BM25 and Beyond,” Found. Trends Inf. Retr., vol. 3, no. 4, pp. 333–389, Apr. 2009.
- A. Z. Broder, D. Carmel, M. Herscovici, A. Soffer, and J. Zien, “Efficient query evaluation us-ing a twolevel retrieval process,” in Proc. CIKM, 2003, pp. 426– 434.
- H. Turtle and J. Flood, “Query evaluation: Strate¬gies and optimizations,” Inf. Process. Manage. vol. 31, no. 6, pp. 831–850, Nov. 1995.
- H. Wu and H. Fang, “Analytical per-formance modeling for top-k query processing,” in Proc. CIKM, 2014, pp. 1619–1628.
- A. Freire, C. Macdonald, N. Tonellotto, I. Ou¬nis, and F. Cacheda, “Hybrid query scheduling for a replicated search engine,” in Proc. ECIR, 2013, pp. 435– 446
- L. A. Barroso, J. Clidaras, and U. H¨olzle, the Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines, 2nd ed. Morgan & Claypool Publishers, 2013.