Large Web search engines are constructed as a collection of services that are deployed on dedicated clusters of distributed-memory processors. In particular, efficient user query throughput heavily relies on using result cache services devoted to maintaining the answers to most frequent queries. Load balancing and fault tolerance are critical to this service. This paper proposes the design of a result cache service based on consistent hashing and a strategy for enabling fault tolerance. Performance evaluation is performed by using actual queries from a commercial search engine. The results show that the proposed cache service outperforms baseline approaches, decreases the average query response time, increases query throughput and efficiently recovers performance after processor failures.

This paper proposes a cache hierarchy that enables Web search engines to efficiently process user queries. The different caches in the hierarchy are used to store pieces of data which are useful to solve frequent queries. Cached items range from specific data such as query answers to generic data such as segments of index retrieved from secondary memory. The paper also presents a comparative study based on discrete-event simulation and bulk-synchronous parallelism. The studied performance metrics include overall query throughput, single-user query latency and power consumption. In all cases, the results show that the proposed cache hierarchy leads to better performance than a baseline approach built on state of the art caching techniques.

This paper proposes a strategy to reduce the amount of hardware involved in the solution of search engine queries. It proposes using a secondary compact cache that keeps minimal information stored in the query receptionist machine to register the processors that must get involved in the solution of queries which are evicted from the standard result cache or are not admitted in it. This cache strategy produces exact answers by using very few processors.

Search engines use inverted files as index data structures to speed up the solution of user queries. The index is distributed on a set of processors forming a cluster of computers and queries are received by a broker machine and scheduled for solution in the cluster. The broker must use a scheduling algorithm to assign queries to processors since the computations associated with the ranking of documents that form part of the solutions to queries can take a significant fraction of the total running time. The cost of this task can be highly variable and depends on the particular user preferences for words when formulating queries in a given period of time. Thus the scheduling algorithm must be able to cope efficiently with a highly dynamic and very large amount of jobs being assigned in an on-line manner to the processors. In this paper we evaluate a number of scheduling algorithms proposed in the literature in the context of scheduling queries on a search engine.