Lucene Indexing and searching with Map/Reduce [duplicate]
Possible Duplicate:
instant searching in petabyte of data…
How to use HADOOP's Map/Reduce in Lucene Indexing and searching?????开发者_如何转开发
The closest thing I could find for you is Katta:
Katta is a distributed application running on many commodity hardware servers very similar to Hadoop MapReduce, Hadoop DFS, HBase, Bigtable or Hypertable.
(...)
Katta supports distributed scoring for its lucene implementation - this is because we do not expect that term distribution is fully balanced over all shards.
Each search query that is done in Katta ends up being two network roundtrips: first we get the document frequencies for a query from all the nodes and on the second trip pass this value and the search query to all nodes. Please note that we also provide a simple count method that just counts documents matching the query but does that within one network roundtrip.
精彩评论