Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Lucene Today, Tomorrow and beyond

Simon Willnauer
October 20, 2011
140

Lucene Today, Tomorrow and beyond

Apache Lucene has grown to one of the most widely used Open Source search technologies. For more than a decade Lucene has been used to retrieve search results for millions of users from mobile phones to world scale applications with billions of queries every day. This talk introduces the current state of the Lucene eco-system from a technical perspective and tries to provide a future vision of the project even beyond the next revolutionary major release.

Simon Willnauer

October 20, 2011
Tweet

Transcript

  1. Who am I? •Lucene Core Committer •Project Management Committee Chair

    (PMC) •Apache Member •BerlinBuzzwords Co-Founder •Addicted to OpenSource •Apache Solr & Lucene User / Consultant / Promoter 2
  2. What makes this talk different? •The most of the talks

    here are presenting what Lucene can do or what people do with Lucene, right? •This talk will show what Lucene can’t do today (trunk) but might be doing in the future. •I won’t talk about what people going to do in the future - maybe next time :) 4
  3. Let’s go back in time a bit 5 Lucene joined

    the ASF Lucene becom es Apache TLP Lucene 1.2 Lucene 1.4 Lucene 2.0 Lucene 2.4 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2014 Lucene 2.3 Lucene 2.9 & 3.0 Lucene 2.1 & 2.2 Lucene & Solr M erge Lucene 3.1 - 3.4 Lucene 4.0 ? Happy Birthday!
  4. And who did all the work? 6 Created from Lucene

    core CHANGES.TXT Especially “via” is interesting since we use this for contributions from non-committers (FooBar via $committer_name)
  5. Where are we now - once 4.0 is out? •Lucene

    4.0 contains a ton of smallish improvements •Lots of refined APIs •Large speed improvements •New modules •And lots of paths to explore for the future! 8
  6. Some random improvements •FuzzyQuery speedup by 20000% (yes 20k!) •Indexing

    throughput improvements 200% to 280% •Document Filtering speedup up to 480% •Loading term dictionaries up to 30x faster using 10% of the memory compared to 3.x •600000 key-value lookups/second •Tremendous reduction of GC needs at runtime 9 Your mileage may vary!
  7. Flexible Indexing & Codecs •Allows to customize low level index

    structure per field •Yields significant performance gains depending on the use-case •Highly optimized data-structures •Allows future improvements due to per codec Backwards Compatibility •Lets you decide on memory consumption 10
  8. IndexDocValues •Value per field & document - similar to FieldCache

    •Type-safe and efficient on-disk & in-memory access •Soon update-able •More flexible than FieldCache •Fast loading times 11
  9. Flexible Scoring •New ranking models in addition to VSM •Adds

    key statistics to Lucene index to support other scoring models •Decoupled matching from ranking •Powerful Similarity API (can use IndexDocValues) 12
  10. What else? •DocumentWriterPerThread •High throughput incremental indexing •Preparation for RT-Search

    •AutomatonQuery (FuzzyQuery) •Query as s Deterministic Finite Automata (DFA) •Levenshtein Automata for fast Fuzzy Queries (up to 20000% improvement over 3.x) •Flexible Automata concatenation 13
  11. This was what we get with Lucene 4.0 (roughly) •What

    is missing in this picture? •Where are we going? •What comes after 4.0? •What is not going to make it into 4.0? 14 All this boils down to: “What do WE & YOU want Lucene to become in the future?”
  12. Positions - not a first class citizen •We have: •Spans

    (Near, First, MultiTerm...) •PhraseQuery (sloppy & strict) •The Problem: •Either use “common” query hierarchy or Spans •Score ALL or NOTHING •Scoring lots of documents takes ages 16
  13. Positions - not a first class citizen •Solutions? •Multi-Phase searches

    •Collect documents without positions •Re-score top N based on position data •Query hierarchy can be complex •We need an API with the same granularity as Scorer •Span semantics should not be bound to a query •Divorce scoring & matching for positions 17
  14. Positions - not a first class citizen •What about highlighting?

    •The implementation is a mess •Tons of If (query instanceof FooQuery) •Hard to extend for custom queries •First steps are already taken! •http://svn.apache.org/repos/asf/lucene/dev/branches/positions/ •Scorer allows to pull positions for any query - Help Wanted! 18
  15. Updates - Huh? Incremental you know! •Everybody wants it, right?

    •Updating a field without reindexing the entire doc? Yeah! •Watch out, this comes not for free! •You can’t simply update a field - it’s a reverse index! •Term -> [ (docID, freq) ] ( how to update this ) •Lucene is write once - no in-place updates (which is good!) •We have write per field per segment deltas and merge them on IndexReader open?! - seems tricky? •Lots of paths need to be explored - maybe “appending fields”? 19
  16. 20 Updates - Huh? Incremental you know! term fre q

    Posting list and 1 6 big 2 2 3 dark 1 6 did 1 4 gown 1 2 had 1 3 house 2 2 3 in 5 1 2 3 5 6 keep 3 1 3 5 keeper 3 1 4 5 keeps 3 1 5 6 light 1 6 never 1 4 night 3 1 4 5 old 4 1 2 3 4 sleep 1 4 sleeps 1 6 the 6 1 2 3 4 5 6 town 2 1 3 where 1 4 1 The old night keeper keeps the keep in the town 2 In the big old house in the big old gown. 3 The house in the town had the big old keep 4 Where the old night keeper never did sleep. 5 The night keeper keeps the keep in the night 6 And keeps in the dark and sleeps in the light. 2 In the small old house in the big old gown. update freq & postings insert new term
  17. Updates - Hu? Incremental you know! •Much easier (and closer)

    for not-indexed values •IndexDocValues •Assumption: •Document Title OR Body changes are low frequent •PageRank OR User-Ratings change very frequently •Maybe available in 4.0 •Bottom Line: this is still far away but on the list! 21
  18. The JVM - or is it the JIT? •Unpredictable Mr.

    JIT 22 Grouping benchmark changes Spans? WTF?
  19. The JVM - or is it the JIT? •The cost

    of a virtual method call 23 ConjunctionScorer Code Specialization
  20. •Lucene has a lot of HOT loops •Each TermScorer needs

    DocID & TermFreq for every possible hit •Calling DocsEnum#next() & #freq() adds up •Inlining seems unreliable •Solutions? 24 The JVM - or is it the JIT?
  21. Possible Solutions / Paths to explore •Native Code / Generation

    (thats gonna be fun!) •Code Specialization •Can bring 50% to 100% performance improvements •ByteCode Generation & Query Compilation •Prototypes for FunctionQuery yields 300% speed improvements •Bulk Reading APIs - BulkPostings branch - watch out its hairy •Reading more than one DocID / TermFreq at a time •More than one step backwards - API wise 25
  22. ByteCode generation •Specializing Queries at Runtime? •Might bring nice speed

    improvements per use-case •Problems arise with testing and correctness? •Could help tremendously with bulk postings •Some people say the API is unusable (Uwe?) •Maybe you don’t need to use it at all? •Would be nice if you could specify you query on a very high level and Lucene generates optimal code for you? 26
  23. The Future beyond the core •Users have two options •Nothing

    - plain Lucene (well its a lot already - a lot to code) •All - Solr / ElasticSearch etc. •I’d like something in between, you? 27
  24. <dream>Lucene 5.0</dream> •actually, XML is backwards: { “dream” : “Lucene

    5.0” } •Solr has grown, grown large and is showing its age! •95% of the time I only want one or two “services” Solr provides •still I got to use it - all or nothing! •I have to setup a (to me) heavy weight container (5 years ago Jetty / Tomcat was lightweight - times ‘r changing) •I got to figure out this documentation - fair enough! 28
  25. {“dream” : “Lucene 5.0”} •Can we get this more modular,

    lightweight & lean? •I rather do some coding than configure 2 lines of XML, you? 29 Suggestions Spellchecking Grouping Join Faceting Replication Durability / Recovery CoreUtils today tomorrow Modules
  26. Isn’t this what Solr is? •Not quiet! •Lucene tries to

    provide APIs where you hardly can’t take anything away •When I think of Solr, you can hardly add anything •Everybody should be able to build their own $Solr •How hard will it be to draw the line? •Who is going to benefit? 30
  27. Back to {“dream” : “Lucene 5.0”} •Can we go one

    step further? •ElasticSearch did a great job making things dead simple! •we should follow this example and less might be more eventually! •Taking it as far as ElasticSearch (all or nothing again) seems not the right path for Lucene but simple is good, no? 31 HTTP - Module Service - Module
  28. Disclaimer •This was my personal vision maybe not the one

    other people have. •Lets see what the community wants / needs - It’s all about the users! 32