solr的配置参数理解

<dataDir>/var/data/solr</dataDir>

mainIndex>

    <!-- lucene options specific to the main on-disk lucene index -->

    <useCompoundFile>false</useCompoundFile>

    <mergeFactor>10</mergeFactor>

    <maxBufferedDocs>1000</maxBufferedDocs>

    <maxMergeDocs>2147483647</maxMergeDocs>

    <maxFieldLength>10000</maxFieldLength>

  </mainIndex>

<updateHandler class="solr.DirectUpdateHandler2">

    <!-- Limit the number of deletions Solr will buffer during doc updating.

        Setting this lower can help bound memory use during indexing.

    -->

    <maxPendingDeletes>100000</maxPendingDeletes>

    <!-- autocommit pending docs if certain criteria are met.  Future versions may expand the available

     criteria -->

    <autoCommit> 

      <maxDocs>10000</maxDocs> <!-- maximum uncommited docs before autocommit triggered -->

      <maxTime>86000</maxTime> <!-- maximum time (in MS) after adding a doc before an autocommit is triggered -->

    </autoCommit>

    ...

    <!-- The RunExecutableListener executes an external command.

         exe  - the name of the executable to run

         dir  -  dir to use as the current working directory. default="."

         wait - the calling thread waits until the executable returns.

                default="true"

         args - the arguments to pass to the program.  default=nothing

         env  - environment variables to set.  default=nothing

      -->

    <!-- A postCommit event is fired after every commit

      -->

    <listener event="postCommit" class="solr.RunExecutableListener">

      <str name="exe">snapshooter</str>

      <str name="dir">solr/bin</str>

      <bool name="wait">true</bool>

      <!--

      <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>

      <arr name="env"> <str>MYVAR=val1</str> </arr>

        -->

    </listener>

  </updateHandler>

<query>

    <!-- Maximum number of clauses in a boolean query... can affect range

         or wildcard queries that expand to big boolean queries. 

         An exception is thrown if exceeded.

    -->

    <maxBooleanClauses>1024</maxBooleanClauses>

<!-- Cache used by SolrIndexSearcher for filters (DocSets),

         unordered sets of *all* documents that match a query.

         When a new searcher is opened, its caches may be prepopulated

         or "autowarmed" using data from caches in the old searcher.

         autowarmCount is the number of items to prepopulate.  For LRUCache,

         the autowarmed items will be the most recently accessed items.

       Parameters:

         class - the SolrCache implementation (currently only LRUCache)

         size - the maximum number of entries in the cache

         initialSize - the initial capacity (number of entries) of

           the cache.  (seel java.util.HashMap)

         autowarmCount - the number of entries to prepopulate from

           and old cache.

         -->

    <filterCache

      class="solr.LRUCache"

      size="512"

      initialSize="512"

      autowarmCount="256"/>

   <!-- queryResultCache caches results of searches - ordered lists of

         document ids (DocList) based on a query, a sort, and the range

         of documents requested.  -->

    <queryResultCache

      class="solr.LRUCache"

      size="512"

      initialSize="512"

      autowarmCount="256"/>

  <!-- documentCache caches Lucene Document objects (the stored fields for each document).

       Since Lucene internal document ids are transient, this cache will not be autowarmed.  -->

    <documentCache

      class="solr.LRUCache"

      size="512"

      initialSize="512"

      autowarmCount="0"/>

    <!-- Example of a generic cache.  These caches may be accessed by name

         through SolrIndexSearcher.getCache().cacheLookup(), and cacheInsert().

         The purpose is to enable easy caching of user/application level data.

         The regenerator argument should be specified as an implementation

         of solr.search.CacheRegenerator if autowarming is desired.  -->

    <!--

    <cache name="myUserCache"

      class="solr.LRUCache"

      size="4096"

      initialSize="1024"

      autowarmCount="1024"

      regenerator="org.mycompany.mypackage.MyRegenerator"

      />

    -->

    <!-- An optimization that attempts to use a filter to satisfy a search.

         If the requested sort does not include a score, then the filterCache

         will be checked for a filter matching the query.  If found, the filter

         will be used as the source of document ids, and then the sort will be

         applied to that.

      -->

    <useFilterForSortedQuery>true</useFilterForSortedQuery>

    <!-- An optimization for use with the queryResultCache.  When a search

         is requested, a superset of the requested number of document ids

         are collected.  For example, of a search for a particular query

         requests matching documents 10 through 19, and queryWindowSize is 50,

         then documents 0 through 50 will be collected and cached. Any further

         requests in that range can be satisfied via the cache.

    -->

    <queryResultWindowSize>50</queryResultWindowSize>

   <!-- This entry enables an int hash representation for filters (DocSets)

         when the number of items in the set is less than maxSize. For smaller

         sets, this representation is more memory efficient, more efficient to

         iterate over, and faster to take intersections.

     -->

    <HashDocSet maxSize="3000" loadFactor="0.75"/>

    <!-- boolToFilterOptimizer converts boolean clauses with zero boost

         cached filters if the number of docs selected by the clause exceeds the

         threshold (represented as a fraction of the total index)

    -->

    <boolTofilterOptimizer enabled="true" cacheSize="32" threshold=".05"/>

    <!-- Lazy field loading will attempt to read only parts of documents on disk that are

         requested.  Enabling should be faster if you aren't retrieving all stored fields.

    -->

    <enableLazyFieldLoading>false</enableLazyFieldLoading>

<!-- a newSearcher event is fired whenever a new searcher is being

         prepared and there is a current searcher handling requests

         (aka registered).

     -->

    <!-- QuerySenderListener takes an array of NamedList and

         executes a local query request for each NamedList in sequence.

     -->

    <!--

    <listener event="newSearcher" class="solr.QuerySenderListener">

      <arr name="queries">

        <lst> <str name="q">solr</str>

              <str name="start">0</str>

              <str name="rows">10</str>

        </lst>

        <lst> <str name="q">rocks</str>

              <str name="start">0</str>

              <str name="rows">10</str>

        </lst>

      </arr>

    -->

<!-- a firstSearcher event is fired whenever a new searcher is being

         prepared but there is no current registered searcher to handle

         requests or to gain prewarming data from.

     -->

    <!--

    <listener event="firstSearcher" class="solr.QuerySenderListener">

      <arr name="queries">

        <lst> <str name="q">fast_warm</str>

              <str name="start">0</str>

              <str name="rows">10</str>

        </lst>

      </arr>

    </listener>