Hello UG

I got a solr server running to index the posts of a forum. The server is
running in a tomcat installation on a 4-processor Opteron server. One of
the threads is eating up 100% of one processor all the time. As you can
see in the ps output it is a fork of one of the childs:
  
23228    0:03 /var/home/solr/src/jdk1.5.0_11/bin/java -Xms1024
23230    0:00  \_ /var/home/solr/src/jdk1.5.0_11/bin/java -Xms
23231  133:05      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23232  133:13      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23233  132:29      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23234  132:40      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23235  149:25      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23236    0:23      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23237    0:31      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23238    0:00      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23239    0:00      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23240    0:15      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23241    0:17      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23242    0:00      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23243    0:02      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23248  8712:36      \_ /var/home/solr/src/jdk1.5.0_11/bin/java
23249    0:59      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23250    0:29      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 
23251    0:00      \_ /var/home/solr/src/jdk1.5.0_11/bin/java 


I do auto-commits every 10s to keep the index up to date. It might be
related to this, but during the night time when no new posts are indexed
the process still runs at 100%. The index is 3.2G and contains 9 million
documents. 

Thanks a lot!

Cheers,

Michael


##################################################
I got the following versions installed:
##################################################

Java: 1.5.0.11
Tomcat: 6.0.10
Solr Specification Version: 1.1.2007.05.24.08.06.21
Solr Implementation Version: nightly - yonik - 2007-05-24 08:06:21
Lucene Specification Version: 2007-05-20_00-04-53
Lucene Implementation Version: build 2007-05-20


##################################################
schema.xml:
##################################################

<?xml version="1.0" ?>
<schema name="tsr" version="1.1">
        <types>
                <fieldtype name="string" class="solr.StrField" 
sortMissingLast="true" omitNorms="true"/>
                <fieldtype name="boolean" class="solr.BoolField" 
sortMissingLast="true" omitNorms="true"/>

                <fieldtype name="integer" class="solr.IntField" 
omitNorms="true"/>
                <fieldtype name="long" class="solr.LongField" omitNorms="true"/>
                <fieldtype name="float" class="solr.FloatField" 
omitNorms="true"/>
                <fieldtype name="double" class="solr.DoubleField" 
omitNorms="true"/>

                <fieldtype name="sint" class="solr.SortableIntField" 
sortMissingLast="true" omitNorms="true"/>
                <fieldtype name="slong" class="solr.SortableLongField" 
sortMissingLast="true" omitNorms="true"/>
                <fieldtype name="sfloat" class="solr.SortableFloatField" 
sortMissingLast="true" omitNorms="true"/>
                <fieldtype name="sdouble" class="solr.SortableDoubleField" 
sortMissingLast="true" omitNorms="true"/>

                <fieldtype name="date" class="solr.DateField" 
sortMissingLast="true" omitNorms="true"/>

                <fieldtype name="text" class="solr.TextField" 
positionIncrementGap="100">
                        <analyzer type="index">
                                <tokenizer 
class="solr.WhitespaceTokenizerFactory"/>
                                <filter class="solr.StopFilterFactory" 
ignoreCase="true" words="stopwords.txt"/>
                                <filter class="solr.WordDelimiterFilterFactory" 
generateWordParts="1" generateNumberParts="1" catenateWords="1" 
catenateNumbers="1" catenateAll="0"/>
                                <filter class="solr.LowerCaseFilterFactory"/>
                                <filter class="solr.EnglishPorterFilterFactory" 
protected="protwords.txt"/>
                                <filter 
class="solr.RemoveDuplicatesTokenFilterFactory"/>
                        </analyzer>
                        <analyzer type="query">
                                <tokenizer 
class="solr.WhitespaceTokenizerFactory"/>
                                <filter class="solr.StopFilterFactory" 
ignoreCase="true" words="stopwords.txt"/>
                                <filter class="solr.WordDelimiterFilterFactory" 
generateWordParts="1" generateNumberParts="1" catenateWords="0" 
catenateNumbers="0" catenateAll="0"/>
                                <filter class="solr.LowerCaseFilterFactory"/>
                                <filter class="solr.EnglishPorterFilterFactory" 
protected="protwords.txt"/>
                                <filter 
class="solr.RemoveDuplicatesTokenFilterFactory"/>
                        </analyzer>
                </fieldtype>
        </types>


        <fields>
                <field name="postid" type="text" indexed="true" stored="true"/>
                <field name="title" type="text" indexed="true" stored="false"/>
                <field name="userid" type="text" indexed="true" stored="false"/>
                <field name="pagetext" type="text" indexed="true" 
stored="false"/>
                <field name="username" type="string" indexed="true" 
stored="false"/>
                <field name="dateline" type="integer" indexed="true" 
stored="false"/>
                <field name="threadid" type="text" indexed="true" 
stored="true"/>
                <field name="forumid" type="text" indexed="true" 
stored="false"/>
                <field name="visible" type="integer" indexed="true" 
stored="false"/>
                <field name="is_starter" type="boolean" indexed="true" 
stored="false"/>
                <field name="string_username" type="string" indexed="true" 
stored="false"/>
                <field name="string_forumtitle" type="string" indexed="true" 
stored="false"/>
                <field name="string_title" type="string" indexed="true" 
stored="false"/>
                <field name="sort_date" type="integer" indexed="true" 
stored="false"/>
                <field name="title_pagetext" type="text" indexed="true" 
stored="false"  multiValued="true"/>
        </fields>

        <uniqueKey>postid</uniqueKey>

        <defaultSearchField>pagetext</defaultSearchField>

        <solrQueryParser defaultOperator="AND"/>
   
   <copyField source="title" dest="title_pagetext"/>
   <copyField source="pagetext" dest="title_pagetext"/>
</schema>


##################################################
solrconfig.xml:
##################################################

<?xml version="1.0" encoding="UTF-8" ?>
<config>

<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>

  <indexDefaults>
    <useCompoundFile>false</useCompoundFile>
    <mergeFactor>10</mergeFactor>
    <maxBufferedDocs>1000</maxBufferedDocs>
    <maxMergeDocs>2147483647</maxMergeDocs>
    <maxFieldLength>10000</maxFieldLength>
    <writeLockTimeout>1000</writeLockTimeout>
    <commitLockTimeout>10000</commitLockTimeout>
  </indexDefaults>

  <mainIndex>
    <useCompoundFile>false</useCompoundFile>
    <mergeFactor>10</mergeFactor>
    <maxBufferedDocs>1000</maxBufferedDocs>
    <maxMergeDocs>2147483647</maxMergeDocs>
    <maxFieldLength>10000</maxFieldLength>

    <unlockOnStartup>false</unlockOnStartup>
  </mainIndex>

  <updateHandler class="solr.DirectUpdateHandler2">

    <autoCommit> 
      <maxDocs>1000</maxDocs>
      <maxTime>10000</maxTime>
    </autoCommit>
  </updateHandler>


  <query>
    <maxBooleanClauses>1024</maxBooleanClauses>

    <filterCache
      class="solr.LRUCache"
      size="512"
      initialSize="512"
      autowarmCount="256"/>

    <queryResultCache
      class="solr.LRUCache"
      size="512"
      initialSize="512"
      autowarmCount="256"/>

    <documentCache
      class="solr.LRUCache"
      size="512"
      initialSize="512"
      autowarmCount="0"/>
    <enableLazyFieldLoading>false</enableLazyFieldLoading>

    <queryResultWindowSize>100</queryResultWindowSize>

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

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

    <useColdSearcher>false</useColdSearcher>

    <maxWarmingSearchers>4</maxWarmingSearchers>

  </query>

  <requestDispatcher handleSelect="true" >
    <requestParsers enableRemoteStreaming="false"
multipartUploadLimitInKB="2048" />
  </requestDispatcher>
  
  <requestHandler name="standard" class="solr.StandardRequestHandler">
     <lst name="defaults">
       <str name="echoParams">explicit</str>
     </lst>
  </requestHandler>
  
  <requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
    <lst name="defaults">
     <str name="echoParams">explicit</str>
     <float name="tie">0.01</float>
     <str name="qf">
        text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
     </str>
     <str name="pf">
        text^0.2 features^1.1 name^1.5 manu^1.4 manu_exact^1.9
     </str>
     <str name="bf">
        ord(poplarity)^0.5 recip(rord(price),1,1000,1000)^0.3
     </str>
     <str name="fl">
        id,name,price,score
     </str>
     <str name="mm">
        2&lt;-1 5&lt;-2 6&lt;90%
     </str>
     <int name="ps">100</int>
     <str name="q.alt">*:*</str>
    </lst>
  </requestHandler>

  <requestHandler name="partitioned" class="solr.DisMaxRequestHandler" >
    <lst name="defaults">
     <str name="echoParams">explicit</str>
     <str name="qf">text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0</str>
     <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
     <str name="bq">incubationdate_dt:[* TO NOW/DAY-1MONTH]^2.2</str>
    </lst>
    
    <lst name="appends">
      <str name="fq">inStock:true</str>
    </lst>
    
    <lst name="invariants">
      <str name="facet.field">cat</str>
      <str name="facet.field">manu_exact</str>
      <str name="facet.query">price:[* TO 500]</str>
      <str name="facet.query">price:[500 TO *]</str>
    </lst>
  </requestHandler>
  
  <requestHandler name="instock" class="solr.DisMaxRequestHandler" >
     <str name="fq">
        inStock:true
     </str>
     <str name="qf">
        text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
     </str>
     <str name="mm">
        2&lt;-1 5&lt;-2 6&lt;90%
     </str>
  </requestHandler>


  <requestHandler name="spellchecker"
class="solr.SpellCheckerRequestHandler">
     <lst name="defaults">
       <int name="suggestionCount">1</int>
       <float name="accuracy">0.5</float>
     </lst>
     
     <str name="spellcheckerIndexDir">spell</str>
     
     <str name="termSourceField">word</str>
     
   </requestHandler>

  
  <requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />

  <requestHandler name="/update/csv" class="solr.CSVRequestHandler"
startup="lazy" />


  <requestHandler name="/admin/luke"
class="org.apache.solr.handler.admin.LukeRequestHandler" />
  <requestHandler name="/admin/system"
class="org.apache.solr.handler.admin.SystemInfoHandler" />
  <requestHandler name="/admin/plugins"
class="org.apache.solr.handler.admin.PluginInfoHandler" />
  <requestHandler name="/admin/threads"
class="org.apache.solr.handler.admin.ThreadDumpHandler" />
  <requestHandler name="/admin/properties"
class="org.apache.solr.handler.admin.PropertiesRequestHandler" />
  
  <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
    <lst name="defaults">
     <str name="echoParams">explicit</str> <!-- for all params
(including the default etc) use: 'all' -->
     <str name="echoHandler">true</str>
    </lst>
  </requestHandler>
  
  <queryResponseWriter name="xslt"
class="org.apache.solr.request.XSLTResponseWriter">
    <int name="xsltCacheLifetimeSeconds">5</int>
  </queryResponseWriter> 
    
  <admin>
    <defaultQuery>solr</defaultQuery>
    <gettableFiles>solrconfig.xml schema.xml
admin-extra.html</gettableFiles>
    <pingQuery>
     qt=dismax&amp;q=solr&amp;start=3&amp;fq=id:[* TO *]&amp;fq=cat:[*
TO *]
    </pingQuery>
  </admin>

</config>



-- 
Michael Thessel <[EMAIL PROTECTED]>
Gossamer Threads Inc. http://www.gossamer-threads.com/
Tel: (604) 687-5804 Fax: (604) 687-5806

Reply via email to