Uploaded image for project: 'Solr'
  1. Solr
  2. SOLR-3360

Problem with DataImportHandler multi-threaded

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Closed
    • Major
    • Resolution: Fixed
    • 3.6
    • 3.6.1
    • None
    • None
    • Solr 3.6.0, Apache Tomcat 6.0.20, jdk1.6.0_15, Windows XP

    Description

      Hi,

      If I use dataimport with 1 thread, I got:

      <lst name="statusMessages">
      <str name="Total Requests made to DataSource">5001</str>
      <str name="Total Rows Fetched">1000</str>
      <str name="Total Documents Skipped">0</str>
      <str name="Full Dump Started">2012-04-16 11:21:57</str>
      <str name="">Indexing completed. Added/Updated: 1000 documents. Deleted 0 documents.</str>
      <str name="Committed">2012-04-16 11:23:19</str>
      <str name="Total Documents Processed">1000</str>
      <str name="Time taken">0:1:22.390</str>
      </lst>

      If I use datamport with 10 threads, I got:

      <lst name="statusMessages">
      <str name="Total Requests made to DataSource">0</str>
      <str name="Total Rows Fetched">10000</str>
      <str name="Total Documents Skipped">0</str>
      <str name="Full Dump Started">2012-04-16 11:31:43</str>
      <str name="">Indexing completed. Added/Updated: 10000 documents. Deleted 0 documents.</str>
      <str name="Committed">2012-04-16 11:41:50</str>
      <str name="Total Documents Processed">10000</str>
      <str name="Time taken">0:10:7.586</str>
      </lst>

      The configuration of 10 threads consumed 10 times longer than the configuration with 1 thread.
      I have 1000 records in the database.
      My db-data-config.xml is shown below:

      <?xml version="1.0" encoding="UTF-8" ?>
      <dataConfig>
      <dataSource driver="com.microsoft.sqlserver.jdbc.SQLServerDriver" url="jdbc:sqlserver://200.XXX.XXX.XXX:1433;databaseName=test" user="user" password="pass"/>
      <document>
      <entity name="indice" rootEntity="true" threads="10" transformer="RegexTransformer,TemplateTransformer" query="select top 1000 i.id_indice, i.a, i.b from indice i where i.status = 'I'" deltaImportQuery="i.id_indice, i.a, i.b from indice i where id_indice in ('${dataimporter.delta.id_indice}')" deltaQuery="select id_indice from indice where status='I' and data_hora_modificacao >= convert(datetime, '${dataimporter.last_index_time}', 120)" deletedPkQuery="select id_indice from indice where status='D' and data_hora_modificacao >= convert(datetime, '${dataimporter.last_index_time}', 120)">
      <field column="id_indice" name="id_indice" />
      <field column="a" name="a" />
      <field column="b" name="b" />
      <entity name="filtro" transformer="RegexTransformer,TemplateTransformer" query="select categoria, sub_categoria from filtro where indice_id_indice = '${indice.id_indice}'">
      <field name="filtro_categoria" column="categoria" />
      <field name="filtro_sub_categoria" column="sub_categoria" />
      <field name="nv_sub_categoria" column="nv_sub_categoria" template="${filtro.categoria}|${filtro.sub_categoria}" />
      </entity>
      <entity name="pagina_relacionada" query="select url from pagina_relacionada where indice_id_indice = '${indice.id_indice}'">
      <field name="pagina_relacionada_url" column="url" />
      </entity>
      <entity name="veja_mais" query="select chamada, url from veja_mais where indice_id_indice = '${indice.id_indice}'">
      <field name="veja_mais_chamada" column="chamada" />
      <field name="veja_mais_url" column="url" />
      </entity>
      <entity name="video" query="select url from video where indice_id_indice = '${indice.id_indice}'">
      <field name="video_url" column="url" />
      </entity>
      <entity name="galeria" query="select url from galeria where indice_id_indice = '${indice.id_indice}'">
      <field name="galeria_url" column="url" />
      </entity>
      </entity>
      </document>
      </dataConfig>

      Thanks.

      Attachments

        1. SOLR-3360.patch
          10 kB
          Mikhail Khludnev
        2. SOLR-3360-test.patch
          5 kB
          James Dyer
        3. SOLR-3360-test.patch
          5 kB
          Mikhail Khludnev
        4. SOLR-3360-test.patch
          5 kB
          James Dyer
        5. SOLR-3360-test.patch
          5 kB
          James Dyer
        6. SOLR-3360-test.patch
          9 kB
          Mikhail Khludnev
        7. SOLR-3360-test.patch
          9 kB
          Mikhail Khludnev

        Activity

          People

            jdyer James Dyer
            claudio_br Claudio R
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: