Ошибка Apache Nutch SolrIndexer в режиме SolrCloud - PullRequest
0 голосов
/ 02 мая 2018

Я настроил Apache Nutch 2.3.1 и просканировал несколько сайтов. Я должен проиндексировать эти документы в Solr (6.6.3), который работает в облачном режиме. Когда я выполняю команду solrindex, я получаю следующее исключение

2018-05-02 13:10:40,679 INFO [main] org.apache.hadoop.mapred.MapTask: Ignoring exception during close for org.apache.hadoop.mapred.MapTask$NewDirectOutputCollector@3bd3d05e
java.io.IOException: org.apache.solr.client.solrj.SolrServerException: Server refused connection at: http://10.11.22.156:8983/solr/collection2
    at org.apache.nutch.indexwriter.solr.SolrIndexWriter.close(SolrIndexWriter.java:103)
    at org.apache.nutch.indexer.IndexWriters.close(IndexWriters.java:114)
    at org.apache.nutch.indexer.IndexerOutputFormat$1.close(IndexerOutputFormat.java:54)
    at org.apache.hadoop.mapred.MapTask$NewDirectOutputCollector.close(MapTask.java:670)
    at org.apache.hadoop.mapred.MapTask.closeQuietly(MapTask.java:2019)
    at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:797)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
    at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:164)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:422)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1754)
    at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158)
Caused by: org.apache.solr.client.solrj.SolrServerException: Server refused connection at: http://10.11.22.156:8983/solr/collection2
    at org.apache.solr.client.solrj.impl.HttpSolrServer.executeMethod(HttpSolrServer.java:559)
    at org.apache.solr.client.solrj.impl.HttpSolrServer.request(HttpSolrServer.java:210)
    at org.apache.solr.client.solrj.impl.HttpSolrServer.request(HttpSolrServer.java:206)
    at org.apache.solr.client.solrj.request.AbstractUpdateRequest.process(AbstractUpdateRequest.java:124)
    at org.apache.solr.client.solrj.SolrServer.add(SolrServer.java:68)
    at org.apache.solr.client.solrj.SolrServer.add(SolrServer.java:54)
    at org.apache.nutch.indexwriter.solr.SolrIndexWriter.close(SolrIndexWriter.java:97)
    ... 11 more
Caused by: org.apache.http.conn.HttpHostConnectException: Connection to http://10.11.22.156:8983 refused
    at org.apache.http.impl.conn.DefaultClientConnectionOperator.openConnection(DefaultClientConnectionOperator.java:190)
    at org.apache.http.impl.conn.ManagedClientConnectionImpl.open(ManagedClientConnectionImpl.java:294)
    at org.apache.http.impl.client.DefaultRequestDirector.tryConnect(DefaultRequestDirector.java:643)
    at org.apache.http.impl.client.DefaultRequestDirector.execute(DefaultRequestDirector.java:479)
    at org.apache.http.impl.client.AbstractHttpClient.execute(AbstractHttpClient.java:906)
    at org.apache.http.impl.client.AbstractHttpClient.execute(AbstractHttpClient.java:805)
    at org.apache.http.impl.client.AbstractHttpClient.execute(AbstractHttpClient.java:784)
    at org.apache.solr.client.solrj.impl.HttpSolrServer.executeMethod(HttpSolrServer.java:448)
    ... 17 more
Caused by: java.net.ConnectException: Connection timed out
    at java.net.PlainSocketImpl.socketConnect(Native Method)
    at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:345)
    at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:206)
    at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:188)
    at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
    at java.net.Socket.connect(Socket.java:589)
    at org.apache.http.conn.scheme.PlainSocketFactory.connectSocket(PlainSocketFactory.java:127)
    at org.apache.http.impl.conn.DefaultClientConnectionOperator.openConnection(DefaultClientConnectionOperator.java:180)

Где проблема? Если я повторяю ту же работу с Solr без облачного режима, он работает штрафов.

...