Nutch を Hadoop と統合し、クロールを実行しました。しかし、データの solrindex を作成したいときに、Job Failed が発生しました。これは私のコマンドです:
$bin/nutch solrindex http://namenode:8983/solr/ crawl/crawldb -linkdb crawl/linkdb crawl/segments/*
ディレクトリ「crawl」にはデータが保存され、HDFS に配置されます。solr リリース内の例を使用しました。また、コマンドを単一ノード モード (分散モードではない) で実行すると、正常に動作します。以下は出力の一部です。
12/04/28 13:51:22 INFO mapred.JobClient: map 100% reduce 23%
12/04/28 13:51:30 INFO mapred.JobClient: Task Id : attempt_201204212112_0076_r_000000_0, Status : FAILED
java.io.IOException
at org.apache.nutch.indexer.solr.SolrWriter.makeIOException(SolrWriter.java:103)
at org.apache.nutch.indexer.solr.SolrWriter.close(SolrWriter.java:98)
at org.apache.nutch.indexer.IndexerOutputFormat$1.close(IndexerOutputFormat.java:48)
at org.apache.hadoop.mapred.ReduceTask$OldTrackingRecordWriter.close(ReduceTask.java:466)
at org.apache.hadoop.mapred.ReduceTask.runOldReducer(ReduceTask.java:530)
at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:420)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Unknown Source)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1059)
at org.apache.hadoop.mapred.Child.main(Child.java:249)
Caused by: org.apache.solr.client.solrj.SolrServerException: java.net.ConnectException: Connection refused
at org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHttpSolrServer.java:478)
at org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHttpSolrServer.java:244)
at org.apache.solr.client.solrj.request.AbstractUpdateRequest.process(AbstractUpdateRequest.java:105)
at org.apache.solr.client.solrj.SolrServer.add(SolrServer.java:49)
at org.apache.nutch.indexer.solr.SolrWriter.close(SolrWriter.java:93)
... 9 more
Caused by: java.net.ConnectException: Connection refused
at java.net.PlainSocketImpl.socketConnect(Native Method)
at java.net.PlainSocketImpl.doConnect(Unknown Source)
at java.net.PlainSocketImpl.connectToAddress(Unknown Source)
at java.net.PlainSocketImpl.connect(Unknown Source)
at java.net.SocksSocketImpl.connect(Unknown Source)
at java.net.Socket.connect(Unknown Source)
at java.net.Socket.connect(Unknown Source)
at java.net.Socket.<init>(Unknown Source)
at java.net.Socket.<init>(Unknown Source)
at org.apache.commons.httpclient.protocol.DefaultProtocolSocketFactory.createSocket(DefaultProtocolSocketFactory.java:79)
at org.apache.commons.httpclient.protocol.DefaultProtocolSocketFactory.createSocket(DefaultProtocolSocketFactory.java:121)
at org.apache.commons.httpclient.HttpConnection.open(HttpConnection.java:706)
at org.apache.commons.httpclient.HttpMethodDirector.executeWithRetry(HttpMethodDirector.java:386)
at org.apache.commons.httpclient.HttpMethodDirector.executeMethod(HttpMethodDirector.java:170)
at org.apache.commons.httpclient.HttpClient.executeMethod(HttpClient.java:396)
at org.apache.commons.httpclient.HttpClient.executeMethod(HttpClient.java:324)
at org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHttpSolrServer.java:422)
... 13 more