8f56f2711b5b1653f60d009d6f642cb653c20462,perfkitbenchmarker/benchmarks/cloudsuite_web_search.py,,_BuildIndex,#Any#Any#,80

Before Change

  Downloads data and builds Solr index from it.
  indexer.Install("nutch")
  hadoop_tmp_dir = posixpath.join(indexer.GetScratchDir(), "hadoop_tmp")
  indexer.RemoteCommand("cd {0} && "
                        "wget {1} && "
                        "mkdir -p {4} && "
                        "sed -i "/<value>http/c\\<value>http://{2}:"
                        "{3}/solr/cloudsuite_web_search</value>" "
                        "nutch-site.xml && "
                        "sed -i "s/HADOOP_TMP_DIR/{4}/g" nutch-site.xml".format(
                            CLOUDSUITE_WEB_SEARCH_DIR,
                            NUTCH_SITE_URL, solr_node.ip_address,
                            SOLR_PORT, re.escape(hadoop_tmp_dir)))
  stdout, _ = indexer.RemoteCommand("cd {0} && "
                                    "cat nutch-site.xml".format(
                                        CLOUDSUITE_WEB_SEARCH_DIR))
  nutch.ConfigureNutchSite(indexer, stdout.replace(""", "\\""))
  scratch_dir = indexer.GetScratchDir()
  indexer.RobustRemoteCommand("cd {0} && "
                              "wget {1}  && "

After Change

                     "tar zxvf index -C {2}".format(
                         solr_core_dir, INDEX_URL, "cloudsuite_web_search*"))

  vm_util.RunThreaded(DownloadIndex, solr_nodes, len(solr_nodes))
  server_heap_size = FLAGS.server_heap_size
  for vm in solr_nodes:
    if vm == solr_nodes[0]:
      solr.StartWithZookeeper(vm, fw, SOLR_PORT, server_heap_size, False)

Instances