#wcsa-ef-ingest.process-ef-json-mode = per-volume wcsa-ef-ingest.process-ef-json-mode = per-page #wcsa-ef-ingest.solr-endpoint-ips = 10.11.0.53,10.11.0.54,10.11.0.55 wcsa-ef-ingest.solr-endpoint-ips = gc0,gc1,gc2,gc3,gc4,gc5,gc6,gc7,gc8,gc9 wcsa-ef-ingest.strict-file-io = false # For guide on number of partitions to use, see "Parallelized collections" section of: # https://spark.apache.org/docs/2.0.1/programming-guide.html # which suggests 2-4 * num_cores # # For a more detailed discussion see: # http://blog.cloudera.com/blog/2015/03/how-to-tune-your-apache-spark-jobs-part-2/ # wcsa-ef-ingest.num-partitions = 12 wcsa-ef-ingest.num-partitions = 120