#wcsa-ef-ingest.process-ef-json-mode = per-volume wcsa-ef-ingest.process-ef-json-mode = per-page #wcsa-ef-ingest.solr-clode-nodes = 10.11.0.53:8983,10.11.0.54:8983,10.11.0.55:8983 wcsa-ef-ingest.solr-cloud-nodes = gc0:8983,gc1:8983,gc2:8983,gc3:8983,gc4:8983,gc5:8983,gc6:8983,gc7:8983,gc8:8983,gc9:8983 wcsa-ef-ingest.strict-file-io = false wcsa-ef-ingest.icu-tokenize = flase # 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 spark.executor.cores=11