I had few queries running fine on a set of indices. I loaded new indices which are big(total size 500GB). Now the queries have become slow. New indices are not queried.
Have the allocation of the shards belonging to the initial set of indices changed? Are you sure the new indices are not queries and you are seeing the effects of less efficient page cache usage? Are there any changes in GC length or frequency?
Apache, Apache Lucene, Apache Hadoop, Hadoop, HDFS and the yellow elephant
logo are trademarks of the
Apache Software Foundation
in the United States and/or other countries.