REPLICA_PREFERENCE Query Option (CDH 5.9 or higher only)

The REPLICA_PREFERENCE query option lets you spread the load more evenly if hotspots and bottlenecks persist, by allowing hosts to do local reads, or even remote reads, to retrieve the data for cached blocks if Impala can determine that it would be too expensive to do all such processing on a particular host.

Type: numeric (0, 2, 4) or corresponding mnemonic strings (CACHE_LOCAL, DISK_LOCAL, REMOTE). The gaps in the numeric sequence are to accommodate other intermediate values that might be added in the future.

Default: 0 (equivalent to CACHE_LOCAL)

Added in: CDH 5.9.0 (Impala 2.7.0)

Related information:

Using HDFS Caching with Impala (CDH 5.1 or higher only), SCHEDULE_RANDOM_REPLICA Query Option (CDH 5.7 or higher only)