Cloudera Docs

Low-latency analytical processing

CDP Public Cloud supports low-latency analytical processing (LLAP) of Hive queries. Using LLAP available in the CDP Data Warehouse service, you can tune your data warehouse infrastructure, components, and client connection parameters to improve the performance and relevance of business intelligence and other applications.

Increasingly, enterprises want to run SQL workloads that return faster results than batch processing can provide. These enterprises often want data analytics applications to support interactive queries. Low-latency analytical processing (LLAP) can improve the performance of interactive queries. A Hive interactive query that runs on the CDP Public Cloud meets low-latency, variably guaged benchmarks to which Hive LLAP responds in 15 seconds or less. LLAP enables application development and IT infrastructure to run queries that return real-time or near-real-time results.

Cloudera Data Warehouse (CDW) includes the following LLAP performance features:

  • Object store optimizations for S3 and ABFS

  • Improvements in S3A and ABFS connectors for improved remote read performance and lower CPU utilization with encryption

  • S3guard metadata caching in authoritative mode

  • Data cache

  • Local on disk caching of remote data from object stores or remote HDFS/Ozone

  • Attached NVMe SSD storage used for larger cache

  • Lazy column decoding with joins improves cpu utilization and latency

  • Cost-Based Optimizations for runtime filtering, shared scans and grouping operations

  • Efficient TopN implementation to speed up LIMIT queries

  • Improvements in handling Decimal type

  • Auto-scaling for adaptive resource management

CDP Private Cloud Base does not support LLAP.