CLP: Efficient and Scalable Search on Compressed Text Logs (2021) usenix.org

Researchers at the University of Toronto and YScope Inc. introduced CLP, a system that losslessly compresses text logs while allowing searches directly on the compressed data. Their 2021 evaluation reports compression about twice as effective as Gzip, search faster than tested alternatives, and ingestion more than 13 times faster than Elasticsearch and Splunk Enterprise; the authors say its distributed design scales to petabytes.