Database compression on Nutanix

DB Compression

Compressability

What space savings should you expect when running databases with default compression in a Nutanix cluster? When we ran the TPCx-HCI benchmark on our cluster we realized about 2:1 savings from compression alone. The TPCx-HCI benchmark mimics a database consolidation setup, meaning that there are many databases per host. The uncompressed data size was about 45TB.

Compression+Encryption

Additionally, we configured data at rest encryption (DARE). Using the cluster features allows us to both compress and encrypt (compression first, then encrypt). If the database engine itself handled encryption, it would reduce the ability to compress.

Data generation

Like ZFS, the Nutanix filesystem uses LZ4 compressiom and 2:1 is about in-line with expectations for a realistic dataset. The TPCx-HCI benchmark uses the E-Gen data generation tool to populate the databases. E-Gen was developed for the TPC-E benchmark and uses sources such as census data and NYSE stock listings to generate real data rather than machine generated strings.

TPCx-HCI Data