upscaledb is a fast key-value database which optimizes storage and algorithms for your specific data types.
Optional compression further reduces file size and I/O, and can keep more data in memory to increase performance and scalability when running full-table scans to query and analyze the data.Learn More
upscaledb can be used to build all functions of a typical SQL database, tailored to the specific needs of your application, and directly linked into your program.
Its blazingly fast analytical functions and database cursors make it a natural fit to process data whenever a SQL database is not fast enough.Learn More
A simple and self-documenting API; extensive documentation and a tutorial are provided. APIs for C/C++, Java, Python, .NET (i.e. C#, VB.NET) and Erlang are available.
Applications using upscaledb are deployed on tens of millions of desktops, but also on cloud instances, cell phones and other embedded devices.Learn More
This benchmark runs a full-table scan over 50 million records and retrieves the maximum. The records are configured as uint32 values.
upscaledb is about 90 times faster than leveldb, and about 140 times faster than BerkeleyDB.
Benchmarks using upscaledb v2.0.0, leveldb v1.11.0, BerkeleyDB v5.1.0 running on 64bit Linux on commodity hardware. Cache size is 4mb. The benchmark is available here.