NoSQL Benchmarks NoSQL use cases NoSQL Videos NoSQL Hybrid Solutions NoSQL Presentations Big Data Hadoop MapReduce Pig Hive Flume Oozie Sqoop HDFS ZooKeeper Cascading Cascalog BigTable Cassandra HBase Hypertable Couchbase CouchDB MongoDB OrientDB RavenDB Jackrabbit Terrastore Amazon DynamoDB Redis Riak Project Voldemort Tokyo Cabinet Kyoto Cabinet memcached Amazon SimpleDB Datomic MemcacheDB M/DB GT.M Amazon Dynamo Dynomite Mnesia Yahoo! PNUTS/Sherpa Neo4j InfoGrid Sones GraphDB InfiniteGraph AllegroGraph MarkLogic Clustrix CouchDB Case Studies MongoDB Case Studies NoSQL at Adobe NoSQL at Facebook NoSQL at Twitter



Improvements and Benchmarks for LevelDB in Riak 1.2

Basho team started to investigate and optimize LevelDB, one of the supported storage engine for Riak and the engine for Riak 2i, and the results are already impressive:

  • reduced stalls (from 10-90s every 3-5min to 10-30s every 2h)
  • increased throughput (from 400 ops/s to 2000 ops/s)
  • a better solution for dealing with an infinite loop during compaction against a corrupted data block
  • LevelDB bloom filter for quickly identifying keys that don’t exist in the data store

The original posts also shows some charts of the throughput and maximum latency measured in Level 1.1 vs Level 1.2.

Original title and link: Improvements and Benchmarks for LevelDB in Riak 1.2 (NoSQL database©myNoSQL)