Blog

April 20th, 2018 marked the end of our first iteration of DAWNBench, the first deep learning benchmark and competition that measures end-to-end performance: the time/cost required to achieve a state-of-the-art accuracy level for common deep learning tasks, as well as the latency/cost of inference at this state-of-the-art accuracy level.

(Editor’s note: I was unaware that Kyle Kingsbury was doing a linearizability analysis of Hazelcast when I was writing this post. Kyle’s analysis resulted in Greg Luck, Hazelcast’s CEO, to write a blog post where he cited the PACELC theorem, and came to some of the same conclusions that I came to in writing this post.

In my previous blog post, I discussed the relatively new Apache Arrow project, and compared it with two similar column-oriented storage formats in ORC and Parquet. In particular, I explained how storage formats targeted for main memory have fundamental differences from storage formats targeted for disk-resident data.

Introduction: In 2012, two research papers were published that described the design of geographically replicated, consistent, ACID compliant, transactional database systems. Both papers criticized the proliferation of NoSQL database systems that compromise replication consistency and transactional support, and argue that it is very possible to build extremely scalable, geographically replicated systems without giving up on consistency and transactional support.

EMC announced today that they are acquiring Greenplum. Below are the first thoughts that crossed my mind when I heard about this deal.

Apache Parquet and Apache ORC have become a popular file formats for storing data in the Hadoop ecosystem. Their primary value proposition revolves around their “columnar data representation format”. To quickly explain what this means: many people model their data in a set of two dimensional tables where each row corresponds to an entity, and each column an attribute about that entity. However, storage is one-dimensional --- you can only read data sequentially from memory or disk in one dimension.

As 24/7 availability becomes increasingly important for modern applications, database systems are frequently replicated in order to stay up and running in the face of database server failure. It is no longer acceptable for an application to wait for a database to recover from a log on disk --- most mission-critical applications need immediate failover to a replica.

I have noticed that Bigtable, HBase, Hypertable, and Cassandra are being called column-stores with increasing frequency (e.g. here, here, and here), due to their ability to store and access column families separately.

Curt Monash has recently been discussing the differences between machine-generated data and human-generated data, and trying to define these terms on his blog. I think this is a good subject to dive into, since I frequently use the existence of machine-generated data to justify to myself why 90% of my research cycles are spent on scalability problems in database systems. Rather than try to fit a response as a comment on his post, I thought I would devote a post to this subject here.