JSON is a ubiquitous data interchange format supported by many systems, including CockroachDB. Historically, at CockroachDB, the majority of our efforts around JSON focused on supporting various JSON functions, operators, and inverted indexes while our JSON parser did not receive much attention. And for a good reason. If you are reading this blog, then you probably already appreciate Golang. There are many aspects to like in Go, and one of them is an excellent collection of standard (and third party) libraries. Becase Go ships with a “jack-of-all-trades” JSON parser out of the box (encoding/json library), it made sense for CockroachDB to use a standard parser when converting strings to internal JSON representation. However, at some point, we began to wonder if the time had arrived for us to invest in finding a better, more performant alternative.

The 2021 Cloud Report stands on benchmarks. Now in its third year, our report is more precise than ever, capturing an evaluation of Amazon Web Services (AWS), Microsoft Azure (Azure), and Google Cloud Platform (GCP) that tells realistic and universal performance stories on behalf of mission-critical OLTP applications.

Last year the BulkIO team at Cockroach Labs replaced the implementation of our IMPORT bulk-loading feature with a simpler and faster data ingestion pipeline. In most of our tests, it looked like a major improvement: the release notes for CockroachDB v19.2 touted "4x faster" IMPORT. Many a 🎉 reaction was clicked, and the team moved on to new projects. But over the following months, it became clear we had celebrated too soon: we started to get reports of some IMPORTs that, instead of being faster, were much slower or even getting stuck. Armed with a test that could reproduce such a case, we started to dig.