Papers We Love: July 2023 meetup
DDSketch: A Fast and Fully-Mergeable Quantile Sketch with Relative-Error Guarantees
About the paper
Monitoring p95, p99 latencies are standard practice. To optimize storage and computation monitoring systems use quantile sketches to calculate these metrics. Distributed nature of systems requires quantile sketches to be mergeable. DDSketch is a fully mergeable quantile sketch, developed and used by Datadog, which has relative error guarantees. Paper discusses how DDSketch works internally, memory requirements of sketch and performance of adding measurement and merge speeds.
Key takeaways for the audience
The paper is published at https://www.vldb.org/pvldb/vol12/p2195-masson.pdf
RSVP and venue
This is an in-person meetup. RSVP to get venue location.
Hosted by
What was the last paper within the realm of computing you read and loved? What did it inspire you to build or tinker with? Come share the ideas in an awesome academic/research paper with fellow engineers, programmers, and paper-readers. Lead a session and show off code that you wrote that implement…
more