Papers We Love: July 2023 meetup
DDSketch: A Fast and Fully-Mergeable Quantile Sketch with Relative-Error Guarantees
Jul 2023
17 Mon
18 Tue
19 Wed
20 Thu
21 Fri 04:15 PM – 05:30 PM IST
22 Sat
23 Sun
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.
The paper is published at https://www.vldb.org/pvldb/vol12/p2195-masson.pdf
This is an in-person meetup. RSVP to get venue location.
Hosted by
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.
The paper is published at https://www.vldb.org/pvldb/vol12/p2195-masson.pdf
This is an in-person meetup. RSVP to get venue location.
Hosted by