This repository describes various traces from parts of the Google cluster management software and systems.
Please join our (low volume) discussion group, so we can send you announcements, and you can let us know about any issues, insights, or papers you publish using these traces. Important: to avoid spammers, you MUST fill out the "reason" field, or your application will be rejected. Once you are a member, you can send email to googleclusterdata-discuss@googlegroups.com to:
We provide a trace bibliography of papers that have used and/or analyzed the traces, and encourage anybody who publishes one to add it to the bibliography using a github pull request [preferred], or by emailing the bibtex entry to googleclusterdata-discuss@googlegroups.com. In either case, please mimic the existing format exactly.
These are traces of workloads running on Google compute cells that are managed by the cluster management software internally known as Borg.
ClusterData2019
) provides data
from eight Borg cells over the month of May 2019.ClusterData2011
) provides data from
a single 12.5k-machine Borg cell from May 2011.In addition, this site hosts a set of execution traces from ETA (Exploratory Testing Architecture) - a testing framework that explores interactions between distributed, concurrently-executing components, with an eye towards improving testing them.
This site also hosts power traces for 57 power domains
during the month of May 2019. This trace is synergistic with the
ClusterData2019
dataset.
The data and trace documentation are made available under the CC-BY license. By downloading it or using them, you agree to the terms of this license.