List of workloads, traces, and models for distributed systems

HPC

Parallel Workloads Archive: a collection of traces and models of workloads for HPC machines.
Lublin-Feitelson: model for parallel tasks in supercomputers.
Pegasus Synthetic Workflows: Profiling data of 20 synthetic workflow applications, each with different size options.

Grid Workloads Archive: a repository of utilization traces of several grids.
Failure Trace Archive: a repository of availability traces of parallel and distributed systems.
PlanetLab Workload Traces: A set of CPU utilization traces from PlanetLab VMs collected during 10 random days in March and April 2011.

Google Cluster Data: traces from requests processed by Google cluster management system (a.k.a. Borg).
Alibaba Clusters Data: traces from Albiba system containing details about jobs/applications.
Yahoo! Cloud Serving Benchmark/: Among other data and tools, it contains a set of core workloads that are indicative of typical cloud services.
WorldCup98: trace of all web requests made to the 1998 FIFA World Cup servers during the event.
Wikipedia Pagecounts-raw: A trace of web requests made to Wikipedia servers and outages and issues with the servers that might affect the traces.
The QWS Dataset: Measurements of over 2,000 web service implementations, collected between 2007 and 2008.
Medical application workload
COVID-19 Open Research Dataset Challenge (CORD-19)

If you have any comments on this page, please contact Dr. Buyya.