Public | Automated Build

Last pushed: 3 years ago
Short Description
Short description is empty for this repo.
Full Description


A benchmarking
for Mesos.


This is work in progress in its early stages. Expect bugs and missing features.


The Mesosaurus framework creates work loads that can be configured to simulate
the behavior of other frameworks on a Mesos cluster.


We intend to come up with configurations that approximate Marathon, Chronos,
Hadoop, MPI, Storm, Spark, and many others. By running multiple instances of
Mesosaurus concurrently, it should be possible to simulate large production
systems comprising of several frameworks competing for resources. It is our goal
that Metrics from such runs can then be used for cluster and Mesos core
performance analysis.

Current Features

  • Poisson-distributed task arrival times.
  • Normal/Gauss-distributed task durations and resource consumptions.
  • Tasks that claim resource offers and
    use up computer resources in the amounts specified.
  • A configurable load factor for actual CPU load.
  • Automated provisioning of the task executor binary.
  • Configurable task failure rate.
    No manual installation steps on any slave nodes necessary.

Planned Features

  • Read in external traces from other systems and create tasks to simulate the
    recreation of past scenarios.
  • Store traces.
  • Real-time plotting of interesting metrics.


  1. Install Mesos on a cluster - or simply on a single machine
    if you just want to try it out. In any case, is easiest to follow the
    instructions at Mesosphere to do this.
  2. Download, install and run the latest version of Mesosaurus:

Building from Source

  1. Check out the latest source code from its git repository:
    git clone

  2. Build the task executor, which is written in C++.
    cd mesosaurus/task

  3. Download and install libraries that Mesosaurus depends on and
    translate the Scala source code to bytecode:

    sbt compile

  4. If you have a Mesos master running on your local machine
    you can simply execute Mesosaurus with default values for all settings:

    sbt run

  5. As a more complex example, you can run 10 tasks
    that take on average 1 second
    and arrive on average every 2 seconds
    on a Mesos installation with its master at a specified IP address and port:

    sbt "run -tasks 10 -duration 1000 -arrival 2000 -master"

Eclipse Support

  1. Install ScalaIDE for Eclipse.
  2. Install sbteclipse.
  3. To create an eclipse project that you can import into Eclipse
    for Mesosaurus development or simply for source code browsing:
    sbt eclipse
    This creates a file with the name ".project" in the Mesosaurus directory.
  4. Import the Mesosaurus project using the Import Wizard in Eclipse,
    indicating Existing Projects into Workspace and
    selecting your Mesosaurus directory as the base of your existing project.


Execute the Mesosaurus program just to peruse a list
of its available command line options:
sbt "run -h"

Coding Conventions

We try to follow the usual
Scala Style Guide,
but no TAB character is allowed anywhere in source code.

Docker Pull Command
Source Repository