https://github.com/mesosphere/mesosaurus

Mesos task load simulator framework for (cluster and Mesos) performance analysis
https://github.com/mesosphere/mesosaurus

dcos dcos-orchestration-guild

Last synced: 3 months ago
JSON representation

Mesos task load simulator framework for (cluster and Mesos) performance analysis

• Host: GitHub
• URL: https://github.com/mesosphere/mesosaurus
• Owner: mesosphere
• License: apache-2.0
• Created: 2014-02-10T12:49:35.000Z (over 10 years ago)
• Default Branch: master
• Last Pushed: 2016-03-02T14:06:47.000Z (over 8 years ago)
• Last Synced: 2024-01-21T03:09:57.677Z (5 months ago)
• Topics: dcos, dcos-orchestration-guild
• Language: Scala
• Size: 98.6 KB
• Stars: 59
• Watchers: 171
• Forks: 13
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-mesos - Mesosaurus

README

        
# Mesosaurus

A benchmarking 

[framework](https://github.com/mesosphere/scala-sbt-mesos-framework.g8) 

for [Mesos](http://mesos.apache.org).

## Status

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

## Overview

The Mesosaurus framework creates work loads that can be configured to simulate 

the behavior of other frameworks on a Mesos cluster.

## Goals

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.

## Installation

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](http://mesosphere.io/downloads/) to do this.

2. Download, install and run the latest version of Mesosaurus:

    


   TODO

    


## Building from Source

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

    


    git clone https://github.com/mesosphere/mesosaurus.git

    


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

    


    cd mesosaurus/task

    make

    


3. Download and install libraries that Mesosaurus depends on and 

   translate the Scala source code to bytecode:

    


    cd mesosaurus/

    sbt compile

    


4. If you have a Mesos master running on your local machine,

   check there is entry in /etc/hosts:

     ` `

   then, you can simply execute Mesosaurus with default values for all settings:

    


    cd mesosaurus/

    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 127.0.0.1:5050"

    


## Eclipse Support

1. Install [ScalaIDE](http://scala-ide.org) for Eclipse.

2. Install [sbteclipse](https://github.com/typesafehub/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.


## Usage

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](http://docs.scala-lang.org/style/),

but no TAB character is allowed anywhere in source code.