Book Image

Distributed Computing with Python

Book Image

Distributed Computing with Python

Overview of this book

CPU-intensive data processing tasks have become crucial considering the complexity of the various big data applications that are used today. Reducing the CPU utilization per process is very important to improve the overall speed of applications. This book will teach you how to perform parallel execution of computations by distributing them across multiple processors in a single machine, thus improving the overall performance of a big data processing task. We will cover synchronous and asynchronous models, shared memory and file systems, communication between various processes, synchronization, and more.
Table of Contents (15 chapters)
Distributed Computing with Python
Credits
About the Author
About the Reviewer
www.PacktPub.com
Preface
Index

Running a Python job using HTCondor


This section assumes access to a cluster managed by the open source HTCondor job scheduler. The installation of HTCondor is not difficult (described in the administrator's manual available at https://research.cs.wisc.edu/htcondor/manual/), but it is outside the scope of this book.

HTCondor comes with a set of command-line tools that can be used to submit jobs to the cluster (condor_submit), view the status of any submitted job (condor_q), kill a job (condor_rm), and view the status of all the machines in the cluster (condor_status). There are many other tools—more than 60 in total; however, we will concentrate on the four main ones listed in this section.

Another way of interacting with an HTCondor cluster is using the Distributed Resource Management Application API (DRMAA), which comes with most (but not all) HTCondor installations and is packaged as a shared library (for example, libdrmaa.so on Linux).

DRMAA abstracts away most of the vendor specificity...