ioprof, blktrace, and blkparse

Understanding how applications perform I/O is important not only because of the volume of data being written and read, but because the performance of some applications is dependent on how I/O is conducted. In this article we profile I/O at the block layer to help you make the best storage decisions.

Tool Your HPC Systems for Data Analytics

As data analytics workloads become more common, HPC administrators need to assess their hardware, software, and processes.

Graphite

Graphite converts confusing columns of time series data into handy diagrams, showing trends in operating system and application metrics at a glance.

A Better Builder

Developers fed up with cryptic Makefiles should take a look at the new Meson build system, which is simple to operate, offers scripting capabilities, integrates external test tools, and supports Linux, Windows, and Mac OS X.

Iron Ore

Google Compute Engine removes the technical and financial headaches of maintaining server, networking, and storage.

Parallel Shells

The most fundamental tool needed to administer an HPC system is a parallel shell, which allows you to run the same command on a series of nodes. In this article, we look at pdsh.

Nerve Center

Ganglia is probably the most popular monitoring framework and tool, in that HPC, Big Data, and even cloud systems are using it. In this article, we show you how to install and configure Ganglia and get it up and running on a simple two-node system.

Metadata for Your Data

Understanding the proliferation of data in your filesystem is key to being an administrator. Understanding file sizes and file ages and their distribution helps you tune filesystems for performance and develop policies for data management.

Storage in the Cloud

When building cloud environments, you need more than just a scalable infrastructure; you also need a high-performance storage component. We look at Ceph, a distributed object store and filesystem that pairs well in the cloud with OpenStack.

Combining Directories on a Single Mountpoint with SSHFS-MUX

With some simple tuning, SSHFS performance is comparable to NFS almost across the board. In an effort to get even more performance from SSHFS, we examine SSHFS-MUX, which allows you to combine directories from multiple servers into a single mountpoint.