/pbench

A benchmarking and performance analysis framework

Primary LanguageShellGNU General Public License v3.0GPL-3.0

Pbench

A Benchmarking and Performance Analysis Framework

The code base includes three sub-systems. The first is the collection agent or harness, pbench-agent, responsible for providing commands for running benchmarks across one or more systems, while properly collecting the configuration of those systems, their logs, and specified telemetry from various tools (sar, vmstat, perf, etc.).

The second sub-system included here is pbench-server, which is responsible for archiving result tar balls, indexing them, and unpacking them for display.

The third sub-system is the web server JS and CSS files used to display various graphs and results, and any other content generated by the background tasks, or by the pbench-agent during benchmark and tool post-processing steps.

How is it installed?

Instructions on installing pbench-agent, can be found in the PBench agent installation guide.

For Fedora, CentOS, and RHEL users, we have made available COPR builds for the pbench-agent, configtools, pbench-server, pbench-web-server and some benchmark and tool packages.

This assumes that somebody has already installed the server bits. The procedure to do that is described in the PBench Server Installation guide.

You can install the web-server subsystem on the machine where you run pbench from. That allows you to view the graphs before sending the results to the server, or even if there is no server to send the results to. See the PBench web server installation guide.

You might want to browse through the rest of the documentation.

How do I use pbench?

Refer to the PBench User Guide.

TL;DR? See TL;DR - How to set up pbench and run a benchmark of the PBench User Guide for a super quick set of introductory steps.

Where is the source kept?

The latest source code is at https://github.com/distributed-system-analysis/pbench.

Is there a mailing list for discussions?

Yes, we use Google Groups

Is there a place to track current and future work items?

Yes, we are using GitHub Issues and Pull Requests managed via Waffle.io for that.