vmstat_plotter

Scratching that vmstat plotting itch


I’ve been working on an article around vmstat-like tools and I started looking for ways to plot the data. There are some reasonable articles on using something like awk and gnuplot to create plots but I wanted something a little more self-contained that would produce a quick report with all of the data plotted. I did see one tool that was on-line only (you had to upload your data) but that was too much of a pain to use, so in true Clusterbuffer fashion I wrote my own.

It’s not a sophisticated tool by any stretch – it’s just some Python code to parse the data and plot it using matplotlib. Go to this page to read more about it and scroll down to the bottom to download the code. You can also see a simple example here.

Please read through the write-up since there are some limitations to the code that require vmstat to be run with certain flags. There are also vmstat options that it can’t plot because the output is not time dependent.

Enjoy!

Advertisements

NFSiostat_plotter V4

I made an update to nfsiostat_plotter_v3 so that the iostat information, which is used for gathering the CPU usage, is optional. This means you don’t have to run iostat while you run nfsiostat. But it also means you won’t get to see the CPU usage plots.

Please go to this page for more details

IOSTAT Plotter V2 – Update

I’ve been updating nfsiostat_plotter and in the process I found a few bugs in iostat_plotter V2.

The first bug was in the way it kept time. If the time stamp ended in “PM” the code adds 12 hours so everything is based on a 24 hour clock. The problem is that if the iostat output is run just after noon, the time reads something like “12:49 PM” which then becomes 24:29. This bug has been fixed.

The second bug was in the plotting routines when doing “combined” plots where all devices are plotted on the same graph. It’s hard to explain but when there two or three plots, one above the other, sometimes the grid didn’t get plotted. And/or one of the graphs was longer than the others. This has been corrected (I hope).

The new version can be found here. The code has the same name as before (sorry about that). Just download the code and run it like you did before.