vmprobe

2016-01-15

In April 2009 I wrote up a simple utility over a weekend called vmtouch. It helped me solve a few problems I was experiencing on the job and, most pressingly, let me run a series of experiments to satisfy my curiosity about how the filesystem page cache works. I have found vmtouch very useful over the past 7 or so years, and apparently a few other people have too.

My favourite aspect of vmtouch has always been that it lets you peek under the hood of your operating system and see what's actually happening. Not theoretically or from a bird's eye view, but in full gory detail, with your own real-life data.

Ever since writing vmtouch (and perhaps even earlier considering my work on nmap) I've tried to squeeze as much as I could out of the tools I use as a programmer, system administrator, and experimenter. Nothing fulfills me more professionally than cleverly solving difficult problems with incomprehensible one-liners consisting of strace, lsof, vmstat, and the rest of the unix zoo (glued together with perl, of course). If I have the time and motivation to package the solution up in a convenient and polished utility for others to use in the future, so much the better.

So, with no exaggeration whatsoever, it brings me tremendous pleasure to say that as of today I am in a position to research my ideas and polish up my solutions full time.

Without wasting any more words I'd like to announce vmprobe: a part research platform and part production tool. I'm not going to describe exactly what it is for right now — there will be plenty of time for that later — but the general idea is that we are going to hook low-level unix wizardry up to brilliant user interfaces.

If you are a developer, a sysadmin, a devops practitioner, a student, a hacker, a professional, or yes, especially an experimenter, I think you're going to like it.

Stay tuned!