I find myself working on the move a lot more recently and I often have to deal with poor terminal emulators, iffy connectivity and sometimes I need resume my work on another machine entirely. As such I am trying out tmux as a way of persisting my working environment between sessions, supporting multiple tabs for when my emulator lacks it (Looking at you PuTTY, Git Bash) and lastly allowing me to resume my work on another desktop.

Log monitoring implies using technology to avoid reading every single log message, with the benefit of catching more interesting events than if you were to read every single line!

In Robinhood NoSQL I experimented with porting the Robinhood database from Elasticsearch, it being a commonly-used NoSQL database with specialisation in behaving like a Search Engine. Having ingested the ENTRIES table I now need to augment the records with filepaths from ANNEX_INFO, as I found out previously:

Robinhood provides indexing, search and management capabilities to computing centres with massive high-performnace filesystems, namely Lustre.

It does this by scanning every file on the filesystem as efficiently as possible to initially populate its MySQL/MariaDB relational database, then it continuously listen for changelogs coming from Lustre to keep its state in-line with reality.

Following on from bashrc, here is a snapshot and explaination of my .motd

Here’s a snapshot of my .bashrc, I put this together to normalise my environment; which is particularly useful when working across CentOS/RHEL 6/7, SLES11/12 & Debian/Ubuntu.

I’ll overexplain some lines and underexplain others, depending on how interesting they are.

The Lustre community supports recent point-releases of RHEL/CentOS but those patches don’t seem to come back into existing Lustre releases, since those releases don’t officially support later kernels. I installed client 2.10 thinking it had the best chance of working but encountered huge numbers of errors when compiling!