Subscribe To Our newsletter
behind the scenes

Raspberry Tau: a Pi cluster
The Raspberry PI is a small ARM computer (hardware specifications in wiki, outline and FAQs). Of course, you can build a cluster with it!

Mirrored SAN vs. DRBD
Every now and then we get asked “why not simply use a mirrored SAN instead of DRBD”? This post shows some important differences.

Best Practice: Use Backup with your DRBD cluster!
We want to take an opportunity to explain LINBIT’s best practices in regards to DRBD and backup procedures.

“read-balancing” with 8.4.1+
DRBD 8.4.1 introduces a new feature: read-balancing, which is configured in the disk section of the configuration file(s). This feature enables DRBD to balance read

LINBIT participates in the German Cloud (“Deutsche Wolke”)
Deutsche Wolke (“German Cloud”) was founded to establish Federal Cloud Infrastructure in Germany. This infrastructure will provide additional legal and security protections for hosted data.

Monitoring: better safe than sorry…
Stumbling upon the Holy time-travellin’ DRBD, batman! blog post there’s only one thing to be said … Be strict in what you emit, liberal in

Maximum volume size on DRBD
From time to time we get asked things like this: I want to use a 100TiB volume with DRBD, is that supported”? The biggest public

Trust, but verify
DRBD tries to ensure data integrity across different computers, and it’s quite good at it. But, as per the old saying Trust, But Verify[1. attributed

DRBD and the sync rate controller (8.3.9 and above)
The sync-rate controller is used for controlling the used bandwidth during resynchronization (not normal replication); it runs in the SyncTarget state, ie. on the (inconsistent)

DRBD causes too much CPU-load
The TL;DR version: don’t use data-integrity-alg in a production setup.

“al-extents” explained
There is quite a bit of confusion about the DRBD configuration value al-extents (activity log extents), so here’s another shot at explaining it.

Make the kernel start write-out earlier
Similar to the recent post about setting the vm.min_free_kbytes value there’s another sysctl that might improve the behaviour: the dirty ratio.

DRBD resources need different monitor intervals
As briefly mentioned in Pacemaker Explained, DRBD devices need two different values set for their monitor intervals: primitive pacemaker-resource-name ocf:linbit:drbd \ params drbd_resource=”drbd-resource” \ op

Increase vm.min_free_kbytes for better OOM resistance
Depending on your setup and your workload (eg. within a virtual machine with little memory and much I/O) you could get into the situation that