Replicated Storage with Shared Disk Semantics
Philipp Reisner, Lars Ellenberg · 2007
Errata: edited the Concurrent Write Detection Algorithm to match reality. Original paper: 18th September 2005, Proceedings of the 12th International Linux System Technology Conference. DRBD is a well established Linux software component to build HA (high availability) clusters out of common off-the-shelf hardware. DRBD’s key point is to replace storage systems by sharednothing networked mirroring. The most outstanding new feature is certainly our new shared disk mode, i.e. support for shareddisk file systems and other storage-aware applications. Provided that you use one of OpenGFS, GFS, OCFS2, this means that applications have read and write access to the mirrored data set on both nodes at the same time, since you can mount the storage on both peers simultanieously. Besides that, DRBD 8 supports effective resource level fencing. It prevents the divergence of the nodes’ copies of the data when DRBD’s communication path fails. Although DRBD has been widely used and under active development for 5 years now, it turned out that the method to determine the node with the up-to-date data was suboptimal. It was replaced by a new scheme based on UUIDs. This new scheme also works correctly in multi-node setups.