Paper Title: Leveraging Linux's Native Storage Functionalities via Open-Source

Paper Abstract: The Linux kernel has a large set of very powerful storage functionalities such as LVM, thin provisioning, RAID, SSD as HDD caches, deduplication, NVMe-oF targets/initiators, and DRBD. They are all compatible on the data plane, but each brings its own control mechanism. We can make use of all of these tools to build and manage block storage volumes (replicated either synchronously or asynchronously) as part of a larger storage cluster. With the use of a management layer which integrates with OpenStack Cinder and Kubernetes Container Storage Interface (CSI), we can provide a fully open source stack which provides persistent storage to containers. This approach can be really powerful for IO-intensive workloads such as databases and works well both on hyper-converged infrastructure or on dedicated storage nodes.

Paper Author: David Hay, Automation Engineer, Lithia Motors

Author Bio: A long-time Linux system engineer, David Hay finds free and open source solutions to global problems as a Cluster Engineer at LINBIT. David started out with open source software back in the Linux 2.4 days, since then having planned and implemented countless clustered systems, leveraging HA and cloud technologies to great effect. When not liberating the enterprise world with free and open software, he spends his time tinkering with electronics and metalworking.