When it comes to assessing fitness of purpose, even audited benchmarks are quite useless unless they incorporate failure testing alongside the load test. I helped develop the TPCx-HCI benchmark which mandates the simulation of a node failure.
Who cares about infrastructure benchmarking?
We have started seeing misaligned partitions on Linux guests runnning certain HDFS distributions. How these partitions became mis-aligned is a bit of a mystery, because the only way I know how to do this on Linux is to create a partition using old DOS format like this (using -c=dos and -u=cylinders) Continue reading
One way of categorizing Hyperconverged filesystems (or any filesystem really) is by how data is distributed across the nodes, and the method used to track/retrieve that data. The following is based on knowledge of the internals of Nutanix and publicly available information for the other systems.
Metadata
Characteristics
Implemented by
| Distributed | Distributed data & metadata | Nutanix | Hash | Random data distribution, hash-lookup (object store) | VSAN | Dedupe | Data stored in HA-Pairs, Lookup by fingerprint | Simplivity | Dedupe | Random data distribution, Lookup by fingerprint | Springpath/Hyperflex | Psuedo Distributed | Data stored in HA pairs, Unified namespace via redirection | NetApp C-Mode |
