Performance Benchmark

Environment

• Cloud provider: Equinix
• Nodes: 3 (each node is a master and also a worker)
• Storage: 1 SSD (Micron_5300_MTFD)

Benchmarking Tools

• Use kbench as the benchmarking tool.
• kbench enables --idle-prof which is harmful for the storage performance, so the --idle-prof needs to be removed before benchmarking.

Results

The baseline of the data disk was also measured using rancher/local-path-provisioner. The benchmarking results are in [Performance Investigation: kbench tab]

V1.2.4 - v1.4

RWO Volume

• Machine: Japan/m3.small.x86
• OS: Ubuntu 22.04 / 5.15.0-33-generic
• Network throughput between nodes (tested by iperf over 60 seconds): 15.0 Gbits/sec

RWX Volume

• share-manager Pod and workload Pod are not located on the same node

v1.5.0

• Machine: Japan/m3.small.x86
• OS: Ubuntu 22.04 / 5.15.0-33-generic
• Network throughput between nodes (tested by iperf over 60 seconds): 15.0 Gbits/sec

RWO Volume

RWX Volume

• share-manager Pod and workload Pod are not located on the same node

v1.6.0

• Machine: Dallas/m3.small.x86
• OS: Rocky Linux 9 / 5.15.0
• Network throughput between nodes (tested by iperf over 60 seconds): 25.0 Gbits/sec

RWO Volume

RWX Volume

• share-manager Pod and workload Pod are not located on the same node

Reference

• https://github.com/longhorn/longhorn/issues/4002
• https://github.com/longhorn/longhorn/issues/3665