elbencho

Free plan LinuxMacSelf-hostedWindows

What elbencho is

elbencho is a free distributed storage benchmark for measuring latency, throughput, and IOPS across file systems, object stores, block devices, and GPU storage. It supports local and shared storage through distributed service mode, with live statistics showing system behavior under load. GPU data-transfer tests can use Nvidia CUDA or GPUDirect Storage. The tool can export results as CSV or JSON and offers aggregate results for the first and last I/O threads to finish. An option verifies data integrity.

Optional S3 support uses the AWS SDK for C++, and NVMe-oF initiator support can be enabled with SPDK. The README includes Slurm and Kubernetes examples, plus instructions for building on macOS with Homebrew. Downloads include Linux packages and static executables for amd64/x86_64 and arm64/aarch64, as well as a Windows build with required DLLs. Static Linux executables omit GPU support; the release page recommends a source build or GPU-enabled container for that capability. The repository lists GPL-3.0 as its license.

Who it suits

elbencho suits users measuring storage throughput, latency, or IOPS for one or multiple clients, including GPU data-transfer testing for deep-learning workloads.

What it does well

Measures latency, throughput, and IOPS.
Supports distributed testing of local and shared storage.
Exports benchmark results as CSV or JSON.
Includes a data integrity verification option.

What to know first

Static Linux executables do not include GPU support.
S3 support is not enabled by default in source builds.

Limits

The static Linux executable excludes GPU support, and source builds need S3_SUPPORT=1 to enable S3 support.

Plans

Plan	Billed and limits	Price
elbencho	GPL-3.0 · distributed storage benchmarking · Linux and Windows downloads	Free

As github.com lists them, read 9 Oct 2026. The maker's own page has the final word.

Getting started

Open the elbencho GitHub project page.
Choose a Linux package or static executable, or the Windows build with its required DLLs.
For macOS, follow the documented Homebrew build route.
Build from source with S3_SUPPORT=1 if you need S3 support.
Use the README examples for Slurm or Kubernetes environments as applicable.

Verdict

elbencho offers distributed benchmarking across several storage types, with live statistics and optional GPU testing. Users needing GPU support should note the limitation of the static Linux executables.

Questions

How much does elbencho cost?

The listed plan is free at 0.00 USD.

Which operating systems can run it?

Platforms include Linux, Windows, and macOS. Linux packages and executables and a Windows build are listed; macOS build instructions use Homebrew.

Can it benchmark GPU storage?

Yes. GPU storage access tests can use Nvidia CUDA or GPUDirect Storage. The static Linux executable does not include GPU support.

Can results be exported?

Yes. Results can be output as CSV for charts.

Is elbencho open source?

Yes. The repository is licensed under GPL-3.0.

Does it support S3 and NVMe-oF?

Optional S3 support is based on the AWS SDK for C++, and NVMe-oF initiator support can be enabled using SPDK. S3 support is not enabled by default in source builds.

Facts from elbencho's own pages

Benchmark metrics: It benchmarks latency, throughput, and IOPS across file, object, and block storage. · github.com, 9 Oct 2026
CLI or automation: Yes · github.com, 23 Sept 2026
Cluster use: The README links to example usage for Slurm and Kubernetes environments. · github.com, 9 Oct 2026
Custom test profiles: Yes · github.com, 23 Sept 2026
Data integrity: The tool has an option for data integrity verification. · github.com, 9 Oct 2026
Distributed mode: It supports local and shared storage through distributed service mode. · github.com, 9 Oct 2026
Download limitation: The Linux static executable does not include GPU support; the release page recommends building from source or using a GPU-enabled container for that capability. · github.com, 9 Oct 2026
Downloads: The releases page lists Linux packages and static executables for amd64/x86_64 and arm64/aarch64, plus a Windows build with required DLLs. · github.com, 9 Oct 2026
Free plan: Yes · github.com, 23 Sept 2026
GPU features: GPU data transfer tests can use Nvidia CUDA or GPUDirect Storage (GDS). · github.com, 9 Oct 2026
GPU support: GPU storage access tests can use Nvidia CUDA or GPUDirect Storage (GDS). · github.com, 9 Oct 2026
Integrity: A data integrity verification option is available. · github.com, 9 Oct 2026
Intended users: The README highlights benchmarking for users who need storage throughput and IOPS results for single or multiple clients, including GPU data-transfer tests for deep-learning workloads. · github.com, 9 Oct 2026
License: The GitHub repository lists the GPL-3.0 license. · github.com, 9 Oct 2026
License and support: The repository is licensed under GPL-3.0, and the README invites questions and comments by email. · github.com, 9 Oct 2026
Live statistics: The tool provides live statistics showing system behavior under load. · github.com, 9 Oct 2026
macOS: The README documents building elbencho on macOS using Homebrew. · github.com, 9 Oct 2026
Maintainer: GitHub identifies Sven Breuner as the elbencho maintainer and lists Germany as his location. · github.com, 9 Oct 2026
Measurements: It benchmarks storage latency, throughput, and IOPS. · github.com, 9 Oct 2026
Operating systems: Linux,Windows,macOS · github.com, 23 Sept 2026
Purpose: elbencho is a distributed storage benchmark for file systems, object stores, and block devices, with support for GPUs. · github.com, 9 Oct 2026
Result export formats: CSV,JSON · github.com, 23 Sept 2026
Results: It can output CSV results for charts and offers aggregate results for the first and last I/O threads to finish. · github.com, 9 Oct 2026
S3 build requirement: S3 support is not enabled by default when building from source and can be enabled with S3_SUPPORT=1. · github.com, 9 Oct 2026

Where elbencho stands on Freedom251

PC Benchmark Software#7 of 73
PC benchmark tools#10 of 70