Documentation

Hardware Checklist

Use the following checklist when planning the hardware configuration for a production, distributed MinIO deployment.

Considerations

When selecting hardware for your MinIO implementation, take into account the following factors:

  • Expected amount of data in tebibytes to store at launch

  • Expected growth in size of data for at least the next two years

  • Number of objects by average object size

  • Average retention time of data in years

  • Number of sites to be deployed

  • Number of expected buckets

Production Hardware Recommendations

The following checklist follows MinIO’s Recommended Configuration for production deployments. The provided guidance is intended as a baseline and cannot replace MinIO SUBNET Performance Diagnostics, Architecture Reviews, and direct-to-engineering support.

MinIO, like any distributed system, benefits from selecting identical configurations for all nodes in a given server pool. Ensure a consistent selection of hardware (CPU, memory, motherboard, storage adapters) and software (operating system, kernel settings, system services) across pool nodes.

Deployments may exhibit unpredictable performance if nodes have varying hardware or software configurations. Workloads that benefit from storing aged data on lower-cost hardware should instead deploy a dedicated “warm” or “cold” MinIO deployment and transition data to that tier.

MinIO does not provide hosted services or hardware sales

See our Reference Hardware page for a curated selection of servers and storage components from our hardware partners.

Description

Minimum

Recommended

Kubernetes worker nodes to exclusively service the MinIO Tenant.

4 workers per Tenant

8+ workers per Tenant

Dedicated Persistent Volumes for the MinIO Tenant.

4 PV per MinIO Server pod

8+ PV per MinIO Server pod

High speed network infrastructure.

25GbE

100GbE

Server-grade CPUs with support for modern SIMD instructions (AVX-512), such as Intel® Xeon® Scalable or better.

4 vCPU per MinIO Pod

8+ vCPU per MinIO Pod

Available memory to meet or exceed per-server usage by a reasonable buffer.

32GB of available memory per worker node

128GB+ of available memory per worker node

Important

The following areas have the greatest impact on MinIO performance, listed in order of importance:

Network Infrastructure

Insufficient or limited throughput constrains performance

Storage Controller

Old firmware, limited throughput, or failing hardware constrains performance and affects reliability

Storage (Drive)

Old firmware, or slow/aging/failing hardware constrains performance and affects reliability

Prioritize securing the necessary components for each of these areas before focusing on other hardware resources, such as compute-related constraints.

The minimum recommendations above reflect MinIO’s experience with assisting enterprise customers in deploying on a variety of IT infrastructures while maintaining the desired SLA/SLO. While MinIO may run on less than the minimum recommended topology, any potential cost savings come at the risk of decreased reliability, performance, or overall functionality.

Networking

MinIO recommends high speed networking to support the maximum possible throughput of the attached storage (aggregated drives, storage controllers, and PCIe busses). The following table provides a general guideline for the maximum storage throughput supported by a given physical or virtual network interface. This table assumes all network infrastructure components, such as routers, switches, and physical cabling, also supports the NIC bandwidth.

NIC Bandwidth (Gbps)

Estimated Aggregated Storage Throughput (GBps)

10Gbps

1.25GBps

25Gbps

3.125GBps

50Gbps

6.25GBps

100Gbps

12.5GBps

Networking has the greatest impact on MinIO performance, where low per-host bandwidth artificially constrains the potential performance of the storage. The following examples of network throughput constraints assume spinning disks with ~100MB/S sustained I/O

  • 1GbE network link can support up to 125MB/s, or one spinning disk

  • 10GbE network can support approximately 1.25GB/s, potentially supporting 10-12 spinning disks

  • 25GbE network can support approximately 3.125GB/s, potentially supporting ~30 spinning disks

Memory

Memory primarily constrains the number of concurrent simultaneous connections per node.

You can calculate the maximum number of concurrent requests per node with this formula:

\(totalRam / ramPerRequest\)

To calculate the amount of RAM used for each request, use this formula:

\(((2MiB + 128KiB) * driveCount) + (2 * 10MiB) + (2 * 1 MiB)\)

10MiB is the default erasure block size v1. 1 MiB is the default erasure block size v2.

The following table lists the maximum concurrent requests on a node based on the number of host drives and the free system RAM:

Number of Drives

32 GiB of RAM

64 GiB of RAM

128 GiB of RAM

256 GiB of RAM

512 GiB of RAM

4 Drives

1,074

2,149

4,297

8,595

17,190

8 Drives

840

1,680

3,361

6,722

13,443

16 Drives

585

1,170

2.341

4,681

9,362

The following table provides general guidelines for allocating memory for use by MinIO based on the total amount of local storage on the node:

Total Host Storage

Recommended Host Memory

Up to 1 Tebibyte (Ti)

8GiB

Up to 10 Tebibyte (Ti)

16GiB

Up to 100 Tebibyte (Ti)

32GiB

Up to 1 Pebibyte (Pi)

64GiB

More than 1 Pebibyte (Pi)

128GiB

Important

Starting with RELEASE.2024-01-28T22-35-53Z, MinIO preallocates 2GiB of memory per node in distributed setups and 1GiB of memory for a single-node setup.

Storage

Exclusive access to drives

MinIO requires exclusive access to the drives or volumes provided for object storage. No other processes, software, scripts, or persons should perform any actions directly on the drives or volumes provided to MinIO or the objects or files MinIO places on them.

Unless directed by MinIO Engineering, do not use scripts or tools to directly modify, delete, or move any of the data shards, parity shards, or metadata files on the provided drives, including from one drive or node to another. Such operations are very likely to result in widespread corruption and data loss beyond MinIO’s ability to heal.

MinIO recommends provisioning a storage class for each MinIO Tenant that meets the performance objectives for that tenant.

Where possible, configure the Storage Class, CSI, or other provisioner underlying the PV to format volumes as XFS to ensure best performance.

Ensure a consistent underlying storage type (NVMe, SSD, HDD) for all PVs provisioned in a Tenant.

Ensure the same presented capacity of each PV across all nodes in each Tenant server pool. MinIO limits the maximum usable size per PV to the smallest PV in the pool. For example, if a pool has 15 10TB PVs and 1 1TB PV, MinIO limits the per-PV capacity to 1TB.