Environment Checklist

Before you install Milvus, check your hardware and software to see if they meet the requirements.

Install with Docker Compose Install on Kubernetes

Hardware requirements

Component	Requirement	Recommendation	Note
CPU	Intel CPU Sandy Bridge or later Apple M1 CPU	standalone: 8 core or more cluster: 16 core or more	Current version of Milvus does not support AMD CPUs.
CPU instruction set	SSE4.2 AVX AVX2 AVX-512	SSE4.2 AVX AVX2 AVX-512	Vector similarity search and index building within Milvus require CPU's support of single instruction, multiple data (SIMD) extension sets. Ensure that the CPU supports at least one of the SIMD extensions listed. See CPUs with AVX for more information.
RAM	standalone: 16G cluster: 64G	standalone: 32G cluster: 128G	The size of RAM depends on the data volume.
Hard drive	SATA 3.0 SSD or higher	NVMe SSD or higher	The size of hard drive depends on the data volume.

Software requirements

Operating system	Software	Note
macOS 10.14 or later	Docker Desktop	Set the Docker virtual machine (VM) to use a minimum of 2 virtual CPUs (vCPUs) and 8 GB of initial memory. Otherwise, installation might fail. See Install Docker Desktop on Mac for more information.
Linux platforms	Docker 19.03 or later Docker Compose 1.25.1 or later	See Install Docker Engine and Install Docker Compose for more information.
Windows with WSL 2 enabled	Docker Desktop	We recommend that you store source code and other data bind-mounted into Linux containers in the Linux file system instead of the Windows file system. See Install Docker Desktop on Windows with WSL 2 backend for more information.

Software	Version	Note
etcd	3.5.0	See additional disk requirements.
MinIO	RELEASE.2020-11-06T23-17-07Z
Pulsar	2.8.2

Additional disk requirements

Disk performance is critical to etcd. It is highly recommended that you use local NVMe SSDs. Slower disk reponse may cause frequent cluster elections that will eventually degrade the etcd service.

To test if your disk is qualified, use fio.

mkdir test-data
fio --rw=write --ioengine=sync --fdatasync=1 --directory=test-data --size=2200m --bs=2300 --name=mytest

Ideally, your disk should reach over 500 IOPS and below 10ms for the 99th percentile fsync latency. Read the etcd Docs for more detailed requirements.

What's next

If your hardware and software meet the requirements, you can:
- Install Milvus standalone with Docker Compose
- Install Milvus cluster with Docker Compose
See System Configuration for parameters you can set while installing Milvus.