General requirements

Verify that all servers to be joined to the cluster meet the following general requirements.

Storage requirements

The following table lists the minimum and recommended storage requirements according to the disk roles (refer to About the storage cluster):

Disk role Quantity Disk size Type Endurance
System One disk per node

100 GB minimum

250 GB recommended

SATA/SAS HDD minimum

SATA/SAS SSD recommended

Metadata

One disk per node

Five disks recommended for one cluster

100 GB Enterprise-grade SSD with power loss protection 1 DWPD minimum
Cache

Optional

One SSD disk per 4-12 HDDs

100+ GB Enterprise-grade SSD with power loss protection and 75 MB/s sequential write performance per serviced HDD

1 DWPD minimum

10 DWPD recommended

Storage At least one per cluster

100 GB minimum

Unlimited size on a physical server; 10 TB maximum recommended inside a virtual machine

SATA/SAS HDD or enterprise-grade SATA/SAS/NVMe SSD with power loss protection 1 DWPD minimum

CPU and RAM reservations

The following table lists the amount of RAM and CPU cores that will be reserved on one node, according to the services you will use:

Service Management node Secondary node
RAM1 CPU cores2 RAM3 CPU cores4
System 4.5 GB 1 core 1.5 GB 1 core
Storage services: each disk with Metadata, Storage, or Cache role (any size)5 0.5 GB 0.2 cores 0.5 GB 0.2 cores
Compute6 Service 8 GB 1 core    
Each virtual machine 128 MB   128 MB  
Database cache up to 10% of node RAM      
Load balancer (add-on service) 1.5 GB 0.5 cores    
Kubernetes (add-on service) 1 GB 0.5 cores    
Metering (add-on service) 3 GB 1 core    
Backup Gateway7 1 GB 0.5 cores 1 GB 0.5 cores
S38 Each S3 gateway 256 MB 1 core 256 MB 1 core
Each OS service 256 MB 0.1 cores 256 MB 0.1 cores
Each NS service 512 MB 0.2 cores 512 MB 0.2 cores
NFS Service 4 GB 1 core 4 GB 1 core
Each share9 up to 9 GB up to 8 cores up to 9 GB up to 8 cores
iSCSI 1 GB 1 core 1 GB 1 core

These reserved values correspond to absolute minimum requirements. In general, the more resources you provide for your cluster, the better it works. All extra RAM is used to cache disk reads, while extra CPU cores increase the performance and reduce latency.

CPU and RAM limits

The following table lists the current RAM and CPU limits for Virtuozzo Hybrid Infrastructure servers:

Hardware Theoretical Certified
RAM 64 TB 1 TB
CPU 5120 logical CPUs10 384 logical CPUs11

CPU recommendations

  • The minimum CPU frequency for Virtuozzo Hybrid Infrastructure servers is 2.0 GHz. The recommended CPU frequency is at least 2.4 GHz.
  • CPU frequency affects the cluster performance. Higher CPU frequency reduces latency almost linearly, thus increasing the performance. If other CPU parameters are the same, higher CPU frequency is preferable to a larger number of CPU cores.
  • Nodes running the metadata service should have high CPU frequency, because this service is CPU intensive.
  • To improve erasure coding performance, it is recommended to use CPUs that support the AVX-512 instruction set, such as Intel Xeon Silver 4110, Intel Xeon Gold 5115, Intel Xeon Platinum 8171, or newer.

Network interface requirements

At least 2 x 10 GbE interfaces are recommended, for internal and external traffic; 25 GbE, 40 GbE, and 100 GbE are even better. Bonding is recommended. However, for external traffic, you can start with 1 GbE links, but they can limit cluster throughput on modern loads.