> For the complete documentation index, see [llms.txt](https://docs.platform9.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.platform9.com/private-cloud-director/getting-started/configuration-maximums.md).

# Configuration Maximums

This page lists the configuration limits Platform9 has validated for Private Cloud Director (PCD). Stay at or below these values to ensure full Platform9 support.

**These are tested limits, not the architectural maximums of the underlying components.** The individual components often support higher values. If your requirements exceed the published values, contact Platform9 support for guidance.

Actual achievable limits depend on hardware selection, workload characteristics, and network topology, and it may not be possible to hit every maximum simultaneously. Consult the individual subsystem sections (compute, network, storage) when sizing your environment. To scale beyond the per-Region maximums, deploy multiple Regions.

## Virtual Machine Maximums

Limits that apply to a single VM running on PCD.

### Storage <a href="#storage" id="storage"></a>

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Virtual disks per VM (root + attached volumes)</td><td>8</td></tr><tr><td>Boot volume size</td><td>4TB</td></tr><tr><td>Ephemeral disk size</td><td>No hard maximums exist</td></tr></tbody></table>

### Networking <a href="#networking" id="networking"></a>

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Security groups per port</td><td>10</td></tr><tr><td>Security group rules per security group</td><td>100</td></tr><tr><td>Floating IPs per VM</td><td>50</td></tr></tbody></table>

## Hypervisor Host Maximums

Limits that apply to a single PCD hypervisor host.

### Host Compute

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Maximum vCPU oversubscription ratio</td><td>16×</td></tr><tr><td>Maximum RAM oversubscription ratio</td><td>~1.5×</td></tr></tbody></table>

### Region Maximums <a href="#region-maximums" id="region-maximums"></a>

Limits that apply to a single PCD Region (the management plane controlling a set of hypervisors). Customers requiring scale beyond these values should plan for multiple Regions.

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Clusters per Region</td><td>8</td></tr><tr><td>Hypervisors per Region</td><td>591 active; 629 total registered</td></tr><tr><td>VMs per Region</td><td>9,673 powered on VMs</td></tr><tr><td>Tenants per Region</td><td>74</td></tr><tr><td>Users per Region</td><td>136</td></tr><tr><td>Host Aggregates per Region</td><td>9</td></tr><tr><td>Flavors per Region</td><td>15</td></tr><tr><td>Images per Region</td><td>7</td></tr><tr><td>Concurrent VM create operations per Region</td><td>50</td></tr><tr><td>Concurrent VM migrate operations per Region</td><td>5</td></tr></tbody></table>

## High Availability (VM HA) and DRR Maximums

Limits that apply to PCD VM HA clusters.

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Hypervisors per cluster</td><td>100</td></tr></tbody></table>

## Networking Maximums

Limits that apply to the software-defined networking layer.

### Networks and Subnets

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Tenant networks per Region</td><td>14</td></tr><tr><td>Subnets per Region</td><td>13</td></tr><tr><td>Subnets per network</td><td>100</td></tr><tr><td>Ports per Region</td><td>19,992</td></tr><tr><td>Ports per network</td><td>10,000</td></tr></tbody></table>

### Addressing and Isolation

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Security groups per Region</td><td>450</td></tr><tr><td>VLAN ID range per physical network</td><td>-</td></tr><tr><td>VXLAN / Geneve tunnel endpoints per Region</td><td>591</td></tr></tbody></table>

### Layer 2 Networks <a href="#layer-2-networks" id="layer-2-networks"></a>

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Ports per Layer 2 network</td><td>500</td></tr></tbody></table>

## Block Storage Maximums <a href="#block-storage-maximums" id="block-storage-maximums"></a>

Limits that apply to the block storage service.

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>Volumes per Region</td><td>10,000</td></tr><tr><td>Volumes per tenant</td><td>10,000</td></tr><tr><td>Backends per Region</td><td>6</td></tr><tr><td>Volume types per Region</td><td>6</td></tr></tbody></table>

## Tenant Maximums <a href="#tenant-maximums" id="tenant-maximums"></a>

Default quotas applied to each tenant.

<table data-header-hidden="false" data-header-sticky><thead><tr><th>Criteria</th><th>Value</th></tr></thead><tbody><tr><td>VMs per tenant</td><td>10,000</td></tr><tr><td>vCPUs per tenant</td><td>10,000</td></tr><tr><td>RAM per tenant</td><td>8,000 GB</td></tr><tr><td>Volumes per tenant</td><td>10,000</td></tr><tr><td>Volume storage per tenant</td><td>10,000 GB</td></tr><tr><td>Networks per tenant</td><td>100</td></tr><tr><td>Routers per tenant</td><td>10</td></tr><tr><td>Floating IPs per tenant</td><td>50</td></tr><tr><td>Security groups per tenant</td><td>500</td></tr><tr><td>Key pairs per user</td><td>100</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.platform9.com/private-cloud-director/getting-started/configuration-maximums.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.