Extreme Persistent Disk

Linux Windows

For high-end performance-critical applications, use Extreme Persistent Disk volumes.Extreme Persistent Disk volumes feature higher maximum IOPS and throughput thanother Persistent Disk volumes, and let you provision IOPS and capacityseparately. Extreme Persistent Disk is available in allzones.

When you create an Extreme Persistent Disk, you can provision 2,500 to 120,000 IOPS.If you need more than 125,000 IOPS, we recommendGoogle Cloud Hyperdisk.Hyperdisk offers the highest IOPS and throughput in Compute Engineand is available on the latest machine types.

This document explains several restrictions of using Extreme Persistent Disk,considerations for reaching maximum possible performance levels, and how to provision IOPSusing the Google Cloud console, the gcloud CLI orREST.

Before you begin

Machine shape support

You can use N2, M2 and M3 machine series with Extreme Persistent Disk. N2 VMsrequire at least 64 vCPUs.The following is list of machine types that support themaximum performance levels offered by Extreme Persistent Disk:

  • N2:

    • n2-*-64
    • n2-*-80
    • n2-*-96
    • n2-*-128

  • M2:

    • m2-*-208
    • m2-*-416

  • M3:

    • m3-*-32
    • m3-*-64

All other machine types are not supported for production use.If you'd like to use an unsupported machine type, we recommendHyperdisk instead.

N2 VMs with 64 or 80 vCPUs require the Intel Ice Lake CPU platform to reach thestated performance limits. N2 VMs using Intel Cascade Lake CPU platforms willhave slightly lower performance. For more information, seesetting the minimumCPU platform for VM instances.

Performance limits for Extreme Persistent Disk

The following table lists the performance limits for the supported machine types.

Machine typevCPU countMaximum IOPSMaximum read throughput (MB/s)Maximum write throughput (MB/s)
N264 or 80 on Intel Cascade Lake120,0002,2002,200
64 or more on Intel Ice Lake120,0004,0003,000
M220840,0002,2001,200
41640,0002,2001,200
M364 or less40,0002,2001,200
12880,0002,2001,700

Performance limits and workload patterns

To reach the maximum performance levels offered by Extreme Persistent Disk volumes,you must consider the following workload parameters:

  • I/O size: Maximum IOPS limits assume that you are using an I/O size of 4or 8 KB. Maximum throughput limits assume that you are using an I/O size of 1MB.
  • Queue length: Queue length is the number of pending requests for apersistent disk. To reach maximum performance limits, you must tune yourqueue length according to the I/O size, IOPS, and latency sensitivity of yourworkload. Optimal queue length varies for each workload, but typically shouldbe larger than 128.
  • Working set size: Working set size is the amount of data of a disk beingaccessed within a short period of time. To achieve optimal performance, limitworking set sizes to less than 1.5 TB.
  • Concurrent use of other persistent disks: Extreme Persistent Disk volumes sharethe per-VM maximum IOPS and throughput limits with all other persistent disksattached to the same VM. When monitoring the performance of your ExtremePersistent Disk volumes, take into account any I/O requests that you are sendingto other disks attached to the same VM.

Other restrictions

  • Extreme Persistent Disk volumes are zonal only. You can't create regional ExtremePersistent Disks.
  • You cannot attach multiple VM instances in read-only mode to an Extreme Persistent Diskvolume.
  • You cannotcreate an image or machine imagefrom an extreme persistent disk.
  • You can resize an Extreme Persistent Disk only once in a 6 hour period.

Throughput

For Extreme Persistent Disk volumes, throughput scales with the number of IOPS youprovision at a rate of 256 KB of throughput per I/O. However,throughput is ultimately capped by per-instance limits that depend on the numberof vCPUs on the VM instance to which your extreme disks are attached.

Throughput for Extreme Persistent Disk volumes isn't full duplex. The maximumthroughput limits listed in this document apply to the sum total of read andwrite throughput.

Provisioning IOPS

To provision IOPS to match your workload requirements, do the following:

  1. Note the IOPS requirement of your workload.
  2. Determine the IOPS required to fulfill the throughput requirements of your workload.
    • Required IOPS = throughput in KB per second / 256
  3. Set the provisioned IOPS to the larger of the two numbers.

Console

  1. Create a new persistent disk.
  2. UnderDisk type, selectExtreme persistent disk.
  3. UnderProvisioned IOPS, select the maximum IOPS limit in the rangeof 2,500 to 120,000 IOPS. There is a cost associated with theprovisioned IOPS.

gcloud

Use thegcloud compute disks create commandto create a new disk and include the following flags:

gcloud compute disks createDISK_NAME \  --size=DISK_SIZE \  --type=pd-extreme \  --provisioned-iops=IOPS_LIMIT

Replace the following:

  • DISK_NAME: the name of the new disk
  • DISK_SIZE: the size, in GB, of the new disk. Thedefault disk size for Extreme Persistent Disk volumes is 1,000 GB.
  • IOPS_LIMIT: the maximum IOPS limit inthe range of 2,500 to 120,000 IOPS. There is a cost associated with theprovisioned IOPS.

REST

Use thedisks.insert methodto create a new disk and include the following flags:

POST https://compute.googleapis.com/compute/v1/projects/PROJECT_ID/zones/ZONE/disks{ "name": "DISK_NAME", "type": "zones/ZONE/diskTypes/pd-extreme" "provisionedIops": "IOPS_LIMIT"}

Replace the following:

  • PROJECT_ID: your project ID
  • ZONE: the target zone for the disk
  • DISK_NAME: a name for the disk
  • IOPS_LIMIT: the maximum IOPS limit inthe range of 2,500 to 120,000 IOPS. There is a cost associated with theprovisioned IOPS.

What's next?

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-12-15 UTC.