RetroSearch Browse

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from http://cloud.google.com/compute/docs/disks/hyperdisk-perf-limits below:

Performance limits for machine series that support Hyperdisk | Compute Engine Documentation

Skip to main content Performance limits for machine series that support Hyperdisk

Stay organized with collections Save and categorize content based on your preferences.

This document lists the performance limits for machine types that support Google Cloud Hyperdisk. For a detailed discussion of how Hyperdisk performance works, see About Hyperdisk performance.

For Persistent Disk performance limits, see Performance limits by machine type for Persistent Disk.

In this document, machine types are denoted in this format: M-*-N, where:

M is the machine series, for example, C3
* represents all memory and CPU configurations, for example, standard or highcpu
N is the number of vCPUs, CPUs, or the GPU designation, for example, 22 for an instance with 22 vCPUs, or 8g for an instance with 8 GPUs

This format includes the following machine types, wherever available:

bare metal machine types (*-metal)
machine types that come with attached Local SSD disks (*-lssd, *-standardlssd, or *-highlssd).

For example, c3-*-176 refers to all C3 machine types with 176 vCPUs, namely c3-standard-176, c3-highcpu-176, c3-highmem-176, and c3-standard-176-lssd. For more information, see Compute Engine terminology.

Determine which limits apply

The performance limit that applies to your scenario depends on the instance's machine type, and the number and type of Hyperdisk volumes you attached to the instance.

Choose from the following scenarios to determine which limits to consult.

You're using multiple Hyperdisk types with the same instance and you want to know the maximum performance for all the disks attached to the instance.

For example, suppose you have 1 Hyperdisk Balanced volume and 2 Hyperdisk Throughput volumes attached to a c3-standard-22 virtual machine (VM) instance. The applicable performance limits are listed in the Performance limits by machine type section of this document.
You attached one or more Hyperdisk volumes of the same type to an instance and you want to know the maximum performance all the volumes can reach.

For example, you have 3 Hyperdisk Balanced volumes attached to a c3-standard-22 VM. The applicable performance limits for the 3 volumes are listed in the Performance limits by Hyperdisk type section of this document.

Performance limits by machine type

If you use different Hyperdisk types with a single instance, the following table lists the maximum performance you can expect. This limit is shared among all Hyperdisk and, if supported, Persistent Disk volumes attached to the instance. To learn more about how these limits work, see How instance performance limits affect performance.

The performance limits also apply to custom N2, N2D, and N4 machine types.

Select a machine series to display the performance limits for its machine types.

Instance machine type Maximum IOPS Maximum throughput (MiB/s) A2 a2-ultragpu-1g 50,000 1,800 a2-ultragpu-2g 100,000 2,400 a2-ultragpu-4g 200,000 3,750 a2-ultragpu-8g 350,000 5,000 A3 (A3+H100 and A3+H200) a3-edgegpu-8g 400,000 8,000 a3-highgpu-1g 120,000 1,800 a3-highgpu-2g 160,000 2,400 a3-highgpu-4g 350,000 5,000 a3-highgpu-8g 400,000 8,000 a3-megagpu-8g 400,000 8,000 a3-ultragpu-8g¹ 500,000 10,000 A4¹ a4-highgpu-8g 500,000 10,000 A4X¹ a4x-highgpu-4g 500,000 10,000 C3 c3-*-4 25,000 400 c3-*-8 50,000 800 c3-*-22 120,000 1,800 c3-*-44 160,000 2,400 c3-*-88 350,000 5,000 c3-*-176 500,000 10,000 c3-*-192 500,000 10,000 C3D c3d-*-4 25,000 400 c3d-*-8 50,000 800 c3d-*-16 75,000 1,200 c3d-*-30 75,000 1,200 c3d-*-60 350,000 5,000 c3d-*-90 350,000 5,000 c3d-*-180 350,000 5,000 c3d-*-360 350,000 5,000 C4¹ c4-*-2¹ 50,000 400 c4-*-4¹ 50,000 400 c4-*-8¹ 50,000 800 c4-*-16¹ 100,000 1,600 c4-*-24¹ 100,000 1,600 c4-*-32¹ 100,000 1,600 c4-*-48¹ 160,000 2,400 c4-*-96¹ 350,000 5,000 c4-*-144¹ 350,000 5,000 c4-*-192¹ 500,000 10,000 c4-*-288¹ 500,000 10,000 C4A c4a-*-1 25,000 400 c4a-*-2 50,000 800 c4a-*-4 50,000 800 c4a-*-8 50,000 1,000 c4a-*-16 80,000 1,600 c4a-*-32 120,000 2,400 c4a-*-48 160,000 3,300 c4a-*-64 350,000 4,400 c4a-*-72 350,000 5,000 C4D¹ c4d-*-2 ¹ 22,500 400 c4d-*-4 ¹ 50,000 400 c4d-*-8 ¹ 50,000 800 c4d-*-16 ¹ 75,000 1,200 c4d-*-32 ¹ 75,000 1,600 c4d-*-48 ¹ 75,000 1,600 c4d-*-64 ¹ 350,000 5,000 c4d-*-96 ¹ 350,000 5,000 c4d-*-192 ¹ 350,000 5,000 c4d-*-384 ¹ 500,000 10,000 G2 g2-standard-4 15,000 800 g2-standard-8 19,200 1,200 g2-standard-12 28,800 1,800 g2-standard-16 38,400 2,400 g2-standard-24 38,400 2,400 g2-standard-32 60,000 2,400 g2-standard-48 60,000 2,400 g2-standard-96 100,000 2,400 G4 (Preview) g4-standard-48 75,000 1,600 g4-standard-96 350,000 5,000 g4-standard-192 350,000 5,000 g4-standard-384 500,000 10,000 H3 h3-standard-88 15,000 240 M1 m1-ultramem-40 60,000 1,200 m1-ultramem-80 100,000 4,000 m1-megamem-96 100,000 4,000 m1-ultramem-160 100,000 4,000 M2 m2-*-208 100,000 4,000 m2-*-416 100,000 4,000 M3 m3-*-32 160,000 2,400 m3-*-64 350,000 5,000 m3-*-128 450,000 7,200 M4¹ m4-*-56¹ 160,000 2,400 m4-*-112¹ 350,000 5,000 m4-*-224¹ 500,000 10,000 N2 n2-*-2 15,000 240 n2-*-4 15,000 240 n2-*-6 15,000 240 n2-*-8 30,000 800 Custom N2 machine types with 10-14 vCPUs,
such as n2-*-10 and n2-*-12 30,000 800 n2-*-16 60,000 1,200 Custom N2 machine types with 18-30 vCPUs,
such as n2-*-18, n2-*-24, and n2-*-30 60,000 1,200 n2-*-32 120,000 1,800 Custom N2 machine types with 36-44 vCPUs,
such as n2-*-36, n2-*-40, and n2-*-44 120,000 1,800 n2-*-48 120,000 2,400 Custom N2 machine types with 36-44 vCPUs,
such as n2-*-36, n2-*-40, and n2-*-44 120,000 2,400 n2-*-80 160,000 5,000 n2-*-96 160,000 5,000 n2-*-128 160,000 5,000 N2D n2d-*-2 800 200 n2d-*-4 960 240 n2d-*-8 3,200 800 n2d-*-16 4,800 1,200 n2d-*-32 7,200 1,800 n2d-*-48 9,600 2,400 n2d-*-64 9,600 2,400 n2d-*-80 9,600 2,400 n2d-*-96 9,600 2,400 n2d-*-128 9,600 2,400 n2d-*-224 9,600 2,400 N4 n4-*-2 15,000 240 n4-*-4 15,000 240 n4-*-6 15,000 240 n4-*-8 80,000 480 Custom N4 machine types with 10-14 vCPUs,
such as n4-*-10, n4-*-12, and n4-*-14 80,000 1,200 n4-*-16 80,000 1,200 Custom N4 machine types with 18-30 vCPUs,
such as n4-*-18, n4-*-24, and n4-*-30 80,000 1,200 n4-*-32 100,000 1,600 Custom N4 machine types with 34-46 vCPUs,
such as n4-*-34, n4-*-42, and n4-*-46 100,000 1,600 n4-*-48 160,000 2,400 Custom N4 machine types with 50-62 vCPUs,
such as n4-*-50, n4-*-58, and n4-*-62 160,000 2,400 n4-*-64 160,000 2,400 Custom N4 machine types with 66-78 vCPUs,
such as n4-*-66, n4-*-72, and n4-*-78 160,000 2,400 n4-*-80 160,000 2,400 T2D t2d-*-1 800 200 t2d-*-2 800 200 t2d-*-4 960 240 t2d-*-8 3,200 800 t2d-*-16 4,800 1,200 t2d-*-32 7,200 1,800 t2d-*-48 9,600 2,400 t2d-*-60 9,600 2,400 X4 x4-*-960 400,000 10,000 x4-*-1440 400,000 10,000 x4-*-1920 400,000 10,000 Z3 z3-*-14
z3-*-16 100,000 1,600 z3-*-22 120,000 1,800 z3-*-32
z3-*-44 160,000 2,400 z3-*-88 350,000 5,000 z3-*-176 350,000 5,000 z3-*-192 500,000 10,000

Also offers steady state performance. For these limits, see Performance limits for machine types with steady state performance.

Performance limits for machine types with steady state performance

Certain machine types offer steady state performance, a minimum performance level that the instance can sustain. The steady state performance is shared between all volumes attached to the instance. For more information, see Steady state performance.

The following table lists the steady state performance limits for the available machine types. If the steady state and maximum performance limits are the same, then the machine type can sustain this performance level in most cases.

Instance machine type Steady state IOPS Maximum IOPS Steady state
throughput (MiB/s) Maximum throughput (MiB/s) A3+H200 a3-ultragpu-8g 500,000 500,000 10,000 10,000 A4 a4-highgpu-8g 500,000 500,000 10,000 10,000 A4X a4x-highgpu-4g 500,000 500,000 10,000 10,000 C4 c4-*-2 6,200 50,000 120 400 c4-*-4 12,500 50,000 240 400 c4-*-8 25,000 50,000 480 800 c4-*-16 50,000 100,000 1,000 1,600 c4-*-24 75,000 100,000 1,200 1,600 c4-*-32 100,000 100,000 1,600 1,600 c4-*-48 160,000 160,000 2,400 2,400 c4-*-96 350,000 350,000 5,000 5,000 c4-*-144 350,000 350,000 5,000 5,000 c4-*-192 500,000 500,000 10,000 10,000 c4-*-288 500,000 500,000 10,000 10,000 C4D c4d-*-2 2,800 22,500 65 400 c4d-*-4 6,200 50,000 120 400 c4d-*-8 12,500 50,000 240 800 c4d-*-16 25,000 75,000 480 1,200 c4d-*-32 50,000 75,000 1,000 1,600 c4d-*-48 75,000 75,000 1,400 1,600 c4d-*-64 350,000 350,000 5,000 5,000 c4d-*-96 350,000 350,000 5,000 5,000 c4d-*-192 350,000 350,000 5,000 5,000 c4d-*-384 500,000 500,000 10,000 10,000 M4 m4-*-56 160,000 160,000 2,400 2,400 m4-*-112 350,000 350,000 5,000 5,000 m4-*-224 500,000 500,000 10,000 10,000 Performance limits by Hyperdisk type

For the performance limits by machine type for each Hyperdisk type, see the following sections:

Hyperdisk Balanced performance limits

This section lists the maximum performance that Hyperdisk Balanced volumes can achieve for each supported instance. A Hyperdisk Balanced volume's performance when it's attached to an instance can't exceed the limits for the instance's machine type. The performance limits are also shared across all Hyperdisk Balanced volumes attached to the same instance, regardless of each volume's provisioned performance.

Achieve higher performance with multiple Hyperdisk Balanced volumes

Certain instances can exceed the maximum performance for a single Hyperdisk Balanced volume— 160,000 IOPS or 2,400 MiB per second (MiB/s). An instance can only achieve these higher limits if you attach multiple Hyperdisk Balanced volumes to the instance.

If an instance's performance limit in the following table exceeds 160,000 IOPS or 2,400 MiB/s, then the instance can only achieve that limit if you attach multiple Hyperdisk Balanced volumes. For example, the performance limit for a c4a-*-72 instance using Hyperdisk Balanced is 240,000 IOPS and 5,000 MiB/s. To achieve this maximum performance you must attach at least two Hyperdisk Balanced volumes to the instance.

To learn more about Hyperdisk Balanced, see About Hyperdisk Balanced.

The performance limits also apply to custom N4 machine types.

Instance machine type Maximum IOPS Maximum throughput (MiB/s) A3 a3-ultragpu-8g² 320,000 10,000 a3-megagpu-8g 160,000 4,800 a3-highgpu-1g 25,000 400 a3-highgpu-2g 120,000 1,800 a3-highgpu-4g 160,000 2,400 a3-highgpu-8g 160,000 4,800 a3-edgegpu-8g 160,000 4,800 A4² a4-highgpu-8g 320,000 10,000 A4X² a4x-highgpu-4g 320,000 10,000 C3 c3-*-4 25,000 400 c3-*-8 50,000 800 c3-*-22 120,000 1,800 c3-*-44 160,000 2,400 c3-*-88 160,000 4,800 c3-*-176 160,000 10,000 c3-*-192 160,000 10,000 C3D c3d-*-4 25,000 400 c3d-*-8 50,000 800 c3d-*-16 75,000 1,200 c3d-*-30 75,000 1,200 c3d-*-60 160,000 2,400 c3d-*-90 160,000 2,400 c3d-*-180 160,000 2,400 c3d-*-360 160,000 2,400 C4 c4-*-2² 50,000 400 c4-*-4² 50,000 400 c4-*-8² 50,000 800 c4-*-16² 100,000 1,600 c4-*-24² 100,000 1,600 c4-*-32² 100,000 1,600 c4-*-48² 160,000 2,400 c4-*-96² 240,000 4,800 c4-*-144² 240,000 4,800 c4-*-192² 320,000 10,000 c4-*-288^1,2 320,000 10,000 C4A c4a-*-1 25,000 400 c4a-*-2 50,000 800 c4a-*-4 50,000 800 c4a-*-8 50,000 1,000 c4a-*-16 60,000 1,600 c4a-*-32 120,000 2,400 c4a-*-48 160,000 3,300 c4a-*-64 240,000 4,400 c4a-*-72 240,000 5,000 C4D c4d-*-2² 22,500 400 c4d-*-4² 50,000 400 c4d-*-8² 50,000 800 c4d-*-16² 75,000 1,200 c4d-*-32² 75,000 1,600 c4d-*-48² 75,000 1,600 c4d-*-64² 160,000 2,400 c4d-*-96² 160,000 2,800 c4d-*-192² 240,000 4,800 c4d-*-384² 320,000 10,000 TPU v6e ct6e-standard-1t 75,000 1,200 ct6e-standard-4t 160,000 2,400 ct6e-standard-8t 160,000 2,400 G4 (Preview) g4-standard-48 75,000 1,600 g4-standard-96 160,000 2,800 g4-standard-192 240,000 4,800 g4-standard-384 320,000 10,000 H3 h3-standard-88 15,000 240 M1 m1-ultramem-40 60,000 1,200 m1-ultramem-80 100,000 2,400 m1-megamem-96 100,000 4,000 m1-ultramem-160 100,000 4,000 M2 m2-*-208 100,000 2,400 m2-*-416 100,000 4,000 M3 m3-*-32 160,000 2,400 m3-*-64 160,000 4,800 m3-*-128 160,000 4,800 M4 m4-*-56² 160,000 2,400 m4-*-112² 240,000 4,800 m4-*-224² 320,000 10,000 N4 n4-*-2 15,000 240 n4-*-4 15,000 240 n4-*-6 15,000 240 n4-*-8 80,000 480 Custom N4 machine types with 10-14 vCPUs,
such as n4-*-10, n4-*-12, and n4-*-14 80,000 1,200 n4-*-16 80,000 1,200 Custom N4 machine types with 18-30 vCPUs,
such as n4-*-18, n4-*-24, and n4-*-30 80,000 1,200 n4-*-32 100,000 1,600 Custom N4 machine types with 34-46 vCPUs,
such as n4-*-34, n4-*-42, and n4-*-46 100,000 1,600 n4-*-48 160,000 2,400 Custom N4 machine types with 50-62 vCPUs,
such as n4-*-50, n4-*-58, and n4-*-62 160,000 2,400 n4-*-64 160,000 2,400 Custom N4 machine types with 66-78 vCPUs,
such as n4-*-66, n4-*-72, and n4-*-78 160,000 2,400 n4-*-80 160,000 2,400 X4 x4-*-960¹ 160,000 4,800 x4-*-1440¹ 160,000 4,800 x4-*-1920¹ 160,000 4,800 Z3 z3-*-8 50,000 800 z3-*-14
z3-*-16 100,000 1,600 z3-*-22 120,000 1,800 z3-*-32
z3-*-44 160,000 2,400 z3-*-88 160,000 4,800 z3-*-176 z3-*-192¹ 160,000 10,000 Includes bare metal instances.
Also offers steady state performance. For more information, see Performance limits for machine types with steady state performance.
Hyperdisk Balanced High Availability performance limits

This section lists the maximum performance that Hyperdisk Balanced High Availability volumes can achieve for each supported instance. A Hyperdisk Balanced High Availability volume's performance when it's attached to an instance can't exceed the limits for the instance's machine type. The performance limits are also shared across all Hyperdisk Balanced High Availability volumes attached to the same instance, regardless of each volume's provisioned performance.

Achieve higher performance with multiple Hyperdisk Balanced High Availability volumes

Certain instances can exceed the maximum performance for a single Hyperdisk Balanced High Availability volume— 100,000 IOPS or 1,200 MiB/s. An instance can achieve these higher limits if you attach multiple Hyperdisk Balanced High Availability volumes to the instance.

If an instance's performance limit in the following table exceeds 100,000 IOPS or 1,200 MiB/s, then the instance can achieve that limit only if you attach multiple Hyperdisk Balanced High Availability volumes. For example, the performance limit for a c4a-*-72 instance using Hyperdisk Balanced High Availability is 240,000 IOPS and 5,000 MiB/s. To achieve this maximum performance you must attach at least five Hyperdisk Balanced High Availability volumes to the instance.

For information about Hyperdisk Balanced High Availability features, see About Hyperdisk Balanced High Availability.

The performance limits also apply to custom N4 machine types.

Instance machine type Maximum IOPS Maximum throughput (MiB/s) a3-highgpu-1g 120,000 1,800 a3-highgpu-2g 160,000 2,400 a3-highgpu-4g 160,000 4,800 a3-highgpu-8g 160,000 4,800 a3-edgegpu-8g 160,000 4,800 a3-ultragpu-8g 320,000 10,000 a3-megagpu-8g 160,000 4,800 c3-*-4 25,000 400 c3-*-8 50,000 600 c3-*-22 100,000 600 c3-*-44 100,000 1,200 c3-*-88 100,000 2,500 c3-*-176 100,000 2,500 c3-*-192 100,000 2,500 c3d-*-4 25,000 400 c3d-*-8 50,000 600 c3d-*-16 100,000 600 c3d-*-30 93,750 600 c3d-*-60 100,000 1,900 c3d-*-90 100,000 2,500 c3d-*-180 100,000 2,500 c3d-*-360 100,000 2,500 c4-*-2 50,000 400 c4-*-4 50,000 400 c4-*-8 50,000 600 c4-*-16 100,000 600 c4-*-24 100,000 600 c4-*-32 100,000 1,200 c4-*-48 100,000 1,900 c4-*-96 100,000 2,500 c4-*-144 100,000 2,500 c4-*-192 100,000 2,500 c4-*-288 100,000 2,500 c4a-*-1 25,000 400 c4a-*-2 50,000 800 c4a-*-4 50,000 800 c4a-*-8 50,000 1,000 c4a-*-16 80,000 1,600 c4a-*-32 120,000 2,400 c4a-*-48 160,000 3,300 c4a-*-64 240,000 4,400 c4a-*-72 240,000 5,000 m3-*-32 100,000 1,200 m3-*-64 100,000 2,500 m3-*-128 100,000 2,500 n4-*-2 15,000 240 n4-*-4 15,000 240 n4-*-6 15,000 240 n4-*-8 15,000 480 Custom N4 machine types with 10-14 vCPUs,
such as n4-*-10, n4-*-12, and n4-*-14 15,000 480 n4-*-16 80,000 1,200 Custom N4 machine types with 18-30 vCPUs,
such as n4-*-18, n4-*-24, and n4-*-30 80,000 1,200 n4-*-32 100,000 1,600 Custom N4 machine types with 34-46 vCPUs,
such as n4-*-34, n4-*-42, and n4-*-46 100,000 1,600 n4-*-48 100,000 1,600 Custom N4 machine types with 50-62 vCPUs,
such as n4-*-50, n4-*-58, and n4-*-62 100,000 1,600 n4-*-64 100,000 1,600 Custom N4 machine types with 66-78 vCPUs,
such as n4-*-66, n4-*-72, and n4-*-78 100,000 1,600 n4-*-80 100,000 1,600 z3-*-88 160,000 4,800 z3-*-176 160,000 4,800 Hyperdisk Extreme performance limits

This section lists the maximum performance that Hyperdisk Extreme volumes can achieve for each supported instance. A Hyperdisk Extreme volume's performance when it's attached to an instance can't exceed the limits for the instance's machine type. The performance limits are also shared across all Hyperdisk Extreme volumes attached to the same instance, regardless of each volume's provisioned performance.

Achieve higher performance with multiple Hyperdisk Extreme volumes

Certain instances can exceed the maximum performance for a single Hyperdisk Extreme volume— 350,000 IOPS or 5,000 MiB/s. An instance can only achieve these higher limits if you attach multiple Hyperdisk Extreme volumes to the instance.

If an instance's performance limit in the following table exceeds 350,000 IOPS or 5,000 MiB/s, then the instance can only achieve that limit if you attach multiple Hyperdisk Extreme volumes. For example, the performance limit for a c3-*-176 instance using Hyperdisk Extreme is 500,000 IOPS and 10,000 MiB/s. To achieve this maximum performance you must attach at least two Hyperdisk Extreme volumes to the instance.

For more information about Hyperdisk Extreme, see About Hyperdisk Extreme.

The performance limits also apply to custom machine types.

Instance machine type Maximum IOPS Maximum throughput (MiB/s) A3 a3-highgpu-4g 350,000 5,000 a3-ultragpu-8g² 500,000 10,000 a3-megagpu-8g 400,000 8,000 a3-highgpu-8g 400,000 8,000 a3-edgegpu-8g 400,000 8,000 A4² a4-highgpu-8g 500,000 10,000 A4X² a4x-highgpu-4g 500,000 10,000 C3 c3-*-88¹ 350,000 5,000 c3-*-176¹ 500,000 10,000 c3-*-192^1,3 500,000 10,000 C3D c3d-*-60¹ 350,000 5,000 c3d-*-90¹ 350,000 5,000 c3d-*-180¹ 350,000 5,000 c3d-*-360¹ 350,000 5,000 C4 c4-*-96² 350,000 5,000 c4-*-144² 350,000 5,000 c4-*-192² 500,000 10,000 c4-*-288^2,3 500,000 10,000 C4A c4a-*-64 350,000 5,000 c4a-*-72 350,000 5,000 C4D c4d-*-64² 350,000 5,000 c4d-*-96² 350,000 5,000 c4d-*-192² 350,000 5,000 c4d-*-384² 500,000 10,000 G4 (Preview) g4-standard-96 350,000 5,000 g4-standard-192 350,000 5,000 g4-standard-384 500,000 10,000 M2 m2-*-208 100,000 4,000 m2-*-416 100,000 4,000 M3 m3-*-64¹ 350,000 5,000 m3-*-128¹ 450,000 7,200 M4 m4-*-112² 350,000 5,000 m4-*-224² 500,000 10,000 N2 n2-*-80¹ 160,000 5,000 n2-*-96 160,000 5,000 n2-*-128 160,000 5,000 X4 x4-*-960^1,3 400,000 10,000 x4-*-1440^1,3 400,000 10,000 x4-*-1920^1,3 400,000 10,000 Z3 z3-*-88¹ 350,000 5,000 z3-*-176¹ 350,000 5,000 z3-*-192^1,3 500,000 10,000 If using Hyperdisk Extreme with an instance that uses Microsoft Windows, refer to the known issues for Windows VM instances.
Also offers steady state performance. For more information, see Performance limits for machine types with steady state performance.
Includes bare metal instances. Hyperdisk ML performance limits

This section lists the maximum performance that Hyperdisk ML volumes can achieve for each supported instance. A Hyperdisk ML volume's performance when it's attached to an instance can't exceed the limits for the instance's machine type. The performance limits are also shared across all Hyperdisk ML volumes attached to the same instance, regardless of each volume's provisioned performance.

Scenarios that require multiple instances to reach provisioned performance

The provisioned throughput for a Hyperdisk ML volume is shared between each instance the volume is attached to, up to the maximum limit for the machine type that's listed in the following table. If a Hyperdisk ML volume's provisioned performance is higher than an instance's performance limit, the volume can achieve its provisioned performance only if it is attached to multiple instances. a3-ultragpu-8 instances have a throughput limit of 4,000 MiB/s.

For example, suppose you have a Hyperdisk ML volume provisioned with 500,000 MiB/s of throughput. and you want to attach the volume to a3-ultragpu-8 instances. A single a3-ultragpu-8 instance can't acheieve more than 4,000 MiB/s of throughput. Therefore, to achieve the volume's provisioned throughput, you must attach the volume to at least 125 (500,000/4,000) a3-ultragpu-8 instances. On the other hand, for the a2-highgpu-1g machine type, you would need 272 instances.

For more information about Hyperdisk ML, see About Hyperdisk ML.

Important: To reach the IOPS limits, you must use an I/O size of 4 KB. Maximum throughput limits require an I/O size of at least 256 KB. Hyperdisk performance is half-duplex, so the IOPS and throughput limits are shared between read and write operations. This means that if a machine type has a 50,000 IOPS limit, then the sum of the reads and writes every second can't exceed 50,000. Instance machine type Maximum IOPS Maximum throughput (MiB/s) a2-*-1g 28,800 1,800 a2-*-2g 38,400 2,400 a2-*-4g 38,400 2,400 a2-*-8g 38,400 2,400 a2-megagpu-16g 38,400 2,400 a3-*-1g 28,800 1,800 a3-*-2g 38,400 2,400 a3-*-4g 38,400 2,400 a3-*-8g (in read-only mode)¹ 64,000 4,000 a3-*-8g (in read-write mode)¹ 38,400 2,400 c3-*-4 6,400 400 c3-*-8 12,800 800 c3-*-22 28,800 1,800 c3-*-44 38,400 2,400 c3-*-88 38,400 2,400 c3-*-176 38,400 2,400 c3-*-192 38,400 2,400 c3d-*-4 6,400 400 c3d-*-8 12,800 800 c3d-*-16 19,200 1,200 c3d-*-30 19,200 1,200 c3d-*-60 38,400 2,400 c3d-*-90 38,400 2,400 c3d-*-180 38,400 2,400 c3d-*-360 38,400 2,400 ct6e-standard-1t 19,200 1,200 ct6e-standard-4t 28,800 1,800 ct6e-standard-8t 28,800 1,800 g2-standard-4 12,800 800 g2-standard-8 19,200 1,200 g2-standard-12 28,800 1,800 g2-standard-16 38,400 2,400 g2-standard-24 38,400 2,400 g2-standard-32 38,400 2,400 g2-standard-48 38,400 2,400 g2-standard-96 38,400 2,400

For a3-*-8g instances, performance depends on whether the Hyperdisk ML volume is attached to the instance in read-only or read-write mode.

Hyperdisk Throughput performance limits

This section lists the maximum performance that Hyperdisk Throughput volumes can achieve for each supported instance. A Hyperdisk Throughput volume's performance when it's attached to an instance can't exceed the limits for the instance's machine type. The performance limits are also shared across all Hyperdisk Throughput volumes attached to the same instance, regardless of each volume's provisioned performance.

Achieve higher performance with multiple Hyperdisk Throughput volumes

Certain instances can exceed the maximum performance for a single Hyperdisk Throughput volume—2,400 MiB/s. An instance can achieve these higher limits if you attach multiple Hyperdisk Throughput volumes to the instance.

If an instance's performance limit in the following table exceeds 2,400 MiB/s, then the instance can achieve that limit only if you attach multiple Hyperdisk Throughput volumes. For example, the performance limit for a a3-*-8g instance using Hyperdisk Throughput volumes is 3,000 MiB/s. Therefore, to achieve 3,000 MiB/s of throughput, you must attach at least two Hyperdisk Throughput volumes to the instance.

For more information about Hyperdisk Throughput, see About Hyperdisk Throughput.

The performance limits also apply to custom N2 and N2D machine types.

Instance machine type Maximum throughput (MiB/s) Maximum IOPS a3-*-1g 1,200 4,800 a3-*-2g 2,400 9,600 a3-*-4g 2,400 9,600 a3-*-8g 3,000 12,000 c3-*-4 240 960 c3-*-8 800 3,200 c3-*-22 1,200 4,800 c3-*-44 1,800 7,200 c3-*-88 2,400 9,600 c3-*-176 4,800 19,200 c3-*-192 4,800 19,200 c3d-*-4 240 960 c3d-*-8 800 3,200 c3d-*-16 1,200 4,800 c3d-*-30 1,800 7,200 c3d-*-60 2,400 9,600 c3d-*-90 2,400 9,600 c3d-*-180 2,400 9,600 c3d-*-360 2,400 9,600 g2-standard-4 240 960 g2-standard-8 800 3,200 g2-standard-12 800 3,200 g2-standard-16 1,200 4,800 g2-standard-24 1,200 4,800 g2-standard-32 1,800 7,200 g2-standard-48 2,400 9,600 g2-standard-96 2,400 9,600 h3-standard-88 240 960 m3-*-32 1,800 7,200 m3-*-64 2,400 9,600 m3-*-128 2,400 9,600 n2-*-2 200 800 n2-*-4 240 960 n2-*-6 240 960 n2-*-8 800 3,200 Custom N2 machine types with 10-14 vCPUs,
such as n2-*-10 and n2-*-12 800 3,200 n2-*-16 1,200 4,800 Custom N2 machine types with 18-30 vCPUs,
such as n2-*-18, n2-*-24, and n2-*-30 1,200 4,800 n2-*-32 1,800 7,200 Custom N2 machine types with 36-44 vCPUs,
such as n2-*-36, n2-*-40, and n2-*-44 1,800 7,200 n2-*-48 2,400 9,600 Custom N2 machine types with 36-44 vCPUs,
such as n2-*-36, n2-*-40, and n2-*-44 2,400 9,600 n2-*-64 3,000 12,000 Custom N2 machine types with 68-76 vCPUs,
such as n2-*-68, n2-*-72, and n2-*-76 3,000 12,000 n2-*-80 3,000 12,000 n2-*-96 3,000 12,000 n2-*-128 2,400 9,600 n2d-*-2 200 800 n2d-*-4 240 960 n2d-*-8 800 3,200 n2d-*-16 1,200 4,800 n2d-*-32 1,800 7,200 n2d-*-48 2,400 9,600 n2d-*-64 2,400 9,600 n2d-*-80 2,400 9,600 n2d-*-96 2,400 9,600 n2d-*-128 2,400 9,600 n2d-*-224 2,400 9,600 t2d-*-1 200 800 t2d-*-2 200 800 t2d-*-4 240 960 t2d-*-8 800 3,200 t2d-*-16 1,200 4,800 t2d-*-32 1,800 7,200 t2d-*-48 2,400 9,600 t2d-*-60 2,400 9,600 z3-*-8 800 3,200 z3-*-14 800 3,200 z3-*-16 800 3,200 z3-*-22 1,200 4,800 z3-*-32 1,200 4,800 z3-*-44 1,800 7,200 z3-*-88 2,400 9,600 z3-*-176 2,400 9,600 Hyperdisk size and attachment limits

The following sections describe the limits to the size and number of Hyperdisk volumes you can attach to a single instance. The limits discussed don't apply to any Local SSD disks attached to the same instance.

Summary of Hyperdisk per-instance limits

Maximum total capacity per instance: The maximum total capacity of all the volumes attached to an instance is between 257 TiB to 512 TiB, depending on various factors. For details, see Maximum total capacity per instance.

Maximum number of volumes attached to an instance: Compute Engine limits the number of Hyperdisk volumes that you can attach to a single instance. The following limits apply in order. When both limits apply, the first rule in the list is enforced.

The number of Hyperdisk volumes that you can attach to the instance: 8 to 128; depending on the Hyperdisk type and the instance's machine type.
The number of Hyperdisk and Persistent Disk volumes that you can attach to the instance: 128. For more information, see Maximum number of disks, across all types.

The following examples demonstrate how the limits work.

Examples

Suppose you have a c3-*-96 instance. The following limits apply.

Maximum number of Hyperdisk volumes across all types: 128. However, for each Hyperdisk type, the limits are as follows:
- Hyperdisk Throughput: 64
- Hyperdisk ML: 64
- Hyperdisk Extreme: 8
- Hyperdisk Balanced or Hyperdisk Balanced High Availability: 32
Maximum number of Persistent Disk and Hyperdisk volumes that you can attach to the instance: 128
Maximum combined total capacity of all volumes: 512 TiB

The following examples illustrate these limits.

Maximum number of a single type of Hyperdisk per instance: If you attach 8 Hyperdisk Extreme volumes to the instance, you can attach up to 123 more Hyperdisk volumes to the instance. However, you can attach only 3 more Hyperdisk Extreme volumes to the instance because the maximum number of Hyperdisk Extreme volumes 8.
Maximum number of Hyperdisk volumes per instance: 128. If you attach 8 Hyperdisk Extreme volumes to the instance, you can attach up to 120 more Hyperdisk volumes to the instance.
Maximum number of disks or volumes per instance, across all types: 128. If you attach a combined total of 128 Hyperdisk volumes to the instance, then you can't attach any more Hyperdisk or Persistent Disk volumes. However, if you attach only 64 Hyperdisk volumes to the instance, you can still attach up to 64 Persistent Disk or Hyperdisk volumes to the instance.

Maximum total capacity per instance

The maximum total disk capacity (in TiB) across all Hyperdisk and Persistent Disk types that you attach to an instance depends on the number of vCPUs that the instance has. The capacity limits are as follows:

For machine types with less than 32 vCPUs:
- 257 TiB for all Hyperdisk or all Persistent Disk
- 257 TiB for a mixture of Hyperdisk and Persistent Disk
For machine types with 32 or more vCPUs:
- 512 TiB for all Hyperdisk
- 512 TiB for a mixture of Hyperdisk and Persistent Disk
- 257 TiB for all Persistent Disk

You can attach a combination of Hyperdisk and Persistent Disk volumes to a single instance but the total disk capacity for Persistent Disk can't exceed 257 TiB.

Maximum number of disks per instance, across all types

The maximum number of individual Hyperdisk, and, if supported, Persistent Disk volumes that you can attach to an instance is 128. If you attach 28 Hyperdisk volumes to a instance, you can still attach up to 100 more Hyperdisk or Persistent Disk volumes to the same instance.

Maximum Hyperdisk volumes per instance

The number of Hyperdisk volumes you can attach to an instance depends on the machine type, with separate limits for each Hyperdisk type. These limits are detailed in the Supported disk types section within the documentation for each machine series. To view these limits, refer to the corresponding links in the following table.

What's next

Learn how to optimize the performance of your Hyperdisk volumes

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

Last updated 2025-08-13 UTC.

[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-13 UTC."],[],[]]

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4