This document contains 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
orhighcpu
N
is the number of vCPUs, CPUs, or the GPU designation, for example, 22 for an instance with 22 vCPUs, or8g
for an instance with 8 GPUs
For example, c3-*-192
refers to all C3 VMs and bare metal instances with 192 vCPUs or
CPUs, respectively, and also includes lssd
machine types. 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.
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-*-1g |
120,000 | 1,800 |
a3-*-2g |
160,000 | 2,400 |
a3-*-4g |
350,000 | 5,000 |
a3-*-8g |
400,000 | 8,000 |
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 |
C4 | ||
See steady state performance limits | ||
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 |
C4D | ||
See steady state performance limits | ||
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 |
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 |
M4 | ||
See steady state performance limits | ||
N2 | ||
n2-*-2 |
15,000 | 240 |
n2-*-4 |
15,000 | 240 |
n2-*-6 |
15,000 | 240 |
n2-*-8 |
30,000 | 800 |
n2-*-10 |
30,000 | 800 |
n2-*-12 |
30,000 | 800 |
n2-*-14 |
30,000 | 800 |
n2-*-16 |
60,000 | 1,200 |
n2-*-18 |
60,000 | 1,200 |
n2-*-20 |
60,000 | 1,200 |
n2-*-22 |
60,000 | 1,200 |
n2-*-24 |
60,000 | 1,200 |
n2-*-26 |
60,000 | 1,200 |
n2-*-28 |
60,000 | 1,200 |
n2-*-30 |
60,000 | 1,200 |
n2-*-32 |
120,000 | 1,800 |
n2-*-36 |
120,000 | 1,800 |
n2-*-40 |
120,000 | 1,800 |
n2-*-44 |
120,000 | 1,800 |
n2-*-48 |
120,000 | 2,400 |
n2-*-52 |
120,000 | 2,400 |
n2-*-56 |
120,000 | 2,400 |
n2-*-60 |
120,000 | 2,400 |
n2-*-64 |
160,000 | 5,000 |
n2-*-68 |
160,000 | 5,000 |
n2-*-72 |
160,000 | 5,000 |
n2-*-76 |
160,000 | 5,000 |
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-*-8 |
15,000 | 480 |
n4-*-16 |
80,000 | 1,200 |
n4-*-32 |
100,000 | 1,600 |
n4-*-48 |
160,000 | 2,400 |
n4-*-64 |
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-*-88 |
350,000 | 5,000 |
z3-*-176 |
350,000 | 5,000 |
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) |
---|---|---|---|---|
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-*-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-*-192 |
500,000 | 500,000 | 10,000 | 10,000 |
C4D | ||||
c4d-*-2
(Preview) |
2,800 | 22,500 | 65 | 400 |
c4d-*-4
(Preview) |
6,200 | 50,000 | 120 | 400 |
c4d-*-8
(Preview) |
12,500 | 50,000 | 240 | 800 |
c4d-*-16
(Preview) |
25,000 | 75,000 | 480 | 1,200 |
c4d-*-32
(Preview) |
50,000 | 75,000 | 1,000 | 1,600 |
c4d-*-48
(Preview) |
75,000 | 75,000 | 1,400 | 1,600 |
c4d-*-64
(Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-96
(Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-192
(Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-384
(Preview) |
400,000 | 400,000 | 10,000 | 10,000 |
M4 | ||||
m4-*-56 |
350,000 | 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
- Hyperdisk Balanced High Availability
- Hyperdisk Extreme
- Hyperdisk ML
- Hyperdisk Throughput
Hyperdisk Balanced performance limits
The following table 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/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 machine types.
Instance machine type | Maximum IOPS | Maximum throughput (MiB/s) |
---|---|---|
a3-*-8g |
160,000 | 4,800 |
a3-ultragpu-8g |
320,000 | 10,000 |
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 1 |
160,000 | 10,000 |
c3-*-192 1 |
160,000 | 10,000 |
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 | See steady state performance limits for Hyperdisk Balanced | |
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 | See steady state performance limits for Hyperdisk Balanced | |
ct6e-standard-1t |
75,000 | 1,200 |
ct6e-standard-4t |
160,000 | 2,400 |
ct6e-standard-8t |
160,000 | 2,400 |
h3-standard-88 |
15,000 | 240 |
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-*-208 |
100,000 | 2,400 |
m2-*-416 |
100,000 | 4,000 |
m3-*-32 |
160,000 | 2,400 |
m3-*-64 |
160,000 | 4,800 |
m3-*-128 |
160,000 | 4,800 |
M4 | See Steady state performance limits for Hyperdisk Balanced | |
n4-*-2 |
15,000 | 240 |
n4-*-4 |
15,000 | 240 |
n4-*-8 |
15,000 | 480 |
n4-*-16 |
80,000 | 1,200 |
n4-*-8 |
80,000 | 1,200 |
n4-*-32 |
100,000 | 1,600 |
n4-*-64 |
160,000 | 2,400 |
n4-*-80 |
160,000 | 2,400 |
x4-*-960 |
160,000 | 4,800 |
x4-*-1440 |
160,000 | 4,800 |
x4-*-1920 |
160,000 | 4,800 |
Steady state performance limits for Hyperdisk Balanced
Instance machine type | Steady state IOPS | Maximum IOPS | Steady state throughput (MiB/s) | Maximum throughput (MiB/s) |
---|---|---|---|---|
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-*-32 |
100,000 | 100,000 | 1,600 | 1,600 |
c4-*-48 |
160,000 | 160,000 | 2,400 | 2,400 |
c4-*-96 |
240,000 | 240,000 | 4,800 | 4,800 |
c4-*-192 |
320,000 | 320,000 | 10,000 | 10,000 |
c4d-*-2 (Preview) |
2,800 | 22,500 | 65 | 400 |
c4d-*-4 (Preview) |
6,200 | 50,000 | 120 | 400 |
c4d-*-8 (Preview) |
12,500 | 50,000 | 240 | 800 |
c4d-*-16 (Preview) |
25,000 | 75,000 | 480 | 1,200 |
c4d-*-32 (Preview) |
50,000 | 75,000 | 1,000 | 1,600 |
c4d-*-48 (Preview) |
75,000 | 75,000 | 1,400 | 1,600 |
c4d-*-64 (Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-96 (Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-192 (Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-384 (Preview) |
400,000 | 400,000 | 10,000 | 10,000 |
m4-*-56 |
160,000 | 160,000 | 2,400 | 2,400 |
m4-*-112 |
240,000 | 240,000 | 4,800 | 4,800 |
m4-*-224 |
320,000 | 320,000 | 10,000 | 10,000 |
Hyperdisk Balanced High Availability performance limits
The following table 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 2,400 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 2,400 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 two 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 machine types.
Instance machine type | Maximum IOPS | Maximum throughput (MiB/s) |
---|---|---|
c3-*-4 |
25,000 | 400 |
c3-*-8 |
50,000 | 600 |
c3-*-22 |
100,000 | 600 |
c3-*-44 |
100,000 | 600 |
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 |
100,000 | 600 |
c3d-*-60 |
100,000 | 1,200 |
c3d-*-90 |
100,000 | 1,200 |
c3d-*-180 |
100,000 | 1,200 |
c3d-*-360 |
100,000 | 1,200 |
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 | 1,900 |
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 |
n4-*-10 |
15,000 | 480 |
n4-*-12 |
15,000 | 480 |
n4-*-14 |
15,000 | 480 |
n4-*-16 |
80,000 | 1,200 |
n4-*-18 |
80,000 | 1,200 |
n4-*-20 |
80,000 | 1,200 |
n4-*-22 |
80,000 | 1,200 |
n4-*-24 |
80,000 | 1,200 |
n4-*-26 |
80,000 | 1,200 |
n4-*-28 |
80,000 | 1,200 |
n4-*-30 |
80,000 | 1,200 |
n4-*-32 |
100,000 | 1,600 |
n4-*-34 |
100,000 | 1,600 |
n4-*-36 |
100,000 | 1,600 |
n4-*-38 |
100,000 | 1,600 |
Hyperdisk Extreme performance limits
The following table 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-highgpu-4g |
350,000 | 5,000 |
a3-megagpu-8g |
400,000 | 8,000 |
a3-highgpu-8g |
400,000 | 8,000 |
a3-ultragpu-8g |
500,000 | 10,000 |
c3-*-88 1 |
350,000 | 5,000 |
c3-*-176 1,2 |
500,000 | 10,000 |
c3-*-192 1,2 |
500,000 | 10,000 |
c3d-*-60 1 |
350,000 | 5,000 |
c3d-*-90 1 |
350,000 | 5,000 |
c3d-*-180 1 |
350,000 | 5,000 |
c3d-*-360 1 |
350,000 | 5,000 |
C4 | See Steady-state performance limits for Hyperdisk Extreme | |
c4a-*-64 |
350,000 | 5,000 |
c4a-*-72 |
350,000 | 5,000 |
C4D | See Steady-state performance limits for Hyperdisk Extreme | |
m2-*-208 |
100,000 | 4,000 |
m3-*-64 1 |
350,000 | 5,000 |
m3-*-128 1 |
450,000 | 7,200 |
m2-*-416 |
100,000 | 4,000 |
M4 | See Steady-state performance limits for Hyperdisk Extreme | |
n2-*-80 |
160,000 | 5,000 |
n2-*-96 |
160,000 | 5,000 |
n2-*-128 |
160,000 | 5,000 |
x4-*-960 2 |
400,000 | 10,000 |
x4-*-1440 2 |
400,000 | 10,000 |
x4-*-1920 |
400,000 | 10,000 |
z3-*-88 |
350,000 | 5,000 |
z3-*-176 |
350,000 | 5,000 |
2 Includes bare metal instances.
Steady state performance limits for Hyperdisk Extreme
Instance machine type | Steady state IOPS | Maximum IOPS | Steady state throughput (MiB/s) | Maximum throughput (MiB/s) |
---|---|---|---|---|
c4-*-96 |
350,000 | 350,000 | 5,000 | 5,000 |
c4-*-192 |
500,000 | 500,000 | 10,000 | 10,000 |
c4d-*-64 (Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-96 (Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-192 (Preview) |
350,000 | 350,000 | 5,000 | 5,000 |
c4d-*-384 (Preview) |
400,000 | 400,000 | 10,000 | 10,000 |
m4-*-112 |
350,000 | 350,000 | 5,000 | 5,000 |
m4-*-224 |
500,000 | 500,000 | 10,000 | 10,000 |
Hyperdisk ML performance limits
The following table 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.
Instance machine type | Maximum throughput (MiB/s) | Maximum IOPS |
---|---|---|
a2-*-1g |
1,800 | 28,800 |
a2-*-2g |
2,400 | 38,400 |
a2-*-4g |
2,400 | 38,400 |
a2-*-8g |
2,400 | 38,400 |
a2-megagpu-16g |
2,400 | 38,400 |
a3-*-1g |
1,800 | 28,800 |
a3-*-2g |
2,400 | 38,400 |
a3-*-4g |
2,400 | 38,400 |
a3-*-8g (in read-only mode) |
4,000 | 64,000 |
a3-*-8g (in read-write mode) |
2,400 | 38,400 |
c3-*-4 |
400 | 6,400 |
c3-*-8 |
800 | 12,800 |
c3-*-22 |
1,800 | 28,800 |
c3-*-44 |
2,400 | 38,400 |
c3-*-88 |
2,400 | 38,400 |
c3-*-176 |
2,400 | 38,400 |
c3-*-192 |
2,400 | 38,400 |
c3d-*-4 |
400 | 6,400 |
c3d-*-8 |
800 | 12,800 |
c3d-*-16 |
1,200 | 19,200 |
c3d-*-30 |
1,200 | 19,200 |
c3d-*-60 |
2,400 | 38,400 |
c3d-*-90 |
2,400 | 38,400 |
c3d-*-180 |
2,400 | 38,400 |
c3d-*-360 |
2,400 | 38,400 |
ct6e-standard-1t |
1,200 | 19,200 |
ct6e-standard-4t |
1,800 | 28,800 |
ct6e-standard-8t |
1,800 | 28,800 |
g2-standard-4 |
800 | 12,800 |
g2-standard-8 |
1,200 | 19,200 |
g2-standard-12 |
1,800 | 28,800 |
g2-standard-16 |
2,400 | 38,400 |
g2-standard-24 |
2,400 | 38,400 |
g2-standard-32 |
2,400 | 38,400 |
g2-standard-48 |
2,400 | 38,400 |
g2-standard-96 |
2,400 | 38,400 |
Hyperdisk Throughput performance limits
The following table 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 —600 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 600 MiB/s,
then the instance can achieve that limit only if you attach multiple Hyperdisk Throughput volumes.
For example, the performance limit for a c3-*-22
instance using Hyperdisk Throughput volumes
is 1,200 MiB/s. Therefore, to achieve 1,200 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 machine types.
Instance machine type | Maximum throughput (MiB/s) | Minimum number of disks needed to reach maximum throughput |
---|---|---|
a3-*-1g |
1,200 | 2 |
a3-*-2g |
2,400 | 4 |
a3-*-4g |
2,400 | 4 |
a3-*-8g |
3,000 | 5 |
c3-*-4 |
240 | 1 |
c3-*-8 |
800 | 2 |
c3-*-22 |
1,200 | 2 |
c3-*-44 |
1,800 | 3 |
c3-*-88 |
2,400 | 4 |
c3-*-176 |
2,400 | 4 |
c3-*-192 |
2,400 | 4 |
c3d-*-4 |
400 | 2 |
c3d-*-8 |
800 | 2 |
c3d-*-16 |
1,200 | 2 |
c3d-*-30 |
1,200 | 2 |
c3d-*-60 |
2,400 | 4 |
c3d-*-90 |
2,400 | 4 |
c3d-*-180 |
2,400 | 4 |
c3d-*-360 |
2,400 | 4 |
g2-standard-4 |
240 | 1 |
g2-standard-8 |
800 | 2 |
g2-standard-12 |
800 | 2 |
g2-standard-16 |
1,200 | 2 |
g2-standard-24 |
1,200 | 2 |
g2-standard-32 |
1,800 | 3 |
g2-standard-48 |
2,400 | 4 |
g2-standard-96 |
2,400 | 4 |
h3-standard-88 |
240 | 1 |
m3-*-32 |
1,800 | 3 |
m3-*-64 |
2,400 | 4 |
m3-*-128 |
2,400 | 4 |
z3-*-88 |
2,400 | 4 |
z3-*-176 |
2,400 | 4 |
n2-*-2 |
200 | 1 |
n2-*-4 |
240 | 1 |
n2-*-6 |
240 | 1 |
n2-*-8 |
800 | 2 |
n2-*-10 |
800 | 2 |
n2-*-12 |
800 | 2 |
n2-*-14 |
800 | 2 |
n2-*-16 |
1,200 | 2 |
n2-*-18 |
1,200 | 2 |
n2-*-20 |
1,200 | 2 |
n2-*-22 |
1,200 | 2 |
n2-*-24 |
1,200 | 2 |
n2-*-26 |
1,200 | 2 |
n2-*-28 |
1,200 | 2 |
n2-*-30 |
1,200 | 2 |
n2-*-32 |
1,800 | 3 |
n2-*-36 |
1,800 | 3 |
n2-*-40 |
1,800 | 3 |
n2-*-44 |
1,800 | 3 |
n2-*-48 |
2,400 | 4 |
n2-*-52 |
2,400 | 4 |
n2-*-56 |
2,400 | 4 |
n2-*-60 |
2,400 | 4 |
n2-*-64 |
3,000 | 5 |
n2-*-68 |
2,400 | 4 |
n2-*-72 |
2,400 | 4 |
n2-*-76 |
2,400 | 4 |
n2-*-80 |
2,400 | 4 |
n2-*-96 |
2,400 | 4 |
n2-*-128 |
2,400 | 4 |
n2d-*-2 |
200 | 1 |
n2d-*-4 |
240 | 1 |
n2d-*-8 |
800 | 2 |
n2d-*-16 |
1,200 | 2 |
n2d-*-32 |
1,800 | 3 |
n2d-*-48 |
2,400 | 4 |
n2d-*-64 |
2,400 | 4 |
n2d-*-80 |
2,400 | 4 |
n2d-*-96 |
2,400 | 4 |
n2d-*-128 |
2,400 | 4 |
n2d-*-224 |
2,400 | 4 |
t2d-*-1 |
200 | 1 |
t2d-*-2 |
200 | 1 |
t2d-*-4 |
240 | 1 |
t2d-*-8 |
800 | 2 |
t2d-*-16 |
1,200 | 2 |
t2d-*-32 |
1,800 | 3 |
t2d-*-48 |
2,400 | 4 |
t2d-*-60 |
2,400 | 4 |
Hyperdisk size and attachment limits
This section describes how many Hyperdisk volumes you can attach to a single instance. The limits discussed don't apply to any Local SSD disks attached to the same VM.
Maximum total capacity per VM
The maximum total disk capacity (in TiB) across all Hyperdisk and Persistent Disk types that you attach to a VM depends on the number of vCPUs the VM 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 VM but the total disk capacity for Persistent Disk can't exceed 257 TiB.
Maximum number of disks per VM, across all types
The maximum number of individual Persistent Disk and Hyperdisk volumes you can attach to a VM is 128. So, if you have attached 28 Hyperdisk volumes to a VM, you can still attach up to 100 more Persistent Disk volumes to the same VM.
Maximum Hyperdisk volumes per VM
The maximum number of Hyperdisk volumes that you can attach to a VM depends on the number of vCPUs that the VM has, as described in the following table:
Number of vCPUs | Maximum number of Hyperdisk, all types1 |
Maximum number of Hyperdisk Balanced disks2 |
Maximum number of Hyperdisk Balanced HA disks |
Maximum number of Hyperdisk Extreme disks |
Maximum number of Hyperdisk ML disks |
Maximum number of Hyperdisk Throughput disks |
---|---|---|---|---|---|---|
1 to 3 | 20 | 16 | 0 | 0 | 20 | 20 |
4 to 7 | 24 | 16 | 16 | 0 | 24 | 24 |
8 to 15 | 32 | 32 | 16 | 0 | 32 | 32 |
16 to 31 | 48 | 32 | 32 | 0 | 48 | 48 |
32 to 63 | 64 | 32 | 32 | 03 | 64 | 64 |
64 or more | 128 | 32 | 32 | 84 | 64 | 64 |
2 The maximum number of Hyperdisk Balanced and Hyperdisk Balanced High Availability disks that you can attach to a VM varies from 16 to 32 volumes, depending on the machine series and machine type. Refer to the specific machine series documentation to learn about its disk limits.
3You can attach up to 8 Hyperdisk Extreme volumes to
c3d-*-60
instances.4 N2 VMs require a minimum of 80 vCPUs to use Hyperdisk Extreme.
Summary of Hyperdisk per-VM limits
For an individual VM, the following limits for using Hyperdisk apply:
- A limit for the total number of Hyperdisk and Persistent Disk volumes that you can attach to the VM, including the boot disk.
- A limit for the combined total capacity of all disks attached to a VM.
- A limit for the total number of Hyperdisk volumes that you can attach to the VM.
- A limit for the number of each type of Hyperdisk that you can attach to the VM.
When multiple limits apply, the most specific limit is enforced. For example, suppose you have a VM with 96 vCPUs, and you want to use a combination of Hyperdisk and Persistent Disk volumes. The following limits apply:
- Maximum number of Persistent Disk and Hyperdisk volumes that you can attach to the VM: 128
- Maximum number of Hyperdisk volumes, across all types: 128
- Maximum number of Hyperdisk Throughput volumes: 64
- Maximum number of Hyperdisk ML volumes: 64
- Maximum number of Hyperdisk Extreme volumes: 8
- Maximum number of Hyperdisk Balanced or Hyperdisk Balanced High Availability volumes: 32
The following examples illustrate these limits.
Maximum number of a single type of Hyperdisk per VM: You can only attach 8 Hyperdisk Extreme volumes to the VM. This is true even if you don't attach any other Persistent Disk or Hyperdisk volumes to the VM.
Maximum number of Hyperdisk volumes per VM: If you attach 8 Hyperdisk Extreme volumes to the VM, you can attach at most 120 other Hyperdisk volumes to the VM. This makes the combined number of Hyperdisk volumes equal to 128, which is the maximum number of Hyperdisk volumes that you can attach to a VM.
Maximum number of disks or volumes per VM, across all types: The maximum number of disks, of all types, that you can attach to a VM is 128. If you attach a combined total of 128 Hyperdisk volumes to the VM, then you can't attach any more Hyperdisk or Persistent Disk volumes. However, if you only attach a combined total of 64 Hyperdisk volumes to the VM, you can still attach up to 64 Persistent Disk volumes to the VM.
What's next
- Learn how to optimize the performance of your Hyperdisk volumes