Network-optimized machine family for Compute Engine

The network-optimized machine family delivers the highest network and block storage performance within Compute Engine. They offer best-in-class price-performance optimized for demanding I/O bound applications such as network and security appliances, high-performance databases, Telco 5G UPF, high-scale data analytics, and distributed file systems. Compared to the general-purpose machine family, the machine series in the network-optimized machine family offer significantly higher:

  • Network bandwidth
  • Packet processing performance (PPS)
  • Storage throughput and IOPS per vCPU

By eliminating the need to over-provision compute resources just to scale I/O capabilities, the network-optimized family delivers significant Total Cost of Ownership (TCO) benefits.

Machine series Workloads
C4N

  • Network and Security appliances

    • Firewall
    • Load balancers
    • Virtual routers
    • DDOS mitigation appliances
    • NatProxy
    • CDN
  • Telco (5G UPF)
  • High density containers
  • Filesystems
  • High performance databases
  • Large-scale data analytics
  • CPU-based AI/ML workloads
M4N
  • High-performance vector databases
  • Retrieval-augmented generation (RAG) data layers
  • Massive in-memory context caching
  • Real-time semantic search

C4N machine series

C4N instances are powered by 5th Generation Intel Xeon Scalable processors (code named Emerald Rapids) running high-frequency DDR5 memory and dual-NIC Titanium offloaded architecture. The C4N machine series is engineered to maximize both networking throughput and extreme block storage performance without requiring premium infrastructure add-ons (such as per VM Tier_1 networking performance).

  • For databases: When compared to similarly sized C4 instances, C4N delivers 45% better queries per second for MySQL when the data resides primarily on disk.
  • For web-serving workloads: C4N significantly boosts performance for network-bound web applications. C4N delivers up to 55% additional Nginx requests per second for typical web request sizes (100-300kb) when compared to C4.

C4N instances are available in 8 predefined machine types across standard, high CPU, and high memory configurations, scaling from 2 to 192 vCPUs and up to 1.5 TB of memory.

C4N offers the following features:

  • Superior VM-to-VM network bandwidth: Achieves up to 400 Gbps of VM-to-VM network bandwidth and supports up to 50 Gbps single-flow bandwidth between C4N instances routed within the same VPC network.
  • Enhanced VM to Internet performance: Internet egress network bandwidth can reach up to 200 Gbps. Internet egress packet processing performance can scale up to 48 million packets per second (MPPS).
  • Industry-leading packet processing: Up to 95 MPPS of sustained packet processing performance (measured using DPDK Pktgen).
  • Optimized I/O for smaller shapes: Up to 25 to 50 Gbps of network bandwidth specifically for machine types with 2 to 16 vCPUs. Additionally, these smaller machine types introduce predictable, steady-state baseline bandwidth limits to provide consistent performance at a lower cost.
  • Enhanced out-of-the-box networking: gVNIC-type network interfaces on C4N now start with more Tx/Rx queues by default, and scale with the number of vCPUs up to a maximum of 64 per vNIC.
  • Titanium-powered efficiency with Dual-NIC Titanium architecture: Features two 200G Titanium network adapters (2 x 200G) to fully offload network and storage management, ensuring your applications run with maximum performance and predictability.
  • Leading Block Storage performance and options: Supports the complete Hyperdisk portfolio, including Hyperdisk Balanced, Hyperdisk Balanced High Availability, Hyperdisk Extreme, Hyperdisk Throughput, and Hyperdisk ML block storage options. C4N with Hyperdisk Extreme provides the low-latency, high-speed data access that modern databases and enterprise AI applications need, with up to 25 GiB/s of block storage throughput and nearly 1M IOPS. C4N offers a 2.5x increase in storage performance over C4.

C4N supports the following discount and consumption options:

  • Resource-based committed use discounts (CUDs)
  • Flexible CUDs
  • Spot VMs
  • Reservations
  • Sole-tenancy
  • Spread and compact placement policies

C4N Limitations

The C4N machine series has the following restrictions:

  • C4N machine types only available as predefined machine types. Custom machine types aren't available.
  • You can't use GPUs with C4N instances.

C4N machine types

C4N highcpu

Machine types vCPUs1 Memory (GB) Titanium SSD Physical NIC count NUMA domains Maximum internal bandwidth (Gbps) Maximum external bandwidth (Gbps)
c4n-highcpu-2 2 4 Not supported 1 1 shared Up to 25 Up to 7
c4n-highcpu-4 4 8 Not supported 1 1 shared Up to 30 Up to 7
c4n-highcpu-8 8 16 Not supported 1 1 shared Up to 40 Up to 15
c4n-highcpu-16 16 32 Not supported 1 1 shared Up to 50 Up to 25
c4n-highcpu-24 24 48 Not supported 1 1 shared 50 Up to 25
c4n-highcpu-48 48 96 Not supported 1 1 isolated 100 Up to 50
c4n-highcpu-96 96 192 Not supported 1 2 200 Up to 100
c4n-highcpu-192 192 384 Not supported 2 4 (full machine) 4002 Up to 200

C4N standard

Machine types vCPUs1 Memory (GB) Titanium SSD Physical NIC count NUMA domains Maximum internal bandwidth (Gbps) Maximum external bandwidth (Gbps)
c4n-standard-2 2 7 Not supported 1 1 shared Up to 25 Up to 7
c4n-standard-4 4 15 Not supported 1 1 shared Up to 30 Up to 7
c4n-standard-8 8 30 Not supported 1 1 shared Up to 40 Up to 15
c4n-standard-16 16 60 Not supported 1 1 shared Up to 50 Up to 25
c4n-standard-24 24 90 Not supported 1 1 shared 50 Up to 25
c4n-standard-48 48 180 Not supported 1 1 isolated 100 Up to 50
c4n-standard-96 96 360 Not supported 1 2 200 Up to 100
c4n-standard-192 192 720 Not supported 2 4 (full machine) 4002 Up to 200

C4N highmem

Machine types vCPUs1 Memory (GB) Titanium SSD Physical NIC count NUMA domains Maximum internal bandwidth (Gbps) Maximum external bandwidth (Gbps)
c4n-highmem-2 2 15 Not supported 1 1 shared Up to 25 Up to 7
c4n-highmem-4 4 31 Not supported 1 1 shared Up to 30 Up to 7
c4n-highmem-8 8 62 Not supported 1 1 shared Up to 40 Up to 15
c4n-highmem-16 16 124 Not supported 1 1 shared Up to 50 Up to 25
c4n-highmem-24 24 186 Not supported 1 1 shared 50 Up to 25
c4n-highmem-48 48 372 Not supported 1 1 isolated 100 Up to 50
c4n-highmem-96 96 744 Not supported 1 2 200 Up to 100
c4n-highmem-192 192 1488 Not supported 2 4 (full machine) 4002 Up to 200

1 Each virtual CPU (vCPU) is implemented as a single hardware multithread, and two vCPUs share each physical CPU core by default.
2 For instances with 192 vCPUs, you must configure at least 2 network interfaces (vNIC), with each network interface attached to a different physical NIC, to achieve the full network throughput. Compute Engine automatically maps the vNIC to a physical NIC in a round-robin fashion.

Supported disk types for C4N

C4N instances support only the NVMe disk interface and can use the following block storage types:

  • Hyperdisk Balanced (hyperdisk-balanced)
  • Hyperdisk Balanced High Availability (hyperdisk-balanced-high-availability)
  • Hyperdisk Throughput (hyperdisk-throughput)
  • Hyperdisk Extreme (hyperdisk-extreme)
  • Hyperdisk ML (hyperdisk-ml)

For the performance limits of each Hyperdisk type, see Hyperdisk performance limits.

Disk and capacity limits

The following restrictions apply:

  • The number of Hyperdisk volumes can't exceed 64 per VM.
  • The maximum total disk capacity across all disks can't exceed 512 TiB.

For details about the capacity limits, see Hyperdisk capacity limits per VM.

C4N storage limits are described in the following table:

C4N highcpu

Maximum number of disks per instance
Machine types All Hyperdisk
types		 Hyperdisk Balanced Hyperdisk Balanced High Availability Hyperdisk Throughput Hyperdisk Extreme Hyperdisk ML
c4n-highcpu-2 8 8 8 8 8 8
c4n-highcpu-4 16 16 16 16 16 16
c4n-highcpu-8 32 32 32 32 32 32
c4n-highcpu-16 32 32 32 32 32 32
c4n-highcpu-24 32 32 32 32 32 32
c4n-highcpu-48 64 64 64 64 64 64
c4n-highcpu-96 128 128 128 128 128 128
c4n-highcpu-192 128 128 128 128 128 128

C4N standard

Maximum number of disks per instance
Machine types All Hyperdisk
types		 Hyperdisk Balanced Hyperdisk Balanced High Availability Hyperdisk Throughput Hyperdisk Extreme Hyperdisk ML
c4n-standard-2 8 8 8 8 8 8
c4n-standard-4 16 16 16 16 16 16
c4n-standard-8 32 32 32 32 32 32
c4n-standard-16 32 32 32 32 32 32
c4n-standard-24 32 32 32 32 32 32
c4n-standard-48 64 64 64 64 64 64
c4n-standard-96 128 128 128 128 128 128
c4n-standard-192 128 128 128 128 128 128

C4N highmem

Maximum number of disks per instance
Machine types All Hyperdisk
types		 Hyperdisk Balanced Hyperdisk Balanced High Availability Hyperdisk Throughput Hyperdisk Extreme Hyperdisk ML
c4n-highmem-2 8 8 8 8 8 8
c4n-highmem-4 16 16 16 16 16 16
c4n-highmem-8 32 32 32 32 32 32
c4n-highmem-16 32 32 32 32 32 32
c4n-highmem-24 32 32 32 32 32 32
c4n-highmem-48 64 64 64 64 64 64
c4n-highmem-96 128 128 128 128 128 128
c4n-highmem-192 128 128 128 128 128 128

Network support for C4N instances

C4N instances deliver up to 400 Gbps standard network bandwidth for VM-to-VM networking, a 4x increase in network bandwidth per vCPU when compared to standard C4 instances. C4N instances don't use per VM Tier_1 networking performance.

For the largest C4N machine types (192 vCPUs), during instance creation you must configure at least 2 network interfaces (vNICs) that use Jumbo frames (8896B) to achieve the full network throughput. Compute Engine maps the vNICs automatically to physical NICs (pNICs) in a round-robin way. The guest OS or your application can then divide the network load across at least two vNICs (mapped to separate pNICs) to achieve the full network throughput and ensure optimal performance.

C4N instances require gVNIC network interfaces. The maximum number of network interfaces that you can attach to an instance scales with the number of vCPUs, up to a maximum of 10 network interfaces. For more information about using multiple network interfaces with Compute Engine, see Multiple network interfaces.

Before migrating to C4N or creating C4N instances, make sure that the operating system image that you use fully supports C4N and higher network bandwidths.

Maintenance experience for C4N instances

During the lifecycle of a Compute Engine instance, the host machine that your instance runs on undergoes multiple host events. A host event can include the regular maintenance of Compute Engine infrastructure, or in rare cases, a host error. Compute Engine also applies some non-disruptive lightweight upgrades for the hypervisor and network in the background.

The C4N machine series offers the following features related to host maintenance:

Machine type Typical scheduled maintenance event frequency Maintenance behavior Advanced notification On-demand maintenance Simulate maintenance
c4n-*-192 Minimum of 30 days Live migrate Up to 7 days Yes Yes
All others Minimum of 30 days Live migrate Up to 7 days No Yes

The maintenance frequencies shown in the previous table are approximations, not guarantees. Compute Engine might occasionally perform maintenance more frequently.

M4N machine series

M4N is engineered to deliver the highest I/O performance available, reaching up to 12,500 MiB/s of combined host storage performance and up to 200 Gbps network bandwidth. This new level of performance opens up new possibilities for I/O-intensive workloads that require extreme bandwidth for data access and processing.

M4N instances are powered by the Intel Emerald Rapids processors and Titanium offload processors. This machine series is well-suited for large in-memory databases such as SAP HANA, as well as online analytical processing (OLAP) and in-memory data analytics workloads. The M4N machine series offers a lower cost per transaction for Oracle Database workloads and the best TCO when compared to any other compute instance for databases that require licensing per core.

M4N machine types allow you to provision up to 112 vCPUs and up to 2.9 TB of RAM. M4N instances use only NVMe for storage, and support Hyperdisk Balanced and Hyperdisk Extreme. M4N instances use only gVNIC for networking. VirtIO-net and SCSI interfaces are not supported.

M4N Limitations

The M4N machine series has the following restrictions:

  • M4N machine type only available as predefined machine types. Custom machine types aren't available.
  • You can't use GPUs with M4N instances.
  • M4N instances are available in only select zones and regions.

M4N machine types

Machine types vCPUs1 Memory (GB) Local SSD Maximum internal network bandwidth
(Gbps)2		 Maximum external network bandwidth
(Gbps)2		 NUMA domains
m4n-hypermem-16 16 248 Not available Up to 50 Up to 25 1
m4n-hypermem-32 32 496 Not available 57 28 1
m4n-hypermem-64 64 992 Not available 114 57 2
m4n-megamem-28 28 372 Not available 50 25 1
m4n-megamem-56 56 744 Not available 100 50 1
m4n-megamem-112 112 1,488 Not available 200 100 2
m4n-ultramem-28 28 744 Not available 50 25 1
m4n-ultramem-56 56 1,488 Not available 100 50 2
m4n-ultramem-112 112 2,976 Not available 200 100 4

1 Each virtual CPU (vCPU) is implemented as a single hardware multithread, and two vCPUs share each physical CPU core by default.
2 Maximum egress bandwidth cannot exceed the number given. Actual egress bandwidth depends on the destination IP address and other factors. See Network bandwidth.

Supported disk types for M4N

M4N instances can use the following block storage types:

  • Hyperdisk Balanced (hyperdisk-balanced)
  • Hyperdisk Extreme (hyperdisk-extreme)

Disk and capacity limits

The following restrictions apply:

  • The number of Hyperdisk volumes can't exceed 64 per VM.
  • The maximum total disk capacity across all disks can't exceed 512 TiB.

For details about the capacity limits, see Hyperdisk capacity limits per VM.

M4N storage limits are described in the following table:

Maximum number of disks
Machine types Hyperdisk
per VM		 Hyperdisk Balanced Hyperdisk Throughput Hyperdisk Extreme
m4n-hypermem-16 16 16 0 8
m4n-hypermem-32 32 32 0 8
m4n-hypermem-64 32 32 0 8
m4n-megamem-28 32 32 0 8
m4n-megamem-56 32 32 0 8
m4n-megamem-112 64 64 0 8
m4n-ultramem-28 32 32 0 8
m4n-ultramem-56 32 32 0 8
m4n-ultramem-112 64 64 0 8

Network support for M4N instances

M4N instances require gVNIC network interfaces. M4N supports up to 200 Gbps network bandwidth for standard networking and doesn't support per VM Tier_1 networking performance.

Before migrating to M4N or creating M4N VM instances, make sure that the operating system image that you use supports the gVNIC driver for VM instances. These images include an updated gVNIC driver, even if the guest OS shows the gve driver version as 1.0.0. If your M4N VM is using an operating system with an older version of gVNIC driver, this is still supported but the VM might experience suboptimal performance such as less network bandwidth or higher latency.

If you use a custom OS image to create a M4N VM, you can manually install the most recent gVNIC driver. The gVNIC driver version v1.4.2 or later is recommended for use with M4N VMs. Google recommends using the latest gVNIC driver version to benefit from additional features and bug fixes.

Maintenance experience for M4N instances

During the lifecycle of a Compute Engine instance, the host machine that your instance runs on undergoes multiple host events. A host event can include the regular maintenance of Compute Engine infrastructure, or in rare cases, a host error. Compute Engine also applies some non-disruptive lightweight upgrades for the hypervisor and network in the background.

The M4N machine series offers the following features related to host maintenance:

Machine type Typical scheduled maintenance event frequency Maintenance behavior Advanced notification On-demand maintenance Simulate maintenance
All machine types Monthly Live migrate 7 days Yes Yes

The maintenance frequencies shown in the previous table are approximations, not guarantees. Compute Engine might occasionally perform maintenance more frequently.

What's next