When creating a Tencent Cloud CVM, the instance type you specify determines the instance's host hardware configuration. Each instance type provides different computing, memory and storage features. You can choose the instance type that suits your application scale. Tencent Cloud provides a range of instance families with varying combinations of CPU, memory, storage, heterogeneous hardware, and network bandwidth. This gives you the flexibility in selecting the appropriate mix of resources for your applications.
Tencent Cloud CVM is pay-as-you-go. Instances can be activated and terminated at any time, and you only pay for resources used. This flexible billing mode lets you meet fluctuating demands while keeping costs low. In addition, usage is billed in seconds to further maximize your savings.
Instance Type
Tencent Cloud instance families are categorized as follows:
| Type |
Sub-type |
Description |
| Standard Instance Family |
|
Standard instances provide a balance of compute, memory, and network resources to accommodate most applications. |
| Memory Optimized Instance Family |
|
Memory optimized instances feature large memory and are suitable for applications that require extensive memory operations, searches, and computations, such as high-performance databases and distributed memory caching. |
| High I/O Instance Family |
|
High I/O instances feature high random IOPS, high throughput and low latency. They are suitable for I/O-intensive applications that require high disk read/write performance and low latency, such as high-performance databases. |
| Big Data Instance Family |
Big Data D2
|
This instance family is equipped with massive storage resources, features high throughput, and is suitable for throughput-intensive applications such as Hadoop distributed computing, massive log processing, distributed file systems, and large data warehouses. |
| Computing Instance Family |
|
This family comes with a powerful processor with a base frequency of 3.2GHz, and provides the highest single-core computing performance. It is suitable for compute-intensive workloads such as batch processing, high performance computing, and dedicated game servers. |
| Heterogeneous Computing Instance Family |
- |
This family is equipped with heterogeneous hardware such as GPU and FPGA to deliver real-time, fast parallel computing and floating-point computing capabilities. It is suitable for high-performance applications such as deep learning, scientific computing, video encoding/decoding, and graphics workstations. |
Note:
Some of the families are discontinued.
Glossary
-
Send/Receive Packets: the maximum number of data packets that the instance can process per second for both sending and receiving, without differentiating private or public network traffic.
-
Private Network Bandwidth Capacity: the maximum number of bits that the instance can transfer per second over private network
-
Multi-queue Technology: multiple send/receive packet queues are supported on a virtual ENI, with the sending and receiving of the data packets of each queue capable of being simultaneously processed by different CPUs
-
Number of Queues: the quantity of send/receive packet queues supported by each virtual ENI (N number of queues indicates that N number of receiving queues and N number of sending queues can be simultaneously supported)
Restrictions on Instances
-
The total number of instances that can be enabled in one region is limited. For more information, please see CVM Instance Purchase Limit.
-
Restrictions on system and data disks mounted on an instance: to ensure premium disk I/O performance, Tencent Cloud sets limits on the size and type of data disks purchased with an instance. For more information, see the supported disks of each instance family. You can also purchase separate cloud disks if you have higher disk requirements.
-
Note that the private network bandwidth capacity of an instance specification is the maximum private network bandwidth limit of the corresponding instance. If the CVM private network traffic exceeds this limit, random packet loss may happen within the private network for your instances.
-
The availability of instance specifications may vary from region to region. Some configurations may be sold out. Please see the purchase page for the latest information.
-
The send/receive packets performance data noted in this document is the results of a one-time network forwarding test. See Network Performance Test for the testing method. Separate testing is needed to estimate the performance for your business.
Here is a complete list of instance families.
Standard Instance Family
Standard instances provide a balance of compute, memory, and network resources to accommodate most applications.
Standard S5
Standard S5 instances are the latest generation of standard instances. Based on an all-new optimized virtualization platform, this family provides a balance of stable computing, memory, and network resources. This is a premium choice for many applications.
Standard S5 instances are equipped with the latest Xeon® Cascade Lake processors with the latest DDR4 memory. They are network optimized by default, and provide excellent private network throughput and bandwidth.
Features
-
2.5 GHz Intel® Xeon® Cascade Lake processor, turbo frequency 3.1 GHz, with the latest generation 6-channel DDR4 for stable memory computing performance
-
New Intel Advanced Vector Extension (AVX-512) instruction set
-
1:2 or 1:4 processor to memory ratio.
-
Supports up to 28 Gbps of private network bandwidth for ultra-high packet throughput to meet the needs of extremely high private network transmission demand
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
Application Scenarios
Standard S5 instances are applicable to the following scenarios:
-
Enterprise applications of different types and sizes
-
Small and medium-sized database systems, caches, and search clusters
-
Computing clusters, memory-intensive data processing
-
Scenarios that require sending and receiving massive network packets, such as video on-screen comments, live video broadcasting, and gaming
Requirements
-
S5 instances are pay-as-you-go.
-
S5 instances can only be launched in a VPC.
-
Configuration purchase is available for S5 instances. Please see the instance specifications below. Make sure that the size of the S5 instance you choose meet the minimum CPU memory requirements of your operating system and applications. In many cases, GUI operating systems (such as Windows) that consume extensive memory and CPU resources may need larger instances. As the needs of your workload for memory and CPU increase, you can expand to higher configurations or choose other instance types.
|
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Standard SA2
A Standard SA2 instance uses the latest generation AMD EPYC™ processor. This ultra-high cost performance instance family supports a variety of specifications, ensuring cost efficiency. Standard SA2 instances provides a balance of computing, memory, and network resources, and it is a good choice for many applications.
Standard SA2 instances are equipped with the latest AMD EPYC™ ROME processors with the latest DDR4 memory, default network optimization, private network throughput up to 7,500,000 pps, and support for up to 25 Gbps of private network bandwidth.
Features
-
Based on the StarLake server developed by Tencent Cloud, providing reliable, secure and stable performance
-
2.6 GHz AMD EPYC™ ROME processor, turbo frequency 3.3 GHz, with the latest generation 8-channel DDR4 for stable memory computing performance
-
Larger instance size, SA2.45XLARGE464, offering 180 vCPUs and 464 GB of memory
-
A wide range of processor to memory ratio, such as 1:2 and 1:4
-
Supports up to 25 Gbps of private network bandwidth for ultra-high packet throughput to meet the needs of extremely high private network transmission demand
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
Application Scenarios
Standard SA2 instances are applicable to the following scenarios:
-
Enterprise applications of different types and sizes
-
Search and other computing clusters
-
Video decoding, video rendering and other applications sensitive to single core performance
Requirements
-
SA2 instances are pay-as-you-go.
-
SA2 instances can only be launched in a VPC.
-
Configuration purchase is available for SA2 instances. Please see the instance specifications below. Make sure that the size of the SA2 instance you choose meet the minimum CPU memory requirements of your operating system and applications. In many cases, GUI operating systems (such as Windows) that consume extensive memory and CPU resources may need larger instances. As the needs of your workload for memory and CPU increase, you can expand to higher configurations or choose other instance types.
|
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Standard S4
Standard S4 instances are a new generation of standard instances. This family provides a balance of computing, memory, and network resources, and it is a good choice for many applications.
Standard S4 instances are equipped with the latest Xeon® Skylake processors with the latest DDR4 memory, default network optimization, private network throughput up to 6,000,000 pps, and support for up to 25 Gbps of private network bandwidth.
Features
-
2.4 GHz Intel Xeon® Skylake 6148 processors with stable computing performance
-
New Intel Advanced Vector Extension (AVX-512) instruction set
-
The latest generation of 6-channel DDR4 memory with a memory bandwidth of 2,666 MT/s
-
Larger instance size, S4.18XLARGE228, offering 72 vCPUs and 228 GB of memory
-
1:2 or 1:4 processor to memory ratio.
-
Supports up to 25 Gbps of private network bandwidth for ultra-high packet throughput to meet the needs of extremely high private network transmission demand
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
Application Scenarios
Standard S4 instances are applicable to the following scenarios:
-
Enterprise applications of different types and sizes
-
Small and medium-sized database systems, caches, and search clusters
-
Computing clusters, memory-intensive data processing
-
Scenarios that require sending and receiving massive network packets, such as video on-screen comments, live video broadcasting, and gaming
Requirements
-
S4 instances are pay-as-you-go.
-
S4 instances can only be launched in a VPC.
-
Configuration purchase is available for S4 instances. Please see the instance specifications below. Make sure that the size of the S4 instance you choose meet the minimum CPU memory requirements of your operating system and applications. In many cases, GUI operating systems (such as Windows) that consume extensive memory and CPU resources may need larger instances. As the needs of your workload for memory and CPU increase, you can expand to higher configurations or choose other instance types.
|
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Standard Network Optimized SN3ne
Standard SN3ne instances are a relatively new generation of network optimized instances. This family provides a balance of computing, memory, and network resources, with outstanding network throughput, and it is a good choice for many applications.
Standard Network Optimized SN3ne instances are equipped with the latest Xeon® Skylake processors with the latest DDR4 memory, default network optimization, and private network throughput up to 6,000,000 pps, with performance is nearly 8 times greater than the Standard S3 family. It can support up to 25 Gbps of private network bandwidth, with performance 2.5 times greater than the Standard S3 family.
Features
-
2.5 GHz Intel Xeon® Skylake 6133 processors with stable computing performance
-
The latest generation of 6-channel DDR4 memory with a memory bandwidth of 2,666 MT/s
-
Larger instance size, SN3ne.18XLARGE228, offering 72 vCPUs and 228 GB of memory
-
1:2 or 1:4 processor to memory ratio.
-
Supports up to 25 Gbps of private network bandwidth for ultra-high packet throughput to meet the needs of extremely high private network transmission demand
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
-
Support all types of cloud disks
Application Scenarios
Standard Network Optimized SN3ne instances are applicable to the following scenarios:
-
Enterprise applications of different types and sizes
-
Small and medium-sized database systems, caches, and search clusters
-
Computing clusters, memory-intensive data processing
-
Scenarios that require sending and receiving massive network packets, such as video on-screen comments, live video broadcasting, and gaming
Requirements
-
SN3ne instances are pay-as-you-go.
-
SN3ne instances can only be launched in a VPC.
-
Configuration purchase is available for SN3ne instances. Please see the instance specifications below. Make sure that the size of the SN3ne instance you choose meet the minimum CPU memory requirements of your operating system and applications. In many cases, GUI operating systems (such as Windows) that consume extensive memory and CPU resources may need larger instances. As the needs of your workload for memory and CPU increase, you can expand to higher configurations or choose other instance types.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Standard S3
Standard S3 instances are a relatively new generation of standard instances. This family provides a balance of computing, memory, and network resources, and it is a good choice for many applications.
Standard S3 instances are equipped with the latest Xeon® Skylake processors with the latest DDR4 memory and support for up to 10 Gbps of private network bandwidth.
Features
-
2.5 GHz Intel Xeon® Skylake 6133 processors with stable computing performance
-
The latest generation of 6-channel DDR4 memory with a memory bandwidth of 2,666 MT/s
-
Larger instance size, S3.20XLARGE320, offering 80 vCPUs and 320 GB of memory
-
1:2 or 1:4 processor to memory ratio.
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
-
Support all types of cloud disks
Application Scenarios
Standard S3 instances are applicable to the following scenarios:
-
Enterprise applications of different types and sizes
-
Small and medium-sized database systems, caches, and search clusters
-
Computing clusters, memory-intensive data processing
Requirements
-
S3 instances are pay-as-you-go.
-
S3 instances can be launched in basic networks and VPCs.
-
Configuration purchase is available for S3 instances. Please see the instance specifications below. Make sure that the size of the S3 instance you choose meet the minimum CPU memory requirements of your operating system and applications. In many cases, GUI operating systems (such as Windows) that consume extensive memory and CPU resources may need larger instances. As the needs of your workload for memory and CPU increase, you can expand to higher configurations or choose other instance types.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Standard SA1
A Standard SA1 instance uses the AMD EPYC™ processor. This ultra-high cost performance instance family supports a variety of specifications, ensuring cost efficiency. Standard SA1 instances provides a balance of computing, memory, and network resources, and it is a good choice for many applications.
Features
-
2.0 GHz AMD EPYC™ 7551 processors with a Turbo Boost clock of 2.55 GHz, offering stable computing performance
-
The latest generation of 8-channel DDR4 memory with a memory bandwidth of 2,666 MT/s
-
1:2 or 1:4 processor to memory ratio.
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
-
Support all types of cloud disks
Application Scenarios
Standard SA1 instances are applicable to the following scenarios:
-
Enterprise applications of different types and sizes
-
Small and medium-sized database systems, caches, and search clusters
-
Computing clusters, memory-intensive data processing
Requirements
-
SA1 instances are pay-as-you-go.
-
SA1 instances can be launched in basic networks and VPCs.
-
Configuration purchase is available for SA1 instances. Please see the instance specifications below. As the needs of your workload for memory and CPU increase, you can expand to higher configurations or choose other instance types.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Note: In the "SA1 Instances Specification List", "-" in the "Send/Receive Packets“ column indicates that, for this specification, the network packet rate and server CPU performance are not guaranteed. If you have strict requirement on the performance, please choose models with performance guarantee.
|
Standard Network Optimized S2ne
Standard Network Optimized S2ne instances are the best choice for applications that require sending and receiving massive network packets. They support sending and receiving up to millions of network packets per second. This family is recommended for businesses with high network PPS requirements, such as large game servers, videos, and live streaming.
Note: This instance type is currently only available to beta users. Contact your account manager if you wish to purchase these instance type.
Features
-
Intel Xeon E5-2680 Broadwell (v4) processors with base frequency of 2.4 GHz and DDR4 memory, offering stable computing performance
-
Up to 48 cores and 192 GB are available for sale.
-
1:2 or 1:4 processor to memory ratio.
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
-
Support all types of cloud disks
Application Scenarios
-
Scenarios that require sending and receiving massive network packets, such as game services, video services, and financial analysis
-
Enterprise applications of different types and sizes
Requirements
-
S2ne instances are pay-as-you-go.
-
S2ne instances can only be launched in a VPC.
-
Configuration purchase is available for S2ne instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Standard S2
Standard S2 instances are a relatively new generation of instances. This family provides a balance of computing, memory, and network resources, and it is a good choice for many applications.
Standard S2 instances are equipped with Intel® Xeon® Broadwell processors with DDR4 memory.
Features
-
Intel Xeon E5-2680 Broadwell (v4) processors with base frequency of 2.4 GHz and DDR4 memory
-
Up to 56 cores and 224 GB are available for sale.
-
1:2 or 1:4 processor to memory ratio.
-
Balance of computing, memory, and network resources
Application Scenarios
This family is used for small and mid-size databases, data processing tasks that require additional memory and cache fleets, and for running backend servers for SAP, Microsoft SharePoint, cluster computing and other enterprise applications.
Requirements
-
S2 instances are pay-as-you-go, and can also be used as production instances of standard host HS20 in CDHs.
-
S2 instances can be launched in basic networks and VPCs.
-
Configuration purchase is available for S2 instances. Please see the instance specifications below. Make sure that the size of the S2 instance you choose meet the minimum CPU memory requirements of your operating system and applications. In many cases, GUI operating systems (such as Windows) that consume extensive memory and CPU resources may need larger instances. As the needs of your workload for memory and CPU increase, you can expand to higher configurations or choose other instance types.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Standard S1
Standard S1 instances offer a range of CPUs from low to high core count. They deliver significant savings with flexible configuration options to meet diverse needs. They also offer a range of data disk options, including local disks and SSD cloud disks. (Options may vary depending on hardware specifications).
Features
Standard S1 instances have the following features:
-
Offer a range of CPUs from low to high core count for flexible configuration options
-
Intel Xeon CPUs and DDR3 memories
-
Support storage options of local disks and SSD cloud disks.
-
Balance of computing, memory, and network resources
Application Scenarios
Standard S1 instances are suitable for large, medium, and small-sized applications and databases.
Requirements
-
S1 instances are pay-as-you-go, and can also be used as production instances of standard host in CDHs.
-
S1 instances can be launched in basic networks and VPCs.
-
"-" indicates that, for this specification, the network packet rate and server CPU performance are not guaranteed. If you have strict requirement on the performance, please choose models with performance guarantee.
-
Configuration purchase is available for S1 instances. Please see the instance specifications below. Make sure that the size of the S1 instance you choose meet the minimum CPU memory requirements of your operating system and applications. In many cases, GUI operating systems (such as Windows) that consume extensive memory and CPU resources may need larger instances. As the needs of your workload for memory and CPU increase, you can expand to higher configurations or choose other instance types.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Note:
Among standard S1 instances, "-" indicates that, for this specification, the network packet rate and server CPU performance are not guaranteed. If you have strict requirement on the performance, please choose models with performance guarantee.
Memory Optimized Instance Family
Memory optimized instances feature large memory and are suitable for applications that require extensive memory operations, searches, and computations, such as high-performance databases and distributed memory caching.
Memory Optimized M5
As the latest generation of memory optimized instances, Memory Optimized M5 instances are designed based on an all-new optimized virtualization platform to deliver fast, stable performance for processing large data sets in memory, and are the best choice for applications demanding high-memory computing.
Memory Optimized M5 instances are equipped with the latest Xeon® Cascade Lake processors with the latest DDR4 memory. They are network optimized by default, and provide excellent private network throughput and bandwidth.
Application Scenarios
These instances are an ideal choice for:
-
Applications that require extensive memory operations, searches, and computations, such as high-performance databases and distributed memory caching.
-
Users who build their own Hadoop clusters or Redis to use in fields such as computational genomics.
-
Scenarios that require sending and receiving massive network packets, such as video on-screen comments, live video broadcasting, and gaming
Features
-
2.5 GHz Intel® Xeon® Cascade Lake processor, with the latest generation 6-channel DDR4 memory for stable memory computing performance
-
New Intel Advanced Vector Extension (AVX-512) instruction set
-
1:8 processor to memory ratio
-
Priced lower than any other memory-optimized instances with the same memory
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
Requirements
-
M5 instances are pay-as-you-go.
-
M5 instances can only be launched in a VPC.
-
Configuration purchase is available for M5 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Memory Optimized M4
As the new generation of memory optimized instances, Memory Optimized M4 instances are designed to deliver high performance for processing large data sets in memory, and are the best choice for applications demanding high-memory computing.
Memory Optimized M4 instances are equipped with the latest Xeon® Skylake processors with the latest DDR4 memory, default network optimization, private network throughput up to 6,000,000 pps, and ultra-high private network bandwidth.
Application Scenarios
These instances are an ideal choice for:
-
Applications that require extensive memory operations, searches, and computations, such as high-performance databases and distributed memory caching.
-
Users who build their own Hadoop clusters or Redis to use in fields such as computational genomics.
-
Scenarios that require sending and receiving massive network packets, such as video on-screen comments, live video broadcasting, and gaming
Features
-
2.4 GHz Intel Xeon® Skylake 6148 processors with stable computing performance
-
New Intel Advanced Vector Extension (AVX-512) instruction set
-
The latest generation of 6-channel DDR4 memory with a bandwidth of 2,666 MT/sec
-
Larger instance size is M4.16XLARGE512, offering 64 vCPUs and 512 GB of memory
-
1:8 or 1:12 processor to memory ratio
-
Priced lower than any other memory-optimized instances with the same memory
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
Requirements
-
M4 instances are pay-as-you-go.
-
M4 instances can only be launched in a VPC.
-
Configuration purchase is available for M4 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Memory Optimized M3
As a relatively new generation of memory optimized instances, Memory Optimized M3 instances are designed to deliver high performance for processing large data sets in memory, and are the best choice for applications demanding high-memory computing.
Memory Optimized M3 instances are equipped with the latest Xeon® Skylake processors with the latest DDR4 memory and support for up to 10 Gbps of private network bandwidth.
Application Scenarios
These instances are an ideal choice for:
-
Applications that require extensive memory operations, searches, and computations, such as high-performance databases and distributed memory caching.
-
Users who build their own Hadoop clusters or Redis to use in fields such as computational genomics.
Features
-
2.5 GHz Intel Xeon® Skylake 6133 processors with stable computing performance
-
The latest generation of 6-channel DDR4 memory with a bandwidth of 2,666 MT/sec
-
Larger instance size is M3.16XLARGE512, offering 64 vCPUs and 512 GB of memory
-
1:8 or 1:12 processor to memory ratio
-
Priced lower than any other memory-optimized instances with the same memory
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
Requirements
-
M3 instances are pay-as-you-go.
-
M3 instances can be launched in basic networks and VPCs.
-
Configuration purchase is available for M3 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Memory Optimized M2
Memory Optimized M2 instances are designed to deliver high performance for processing large data sets in memory. They feature large memory, which makes them the perfect choice for applications demanding high memory computing.
Application Scenarios
These instances are an ideal choice for:
- Applications that require extensive memory operations, searches, and computations, such as high-performance databases and distributed memory caching.
- Users who build their own Hadoop clusters or Redis to use in fields such as computational genomics.
Features
-
2.4 GHz Intel Xeon® E5-2680v4 processors, DDR4 memory
-
Up to 448 GB memory available. M2.14XLARGE448, offering 56 vCPUs and 448 GB of memory
-
1:8 processor to memory ratio
-
Priced lower than any other memory-optimized instances with the same memory
Requirements
-
M2 instances are pay-as-you-go, and can also be used as production instances of memory optimized host HM20 in CDHs.
-
M2 instances can be launched in basic networks and VPCs.
-
Configuration purchase is available for M2 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Memory Optimized M1
Memory Optimized M1 instances come with approximately 1:8 CPU to memory ratio. They are well-suited for applications that require extensive memory operations, searches, and computations, such as high-performance databases and distributed memory caching.
Features
-
2.3 GHz Intel Xeon® E5-2670 v3 processors and DDR3 memories, providing larger-sized instances with stronger computing capacities.
-
Memory-intensive with a golden CPU to memory ratio, satisfying the needs for large-scale business deployment.
Application Scenarios
These instances are an ideal choice for:
-
Applications that require extensive memory operations, searches, and computations, such as high-performance databases and distributed memory caching.
-
Users who build their own Hadoop clusters or Redis to use in fields such as computational genomics.
Requirements
-
M1 instances are pay-as-you-go.
-
M1 instances can be launched in basic networks and VPCs.
-
"-" indicates that, for this specification, the network packet rate and server CPU performance are not guaranteed. If you have strict requirement on the performance, please choose models with performance guarantee.
-
Configuration purchase is available for M1 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Note:
Among M1 instances, "-" indicates that, for this specification, the network packet rate is not guaranteed. If you have strict requirement on the performance, please choose models with performance guarantee.
High I/O Instance Family
High I/O instances feature high random IOPS, high throughput and low latency and are well-suited for I/O-intensive applications that require high disk read/write performance and low latency, such as high-performance databases.
High I/O IT5
High I/O IT3 instances, based on NVMe SSD instance storage, are designed for I/O-intensive workloads. They come with the storage resources featuring low latency, super high IOPS and high throughput. They offer an IOPS of up to 1.8 million and a throughput reaching up to 11 GB/s, allowing for an ultra high IOPS at a low cost. This instance type is suitable for I/O-intensive workloads such as high performance relational databases, Elasticsearch, etc.
IT3 instances feature inexpensive and intensive storage, providing higher IOPS and larger private network bandwidth for each CPU core. Note: High I/O IT3 instances are currently only available to beta users. Contact your account manager if you wish to purchase these instances.
Application Scenarios
-
High-performance databases, NoSQL databases (e.g. MongoDB), and clustered databases
-
I/O intensive applications that require low latency, such as online transaction processing (OLTP) systems, and Elasticsearch.
Features
-
2.5 GHz Intel Xeon® Skylake 6133 processors with stable computing performance
-
The latest generation of 6-channel DDR4 memory
-
Supports up to 23 Gbps of private network bandwidth to meet extremely high private network transmission requirements
NVMe SSD is used for instance storage, offering low latency and ultra-high IOPS
Up to 620,000 (4 KB block size) random read IOPS, and up to 2.9 GB/s (128 KB block size) sequential read throughout for a single disk Up to 1.8 million (4 KB block size) random read IOPS, and up to 11 GB/s (128 KB block size) sequential read throughout for a CVM.
Requirements
-
IT3 instances use local disks as data disks, which may lead to a risk of data loss (in case of host crash). If your application does not have a data reliability architecture, we strongly recommend choosing instances using cloud disks as data disks.
If the local disk is damaged, you will need to shut down the CVM instance for us to replace the local disk. We will notify you and perform fixes if the CVM instance crashes.
If Agent has not been installed, your CVM instance cannot be monitored. You will not receive a notification if the CVM instance fails, which is very risky. For more information on installing Agent, see Installing CVM Agents. -
IT3 instances are pay-as-you-go.
-
IT3 instances can only be launched in a VPC.
-
The configuration of IT3 instances cannot be changed.
-
Configuration purchase is available for IT3 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
1 × 3720 GB local NVMe SSD
|
|
|
|
|
|
|
|
2 × 3720 GB local NVMe SSD
|
|
|
|
|
|
|
|
4 × 3720 GB local NVMe SSD
|
|
High I/O IT3
High I/O IT3 instances, based on NVMe SSD instance storage, are designed for I/O-intensive workloads. They come with the storage resources featuring low latency, super high IOPS and high throughput. They offer an IOPS of up to 1.8 million and a throughput reaching up to 11 GB/s, allowing for an ultra high IOPS at a low cost. This instance type is suitable for I/O-intensive workloads such as high performance relational databases, Elasticsearch, etc.
IT3 instances feature inexpensive and intensive storage, providing higher IOPS and larger private network bandwidth for each CPU core.
Application Scenarios
-
High-performance databases, NoSQL databases (e.g. MongoDB), and clustered databases
-
I/O intensive applications that require low latency, such as online transaction processing (OLTP) systems, and Elasticsearch.
Features
-
2.5 GHz Intel Xeon® Skylake 6133 processors with stable computing performance
-
The latest generation of 6-channel DDR4 memory
-
Supports up to 23 Gbps of private network bandwidth to meet extremely high private network transmission requirements
NVMe SSD is used for instance storage, offering low latency and ultra-high IOPS
Up to 620,000 (4 KB block size) random read IOPS, and up to 2.9 GB/s (128 KB block size) sequential read throughout for a single disk Up to 1.8 million (4 KB block size) random read IOPS, and up to 11 GB/s (128 KB block size) sequential read throughout for a CVM.
Requirements
-
IT3 instances use local disks as data disks, which may lead to a risk of data loss (in case of host crash). If your application does not have a data reliability architecture, we strongly recommend choosing instances using cloud disks as data disks.
If the local disk is damaged, you will need to shut down the CVM instance for us to replace the local disk. We will notify you and perform fixes if the CVM instance crashes.
If Agent has not been installed, your CVM instance cannot be monitored. You will not receive a notification if the CVM instance fails, which is very risky. For more information on installing Agent, see Installing CVM Agents. -
IT3 instances are pay-as-you-go.
-
IT3 instances can only be launched in a VPC.
-
The configuration of IT3 instances cannot be changed.
-
Configuration purchase is available for IT3 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
1 × 3720 GB local NVMe SSD
|
|
|
|
|
|
|
|
2 × 3720 GB local NVMe SSD
|
|
|
|
|
|
|
|
4 × 3720 GB local NVMe SSD
|
|
Big Data Instance Family
The big data instance family is equipped with massive storage resources, features high throughput, and is suitable for throughput-intensive applications such as Hadoop distributed computing, massive log processing, distributed file systems, and large data warehouses.
Big Data D2
Big Data D2 instances are equipped with massive storage resources, and carry up to 144 TB SATA HDD local storage, making them suitable for throughput-intensive services, such as Hadoop distributed computing and parallel data processing.
Application Scenarios
-
Distributed computing services such as Hadoop MapReduce/HDFS/Hive/HBase.
-
Workloads such as Elasticsearch, log processing, and large data warehouse.
-
Customers in the Internet, finance, and other industries who require big data computing and storage analysis, as well as workloads requiring massive data storage and computing.
Features
-
2.4 GHz Intel Xeon® Skylake 6148 processors with DDR4 memory
-
Instances come with up to 12 local disks of 12 TB in size and are equipped with up to 144 TB of HDD local storage
-
For a single disk, the sequential read throughput is 220+ MB/s, and sequential write throughput is 220+ MB/s (128 KB block size and depth of 32)
-
For the CVM, the throughput can reach up to 2.8 GB/s (128 KB block size and depth of 32).
-
The read/write delay is as low as 2-5 ms.
-
Larger instance size, D2.19XLARGE320, offering 76 vCPUs and 320 GB of memory
-
The unit price of local storage is as low as 1/10 of that of S2. The total cost is similar to that of Hadoop clusters built in IDC.
-
The 1:4 processor to memory ratio is tailored for the big data scenarios.
Requirements
-
Big Data D2 instances use local disks as data disks, which may lead to a risk of data loss (in case of host crash). If your application does not have a data reliability architecture, we strongly recommend choosing instances using cloud disks as data disks.
-
If the local disk is damaged, you will need to shut down the CVM instance for us to replace the local disk.
-
We will notify you and perform fixes if the CVM instance crashes.
-
Big Data D2 instances are pay-as-you-go.
-
D2 instances can only be launched in a VPC.
-
The configuration of D2 instances cannot be changed.
-
Configuration purchase is available for D2 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
Equipped with one 11176 GB SATA HDD local disk
|
|
|
|
|
|
|
|
Equipped with two 11176 GB SATA HDD local disks
|
|
|
|
|
|
|
|
Equipped with three 11176 GB SATA HDD local disks
|
|
|
|
|
|
|
|
Equipped with four 11176 GB SATA HDD local disks
|
|
|
|
|
|
|
|
Equipped with eight 11176 GB SATA HDD local disks
|
|
|
|
|
|
|
|
Equipped with twelve 11176 GB SATA HDD local disks
|
|
Computing Instance Family
This family comes with a powerful processor with a base frequency of 3.2GHz, and provides the highest single-core computing performance. It is suitable for compute-intensive workloads such as batch processing, high performance computing, and dedicated game servers.
Compute CN3
As the latest generation of computing instances, Compute CN3 instances have up to 25 Gbps of private network bandwidth for greater bandwidth and lower latency. These instances have the most powerful processors and the best cost performance among CVMs. They are ideal for compute bound applications that require high computing performance and high concurrent read and write.
Compute CN3 instances are equipped with the new Xeon® Skylake processors and support up to 25 Gbps of private network bandwidth, which is 2.5 times greater than Compute C3.
Application Scenarios
These instances are an ideal choice for:
-
Batch processing workloads and high performance computing (HPC)
-
High-traffic Web frontend server
-
Other compute-intensive services such as massively multiplayer online (MMO) game servers
Features
-
3.2 GHz Intel Xeon® Skylake 6146 processors
-
New Intel Advanced Vector Extension (AVX-512) instruction set
-
Supports up to 25 Gbps of private network bandwidth to meet extremely high private network transmission requirements
-
The latest generation of 6-channel DDR4 memory with a memory bandwidth of 2,666 MT/s
-
1:2 or 1:4 processor to memory ratio.
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
-
Support all types of cloud disks
Requirements
-
CN3 instances are pay-as-you-go.
-
CN3 instances can be launched in basic networks and VPCs.
-
Configuration purchase is available for CN3 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Compute C3
As the latest generation of computing instances, Compute C3 instances have the most powerful processors and the best cost performance among CVMs. They are ideal for compute bound applications that require high computing performance and high concurrent read and write.
Compute C3 instances are equipped with the latest Xeon® Skylake processors with the latest DDR4 memory and support for higher private network bandwidth.
Application Scenarios
These instances are an ideal choice for:
-
Batch processing workloads and high performance computing (HPC)
-
High-traffic Web frontend server
-
Other compute-intensive services such as massively multiplayer online (MMO) game servers
Features
-
3.2 GHz Intel Xeon® Skylake 6146 processors
-
New Intel Advanced Vector Extension (AVX-512) instruction set
-
The latest generation of 6-channel DDR4 memory with a memory bandwidth of 2,666 MT/s
-
1:2 or 1:4 processor to memory ratio.
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
-
Support all types of cloud disks
Requirements
-
C3 instances are pay-as-you-go.
-
C3 instances can be launched in basic networks and VPCs.
-
Configuration purchase is available for C3 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Compute C2
Compute C2 instances are optimized with high performing processors and deliver the best cost performance among CVMs. They are ideal for compute bound applications that require high computing performance and high concurrent read and write.
Application Scenarios
These instances are an ideal choice for:
-
Batch processing workloads
-
High-traffic Web servers, massively multiplayer online (MMO) game servers
-
High-performance computing (HPC) and other compute-intensive applications.
Features
-
3.2 GHz Intel Xeon® E5-2667v4 processors with up to 3.6 GHz of turbo frequency; DDR4 memory
-
1:2 or 1:4 processor to memory ratio.
-
The network performance of an instance is determined by its specification. A higher specification means a greater network forwarding performance and a higher maximum private network bandwidth limit.
-
Support all types of cloud disks
Requirements
-
C2 instances are pay-as-you-go, and can also be used as production instances of computing host HC20 in CDHs.
-
C2 instances can be launched in basic networks and VPCs.
-
Configuration purchase is available for C2 instances. Please see the instance specifications below.
|
|
|
|
Send/receive packets (pps)
|
|
Private network bandwidth (Gbps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Heterogeneous Computing Instance Family
This family is equipped with heterogeneous hardware such as GPU and FPGA to deliver real-time, fast parallel computing and floating-point computing capabilities. It is suitable for high-performance applications such as deep learning, scientific computing, video encoding/decoding, and graphics workstations.
The AMD GPU instances use AMD FirePro S7150 to provide outstanding graphics processing capability. It is the best choice for applications such as remote desktop, 3D rendering, and cloud gaming.
NVIDIA GPU instances use NVIDIA Tesla GPUs, including the previous generation M40, the current mainstream choice P4/P40, and the latest generation V100, to provide excellent general-purpose computing capability, making this the top choice for applications such as deep learning training/reasoning and scientific computing. NVIDIA GPU Instances >
Was this page helpful?