Ecs Productdesc

Elastic Cloud Server
Service Overview
Issue 19
Date 2019-04-25
HUAWEI TECHNOLOGIES CO., LTD.

Copyright © Huawei Technologies Co., Ltd. 2019. All rights reserved.
No part of this document may be reproduced or transmitted in any form or by any means without prior written
consent of Huawei Technologies Co., Ltd.
Trademarks and Permissions
and other Huawei trademarks are trademarks of Huawei Technologies Co., Ltd.
All other trademarks and trade names mentioned in this document are the property of their respective
holders.
Notice
The purchased products, services and features are stipulated by the contract made between Huawei and the
customer. All or part of the products, services and features described in this document may not be within the
purchase scope or the usage scope. Unless otherwise specified in the contract, all statements, information,
and recommendations in this document are provided "AS IS" without warranties, guarantees or
representations of any kind, either express or implied.
The information in this document is subject to change without notice. Every effort has been made in the
preparation of this document to ensure accuracy of the contents, but all statements, information, and
recommendations in this document do not constitute a warranty of any kind, express or implied.
Huawei Technologies Co., Ltd.

Address: Huawei Industrial Base
Bantian, Longgang
Shenzhen 518129
People's Republic of China
Website: http://www.huawei.com
Email: support@huawei.com
Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. i

Service Overview Contents
Contents
1 ECS................................................................................................................................................... 1
2 Regions and AZs............................................................................................................................3
3 Storage............................................................................................................................................. 4
4 Network and Security................................................................................................................... 6
4.1 VPC................................................................................................................................................................................ 6
4.2 User Encryption.............................................................................................................................................................. 6
4.3 Cloud-Init........................................................................................................................................................................8
4.4 Project and Enterprise Project........................................................................................................................................ 9
5 IMS................................................................................................................................................. 11
6 ECS Instances............................................................................................................................... 13
6.1 Lifecycle....................................................................................................................................................................... 13
6.2 Spot ECSs..................................................................................................................................................................... 15
7 ECS Types and Specifications...................................................................................................18

7.1 ECS Types.................................................................................................................................................................... 18
7.2 ECS Specifications....................................................................................................................................................... 19
7.3 General Computing ECSs.............................................................................................................................................37
7.4 General Computing-Plus ECSs.................................................................................................................................... 42
7.5 General-Entry ECSs..................................................................................................................................................... 46
7.6 Memory-optimized ECSs............................................................................................................................................. 47
7.7 Large-Memory ECSs.................................................................................................................................................... 50
7.8 Disk-intensive ECSs..................................................................................................................................................... 53
7.9 Ultra-high I/O ECSs..................................................................................................................................................... 57
7.10 High-Performance Computing ECSs..........................................................................................................................59
7.11 Ultra-high Performance Computing ECSs................................................................................................................. 62
7.12 GPU-accelerated ECSs............................................................................................................................................... 64
7.13 FPGA-accelerated ECSs.............................................................................................................................................75
7.14 AI-accelerated ECSs...................................................................................................................................................78
8 Accessing and Using ECSs.........................................................................................................81

8.1 Accessing ECSs............................................................................................................................................................ 81
8.2 ECS and Other Services............................................................................................................................................... 81
Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. ii

Service Overview Contents
9 Change History............................................................................................................................ 85
Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. iii

Service Overview 1 ECS
1 ECS
An Elastic Cloud Server (ECS) is a computing server consisting of vCPUs, memory, image,
and Elastic Volume Service (EVS) disks that allow on-demand allocation and elastic scaling.
ECSs integrate Virtual Private Cloud (VPC), virtual firewalls, and multi-data-copy
capabilities to create an efficient, reliable, and secure computing environment. This ensures
the stable and uninterrupted operation of services. After creating an ECS, you can use it like
using your local computer or physical server.
ECSs support self-service creation, modification, and operation. You can create ECSs by
specifying the vCPU, memory, image specifications, and login authentication. After creating
an ECS, you can modify its specifications as required.
System Architecture
ECS works with other products and services to provide computing, storage, network, and
image installation functions.
l ECSs are deployed in multiple availability zones (AZs) connected with each other
through an internal network. If an AZ becomes faulty, other AZs in the same region will
not be affected.
l With the Virtual Private Cloud (VPC) service, you can build a dedicated network, set the
subnet and security group, and allow the VPC to communicate with the external network
through an EIP (bandwidth support required).
l With the Image Management Service (IMS), you can install images on ECSs, or create
ECSs using private images and deploy services quickly.
l The Elastic Volume Service (EVS) provides storage and Volume Backup Service (VBS)
provides data backup and recovery functions.
Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 1

Service Overview 1 ECS
Figure 1-1 ECS architecture

Service Overview 2 Regions and AZs
2 Regions and AZs
A region is a geographic area where resources used by your ECSs are located.
ECSs in the same region can communicate with each other over an intranet, but ECSs in
different regions cannot.
Public cloud data centers are deployed worldwide. Creating ECSs in different regions can
better suit certain user requirements. For example, applications can be designed to meet user
requirements in specific regions or comply with local laws or regulations. ECS pricing also
changes based on region.
Each region contains many AZs where power and networks are physically isolated. AZs in the
same region can communicate with each other over an intranet. Each AZ provides cost-
effective and low-latency network connections that are unaffected by faults that may occur in
other AZs.

Service Overview 3 Storage
3 Storage
EVS Disk Types

ECSs support the following types of EVS disks for storing data:
l Common I/O: EVS disks of this type deliver a maximum of 2,200 IOPS. This disk type
is suitable for application scenarios that require large capacity, a medium read/write rate,
and fewer transactions, such as enterprise office applications and small-scale testing.
l High I/O: EVS disks of this type deliver a maximum of 5,000 IOPS and a minimum of 1
ms read/write latency. This disk type is designed to meet the needs of mainstream high-
performance, high-reliability application scenarios, such as enterprise applications, large-
scale development and testing, and web server logs.
l Ultra-high I/O: EVS disks of this type deliver a maximum of 33,000 IOPS and a
minimum of 1 ms read/write latency. This disk type is excellent for ultra-high I/O, ultra-
high bandwidth, and read/write-intensive application scenarios, such as distributed file
systems in HPC scenarios or NoSQL/RDS in I/O-intensive scenarios.
l Ultra-high I/O (latency-optimized): EVS disks of this type deliver a maximum of 1 GB/s
throughput and a minimum of 1 ms read/write latency. They can be used for key
enterprise services, such as SAP HANA.
NOTE
Ultra-high I/O (latency-optimized) EVS disks can be attached to SAP HANA ECSs only.
EVS disks with different I/O capacities provide different features at different prices. Choose
EVS disks based on your requirements. For more information about EVS disk specifications
and performance, see Elastic Volume Service User Guide.
EVS Disk Device Types

EVS disks have two device types, Virtual Block Device (VBD) and Small Computer System
Interface (SCSI).
l VBD
When you create an EVS disk on the management console, Device Type of the EVS disk
is VBD by default. VBD EVS disks support only simple SCSI read/write commands.
l SCSI
You can create EVS disks for which Device Type is SCSI on the management console.
These EVS disks support transparent SCSI command transmission, allowing ECS OS to

Service Overview 3 Storage
directly access underlying storage media. SCSI EVS disks support both basic and
advanced SCSI commands.
NOTE
For more information about how to use SCSI EVS disks, for example, how to install the driver, see
section Do I Need to Install a Driver for SCSI EVS Disks?

Service Overview 4 Network and Security
4 Network and Security
4.1 VPC
VPC allows you to create customized virtual networks in your logically isolated AZ. Such
networks are dedicated zones that are logically isolated for your ECSs. You can define
security groups, virtual private networks (VPNs), IP address segments, and bandwidth for a
VPC. This facilitates internal network configuration and management as well as secure and
convenient network modification. You can also customize the ECS access rules within a
security group and between security groups to strengthen ECS security protection. For more
information, see Virtual Private Cloud User Guide.
4.2 User Encryption

User encryption allows you to use the encryption feature provided on the public cloud
platform to encrypt ECS resources, improving data security. User encryption includes image
encryption and EVS disk encryption.
Image Encryption
Key encryption supports encrypting private images. When creating an ECS, if you select an
encrypted image, the system disk of the created ECS automatically has encryption enabled,
implementing system disk encryption and improving data security.
Use either of the following methods to create an encrypted image:
l Create an encrypted image using an existing encrypted ECS.

l Create an encrypted image using an external image file.
For more information about image encryption, see Image Management Service User Guide.
EVS Disk Encryption

EVS disk encryption supports system disk encryption and data disk encryption.
l When creating an ECS, you can encrypt added data disks.

l System disk encryption relies on the image. When creating an ECS, if you select an
encrypted image, the system disk of the created ECS automatically has encryption
enabled, and the encryption mode complies with the image encryption mode.
For more information about EVS disk encryption, see Elastic Volume Service User Guide.
Impact on AS
If you use an encrypted ECS to create an Auto Scaling (AS) configuration, the encryption
mode of the created AS configuration complies with the ECS encryption mode.
About Keys
The key required for encryption relies on Data Encryption Workshop (DEW). DEW uses a
data encryption key (DEK) to encrypt data and a customer master key (CMK) to encrypt the
DEK.
Figure 4-1 Data encryption process
Table 4-1 describes the keys involved in the data encryption process.
Table 4-1 Keys

Name Description Function
DEK An encryption key that is used for encrypting Encrypts specific data.
data.
CMK An encryption key created using DEW for Supports CMK disabling
encrypting DEKs. and scheduled deletion.
A CMK can encrypt multiple DEKs.
Default CMK A master key automatically generated by the l Supports viewing

system when you use DEW for encryption details of the default
for the first time. CMK on the KMS
The name extension of a default CMK is / console.
default, for example, evs/default. l Does not support
CMK disabling or
scheduled deletion.

NOTE
After disabling a CMK or scheduling the deletion of a CMK takes effect, the EVS disk encrypted using
this CMK can still be used until the disk is detached from and then attached to an ECS again. During
this process, the disk fails to be attached to the ECS because the CMK cannot be obtained. Therefore,
the EVS disk becomes unavailable.
For details about DEW, see Data Encryption Workshop User Guide.
4.3 Cloud-Init
Cloud-Init is an open-source cloud initialization program, which initializes specified
customized configurations, such as the hostname, key pair, and user data, of a newly created
ECS.
Using Cloud-Init to initialize your ECSs will affect your ECS, IMS, and AS services.
Impact on IMS
To ensure that ECSs created using private images support customized configurations, you
must install Cloud-Init or Cloudbase-Init before creating private images.
l For Windows OSs, download and install Cloudbase-Init.

l For Linux OSs, download and install Cloud-Init.
After Cloud-Init or Cloudbase-Init is installed in an image, Cloud-Init or Cloudbase-Init

automatically configures initial ECS attributes when the ECS is created. For instructions
about how to install Cloud-Init or Cloudbase-Init, see Image Management Service User
Guide.
Impact on ECS
l When creating an ECS, if the selected image supports Cloud-Init, you can use user data
injection to inject customized configuration, such as ECS login password, for
initializing.
l After Cloud-Init is supported, ECS login modes will be affected.
l After Cloud-Init is supported, you can view and use metadata to configure and manage
running ECSs.
Impact on AS
l When creating an AS configuration, you can use user data injection to specify ECS
configurations for initialization. If the AS configuration has taken effect in an AS group,
the ECSs newly created in the AS group will automatically initialize their configurations.
l For an existing AS configuration, if its private image does not have Cloud-Init or
Cloudbase-Init installed, the login mode of the ECSs created in the AS group where the
AS configuration takes effect will be affected. To resolve this issue, see section "How
Does Cloud-Init Influence the AS Service?" in Auto Scaling User Guide.
For more information about AS, see Auto Scaling User Guide.
Notes
l When using Cloud-Init, enable DHCP in the VPC to which the ECS belongs.

l When using Cloud-Init, ensure that security group rules in the outbound direction meet
the following requirements:
– Protocol: TCP
– Port Range: 80
– Remote End: 169.254.0.0/16
NOTE
If you use the default security group rules in the outbound direction, the preceding requirements
are met, and the metadata can be accessed. Default security group rules in the outbound direction
are as follows:
l Protocol: ANY
l Port Range: ANY
l Remote End: 0.0.0.0/16
4.4 Project and Enterprise Project

Projects in IAM are used to group and isolate OpenStack resources (computing resources,
storage resources, and network resources). Resources in your account must be mounted under
projects. A project can be a department or a project team. Multiple projects can be created for
one account.
Enterprise projects are used to categorize and manage multiple resources. Resources in
different regions can belong to one enterprise project. An enterprise can classify resources
based on department or project group and put relevant resources into one enterprise project
for management. Resources can be migrated between enterprise projects.
Differences Between Projects and Enterprise Projects

l IAM project
Projects are used to categorize and physically isolate resources in a region. Resources in
an IAM project cannot be transferred. They can only be deleted and then rebuilt.
l Enterprise project
Enterprise projects are upgraded based on IAM projects and used to categorize and
manage resources of different projects of an enterprise. An enterprise project can contain
resources of multiple regions, and resources can be added to or removed from enterprise
projects. If you have enabled enterprise management, you cannot create an IAM project
and can only manage existing projects. In the future, IAM projects will be replaced by
enterprise projects, which are more flexible.

Both projects and enterprise projects can be managed by one or more user groups. Users who
manage enterprise projects belong to user groups. After a policy is granted to a user group,
users in the group can obtain the rights defined in the policy in the project or enterprise
project.
For details about how to create a project, create an enterprise project, and grant policies, see
Managing Projects and Enterprise Projects.

Service Overview 5 IMS
5 IMS
Introduction
IMS allows you to create ECSs using images. An image is an ECS template that contains an
OS and may also contain proprietary software and application software, such as database
software.
Images can be public, private, or shared. Public images are provided by the system by default,
private images are manually created, and shared images are private images that are shared by
another user. You can use any type of image to create an ECS. You can also create a private
image using an existing ECS. This provides you with a simple way to create ECSs that
comply with your service requirements. For example, if you use web services, your image can
contain a web server, static configurations, and dynamic page code. When you use this image
to create an ECS, your web server and applications will be available for use immediately.
Image Types
Table 5-1 Image types
Image Description
Type
Public image A standard, widely used image. It contains an OS, comes with preinstalled
public applications, and is available to all users.
Private An image that is available only to the user who created it based on an ECS
image or EVS backup (system disk backup). Such a private image contains an OS,
preinstalled public applications, and the user's private applications.
A private image can be a system image or a data image.
l System image: contains an OS, comes with preinstalled application
software for running services. You can use a system image to create
ECSs and migrate your services to the cloud.
l Data image: contains only your service data. You can use a data image
to create EVS disks and migrate your service data to the cloud.
Shared A private image shared by another user.

image

Service Overview 5 IMS
Image Description
Type
Marketplace A third-party image that has the OS, application environment, and software
image pre-installed. You can use the images to deploy websites and application
development environments with a few clicks. No additional configuration
operation is required.
Conversion Between Images and ECSs

You can use images to create ECSs and you can convert ECS configurations into images.

Service Overview 6 ECS Instances
6 ECS Instances
6.1 Lifecycle
A lifecycle indicates the ECS statuses recorded from the time when the ECS is created
through the time when the ECS is deleted or released.
Table 6-1 ECS statuses

Status Status Description API Status
Attribute
Creating Intermediate The ECS has been created but is not BUILD or
running. BUILDING
Starting Intermediate The ECS is between the Stopped and SHUTOFF

Running states.
Running Stable The ECS is running properly. ACTIVE

An ECS in this state can provide
services.
Stopping Intermediate The ECS is between the Running ACTIVE

and Stopped states.
Stopped Stable The ECS has been properly stopped. SHUTOFF

An ECS in this state cannot provide
services.
Restarting Intermediate The ECS is being restarted. REBOOT
Resizing Intermediate The ECS has received a resizing RESIZE

request and has started to resize.
Verifying Intermediate The ECS is verifying the modified VERIFY_RESIZE

resizing configuration.


Attribute
Deleting Intermediate The ECS is being deleted. ACTIVE,

If the ECS remains in this state for a SHUTOFF,
long time, exceptions may have REBOOT, RESIZE,
occurred. In such an event, contact VERIFR_RESIZE,
the administrator. HARD_REBOOT,
REVERT_RESIZE,
or ERROR
Deleted Intermediate The ECS has been deleted. An ECS DELETED

in this state cannot provide services
and will be promptly cleared from the
system.
Faulty Stable An exception has occurred on the ERROR

ECS.
services. Contact the administrator.
Reinstalling Intermediate The ECS has received a request to SHUTOFF

OS reinstall the OS and has begun the
reinstallation.
Reinstalling Stable The ECS received a request to SHUTOFF

OS failed reinstall the OS, but due to
exceptions, the reinstallation failed.
Changing Intermediate The ECS received a request to change SHUTOFF

OS the OS and has begun implementing
the changes.
OS Change Stable The ECS has received a request to SHUTOFF

failed change the OS, but due to exceptions,
the changes failed to be implemented.
Forcibly Intermediate The ECS is being forcibly restarted. HARD_REBOOT

restarting
Rolling Intermediate The ECS is rolling back resizing. REVERT_RESIZE

back
resizing


Attribute
Frozen Stable The ECS has been stopped by the SHUTOFF

administrator because the order has
expired or is overdue.
services. The system retains it for a
period of time. If it is not renewed
after the time expires, the system will
automatically delete the ECS.
Locked Intermediate The ECS has been locked and is in N/A

or Stable
protected state, and is displayed
in the status bar. In such a case,
certain operations will be forbidden
on the ECS. For details, see prompts.
To view the lock reason, click the link
below the lock icon.
6.2 Spot ECSs

Concept
HUAWEI CLOUD sells idle computing resources at a discount. The price changes in real
time depending on market demands. This is the spot pricing billing mode. An ECS billed in
spot pricing mode is a spot ECS.
In spot billing mode, you can purchase and use ECSs at a discount price. The performance of
the ECSs is the same as that of ECSs with the same specifications in other billing modes.
However, when inventory resources are insufficient, or the market price increases and exceeds
your expected price, the system will automatically release your ECS resources and reclaim the
ECSs. Compared with pay-per-use and yearly/monthly ECSs, spot ECSs offer the same level
of performance while at lower costs.
Working Rules
The market price for the ECSs of a certain flavor fluctuates due to supply-and-demand
changes. You can purchase and use spot ECSs at a low market price to reduce computing
costs.
When purchasing a spot ECS, you are required to set the highest price for a specified flavor
you are willing to pay for. This process is also known as price quoting. A higher quoted price
makes it more likely for you to purchase such an ECS.
l If the quotation is greater than or equal to the market price and the inventory resources
are sufficient, the spot ECS is purchased. The ECS is billed at the market price.
l If the quotation is less than the market price, the spot ECS cannot be purchased.

After purchasing a spot ECS, you can use it like using the ECSs in other billing modes.
However, the system will periodically compare your quotation with the market price and
check the inventory resources.
l If the quotation is greater than or equal to the market price and the inventory resources
are sufficient, you can continue using the ECS.
l If the quotation is less than the market price or the inventory resources are insufficient,
the system notifies you of releasing the ECS resources if notification is enabled and
automatically deletes the ECS in about 5 minutes.
Figure 6-1 Lifecycle of a spot ECS
Application Scenarios
l What are supported?
Spot ECSs are suitable for image rendering, stateless web service, gene sequencing,
offline analysis, function calculation, batch calculation, sample analysis, CI/CD, and test.
NOTE
When the market price is higher than your quotation or the inventory resources are insufficient, the
spot ECSs will be reclaimed. Therefore, back up data when using such ECSs.
l What are not supported?
To prevent ECS reclamation from interrupting services, do not use spot ECSs to run the
services requiring long-time operations or high stability.
Notes
l Only KVM ECSs support spot pricing payments. For details about the ECS flavors, see
the information displayed on the management console.
l The market prices of the ECSs of the same flavor may vary depending on AZs.
l Spot ECSs do not support OS changing.
l Spot ECSs do not support automatic recovery.
l Spot ECSs do not support specifications modification.
l Spot ECSs cannot be created using a Marketplace image.
l Spot ECSs cannot be switched to yearly/monthly ECSs.
l When a spot ECS is being reclaimed,
– It cannot be used to create system disk images and full-ECS images. However, data
disks of the ECS can be used to create data disk images.
– It cannot be deleted.

Billing Rules
For details, see section Billing Modes.
Purchasing a Spot ECS

You can purchase a spot ECS on the management console or by calling APIs.
l For instructions about how to purchase a spot ECS on the management console, see
section Purchasing a Spot ECS.
l For instructions about how to purchase a spot ECS by calling APIs, see section
"Creating ECSs" in Elastic Cloud Server API Reference.
Reclaiming an ECS
HUAWEI CLOUD may reclaim and terminate your spot ECS at any time. A spot ECS that is
being reclaimed cannot be used to create images.
The reclamation may be due to:
l Higher market price than your quotation
l Insufficient inventory resources
NOTE
l If a spot ECS is reclaimed within the first hour after it is provisioned due to insufficient
inventory resources or lower quotation than the market price, the spot ECS is not billed.
l In the first settlement period (in hours) of a spot ECS, the spot ECS is billed, regardless of
whether it runs.
l The time required for reclaiming a spot ECS is 5 minutes. During the reclaiming, if the sharp
clock is exceeded, the spot ECS is billed at the market price for the time after the sharp clock.
l During the running of a spot ECS, its price is updated once an hour. After a spot ECS is
restarted, or it is stopped and then started, it is billed at the market price when the ECS starts.
Therefore, back up your data. Before reclaiming your spot ECS, the system will notify you of
resource releasing if notification is enabled. Use either of the following methods to enable
notification:
l Method 1: Use the spot metadata. For details, see section Managing ECS Metadata.
l Method 2: Use Cloud Trace Service (CTS) and Simple Message Notification (SMN)
provided on the public cloud. For details, see section Purchasing a Spot ECS.
FAQs
See section FAQs.

Service Overview 7 ECS Types and Specifications
7 ECS Types and Specifications
7.1 ECS Types

The public cloud provides the following ECS types for different application scenarios:
l General computing
l General computing-plus
l General-entry
l Memory-optimized
l Large-memory
l Disk-intensive
l Ultra-high I/O
l High-performance computing
l Ultra-high performance computing
l GPU-accelerated
l FPGA-accelerated
l AI-accelerated
ECS Flavor Naming Rules

ECS flavors are named using the format "AB.C.D".
The format is defined as follows:
l A specifies the ECS type. For example, s indicates a general computing ECS, c a
computing ECS, and m a memory-optimized ECS.
l B specifies the type ID. For example, the 1 in s1 indicates a general computing first-
generation ECS, and the 2 in s2 indicates a general computing second-generation ECS.
l C specifies the flavor size, such as medium, large, or xlarge.
l D specifies the ratio of vCPUs to memory expressed in a digit. For example, value 4
indicates that the ratio of vCPUs to memory is 4.

Obtaining Specifications When Creating an ECS

Specifications for the ECS being created are located in the specifications list.
Network Bandwidth
The intranet bandwidth and PPS of an ECS are determined based on ECS specifications.
l Assured intranet bandwidth: indicates the assured ECS bandwidth.
l Maximum intranet bandwidth: indicates the maximum ECS bandwidth.
l Maximum intranet PPS: indicates the maximum ECS capabilities in transmitting and
receiving packets.
NOTE
l Network bandwidth has been released in CN South, East, North, and Hong Kong, and will be
released in other regions.
l For instructions about how to test packet transmit and receive, see section How Can I Test Network
Performance?
l For instructions about how to enable NIC multi-queue, see section Enabling NIC Multi-Queue.
7.2 ECS Specifications

Table 7-1 S1 ECS specifications
Flavor vCPUs Memory Maximu Maximum Virtualization

(GB) m/ PPS Type
Assured
Bandwidt
h
s1.medium 1 4 Low Low XEN
s1.large 2 8 Low Low XEN


(GB) m/ PPS Type
Assured
Bandwidt
h
s1.xlarge 4 16 Medium Medium XEN
s1.2xlarge 8 32 Medium Medium XEN
Table 7-2 C1 ECS specifications

Flavor vCPUs Memory Maximu Maximum PPS Virtualization
(GB) m/ Type
Assured
Bandwidt
h
c1.medium 1 1 Low Low XEN
c1.large 2 2 Low Low XEN
c1.xlarge 4 4 Medium Medium XEN
c1.2xlarge 8 8 Medium Medium XEN

(GB) m/ Type
Assured
Bandwidt
h


Flavor vCPUs Memory Maximu Maximu NIC Virtualizatio
(GB) m/ m PPS Multi n Type
Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
s2.small.1 1 1 0.5/0.1 5 1 KVM
s2.medium. 1 2 0.5/0.1 5 1 KVM

2
s2.large.2 2 4 0.8/0.2 10 1 KVM
s2.xlarge.2 4 8 1.5/0.4 15 1 KVM
s2.2xlarge.2 8 16 3/0.8 20 2 KVM
s2.4xlarge.2 16 32 4/1.5 30 4 KVM
s2.8xlarge.2 32 64 6/3 50 8 KVM
s2.medium. 1 4 0.5/0.1 5 1 KVM

4
s2.large.4 2 8 0.8/0.2 10 1 KVM
s2.xlarge.4 4 16 1.5/0.4 15 1 KVM
s2.2xlarge.4 8 32 3/0.8 20 2 KVM
s2.4xlarge.4 16 64 4/1.5 30 4 KVM
s2.8xlarge.4 32 128 6/3 50 8 KVM

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
s3.small.1 1 1 0.5/0.1 5 1 KVM
s3.medium. 1 2 0.5/0.1 5 1 KVM

2
s3.large.2 2 4 0.8/0.2 10 1 KVM
s3.xlarge.2 4 8 1.5/0.4 15 1 KVM
s3.2xlarge.2 8 16 3/0.8 20 2 KVM
s3.4xlarge.2 16 32 4/1.5 30 4 KVM


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
s3.medium. 1 4 0.5/0.1 5 1 KVM

4
s3.large.4 2 8 0.8/0.2 10 1 KVM
s3.xlarge.4 4 16 1.5/0.4 15 1 KVM
s3.2xlarge.4 8 32 3/0.8 20 2 KVM
s3.4xlarge.4 16 64 4/1.5 30 4 KVM
Table 7-6 SN3 ECS specifications

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
sn3.small.1 1 1 0.8/0.2 10 1 KVM
sn3.medium 1 2 0.8/0.2 10 1 KVM

.2
sn3.large.2 2 4 1.5/0.35 15 1 KVM
sn3.xlarge.2 4 8 2/0.7 25 1 KVM
sn3.2xlarge. 8 16 3/1.3 50 2 KVM

2
sn3.4xlarge. 16 32 6/2.5 100 4 KVM

2
sn3.medium 1 4 0.8/0.2 10 1 KVM

.4
sn3.large.4 2 8 1.5/0.35 15 1 KVM
sn3.xlarge.4 4 16 2/0.7 25 1 KVM
sn3.2xlarge. 8 32 3/1.3 50 2 KVM

4
sn3.4xlarge. 16 64 6/2.5 100 4 KVM

4


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
s6.small.1 1 1 0.8/0.1 10 1 KVM
s6.medium. 1 2 0.8/0.1 10 1 KVM

2
s6.large.2 2 4 1.5/0.2 15 1 KVM
s6.xlarge.2 4 8 2/0.35 25 1 KVM
s6.2xlarge.2 8 16 3/0.75 50 2 KVM
s6.medium. 1 4 0.8/0.1 10 1 KVM

4
s6.large.4 2 8 1.5/0.2 15 1 KVM
s6.xlarge.4 4 16 2/0.35 25 1 KVM
s6.2xlarge.4 8 32 3/0.75 50 2 KVM

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c3.large.2 2 4 1.5/0.6 30 2 KVM
c3.xlarge.2 4 8 3/1 50 2 KVM
c3.2xlarge.2 8 16 5/2 90 4 KVM
c3.3xlarge.2 12 24 7/3 110 4 KVM
c3.4xlarge.2 16 32 10/4 130 4 KVM
c3.6xlarge.2 24 48 12/6 200 8 KVM
c3.8xlarge.2 32 64 15/8 260 8 KVM
c3.15xlarge. 60 128 17/16 500 16 KVM

2
c3.large.4 2 8 1.5/0.6 30 2 KVM
c3.xlarge.4 4 16 3/1 50 2 KVM


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c3.2xlarge.4 8 32 5/2 90 4 KVM
c3.3xlarge.4 12 48 7/3 110 4 KVM
c3.4xlarge.4 16 64 10/4 130 4 KVM
c3.6xlarge.4 24 96 12/6 200 8 KVM
c3.8xlarge.4 32 128 15/8 260 8 KVM
c3.15xlarge. 60 256 17/16 500 16 KVM

4
Table 7-9 C3ne ECS specifications

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c3ne.large.2 2 4 4/1.3 40 2 KVM
c3ne.xlarge.2 4 8 8/2.5 80 2 KVM
c3ne.2xlarge. 8 16 15/5 150 4 KVM

2
c3ne.4xlarge. 16 32 20/10 280 8 KVM

2
c3ne.8xlarge. 32 64 30/20 550 16 KVM

2
c3ne. 60 128 40/40 1000 32 KVM

15xlarge.2
c3ne.large.4 2 8 4/1.3 40 2 KVM
c3ne.xlarge.4 4 16 8/2.5 80 2 KVM
c3ne.2xlarge. 8 32 15/5 150 4 KVM

4
c3ne.4xlarge. 16 64 20/10 280 8 KVM

4
c3ne.8xlarge. 32 128 30/20 550 16 KVM

4


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c3ne. 60 256 40/40 1000 32 KVM

15xlarge.4

Flavor vCPUs Memory Maximu Maximum NIC Virtualizatio
(GB) m/ PPS Multi n Type
Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c6.large.2 2 4 4/1.2 40 2 KVM
c6.xlarge. 4 8 8/2.4 80 2 KVM

2
c6.2xlarge 8 16 15/4.5 150 4 KVM

.2
c6.3xlarge 12 24 17/7 200 4 KVM

.2
c6.4xlarge 16 32 20/9 280 8 KVM

.2
c6.6xlarge 24 48 25/14 400 8 KVM

.2
c6.8xlarge 32 64 30/18 550 16 KVM

.2
c6.16xlarg 64 128 40/36 1000 32 KVM

e.2
c6.large.4 2 8 4/1.2 40 2 KVM
c6.xlarge. 4 16 8/2.4 80 2 KVM

4
c6.2xlarge 8 32 15/4.5 150 4 KVM

.4
c6.3xlarge 12 48 17/7 200 4 KVM

.4
c6.4xlarge 16 64 20/9 280 8 KVM

.4


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c6.6xlarge 24 96 25/14 400 8 KVM

.4
c6.8xlarge 32 128 30/18 550 16 KVM

.4
c6.16xlarg 64 256 40/36 1000 32 KVM

e.4
Table 7-11 T6 ECS specifications

Flavor vCPU Memor Initial Maxi vCPU vCPU Averag Virtua
s y (GB) Credit mum Credi Bench e vCPU lizatio
s Credit ts/ mark Benchm n Type
s Hour (%) ark (%)
t6.smal 1 1 30 144 6 10 10 KVM

l.1
t6.large 2 2 60 576 24 40 20 KVM

.1
t6.xlarg 4 4 120 1152 48 80 20 KVM

e.1
t6.2xlar 8 8 120 1728 72 120 15 KVM

ge.1
t6.4xlar 16 16 160 3456 144 240 15 KVM

ge.1
t6.medi 1 2 30 144 6 10 10 KVM

um.2
t6.large 2 4 60 576 24 40 20 KVM

.2
t6.xlarg 4 8 120 1152 48 80 20 KVM

e.2
t6.2xlar 8 16 120 1728 72 120 15 KVM

ge.2
t6.4xlar 16 32 160 3456 144 240 15 KVM

ge.2
t6.large 2 8 60 576 24 40 20 KVM

.4


s Hour (%) ark (%)
t6.xlarg 4 16 120 1152 48 80 20 KVM

e.4
t6.2xlar 8 32 120 1728 72 120 15 KVM

ge.4
Table 7-12 M1 ECS specifications

Flavor vCPUs Memory Maximum Maximum Virtualization
(GB) /Assured PPS Type
Bandwidt
h
m1.medium 1 8 Low Low XEN
m1.large 2 16 Low Low XEN
m1.xlarge 4 32 Medium Medium XEN
m1.2xlarge 8 64 Medium Medium XEN

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
m2.large.8 2 16 1.5/0.5 10 1 KVM
m2.xlarge.8 4 32 3/1 15 1 KVM
m2.2xlarge. 8 64 5/2 30 2 KVM

8
m2.4xlarge. 16 128 8/4 40 4 KVM

8
m2.8xlarge. 32 256 13/8 60 8 KVM

8


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
m3.large.8 2 16 1.5/0.6 30 2 KVM
m3.xlarge.8 4 32 3/1.1 50 2 KVM
m3.2xlarge. 8 64 5/2 90 4 KVM

8
m3.3xlarge. 12 96 8/3.5 110 4 KVM

8
m3.4xlarge. 16 128 10/4.5 130 4 KVM

8
m3.6xlarge. 24 192 12/6.5 200 8 KVM

8
m3.8xlarge. 32 256 15/9 260 8 KVM

8
m3.15xlarge 60 512 17/17 500 16 KVM

.8
Table 7-15 M3ne ECS specifications

Flavor vCPUs Memory Maximum/ Maximu NIC Virtuali
(GB) Assured m PPS Multi zation
Bandwidth (10,000) - Type
(Gbit/s) Queu
e
m3ne.large.8 2 16 4/1.3 40 2 KVM
m3ne.xlarge.8 4 32 8/2.5 80 2 KVM
m3ne.2xlarge.8 8 64 15/5 150 4 KVM
m3ne.3xlarge.8 12 96 17/8 200 4 KVM
m3ne.4xlarge.8 16 128 20/10 280 8 KVM
m3ne.6xlarge.8 24 192 25/16 400 8 KVM
m3ne.8xlarge.8 32 256 30/20 550 16 KVM
m3ne.15xlarge. 60 512 40/40 1000 32 KVM

8

Table 7-16 E1 ECS specifications

Bandwidt
h
e1.4xlarge 16 470 Medium Medium XEN

Bandwidt
h
Table 7-18 ET2 ECS specifications

Bandwidt
h
et2.2xlarge. 8 128 Medium Medium XEN

16

14

14
Flavor vCPUs Memory Maximum Virtualization

(GB) NICs Type
e3.7xlarge.12 28 348 8 KVM
e3.14xlarge.12 56 696 8 KVM
e3.26xlarge.14 104 1466 8 KVM


(GB) NICs Type
e3.52xlarge.14 208 2932 8 KVM
e3.52xlarge.20 208 4095 8 KVM
Table 7-20 D1 ECS specifications

Flavor vCPUs Memor Maximu Maximum Local Virtualizatio
y (GB) m/ PPS Disks n Type
Assured (GB)
Bandwidt
h
d1.xlarge 4 32 Medium Medium 3x XEN

1800
d1.2xlarge 8 64 Medium Medium 6x XEN

1800
d1.4xlarge 16 128 Medium Medium 12 x XEN

1800

1800

Flavor vCPUs Memor Maximu Maximu NIC Local Virtua
y (GB) m/ m PPS Multi Disks lizatio
Assured (10,000) - (GB) n
Bandwidt Queu Type
h (Gbit/s) e
d2.xlarge.8 4 32 3/1 15 2 2x KVM

1800
d2.2xlarge. 8 64 5/2 30 2 4x KVM

8 1800
d2.4xlarge. 16 128 8/4 40 4 8x KVM

8 1800
d2.6xlarge. 24 192 10/6 50 6 12 x KVM

8 1800
d2.8xlarge. 32 256 13/8 60 8 16 x KVM

8 1800
d2.12xlarg 48 384 13/13 90 8 24 x KVM

e.8 1800

Table 7-22 Ultra-high I/O I3 ECS specifications

Flavor vCPUs Memor Maximu Maximu NIC Local Virtual
y (GB) m/ m PPS Multi Disks ization
Assured (10,000) - Type
Bandwid Queu
th e
(Gbit/s)
i3.2xlarge. 8 64 8/3.5 100 4 1x KVM

8 1600
GB
NVMe
i3.4xlarge. 16 128 15/7 160 4 2x KVM

8 1600
GB
NVMe
i3.8xlarge. 32 256 20/14 280 8 4x KVM

8 1600
GB
NVMe
i3.12xlarg 48 384 25/20 420 8 6x KVM

e.8 1600
GB
NVMe
i3.15xlarg 60 512 25/25 500 16 7x KVM

e.8 1600
GB
NVMe
Table 7-23 H1 ECS specifications

(GB) m/ PPS Type
Assured
Bandwidt
h
h1.xlarge.4 4 16 Medium Medium XEN
h1.2xlarge.4 8 32 Medium Medium XEN

Table 7-24 HC2 ECS specifications

(GB) m/ m PPS Multi- n Type
Assured (10,000) Queu
Bandwidt e
h (Gbit/s)
hc2.large.2 2 4 1.5/0.5 10 1 KVM
hc2.xlarge.2 4 8 3/1 15 1 KVM
hc2.2xlarge. 8 16 5/2 30 2 KVM

2
hc2.4xlarge. 16 32 8/4 40 4 KVM

2
hc2.8xlarge. 32 64 13/8 60 8 KVM

2
hc2.large.4 2 8 1.5/0.5 10 1 KVM
hc2.xlarge.4 4 16 3/1 15 1 KVM
hc2.2xlarge. 8 32 5/2 30 2 KVM

4
hc2.4xlarge. 16 64 8/4 40 4 KVM

4
hc2.8xlarge. 32 128 13/8 60 8 KVM

4

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
h3.large.2 2 4 2/1 30 2 KVM
h3.xlarge.2 4 8 4/2 60 2 KVM
h3.2xlarge. 8 16 6/3.5 120 4 KVM

2
h3.3xlarge. 12 24 6/5.5 160 4 KVM

2
h3.4xlarge. 16 32 12/7.5 200 8 KVM

2


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
h3.6xlarge. 24 48 15/11 300 8 KVM

2
h3.8xlarge. 32 64 17/15 400 16 KVM

2
h3.large.4 2 8 2/1 30 2 KVM
h3.xlarge.4 4 16 4/2 60 2 KVM
h3.2xlarge. 8 32 6/3.5 120 4 KVM

4
h3.3xlarge. 12 48 6/5.5 160 4 KVM

4
h3.4xlarge. 16 64 12/7.5 200 8 KVM

4
h3.6xlarge. 24 96 15/11 300 8 KVM

4
h3.8xlarge. 32 128 17/15 400 16 KVM

4

Flavor vCPU Memor Maximu Maximu NIC Local Virtualiz
s y (GB) m/ m PPS Multi Disks ation
Assured (10,000) - (TB) Type
Bandwid Queu
th e
(Gbit/s)
h2.3xlarg 16 128 13/8 90 8 1 x 3.2 KVM

e.10
h2.3xlarg 16 256 13/8 90 8 1 x 3.2 KVM

e.20

Table 7-27 G3 ECS specifications

Flavor vC Memor Maximu Max. NIC GPUs GPU Virtu
PU y (GB) m/ PPS Multi Memor alizat
s Assured (10,000 - y (GB) ion
Bandwidt ) Queu Type
h (Gbit/s) e
g3.4xlar 16 64 8/2.5 50 2 1x 1x8 KVM

ge.4 M60
g3.8xlar 32 128 10/5 100 4 2x 2x8 KVM

ge.4 M60

Flavor vCPUs Memory Maximu Maximu GPUs GPU Virtu
(GB) m/ m PPS Memor alizat
Assured y (GB) ion
Bandwidt Type
h
g1.xlarg 4 8 Medium Medium 1x 1 XEN

e M60-1
Q

e.4 M60-1
Q
g1.2xlar 8 16 Medium Medium 1x 2 XEN

ge M60-2
Q
g1.2xlar 8 64 Medium Medium Passthr 8 XEN

ge.8 ough

ge M60-4
Q

Table 7-29 P2v ECS specifications

Flavor vCP Mem Maxim Maxi NIC GPU GPU GPU Virt
Us ory um/ mum Multi s Con Mem ualiz
(GB) Assure PPS - necti ory ation
d (10,00 Queu on (GB) Type
Bandwi 0) e
dth
(Gbit/s)
p2v. 8 64 10/4 50 4 1x N/A 1 x 16 KVM

2xlarge. V100 GB
8
p2v. 16 128 15/8 100 8 2x NVLi 2 x 16 KVM

4xlarge. V100 nk GB
8
p2v. 32 256 25/15 200 16 4x NVLi 4 x 16 KVM

8xlarge. V100 nk GB
8
p2v. 64 512 30/30 400 32 8x NVLi 8 x 16 KVM

16xlarge V100 nk GB
.8
Table 7-30 P1 ECS specifications

Flavor vC Me Max./ Max. NIC GPUs GPU Local Virtu
PU mor Assure PPS Multi Mem Disks alizat
s y d (10,00 - ory ion
(GB) Bandw 0) Queu (GB) Type
idth e
(Gbit/s
)
p1.2xlar 8 64 5/1.6 35 2 1x 1 x 16 1 x 800 KVM

ge.8 P100 GB
NVMe
p1.4xlar 16 128 8/3.2 70 4 2x 2 x 16 2 x 800 KVM

ge.8 P100 GB
NVMe
p1.8xlar 32 256 10/6.5 140 8 4x 4 x 16 4 x 800 KVM

ge.8 P100 GB
NVMe

Table 7-31 PI1 ECS specifications

Flavor vCP Mem Max./ Maxi NIC GPU GPU Local Virt
Us ory Assure mum Multi s Mem Disks ualiz
(GB) d PPS - ory ation
Bandwi (10,00 Queu (GB) Type
dth 0) e
(Gbit/s)
pi1.2xlar 8 32 5/1.6 40 2 1x 1x8 N/A KVM

ge.4 P4 GB
pi1.4xlar 16 64 8/3.2 70 4 2x 2x8 N/A KVM

ge.4 P4 GB
pi1.8xlar 32 128 10/6.5 140 8 4x 4x8 N/A KVM

ge.4 P4 GB
Table 7-32 Specifications of ECSs with high-performance architecture

Flavor vCPUs Memor Maximu Maximu NIC FPGA Virtual
y (GB) m/ m PPS Multi s ization
Bandwidt Queu
h (Gbit/s) e
fp1.2xlarge 8 88 5/1.3 20 2 1x KVM

.11 VU9P
fp1.8xlarge 32 352 10/5 60 8 4x KVM

.11 VU9P
fp1.16xlar 64 704 10/10 100 8 8x KVM

ge.11 VU9P
fp1.8xlarge 32 224 10/5 60 8 1x KVM

.8 VU9P
fp1.16xlar 64 448 10/10 100 8 2x KVM

ge.8 VU9P
Table 7-33 Specifications of ECSs with general-computing architecture

Bandwidt Queu
h (Gbit/s) e
fp1c. 8 88 5/1.3 20 2 1x KVM

2xlarge.11 VU9P


Bandwidt Queu
h (Gbit/s) e
fp1c. 32 352 10/5 60 8 4x KVM

8xlarge.11 VU9P
fp1c. 64 704 10/10 100 8 8x KVM

16xlarge. VU9P
11
fp1c. 32 224 10/5 60 8 1x KVM

8xlarge.8 VU9P
fp1c. 64 448 10/10 100 8 2x KVM

16xlarge.8 VU9P
Table 7-34 AI1 ECS specifications
Flavor vCPUs Memor Maximu Maximu Ascen Ascend Virtuali

y (GB) m/ m PPS d 310 RAM zation
Assured (10,000) Chips (GB) Type
Bandwidt
h
Ai1.large 2 8 4/1.3 12.5 1 8 KVM

.4
Ai1.xlar 4 16 6/2 25 2 16 KVM

ge.4
Ai1.2xla 8 32 10/4 50 4 32 KVM

rge.4
Ai1.4xla 16 64 15/8 100 8 64 KVM

rge.4
Ai1.8xla 32 128 25/15 200 16 128 KVM

rge.4
7.3 General Computing ECSs

Overview
General computing ECSs provide a baseline level of CPU performance with the ability to
burst above the baseline and a balance of computing, memory, and network resources. These
ECSs are suitable for many applications, such as web servers, enterprise R&D, and small-
scale databases.

Compared with S1 ECSs, S2 ECSs are based on the latest-generation virtualization platform
and use non-uniform memory access (NUMA) binding to provide higher computing
performance.
Compared with S1 and S2 ECSs, S3 ECSs use latest-generation Intel Xeon Skylake CPUs,
which significantly improve the comprehensive performance. They provide a baseline level of
CPU performance with the ability to burst above the baseline and a balance of computing,
memory, and network resources. These ECSs are suitable for many applications.
Compared with S3 ECSs, SN3 ECSs feature improved network performance. Working in 25
Gbit/s networks, SN3 ECSs offer higher bandwidths, lower latency, more stable computing
performance for high PPS and cost-effectiveness.
S6 ECSs are suitable for applications that require moderate performance generally but
occasionally burstable high performance, such as light-load web servers, enterprise R&D and
testing environments, and low- and medium-performance databases. S6 ECS performance is
neither restricted by vCPU credits nor billed for additional credits. You can determine the
CPU usage and vCPU credits in monitoring details.
Specifications

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
s6.small.1 1 1 0.8/0.1 10 1 KVM
s6.medium. 1 2 0.8/0.1 10 1 KVM

2
s6.large.2 2 4 1.5/0.2 15 1 KVM
s6.xlarge.2 4 8 2/0.35 25 1 KVM
s6.2xlarge.2 8 16 3/0.75 50 2 KVM
s6.medium. 1 4 0.8/0.1 10 1 KVM

4
s6.large.4 2 8 1.5/0.2 15 1 KVM
s6.xlarge.4 4 16 2/0.35 25 1 KVM
s6.2xlarge.4 8 32 3/0.75 50 2 KVM

Table 7-36 SN3 ECS specifications

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
sn3.small.1 1 1 0.8/0.2 10 1 KVM
sn3.medium 1 2 0.8/0.2 10 1 KVM

.2
sn3.large.2 2 4 1.5/0.35 15 1 KVM
sn3.xlarge.2 4 8 2/0.7 25 1 KVM
sn3.2xlarge. 8 16 3/1.3 50 2 KVM

2
sn3.4xlarge. 16 32 6/2.5 100 4 KVM

2
sn3.medium 1 4 0.8/0.2 10 1 KVM

.4
sn3.large.4 2 8 1.5/0.35 15 1 KVM
sn3.xlarge.4 4 16 2/0.7 25 1 KVM
sn3.2xlarge. 8 32 3/1.3 50 2 KVM

4
sn3.4xlarge. 16 64 6/2.5 100 4 KVM

4

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
s3.small.1 1 1 0.5/0.1 5 1 KVM
s3.medium. 1 2 0.5/0.1 5 1 KVM

2
s3.large.2 2 4 0.8/0.2 10 1 KVM
s3.xlarge.2 4 8 1.5/0.4 15 1 KVM
s3.2xlarge.2 8 16 3/0.8 20 2 KVM
s3.4xlarge.2 16 32 4/1.5 30 4 KVM


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
s3.medium. 1 4 0.5/0.1 5 1 KVM

4
s3.large.4 2 8 0.8/0.2 10 1 KVM
s3.xlarge.4 4 16 1.5/0.4 15 1 KVM
s3.2xlarge.4 8 32 3/0.8 20 2 KVM
s3.4xlarge.4 16 64 4/1.5 30 4 KVM

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
s2.small.1 1 1 0.5/0.1 5 1 KVM
s2.medium. 1 2 0.5/0.1 5 1 KVM

2
s2.large.2 2 4 0.8/0.2 10 1 KVM
s2.xlarge.2 4 8 1.5/0.4 15 1 KVM
s2.2xlarge.2 8 16 3/0.8 20 2 KVM
s2.4xlarge.2 16 32 4/1.5 30 4 KVM
s2.8xlarge.2 32 64 6/3 50 8 KVM
s2.medium. 1 4 0.5/0.1 5 1 KVM

4
s2.large.4 2 8 0.8/0.2 10 1 KVM
s2.xlarge.4 4 16 1.5/0.4 15 1 KVM
s2.2xlarge.4 8 32 3/0.8 20 2 KVM
s2.4xlarge.4 16 64 4/1.5 30 4 KVM
s2.8xlarge.4 32 128 6/3 50 8 KVM


(GB) m/ PPS Type
Assured
Bandwidt
h
s1.medium 1 4 Low Low XEN
s1.large 2 8 Low Low XEN
s1.xlarge 4 16 Medium Medium XEN

(GB) m/ Type
Assured
Bandwidt
h

(GB) m/ Type
Assured
Bandwidt
h


(GB) m/ Type
Assured
Bandwidt
h
Scenarios
l Web servers, small-load applications, and development and test environments
l Small-and medium-sized databases, cache servers, and search clusters
7.4 General Computing-Plus ECSs

Overview
Compared with general computing ECSs, the general computing-plus ECSs provide the
combinations of vCPUs and memory with larger specifications, offering more options for you
to select. In addition, the ECSs use latest-generation network acceleration engines and DPDK
rapid packet processing mechanism to provide higher network performance, meeting
requirements in different scenarios.
l C3 ECSs are newly released on the public cloud platform. They use latest-generation
Intel Xeon Skylake CPUs and feature high and stable computing performance. Working
in high-performance networks, the C3 ECSs provide higher performance and stability,
meeting enterprise-class application requirements.
l C3ne ECSs provide higher computing and network forwarding capabilities than C3
ECSs. Using latest-generation Intel Xeon Skylake CPUs and high-speed smart 25GE
NICs, the C3ne ECSs provide a maximum intranet bandwidth of 40 Gbit/s and 10
million PPS for enterprise-class applications with high network performance
requirements.
l C6 ECSs use latest-generation Intel Xeon Cascade Lake CPUs with technologies
optimized and Huawei high-speed smart 25GE NICs to offer powerful and stable
computing performance, including ultra-high network bandwidth and PPS.

Specifications

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c3.large.2 2 4 1.5/0.6 30 2 KVM
c3.xlarge.2 4 8 3/1 50 2 KVM
c3.2xlarge.2 8 16 5/2 90 4 KVM
c3.3xlarge.2 12 24 7/3 110 4 KVM
c3.4xlarge.2 16 32 10/4 130 4 KVM
c3.6xlarge.2 24 48 12/6 200 8 KVM
c3.8xlarge.2 32 64 15/8 260 8 KVM
c3.15xlarge. 60 128 17/16 500 16 KVM

2
c3.large.4 2 8 1.5/0.6 30 2 KVM
c3.xlarge.4 4 16 3/1 50 2 KVM
c3.2xlarge.4 8 32 5/2 90 4 KVM
c3.3xlarge.4 12 48 7/3 110 4 KVM
c3.4xlarge.4 16 64 10/4 130 4 KVM
c3.6xlarge.4 24 96 12/6 200 8 KVM
c3.8xlarge.4 32 128 15/8 260 8 KVM
c3.15xlarge. 60 256 17/16 500 16 KVM

4
Table 7-43 C3ne ECS specifications

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c3ne.large.2 2 4 4/1.3 40 2 KVM
c3ne.xlarge.2 4 8 8/2.5 80 2 KVM


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c3ne.2xlarge. 8 16 15/5 150 4 KVM

2
c3ne.4xlarge. 16 32 20/10 280 8 KVM

2
c3ne.8xlarge. 32 64 30/20 550 16 KVM

2
c3ne. 60 128 40/40 1000 32 KVM

15xlarge.2
c3ne.large.4 2 8 4/1.3 40 2 KVM
c3ne.xlarge.4 4 16 8/2.5 80 2 KVM
c3ne.2xlarge. 8 32 15/5 150 4 KVM

4
c3ne.4xlarge. 16 64 20/10 280 8 KVM

4
c3ne.8xlarge. 32 128 30/20 550 16 KVM

4
c3ne. 60 256 40/40 1000 32 KVM

15xlarge.4

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c6.large.2 2 4 4/1.2 40 2 KVM
c6.xlarge. 4 8 8/2.4 80 2 KVM

2
c6.2xlarge 8 16 15/4.5 150 4 KVM

.2
c6.3xlarge 12 24 17/7 200 4 KVM

.2
c6.4xlarge 16 32 20/9 280 8 KVM

.2


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
c6.6xlarge 24 48 25/14 400 8 KVM

.2
c6.8xlarge 32 64 30/18 550 16 KVM

.2
c6.16xlarg 64 128 40/36 1000 32 KVM

e.2
c6.large.4 2 8 4/1.2 40 2 KVM
c6.xlarge. 4 16 8/2.4 80 2 KVM

4
c6.2xlarge 8 32 15/4.5 150 4 KVM

.4
c6.3xlarge 12 48 17/7 200 4 KVM

.4
c6.4xlarge 16 64 20/9 280 8 KVM

.4
c6.6xlarge 24 96 25/14 400 8 KVM

.4
c6.8xlarge 32 128 30/18 550 16 KVM

.4
c6.16xlarg 64 256 40/36 1000 32 KVM

e.4
Scenarios
l C3 ECSs
Small- and medium-scale databases, cache servers, and search clusters with high
requirements on stability; enterprise-class applications of diverse types and in various
scales
l C3ne ECSs
Network data forwarding, databases, cache servers, and search clusters with high
requirements on computing and network performance; enterprise-class applications of
diverse types and in various scales
l C6 ECSs
Websites and web applications, generalized databases and cache servers, and medium-
and heavy-workload enterprise applications with strict requirements on computing and
network performance

7.5 General-Entry ECSs

Overview
General-entry ECSs provide a balance of computing, memory, and network resources and use
the vCPU credit mechanism to ensure the baseline level of computing performance. They are
suitable for applications requiring burstable high performance while keeping costs low.
Working Rules
The credit mechanism is used on general-entry ECSs to prevent an overcommitted ECS from
occupying CPU resources for a long period of time. The initial credits are allocated to meet
the burstable performance requirement after the ECS is purchased. After the ECS runs, the
system allocates credits at a certain rate, and the credits can be accumulated. The upper limit
for the accumulated credits is the credit allocation rate multiplied by 24 hours. When the
upper limit is exceeded, the credits are not accumulated any more. The initial credits are not
counted in the upper limit for accumulated credits. If the actual ECS resource usage is higher
than the vCPU benchmark for a long period of time, the accumulated credits are continuously
consumed. When the accumulated credits reach 0, the vCPU usage cannot exceed the vCPU
benchmark.
The credit mechanism applies to applications with performance limited by vCPU benchmark
and credits.
Specifications
Table 7-45 T6 ECS specifications

s Hour (%) ark (%)
t6.smal 1 1 30 144 6 10 10 KVM

l.1
t6.large 2 2 60 576 24 40 20 KVM

.1
t6.xlarg 4 4 120 1152 48 80 20 KVM

e.1
t6.2xlar 8 8 120 1728 72 120 15 KVM

ge.1
t6.4xlar 16 16 160 3456 144 240 15 KVM

ge.1
t6.medi 1 2 30 144 6 10 10 KVM

um.2


s Hour (%) ark (%)
t6.large 2 4 60 576 24 40 20 KVM

.2
t6.xlarg 4 8 120 1152 48 80 20 KVM

e.2
t6.2xlar 8 16 120 1728 72 120 15 KVM

ge.2
t6.4xlar 16 32 160 3456 144 240 15 KVM

ge.2
t6.large 2 8 60 576 24 40 20 KVM

.4
t6.xlarg 4 16 120 1152 48 80 20 KVM

e.4
t6.2xlar 8 32 120 1728 72 120 15 KVM

ge.4
7.6 Memory-optimized ECSs

Overview
l M1 ECSs have a large memory size and provide high memory performance. They are
designed for memory-intensive applications that process a large amount of data, such as
precision advertising, e-commerce big data analysis, and IoV big data analysis.
l M2 ECSs use Intel Xeon E5-2690 v4 CPUs and are designed for memory-optimized
applications.
l M3 ECSs are developed based on the KVM virtualization platform and designed for
processing large-scale data sets in the memory. They use latest-generation Intel Xeon
Skylake CPUs, network acceleration engines, and DPDK rapid packet processing
mechanism to provide higher network performance, providing a maximum memory size
of 512 GB based on DDR4 for high-memory computing applications.
l M3ne ECSs are suited for large-memory datasets with high network performance
requirements. Using latest-generation Intel Xeon Skylake CPUs and high-speed smart
Hi1822 NICs, the M3ne ECSs provide a maximum memory size of 512 GB based on
DDR4 for large-memory applications with high requirements on network performance.

Specifications

Bandwidt
h
m1.medium 1 8 Low Low XEN
m1.large 2 16 Low Low XEN
m1.xlarge 4 32 Medium Medium XEN

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
m2.large.8 2 16 1.5/0.5 10 1 KVM
m2.xlarge.8 4 32 3/1 15 1 KVM
m2.2xlarge. 8 64 5/2 30 2 KVM

8
m2.4xlarge. 16 128 8/4 40 4 KVM

8
m2.8xlarge. 32 256 13/8 60 8 KVM

8

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
m3.large.8 2 16 1.5/0.6 30 2 KVM
m3.xlarge.8 4 32 3/1.1 50 2 KVM


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
m3.2xlarge. 8 64 5/2 90 4 KVM

8
m3.3xlarge. 12 96 8/3.5 110 4 KVM

8
m3.4xlarge. 16 128 10/4.5 130 4 KVM

8
m3.6xlarge. 24 192 12/6.5 200 8 KVM

8
m3.8xlarge. 32 256 15/9 260 8 KVM

8
m3.15xlarge 60 512 17/17 500 16 KVM

.8
Table 7-49 M3ne ECS specifications

Flavor vCPUs Memory Maximum/ Maximu NIC Virtuali
(GB) Assured m PPS Multi zation
Bandwidth (10,000) - Type
(Gbit/s) Queu
e
m3ne.large.8 2 16 4/1.3 40 2 KVM
m3ne.xlarge.8 4 32 8/2.5 80 2 KVM
m3ne.2xlarge.8 8 64 15/5 150 4 KVM
m3ne.3xlarge.8 12 96 17/8 200 4 KVM
m3ne.4xlarge.8 16 128 20/10 280 8 KVM
m3ne.6xlarge.8 24 192 25/16 400 8 KVM
m3ne.8xlarge.8 32 256 30/20 550 16 KVM
m3ne.15xlarge. 60 512 40/40 1000 32 KVM

8
Scenarios
l Applications

Memory-optimized ECSs are suitable for applications that process large volumes of data
and require a large amount of memory, rapid data switching and processing, and low-
latency storage resources.
l Application scenarios
Big data analysis, precision advertising, e-commerce big data analysis, IoV big data
analysis, relational databases, NoSQL databases, and memory data analysis
Notes on Using M2 ECSs

l M2 ECSs support all rollout OSs.
l M2 ECSs do not have InfiniBand or SSD NICs configured.
l M2 ECSs support modifying specifications if the source and target ECSs are of the same
type.
l To improve network performance, you can set the NIC MTU to 8888.
Notes on Using M3 ECSs

l M3 ECSs support all rollout OSs.
l M3 ECSs do not have InfiniBand or SSD NICs configured.
l M3 ECSs support modifying specifications if the source and target ECSs are of the same
type.
7.7 Large-Memory ECSs

Overview
Large-memory ECSs provide an even larger amount of memory than memory-optimized
ECSs. They are used for applications that require a large amount of memory, rapid data
switching, low latency, and process large volumes of data. Large-memory ECSs provide large
memory and high computing, storage, and network performance.
l Applications
Large-memory ECSs are suitable for applications that require a large amount of memory,
rapid data switching, and low latency, and process large volumes of data.
E1 ECSs: OLTP applications, such as in-memory databases (SAP HANA BWoH, SAP
HANA applications, including Business Suite S/4HANA, Business Suite on HANA, and
Business Warehouse on HANA), big data processing engines (Apache Spark), and data
mining
E2 ECSs: OLAP applications, such as in-memory databases (SAP HANA SoH, SAP
HANA applications, including Business Suite S/4HANA, Business Suite on HANA, and
Business Warehouse on HANA), big data processing engines (Apache Spark), high-
performance databases, and distributed memory cache
E3 ECSs: OLAP and OLTP applications with hyper-threading enabled

Specifications

Bandwidt
h

Bandwidt
h
Table 7-52 ET2 ECS specifications

Bandwidt
h

16

14

14

(GB) NICs Type
e3.7xlarge.12 28 348 8 KVM
e3.14xlarge.12 56 696 8 KVM


(GB) NICs Type
e3.26xlarge.14 104 1466 8 KVM
e3.52xlarge.14 208 2932 8 KVM
e3.52xlarge.20 208 4095 8 KVM
Features
Large-memory ECSs use SR-IOV+OVS networks to provide a bandwidth as high as 10
Gbit/s.
Notes
l Large-memory ECSs do not support NIC hot swapping.
l E3 ECSs support the following OS that has been verified:
SUSE Enterprise Linux Server 12 SP2 64bit
l E1 and E2 ECSs can use the following types of EVS disks as system disk and data disk:
– High I/O (performance-optimized I)
– Ultra-high I/O (latency-optimized)
l The primary and extension NICs of a large-memory ECS have specified application
scenarios. For details, see Table 7-54.
Table 7-54 Application scenarios of the NICs of a large-memory ECS

NIC Type Application Scenario Remarks
Primary NIC Applies to vertical layer 3 N/A

communication.
Extension NIC Applies to horizontal layer To improve network performance, you

2 communication. can set the MTU of the extension NIC
to 8888.
l Up to 60 disks (including the system disk) can be attached to an ECS. For details about
restrictions, see section Can Multiple Disks Be Attached to an ECS?
An example is provided as follows:
If you create an e1.xlarge large-memory ECS, it can be attached with up to 60 disks,
where
– The number of system disks is 1.
– The number of EVS disks is at most 59.

7.8 Disk-intensive ECSs

Overview
D1 ECSs are developed based on the XEN virtualization platform, use local storage, and
provide high network performance. They are designed for applications requiring sequential
read/write on ultra-large datasets in local storage (such as distributed Hadoop computing) as
well as large-scale parallel data processing and log processing.
Compared with D1 ECSs, D2 ECSs are developed based on KVM virtualization, use local
storage, and provide high storage performance and intranet bandwidth. They are designed for
distributed Hadoop computing, large data warehouse, distributed file system, data processing,
and log processing.
NOTE
D1 ECSs have been discontinued. D2 ECSs that feature higher performance are available for new orders
and capacity expansion for D1 ECSs.
Specifications

Flavor vCPUs Memor Maximu Maximum Local Virtualizatio
y (GB) m/ PPS Disks n Type
Assured (GB)
Bandwidt
h
d1.xlarge 4 32 Medium Medium 3x XEN

1800
d1.2xlarge 8 64 Medium Medium 6x XEN

1800

1800

1800

Bandwidt Queu Type
h (Gbit/s) e
d2.xlarge.8 4 32 3/1 15 2 2x KVM

1800


Bandwidt Queu Type
h (Gbit/s) e
d2.2xlarge. 8 64 5/2 30 2 4x KVM

8 1800
d2.4xlarge. 16 128 8/4 40 4 8x KVM

8 1800
d2.6xlarge. 24 192 10/6 50 6 12 x KVM

8 1800
d2.8xlarge. 32 256 13/8 60 8 16 x KVM

8 1800
d2.12xlarg 48 384 13/13 90 8 24 x KVM

e.8 1800
Scenarios
l Applications
Disk-intensive ECSs are suitable for applications that require large volumes of data to
process, high I/O performance, and rapid data switching and processing.
Big data computing, network file systems, data processing, MapReduce, Hadoop, and
data-intensive computing
Features of D2 ECSs
l D2 ECSs use local disks to provide high sequential read/write performance and low
latency, improving file read/write performance.
l D2 ECSs provide powerful and stable computing capabilities, ensuring efficient data
processing.
l D2 ECSs with a CPU/memory ratio of 1:8 process large volumes of data.
l D2 ECSs provide high intranet performance, including high intranet bandwidth and
packet per second (pps), meeting requirements for data exchange between ECSs during
peak hours.
Notes on Using D1 ECSs

l D1 ECSs do not support NIC hot swapping.
l The primary and extension NICs of a D1 ECS have specified application scenarios. For
details, see Table 7-57.

Table 7-57 Application scenarios of the NICs of a D1 ECS


communication.
Extension NIC Applies to horizontal layer To improve network performance, you

2 communication. can set the MTU of the extension NIC
to 8888.
l D1 ECSs do not support modifying specifications.

l D1 ECSs do not support OS reinstallation or change.
l D1 ECSs support the following OSs:
– CentOS 7.2 64bit
– SUSE Enterprise Linux Server 11 SP3 64bit
– Red Hat Enterprise Linux 6.8 64bit
l D1 ECSs can use both local disks and EVS disks to store data. Use restrictions on the
two types of storage media are as follows:
– Only an EVS disk, not a local disk, can be used as the system disk of a D1 ECS.
– Both an EVS disk and a local disk can be used as the data disk of a D1 ECS.
– A maximum of 60 disks (including local disks) can be attached to a D1 ECS. For
details about restrictions, see section Can Multiple Disks Be Attached to an
ECS?
NOTE
The maximum number of disks attached to an existing D1 ECS remains unchanged.

l The basic resources, including vCPUs, memory, and image of a stopped D1 ECS are still
billed. To stop billing such an ECS, delete it.
Notes on Using D2 ECSs

l D2 ECSs support the following OSs:
– CentOS 6.7/6.8/7.2/7.3/7.4 64bit
– SUSE Enterprise Linux Server 11 SP3/SP4 64bit
– SUSE Enterprise Linux Server 12 SP1/SP2 64bit
– Red Hat Enterprise Linux 6.8/7.3 64bit
– Windows Server 2008 R2 Enterprise 64bit
– Windows Server 2012 R2 Standard 64bit
– Windows Server 2016 Standard 64bit

– Debian 8.7/9/9.0.0 64bit

– EulerOS 2.2 64bit
– Fedora 25/26 64bit
– OpenSUSE 42.2/42.3 64bit
l When the physical host where a D2 ECS is deployed becomes faulty, the ECS cannot be
migrated.
l To improve network performance, you can set the NIC MTU to 8888.
l D2 ECSs do not support modifying specifications.
l D2 ECSs do not support local disk snapshot or backup.
l D2 ECSs do not support OS reinstallation or change.
l D2 ECSs do not support automatic recovery.
l D2 ECSs can use both local disks and EVS disks to store data. In addition, they can have
EVS disks attached to provide a larger storage size. Use restrictions on the two types of
storage media are as follows:
– Only an EVS disk, not a local disk, can be used as the system disk of a D2 ECS.
– Both an EVS disk and a local disk can be used as the data disk of a D2 ECS.
– A D2 ECS can be attached with a maximum of 60 disks (including VBD, SCSI, and
local disks). Among the 60 disks, the maximum number of SCSI disks is 30, and
the maximum number of VBD disks is 24 (including the system disk). For details
about restrictions, see section Can Multiple Disks Be Attached to an ECS?
NOTE
The maximum number of disks attached to an existing D2 ECS remains unchanged.

– You are advised to use World Wide Names (WWNs), but not drive letters, in
applications to perform operations on local disks to prevent drive letter drift (low
probability) on Linux. Take local disk attachment as an example:
If the local disk WWN is wwn-0x50014ee2b14249f6, run the mount /dev/disk/by-
id/wwn-0x50014ee2b14249f6 command.
NOTE
How can I view the local disk WWN?

1. Log in to the ECS.
2. Run the following command to view the WWN:
ll /dev/disk/by-id
l The basic resources, including vCPUs, memory, and image of a stopped D2 ECS are still
billed. To stop billing such an ECS, delete it.
l The local disk data of a D2 ECS may be lost due to some reasons, such as host machine
breakdown or local disk damage. If your application does not use the data reliability
architecture, you are strongly advised to use EVS disks to build your ECS.
l When a D2 ECS is deleted, its local disk data is automatically deleted. Back up the data
before deleting such an ECS. Deleting local disk data is time-consuming. Therefore, a
D2 ECS requires a longer period of time than other ECSs for releasing resources.
l Do not store service data for a long time in local disks. Instead, use EVS disks to store
the data. In addition, back up data in a timely manner and use a high availability
architecture.

l You are not allowed to buy additional local disks. The quantity and capacity of your
local disks are determined according to the specifications of your ECS. For D2 ECSs, if
additional local disks are required, buy them when creating the ECSs.
7.9 Ultra-high I/O ECSs

Overview
Ultra-high I/O ECSs use high-performance local NVMe SSDs to provide high storage IOPS
and low read/write latency. The ratio of vCPU to memory is 1:8. You can create such ECSs
with high-performance NVMe SSDs attached on the management console.
Ultra-high I/O ECSs can be used for high-performance relational databases, NoSQL databases
(such as Cassandra and MongoDB), and ElasticSearch.
Specifications
Table 7-58 Ultra-high I/O I3 ECS specifications
Flavor vCPUs Memor Maximu Maximu NIC Local Virtual

y (GB) m/ m PPS Multi Disks ization
Bandwid Queu
th e
(Gbit/s)
i3.2xlarge. 8 64 8/3.5 100 4 1x KVM

8 1600
GB
NVMe
i3.4xlarge. 16 128 15/7 160 4 2x KVM

8 1600
GB
NVMe
i3.8xlarge. 32 256 20/14 280 8 4x KVM

8 1600
GB
NVMe
i3.12xlarg 48 384 25/20 420 8 6x KVM

e.8 1600
GB
NVMe
i3.15xlarg 60 512 25/25 500 16 7x KVM

e.8 1600
GB
NVMe

Features
Table 7-59 lists the IOPS performance of I3 ECSs.
Table 7-59 IOPS performance

Flavor Maximum IOPS for Random 4 KB Read
i3.2xlarge.8 750000
i3.4xlarge.8 1500000
i3.8xlarge.8 3000000
i3.12xlarge.8 4500000
i3.15xlarge.8 5250000
Notes
l I3 ECSs do not support specifications modification.
l After an I3 ECS is deleted, the data on the local NVMe SSD is automatically deleted.
Back up the data before deleting such an ECS. Deleting local disk data is time-
consuming. Therefore, an I3 ECS requires a longer period of time than other ECSs for
releasing resources.
l The data reliability of local disks depends on the reliability of physical servers and hard
disks, which are SPOF-prone. Therefore, you are advised to perform data redundancy at
the application layer to ensure data availability. Use EVS disks to store long-term service
data.
l The device name of a local disk attached to an I3 ECS is /dev/nvme0n1 or /dev/
nvme0n2. For instructions about how to initialize a local disk, see section Initializing
EVS Data Disks.
l I3 ECSs support the following OSs:
o EulerOS 2.2
o CentOS 7.2
o CentOS 7.3
o Ubuntu Server 16.04
o SUSE Linux Enterprise Server 12 SP2
o Fedora 25 64bit
o OpenSUSE 42.2 64bit
NOTE
You are advised to use EulerOS 2.2 or Ubuntu Server 16.04 for optimal performance.
l If you use an I3 ECS created using a private image, make sure that the NVMe driver has
been installed during private image creation. If the driver has not been installed, install it
after creating the I3 ECS. For details, see section "(Optional) Installing Special
Drivers" in Image Management Service User Guide.
l An I3 ECS can be attached with a maximum of 60 disks (including VBD, SCSI, and
local disks). Among the 60 disks, the maximum number of SCSI disks is 30, and the

maximum number of VBD disks is 24 (including the system disk). For details about
restrictions, see section Can Multiple Disks Be Attached to an ECS?
l The basic resources, including vCPUs, memory, and image of an I3 ECS are still billed.
To stop billing such an ECS, delete it.
7.10 High-Performance Computing ECSs

Overview
H1 ECSs provide a large number of CPU cores, large memory size, and high throughput.
These ECSs are suitable for high-performance processor applications restricted by computing
performance.
The processor and memory ratio of an HC2 ECS is 1:2 or 1:4. Each vCPU corresponds to the
hyperthreading of an Intel Xeon processor core. HC2 ECSs can be used for high-performance
computing services. They provide a large number of parallel computing resources and high-
performance infrastructure services to meet the requirements of high-performance computing
and massive storage and ensure rendering efficiency. HC2 ECSs are frequently used in the
following scenarios:
l Computing and storage systems for genetic engineering, games, animations,
biopharmaceuticals, and scientific computing
l Public rendering platforms for renderfarms and animation and film bases; other
rendering platforms for movies and videos
l High-performance frontend clusters, web servers, high-performance science and
engineering applications, advertisements, video coding, and distributed analysis
H3 ECSs use high-performance Intel Xeon SkyLake CPUs. Each vCPU corresponds to the
hyper-thread of an Intel Xeon processor core, providing stable computing capabilities. H3
ECSs are suitable for high-performance computing services. In addition, the ECSs use latest-
generation network acceleration engines and DPDK rapid packet processing mechanism to
provide high network performance.
Specifications

(GB) m/ PPS Type
Assured
Bandwidt
h
h1.xlarge.4 4 16 Medium Medium XEN

Table 7-61 HC2 ECS specifications

(GB) m/ m PPS Multi- n Type
Assured (10,000) Queu
Bandwidt e
h (Gbit/s)
hc2.large.2 2 4 1.5/0.5 10 1 KVM
hc2.xlarge.2 4 8 3/1 15 1 KVM
hc2.2xlarge. 8 16 5/2 30 2 KVM

2
hc2.4xlarge. 16 32 8/4 40 4 KVM

2
hc2.8xlarge. 32 64 13/8 60 8 KVM

2
hc2.large.4 2 8 1.5/0.5 10 1 KVM
hc2.xlarge.4 4 16 3/1 15 1 KVM
hc2.2xlarge. 8 32 5/2 30 2 KVM

4
hc2.4xlarge. 16 64 8/4 40 4 KVM

4
hc2.8xlarge. 32 128 13/8 60 8 KVM

4

Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
h3.large.2 2 4 2/1 30 2 KVM
h3.xlarge.2 4 8 4/2 60 2 KVM
h3.2xlarge. 8 16 6/3.5 120 4 KVM

2
h3.3xlarge. 12 24 6/5.5 160 4 KVM

2
h3.4xlarge. 16 32 12/7.5 200 8 KVM

2


Assured (10,000) -
Bandwidt Queu
h (Gbit/s) e
h3.6xlarge. 24 48 15/11 300 8 KVM

2
h3.8xlarge. 32 64 17/15 400 16 KVM

2
h3.large.4 2 8 2/1 30 2 KVM
h3.xlarge.4 4 16 4/2 60 2 KVM
h3.2xlarge. 8 32 6/3.5 120 4 KVM

4
h3.3xlarge. 12 48 6/5.5 160 4 KVM

4
h3.4xlarge. 16 64 12/7.5 200 8 KVM

4
h3.6xlarge. 24 96 15/11 300 8 KVM

4
h3.8xlarge. 32 128 17/15 400 16 KVM

4
Scenarios
l Computing and storage systems for genetic engineering, games, animations, and
biopharmaceuticals
l Public rendering platforms for renderfarms and animation and film bases; other
rendering platforms for movies and videos
l High-performance frontend clusters, web servers, high-performance science and
engineering applications, advertisements, video coding, and distributed analysis
l Batch-processed workload, high-performance computing (HPC), and SAP applications
l Computing-intensive services, such as large-scale multiplayer online (MMO) gaming
Notes on Using H1 ECSs

l H1 ECSs do not support NIC hot swapping.
l H1 ECSs support modifying specifications only if the source and target ECSs are of the
same type.
l H1 ECSs support the following OSs:

– Windows Server 2008

l The primary and extension NICs of an H1 ECS have specified application scenarios. For
details, see Table 7-63.
Table 7-63 Application scenarios of the NICs of an H1 ECS

communication.
Extension NIC Applies to horizontal layer To improve network performance,

2 communication. you can set the MTU of the
extension NIC to 8888.
7.11 Ultra-high Performance Computing ECSs

Overview
Ultra-high performance computing ECSs are designed to meet high-end computational needs,
such as industrial simulation, molecular modeling, and computational fluid dynamics. In
addition to the substantial CPU power, the ultra-high performance computing ECSs offer
diverse options for low-latency RDMA networking using EDR InfiniBand NICs to support
memory-intensive computational requirements.
Specifications

Bandwid Queu
th e
(Gbit/s)
h2.3xlarg 16 128 13/8 90 8 1 x 3.2 KVM

e.10


Bandwid Queu
th e
(Gbit/s)
h2.3xlarg 16 256 13/8 90 8 1 x 3.2 KVM

e.20
Features
l Large memory capacity and more processor cores than other types of ECSs
l InfiniBand NICs providing a bandwidth of 100 Gbit/s
l 100 Gbit/s EDR InfiniBand network
Notes on Using H2 ECSs

l H2 ECSs do not support OS reinstallation or change.
l H2 ECSs do not support specifications modification.
l H2 ECSs do not support cold migration, live migration, or HA.
l H2 ECSs support the following OSs:
– For public images:
n CentOS 7.2 64bit
n CentOS 6.5 64bit
– For private images:
n CentOS 6.5 64bit
n CentOS 7.2 64bit
n CentOS 7.3 64bit
n SUSE Linux Enterprise Server 11 SP4 64bit
n SUSE Linux Enterprise Server 12 SP2 64bit
n Red Hat Enterprise Linux 7.2 64bit
n Red Hat Enterprise Linux 7.3 64bit
l H2 ECSs use InfiniBand NICs that provide a bandwidth of 100 Gbit/s.
l Each H2 ECS uses one PCIe 3.2 TB SSD card for temporary local storage.
l If an H2 ECS is created using a private image, install an InfiniBand NIC driver on the
ECS after the ECS creation following the instructions provided by Mellanox. Download
the required version (4.2-1.0.0.0) of InfiniBand NIC driver from the official Mellanox
website and install the driver by following the instructions provided by Mellanox.
– InfiniBand NIC type: Mellanox Technologies ConnectX-4 Infiniband HBA
(MCX455A-ECAT)
– Mellanox official website: http://www.mellanox.com/
– NIC driver download path: http://www.mellanox.com/page/products_dyn?
product_family=26&mtag=linux_sw_drivers

l If Internet Protocol over Infiniband (IPoIB) is required on an H2 ECS running a SUSE

OS, you must manually allocate an IP address to the InfiniBand NIC after installing the
InfiniBand NIC driver.
l After you delete an H2 ECS, the data stored in SSDs is automatically cleared. Therefore,
do not store persistence data into SSDs during ECS running.
l An H2 ECS is charged even if it is stopped. To stop charging such an ECS, delete it.
7.12 GPU-accelerated ECSs

GPU-accelerated ECSs provide outstanding floating-point computing capabilities. They are
suitable for scenarios that require real-time, highly concurrent massive computing.
GPU-accelerated ECSs are classified as graphics-accelerated (G series) and computing-
accelerated (P series) ECSs.
l G series of ECSs are suitable for 3D animation rendering and CAD.
l P series of ECSs are designed for deep learning, scientific computing, and CAE.
GPU-accelerated ECS Types

G and P series of ECSs are as follows:
l G series
– Graphics-accelerated Enhancement G3
– Graphics-accelerated G1
l P series
– Computing-accelerated P2v
– Computing-accelerated P1
– Inference-accelerated PI1
Helpful links:
l Images Supported by GPU-accelerated ECSs
l Installing the GRID Driver
l Installing the NVIDIA GPU Driver and CUDA Toolkit

Table 7-65 GPU-accelerated ECSs

Clas ECS GPU Application AZ Remarks
sific Type Scenario
ation
G G5 NVIDIA V100 Cloud CN North- Remote login on

series (GPU desktop, Beijing 1, AZ 2 the management
virtualization) image CN North- console is
rendering, 3D Beijing 4, AZ 1 unavailable. To
visualization, log in to such an
and heavy- CN East- ECS, use VNC or
load graphics Shanghai 2, AZ third-party VDI.
design 2
CN South-
Guangzhou, AZ
3
G3 NVIDIA M60 CN North- Remote login on

(GPU Beijing 1, AZ 1 the management
passthrough) CN East- console is
Shanghai 2, AZ unavailable. To
2 log in to such an
ECS, use VNC or
CN South- third-party VDI.
Guangzhou, AZ
2
G1 NVIDIA M60 CN North- G1 ECSs of flavor

(GPU Beijing 1, AZ 2 g1.2xlarge.8 use
virtualization) CN East- GPU passthrough.
Shanghai 2, AZ Remote login on
1 the management
console is
CN South- unavailable. To
Guangzhou, AZ log in to such an
1 ECS, use VNC or
third-party VDI.
P P2v NVIDIA V100 Machine CN North- N/A

series NVLink (GPU learning, deep Beijing 1, AZ 2
passthrough) learning, CN North-
reference Beijing 4, AZ 1
training,
scientific CN East-
computing, Shanghai 2, AZ
seismic 2
analysis,
computing
finance,
rendering,
multimedia
encoding and
decoding

Clas ECS GPU Application AZ Remarks

sific Type Scenario
ation
P1 NVIDIA P100 CN North- Local NVMe

(GPU Beijing 1, AZ 1 SSDs are used.
passthrough) CN East- Pay-per-use ECSs
Shanghai 2, AZ are billed after
2 they are stopped.
CN South-
Guangzhou, AZ
2
PI1 NVIDIA P4 CN North- N/A

(GPU Beijing 1, AZ 1
passthrough)
NOTE
l Remote login on the management console can be used for O&M, but it cannot be used in the
production environment. Physical GPUs cannot be used if an ECS is remotely logged in through the
management console.
l If remote login on the management console is unavailable, use Windows MSTSC or a third-party
desktop protocol, such as TeamViewer or VNC for login.
Images Supported by GPU-accelerated ECSs
Table 7-66 Image list

Classification ECS Type Supported Image
G series G5 Windows Server 2012 R2 Standard 64bit

Windows Server 2016 Standard 64bit
CentOS 7.5 64bit
G series G3 Windows Server 2012 R2 Standard 64bit

Windows Server 2008 R2 Enterprise
G1 Windows Server 2012 R2 Standard 64bit

Windows Server 2008 R2 Enterprise
P series P2v Windows Server 2016 Standard 64bit

Windows Server 2012 R2 Standard 64bit
Ubuntu 16.04 64bit
CentOS 7.4 64bit
EulerOS 2.2 64bit

Classification ECS Type Supported Image
P1 Windows Server 2012 R2 Standard 64bit

CentOS 7.3 64bit
EulerOS 2.2 64bit
Ubuntu 16.04 64bit
Debian 8.0.0 64bit
PI1 CentOS 7.3 64bit

Ubuntu 16.04 64bit
Ubuntu 14.04 64bit
Graphics-accelerated Enhancement G3
Overview
G3 ECSs are based on PCI passthrough and exclusively use GPUs for professional graphics
acceleration. In addition, G3 ECSs use NVIDIA Tesla M60 GPUs and support DirectX and
OpenGL with up to 16 GB of GPU memory and 4,096 x 2,160 resolution. They are ideal for
professional graphics workstations.
Specifications

Flavor vC Memor Maximu Max. NIC GPUs GPU Virtu
PU y (GB) m/ PPS Multi Memor alizat
s Assured (10,000 - y (GB) ion
Bandwidt ) Queu Type
h (Gbit/s) e
g3.4xlar 16 64 8/2.5 50 2 1x 1x8 KVM

ge.4 M60
g3.8xlar 32 128 10/5 100 4 2x 2x8 KVM

ge.4 M60
NOTE
Every NVIDIA Tesla M60 card is equipped with two M60 GPUs, each of which provides 2,048 CUDA
cores and 8 GB of GPU memory. M60 in G series of ECSs indicates M60 GPUs, but not M60 cards.
G3 ECS Features
l Professional graphics acceleration APIs
l NVIDIA M60 GPUs
l Graphics acceleration applications
l GPU passthrough
l Application flow identical to common ECSs

l Automatic scheduling of G3 ECSs to AZs where NVIDIA M60 GPUs are used
l A maximum specification of 16 GB of GPU memory and 4,096 x 2,160 resolution for
processing graphics and videos
Notes
l G3 ECSs do not support specifications modification.

l G3 ECSs support the following OSs:
– Windows Server 2008 R2 Enterprise SP1 64bit
l G3 ECSs do not support the remote login function provided by the public cloud
platform. To remotely log in to such an ECS, use MSTSC to log in to it and install VNC
on the ECS.
l If a G3 ECS is created using a private image, install a GPU driver on the ECS after the
ECS creation. For details, see section Installing the GRID Driver.
Graphics-accelerated G1
Overview
G1 ECSs are based on NVIDIA GRID vGPUs and provide economical graphics acceleration.
They use NVIDIA Tesla M60 GPUs and support DirectX and OpenGL. The ECSs have up to
8 GB of GPU memory and 4,096 x 2,160 resolution, and are used for applications that require
high performance in graphics rendering.
Specifications

Flavor vCPUs Memory Maximu Maximu GPUs GPU Virtu
(GB) m/ m PPS Memor alizat
Assured y (GB) ion
Bandwidt Type
h

e M60-1
Q

e.4 M60-1
Q

ge M60-2
Q
g1.2xlar 8 64 Medium Medium Passthr 8 XEN

ge.8 ough

ge M60-4
Q

NOTE
M60-xQ support vGPUs. x can be 1, 2, 4, or 8, indicating that M60 GPUs are virtualized to vGPUs with
different specifications and models using GRID. x specifies the vGPU memory, and Q indicates that the
vGPU of this type is designed to work in workstations and desktop scenarios. For more details about
GRID vGPUs, see GRID VIRTUAL GPU User Guide.
G1 ECS Features
l NVIDIA M60 GPUs
l Graphics acceleration applications
l GPU hardware virtualization (vGPUs) and GPU passthrough
l Application flow identical to common ECSs
l Automatic scheduling of G1 ECSs to AZs where NVIDIA M60 GPUs are used
l A maximum specification of 8 GB of GPU memory and 4,096 x 2,160 resolution for
processing graphics and videos
Notes
l G1 ECSs do not support specifications modification.
l G1 ECSs support the following OSs:
– Windows Server 2008 R2 Enterprise SP1 64bit
l g1.2xlarge.8 G1 ECSs do not support the remote login function provided by the public
cloud platform. To remotely log in to such an ECS, use MSTSC to log in to it and install
VNC on the ECS.
Non-g1.2xlarge.8 G1 ECSs support the remote login function provided by the public
cloud platform. For details, see section Login Using VNC.
l If a G1 ECS is created using a private image, install a GPU driver on the ECS after the
ECS creation. For details, see section Installing the GRID Driver.
Computing-accelerated P2v
Overview
P2v ECSs use NVIDIA Tesla V100 GPUs and provide flexibility, high-performance
computing, and cost-effectiveness. These ECSs use GPU NVLink for direct communication
between GPUs, improving data transmission efficiency. P2v ECSs provide outstanding
universal computing capabilities and have strengths in AI-based deep learning, scientific
computing, Computational Fluid Dynamics (CFD), computing finance, seismic analysis,
molecular modeling, and genomics.
Specifications

Table 7-69 P2v ECS specifications

Flavor vCP Mem Maxim Maxi NIC GPU GPU GPU Virt
Us ory um/ mum Multi s Con Mem ualiz
(GB) Assure PPS - necti ory ation
d (10,00 Queu on (GB) Type
Bandwi 0) e
dth
(Gbit/s)
p2v. 8 64 10/4 50 4 1x N/A 1 x 16 KVM

2xlarge. V100 GB
8
p2v. 16 128 15/8 100 8 2x NVLi 2 x 16 KVM

4xlarge. V100 nk GB
8
p2v. 32 256 25/15 200 16 4x NVLi 4 x 16 KVM

8xlarge. V100 nk GB
8
p2v. 64 512 30/30 400 32 8x NVLi 8 x 16 KVM

16xlarge V100 nk GB
.8
P2v ECS Features

l Up to eight NVIDIA Tesla V100 GPUs on an ECS
l NVIDIA CUDA parallel computing and common deep learning frameworks, such as
TensorFlow, Caffe, PyTorch, and MXNet
l 15.7 TFLOPS of single-precision computing and 7.8 TFLOPS of double-precision
computing
l NVIDIA Tensor cores with 125 TFLOPS of single- and double-precision computing for
deep learning
l Up to 30 Gbit/s of network bandwidth on a single ECS
l 16 GB of HBM2 GPU memory with a bandwidth of 900 Gbit/s
l Comprehensive basic capabilities
Networks are user-defined, subnets can be divided, and network access policies can be
configured as needed. Mass storage is used, elastic capacity expansion as well as backup
and restoration are supported to make data more secure. Auto Scaling allows you to add
or reduce the number of ECSs quickly.
l Flexibility
Similar to other types of ECSs, P2v ECSs can be provisioned in a few minutes.
l Excellent supercomputing ecosystem
The supercomputing ecosystem allows you to build up a flexible, high-performance,
cost-effective computing platform. A large number of HPC applications and deep-
learning frameworks can run on P2v ECSs.
Supported Common Software

P2v ECSs are used in computing acceleration scenarios, such as deep learning training,
inference, scientific computing, molecular modeling, and seismic analysis. If the software
requires GPU CUDA parallel computing, use P2v ECSs. P2v ECSs support the following
commonly used software:
l Common deep learning frameworks, such as TensorFlow, Caffe, PyTorch, and MXNet
l CUDA GPU rendering supported by RedShift for Autodesk 3dsMax and V-Ray for 3ds
Max
l Agisoft PhotoScan
l MapD
Notes
l If a P2v ECS is created using a private image, make sure that the NVIDIA driver has
been installed during the private image creation. If not, install the driver after the P2v
ECS is created for computing acceleration. For details, see section Installing the
NVIDIA GPU Driver and CUDA Toolkit.
l P2v ECSs do not support specifications modification.
l Pay-per-use P2v ECSs support the following OSs:
– Ubuntu Server 16.04 64bit
– Windows Server 2016 Standard 64bit
Computing-accelerated P1
Overview
P1 ECSs use NVIDIA Tesla P100 GPUs and provide flexibility, high performance, and cost-
effectiveness. These ECSs support GPU Direct for direct communication between GPUs,
improving data transmission efficiency. P1 ECSs provide outstanding universal computing
capabilities and have strengths in deep learning, graphic databases, high-performance
databases, Computational Fluid Dynamics (CFD), computing finance, seismic analysis,
molecular modeling, and genomics. They are designed for scientific computing.
Specifications
Table 7-70 P1 ECS specifications

idth e
(Gbit/s
)
p1.2xlar 8 64 5/1.6 35 2 1x 1 x 16 1 x 800 KVM

ge.8 P100 GB
NVMe


idth e
(Gbit/s
)
p1.4xlar 16 128 8/3.2 70 4 2x 2 x 16 2 x 800 KVM

ge.8 P100 GB
NVMe
p1.8xlar 32 256 10/6.5 140 8 4x 4 x 16 4 x 800 KVM

ge.8 P100 GB
NVMe
P1 ECS Features
l Up to four NVIDIA Tesla P100 GPUs on a P1 ECS (If eight P100 GPUs are required on
an instance, use BMS.)
l GPU hardware passthrough
l 9.3 TFLOPS of single-precision computing and 4.7 TFLOPS of double-precision
computing
l Maximum network bandwidth of 10 Gbit/s
l 16 GB of HBM2 GPU memory with a bandwidth of 732 Gbit/s
l 800 GB NVMe SSDs for temporary local storage
l Comprehensive basic capabilities
Networks are user-defined, subnets can be divided, and network access policies can be
configured as needed. Mass storage is used, elastic capacity expansion as well as backup
and restoration are supported to make data more secure. Auto Scaling allows you to add
or reduce the number of ECSs quickly.
l Flexibility
Similar to other types of ECSs, P1 ECSs can be provisioned in a few minutes. You can
configure specifications as needed. P1 ECSs with two, four, and eight GPUs will be
supported later.
l Excellent supercomputing ecosystem
The supercomputing ecosystem allows you to build up a flexible, high-performance,
cost-effective computing platform. A large number of HPC applications and deep-
learning frameworks can run on P1 ECSs.
P1 ECSs are used in computing acceleration scenarios, such as deep learning training,
inference, scientific computing, molecular modeling, and seismic analysis. If the software
requires GPU CUDA parallel computing, use P1 ECSs. P1 ECSs support the following
commonly used software:
l Deep learning frameworks, such as TensorFlow, Caffe, PyTorch, and MXNet
l RedShift for Autodesk 3dsMax, V-Ray for 3ds Max

l Agisoft PhotoScan
l MapD
Notes
l It is recommended that the system disk of a P1 ECS be greater than 40 GB.
l P1 ECSs have local NVMe SSDs attached, which are still billed after the ECSs are
stopped. To stop billing such an ECS, delete it.
l The local NVMe SSDs attached to P1 ECSs are dedicated for services with strict
requirements on storage I/O performance, such as deep learning training and HPC. Local
disks are attached to the ECSs of specified flavors and cannot be separately bought. In
addition, you are not allowed to detach a local disk and then attach it to another ECS.
NOTE
Data may be lost on the local NVMe SSDs attached to P1 ECSs due to a fault, for example, due to
a disk or host fault. Therefore, you are suggested to store only temporary data in local NVMe
SSDs. If you store important data in such a disk, securely back up the data.
l If a P1 ECS is created using a private image, make sure that the NVIDIA driver has been
installed during the private image creation. If not, install the driver after the P1 ECS is
created for computing acceleration. For details, see section Installing the NVIDIA GPU
Driver and CUDA Toolkit.
NOTE
For instructions about how to create a private image, see Image Management Service User Guide.
l P1 ECSs do not support specifications modification.
l P1 ECSs do not support automatic recovery.
l P1 ECSs support the following OSs:
– Debian 8.0 64bit
l After you delete a P1 ECS, the data stored in local NVMe SSDs is automatically cleared.
Inference-accelerated PI1
Overview
PI1 ECSs use NVIDIA Tesla P4 GPUs dedicated for real-time AI inference. Working with P4
INT8 calculators, PI1 ECSs have shortened the inference latency by 15 times. Working with
hardware decoding engines, PI1 ECSs concurrently support real-time 35-channel HD video
transcoding and inference.
Specifications

Table 7-71 PI1 ECS specifications

Flavor vCP Mem Max./ Maxi NIC GPU GPU Local Virt
Us ory Assure mum Multi s Mem Disks ualiz
(GB) d PPS - ory ation
Bandwi (10,00 Queu (GB) Type
dth 0) e
(Gbit/s)
pi1.2xlar 8 32 5/1.6 40 2 1x 1x8 N/A KVM

ge.4 P4 GB
pi1.4xlar 16 64 8/3.2 70 4 2x 2x8 N/A KVM

ge.4 P4 GB
pi1.8xlar 32 128 10/6.5 140 8 4x 4x8 N/A KVM

ge.4 P4 GB
PI1 ECS Features

l Up to four NVIDIA Tesla P4 GPUs on a PI1 ECS
l GPU hardware passthrough
l Up to 5.5 TFLOPS of single-precision computing on a single GPU
l Up to 22 TOPS of INT8 computing on a single GPU
l 8 GB of ECC GPU memory with a bandwidth of 192 Gbit/s on a single GPU
l Hardware video encoding and decoding engines embedded in GPUs for concurrent real-
time 35-channel HD video transcoding and inference
PI1 ECSs are used in GPU-based inference computing scenarios, such as image recognition,
voice recognition, and natural language processing.
PI1 ECSs support the following commonly used software:
l Deep learning frameworks, such as TensorFlow, Caffe, PyTorch, and MXNet
Notes
l The basic resources, including vCPUs, memory, and image of a pay-per-use PI1 ECS of
flavor pi1.2xlarge.4, pi1.4xlarge.4, or pi1.8xlarge.4 are not billed after the ECS is
stopped, but the system disk of the ECS is still being billed according to the disk
capacity. If the ECS is bound with other resources, such as EVS disks, EIPs, and
bandwidths, these resources are billed using their own billing mode (yearly/monthly or
pay-per-use). For details, see section ECS Pricing Details.
The resources of a pay-per-use PI1 ECS of flavor pi1.2xlarge.4, pi1.4xlarge.4, or

pi1.8xlarge.4 are released after the ECS is stopped. If the underlying resources are
insufficient when the ECS is started, starting the ECS may fail. If you want to use such
an ECS for a long period of time, you are advised to keep the ECS running or select the
yearly/monthly payment.

l If a PI1 ECS is created using a private image, make sure that the GPU driver has been
installed during the private image creation. If not, install the driver after the PI1 ECS is
created for inference acceleration. For details, see section Installing the NVIDIA GPU
Driver and CUDA Toolkit.
l PI1 ECSs support the following OSs:
l PI1 ECSs do not support specifications modification.
l PI1 ECSs support automatic recovery when the hosts accommodating such ECSs
become faulty.
7.13 FPGA-accelerated ECSs

Overview
A field-programmable gate array (FPGA)-accelerated ECS provides a tool and environment
for developing and using FPGA. With it, you can easily develop FPGA accelerators, deploy
FPGA-based services, and provide easy-to-use, cost-effective, agile, and secure FPGA cloud
services.
FPGA-accelerated ECSs are classified as the following types:

l ECSs using a high-performance architecture
The ECSs of this type are based on high-performance DPDK interaction framework and
support the flow calculation model and data flow concurrency. They are designed for
RTL development and meet the requirements of high bandwidth and low latency.
l ECSs using a universal architecture
The ECSs of this type are based on the general-purpose SDAccel interaction framework
and support the block calculation module and Xilinx SGDMA data transmission. They
are designed for advanced language development or existing algorithm transplantation
and meet the requirements of fast service rollout.
Specifications
Table 7-72 Specifications of ECSs with high-performance architecture

Bandwidt Queu
h (Gbit/s) e
fp1.2xlarge 8 88 5/1.3 20 2 1x KVM

.11 VU9P
fp1.8xlarge 32 352 10/5 60 8 4x KVM

.11 VU9P


Bandwidt Queu
h (Gbit/s) e
fp1.16xlar 64 704 10/10 100 8 8x KVM

ge.11 VU9P
fp1.8xlarge 32 224 10/5 60 8 1x KVM

.8 VU9P
fp1.16xlar 64 448 10/10 100 8 2x KVM

ge.8 VU9P
NOTE
Network: 10 GbE
Table 7-73 Specifications of ECSs with general-computing architecture

Bandwidt Queu
h (Gbit/s) e
fp1c. 8 88 5/1.3 20 2 1x KVM

2xlarge.11 VU9P
fp1c. 32 352 10/5 60 8 4x KVM

8xlarge.11 VU9P
fp1c. 64 704 10/10 100 8 8x KVM

16xlarge. VU9P
11
fp1c. 32 224 10/5 60 8 1x KVM

8xlarge.8 VU9P
fp1c. 64 448 10/10 100 8 2x KVM

16xlarge.8 VU9P
NOTE
Network: 10 GbE
Scenarios
l Applications
FPGA-accelerated ECSs are suitable for applications that require dense computing, high
concurrency, and high bandwidth, such as video processing, machine learning, genomics,
and financial risk analysis.

– Video processing: Video applications, such as automatic image recognition and
classification, image search, video transcoding, real-time rendering, Internet-based
live programs, and AR/VR, require high real-time computing performance, which
cannot be provided by common ECSs. FPGA ECSs offer cost-effective video
solutions, which are ideal for video scenarios.
– Machine learning: Multi-layer neural networks in machine learning require a large
number of computing resources. The training process involves handling massive
data, while the inference process requires ultra-low latency. In addition, machine
learning algorithms are being continuously optimized. FPGA ECSs meet the
preceding requirements due to their high parallel computing, programmable
hardware, low power consumption, and low latency. FPGA dynamically provides
the optimal hardware circuit design for different machine learning algorithms,
meeting strict requirements on massive computing and ultra-low latency. Therefore,
FPGA ECSs meet hardware requirements for machine learning.
– Genomics research: Precision medicine can be implemented through gene
sequencing and analysis as well as rapid analysis on massive biological and medical
data. Many fields, such as pharmaceutical development and molecular breeding,
also require the processing of massive data. These fields require hardware
acceleration to resolve performance bottleneck problems for biological
computation. FPGA ECSs meet such requirements due to their outstanding
programmable hardware computing performance.
– Financial risk analysis: The financial industry has strict requirements on computing
capabilities and real-time performance based on ultra-low latency and high
throughput for services, such as pricing tree model-based financial computing,
high-frequency trading, fund or securities trading algorithms, financial risk analysis
and decision-making, and transaction security assurance. Using programmable
hardware acceleration, FPGA ECSs offer an optimal hardware acceleration solution
for various scenarios. In certain scenarios, FPGA ECS performance has been
improved by thousands of times when compared with the performance of stand-
alone software.
Features
l FPGA development kit
FPGA cloud services provide the hardware development kit (HDK). The HDK contains
accelerator examples, the encoding environment, simulation platform, automatic
compilation tool, and code encrypting and commissioning tool package. You can quickly
develop and test your FPGA hardware accelerator by referring to the application
examples and development guide.
l Software development kit
FPGA cloud services provide the software development kit (SDK). The SDK contains
application examples, hardware abstract interfaces, accelerator abstract interfaces,
accelerator driver and runtime, and the version management tool. Accelerator abstract
interfaces allow your applications to invoke the hardware accelerator in the same way as
the software function library, helping you easily develop high-performance applications
based on the hardware accelerator.
l FPGA hardware configuration
Each FPGA ECS provides up to eight FPGAs and each of them contains 2.5 million
logic units. The PCIe 3.0 x 16 interface is supported, and the throughput reaches 100
Gbit/s. FPGAs communicate with each other through a mesh optical network with a

bandwidth of 300 Gbit/s. Each FPGA provides 64 GB DDR4 memory and an interface
rate of 2133 MHz. FPGA frees your applications from hardware restrictions.
l Hardware acceleration resource pool
FPGA cloud services have a pool of hardware acceleration resources. You can allocate
desirable FPGA resources in a cost-effective way like allocating CPU resources. With
the FPGA virtualization, isolation, and distributed technology, you can share FPGA
resources on a node, which is transparent to your resources and can meet hardware
acceleration requirements of your business to the largest extent.
Notes
l FPGA-accelerated ECSs support only the CentOS 7.3 64bit OS.
l FPGA-accelerated ECSs do not support modifying specifications.
l FPGA-accelerated ECSs cannot be migrated.
l FPGA-accelerated ECSs do not support automatic recovery.
l FP1 and FP1c ECSs are equipped with FPGAs, which are still billed after the ECSs are
stopped. To stop billing such an ECS, delete it.
Follow-up Procedure
After the ECS is created, you can develop and use accelerated engine images (AEIs) through
the hardware development kit (HDK) and application development kit (SDK) provided by the
ECS. For more details, see FACS User Guide.
Related Links
FACS User Guide
7.14 AI-accelerated ECSs

Overview
AI-accelerated AI1 ECSs use Huawei Ascend 310 chips for acceleration. Featuring low power
consumption and high computing capabilities, Ascend 310 chips have significantly improved
energy efficiency ratio (EER), assisting in the wide application of AI inference. AI1 ECSs
release the computing acceleration capabilities of the Ascend 310 chips on the public cloud.
This helps users quickly and simply use the Ascend 310 chips.
AI1 ECSs are used for general technologies, such as machine vision, voice recognition, and
natural language processing to support smart retail, smart campus, robot cloud brain, and safe
city scenarios.

Specifications
Table 7-74 AI1 ECS specifications

Flavor vCPUs Memor Maximu Maximu Ascen Ascend Virtuali
y (GB) m/ m PPS d 310 RAM zation
Assured (10,000) Chips (GB) Type
Bandwidt
h
Ai1.large 2 8 4/1.3 12.5 1 8 KVM

.4
Ai1.xlar 4 16 6/2 25 2 16 KVM

ge.4
Ai1.2xla 8 32 10/4 50 4 32 KVM

rge.4
Ai1.4xla 16 64 15/8 100 8 64 KVM

rge.4
Ai1.8xla 32 128 25/15 200 16 128 KVM

rge.4
Features
AI1 ECSs have the following features:
l Ascend 310 chips, four of which in an Hi1910 accelerator

l 8 TeraFLOPS of half-precision computing (FP16) on one chip
l 16 TeraOPS of integer-precision computing on a single chip (INT8)
l 8 GB of GPU memory with a memory bandwidth of 50 GB/s on one chip
l 16-channel HD video decoder (H.264/H.265) based on built-in hardware video codec
engine
NOTE
AI-accelerated ECSs are in the beta test phase.
Notes
1. AI1 ECSs support the following OSs:
Ubuntu Server 14.04 64bit
2. AI1 ECSs do not support specifications modification.
3. AI1 ECSs support automatic recovery when the hosts accommodating such ECSs
become faulty.
Using an AI-accelerated ECS

Perform the following operations to purchase and use an AI-accelerated ECS:

1. Purchase an AI-accelerated ECS.

Make sure that the ECS to be purchased has had Mind Studio installed for Ascend chip
inference and orchestration. For details, see Purchasing and Logging In to a Linux
ECS.
2. Remotely log in to the ECS.
Use an SSH password to log in to the ECS. For details, see Login Using an SSH
Password.
3. If an AI1 ECS is created using a private image, make sure that the Ascend 310
development environment has been installed during the private image creation. If not,
install the environment after the AI1 ECS is created for inference and orchestration
acceleration. For details about download addresses and installation guide for
MindStudio, see Table 7-75.
Table 7-75 Download addresses and installation guide for MindStudio

Tool/Installation Guide How to Obtain
mini_mind_studio_Ubuntu.rar https://support.huawei.com/carrier/navi?
coltype=software#col=software&detailId=PBI
1-23772363&path=PBI1-21430725/
PBI1-21430756/PBI1-22892969/
PBI1-22368564
Ascend chip guide: Mind Studio https://www.huawei.com/minisite/ascend/en/

Installation Guide converge.html
4. Use AI to accelerate application development.

The Mind Studio orchestration development platform provided in the AI-accelerated
ECS allows you to customize orchestration for AI service flows. This platform centrally
manages the application model and data set of inference services. Additionally, this
platform offers additional functions, such as log analysis, performance analysis, and
black box. Using Mind Studio, you can develop and manage Ascend chip-based AI
projects and convert other framework training models.
For details about Ascend chips, see https://www.huawei.com/minisite/ascend/en/
converge.html.

Service Overview 8 Accessing and Using ECSs
8 Accessing and Using ECSs
8.1 Accessing ECSs

The public cloud provides a web-based service management platform. You can access ECSs
through HTTPS-compliant application programming interfaces (APIs) or the management
console. These two access modes differ as follows:
l Accessing ECSs through APIs
Use this mode if you are required to integrate the ECSs on the public cloud platform into
a third-party system for secondary development. For detailed operations, see Elastic
Cloud Server API Reference.
l Accessing ECSs through the management console
Use this mode if you are not required to integrate ECSs with a third-party system. After
registering on the public cloud, log in to the management console and click Elastic
Cloud Server under Computing on the homepage. If you have not registered with the
public cloud, see Registering Yourself on the Public Cloud.
8.2 ECS and Other Services

Figure 8-1 shows the relationships between ECS and other services.

Figure 8-1 Relationships between ECS and other services
ECS-related Services
Table 8-1 ECS-related services

Service Function Related Operation
Auto Scaling (AS) Automatically adjusts ECS l Using an Existing ECS to

service resources based on the Create an AS Configuration
configured AS policies. This l Using a New Specifications
improves resource usage and Template to Create an AS
reduces resource costs. Configuration
Load Balancer Automatically distributes l Backend ECS (Classic Load

traffic to multiple ECSs. This Balancer)
enhances system service and l Backend Server (Enhanced
fault tolerance capabilities. Load Balancer)
Elastic Volume Enables you to attach EVS l Attaching a Non-shared

Service (EVS) disks to an ECS and expand EVS Disk
their capacity. l Attaching a Shared EVS
Disk

Virtual Private Enables you to configure l Assigning an EIP and

Cloud (VPC) internal networks and change Binding It to an ECS
network configurations by l Adding a Security Group
customizing security groups, Rule
VPNs, IP address segments,
and bandwidth. This simplifies
network management. You can
also customize the ECS access
rules within a security group
and between security groups to
strengthen ECS security
protection.
Image Management Enables you to create ECSs l Creating a Data Disk Image
Service (IMS) using images. This improves Using an ECS Data Disk
the efficiency of ECS creation. l Creating a Full-ECS Image
You can also use an existing Using an ECS
ECS to create a private image
and export the data of the ECS
system disk or data disks.
Dedicated To physically isolate your l Enabling a DeC

Computing Cluster ECS, apply for a DCC before l Applying for DCC
(DCC) creating the ECS. After you Resources
obtain the DCC and set a
region for it, your ECS is
automatically allocated to the
DCC.
Cloud Eye Allows you to check the status l ECS Metrics

of monitored service objects l ECS Metrics Under OS
after you have obtained an Monitoring
ECS. This can be done without
requiring additional plug-ins
be installed.
Data Encryption The encryption feature relies l EVS Disk Encryption

Workshop (DEW) on DEW. You can use an l Encrypting Images
encrypted image or EVS disks
when creating an ECS. In such l Creating a Key Pair
a case, you are required to use
the key provided by DEW to
improve data security.
Cloud Trace Service Records ECS-related l Key Operations on ECS

(CTS) operations for later query,
audit, and backtrack.

Cloud Server Backs up ECSs for restoration. l Creating a CSBS Backup

Backup Service CSBS backs up all EVS disks
(CSBS) of an ECS, including the
system disk and data disks, and
uses the backup to restore the
ECS.
Volume Backup Allows you to create data l Creating a VBS Backup

Service (VBS) backups for EVS disks and use
the backups to restore the EVS
disks. This maximizes data
security and correctness and
ensures service security.

Service Overview 9 Change History
9 Change History
Released On Description
2019-04-25 This issue is the nineteenth official release.

l Added EVS disk backup in section 8.2 ECS and Other Services.
l Modified application scenarios of E1 and E2 ECSs in section 7.7
Large-Memory ECSs.
2019-03-29 This issue is the eighteenth official release.

l Terminated s6.4xlarge.2 and s6.4large.4 ECSs in section 7.3
General Computing ECSs.
l Modified section 4.4 Project and Enterprise Project.
2019-03-12 This issue is the seventeenth official release.

Added the following content:
l 7.2 ECS Specifications
2019-03-01 This issue is the sixteenth official release.

l Added C6 ECSs in section 7.4 General Computing-Plus ECSs.
2019-02-21 This issue is the fifteenth official release.

l Added flavors m3ne.3xlarge.8 and m3ne.6xlarge.8 in section 7.6
Memory-optimized ECSs.
l Added flavors e3.26xlarge.14, e3.52xlarge.14, and e3.52xlarge.20 in
section 7.7 Large-Memory ECSs.
2019-02-18 This issue is the fourteenth official release.

Modified the following content:
l 7.14 AI-accelerated ECSs
l 8.2 ECS and Other Services

2019-01-18 This issue is the thirteenth official release.

l 7.14 AI-accelerated ECSs
l Added S6 ECSs in section 7.3 General Computing ECSs.
l 7.12 GPU-accelerated ECSs
2018-12-22 This issue is the twelfth official release.

l Modified description in section 7.13 FPGA-accelerated ECSs
because FPGA-accelerated ECSs have been commercially used.
2018-12-10 This issue is the eleventh official release.

l Added newly released G5 and P2v ECSs and canceled P2 ECSs in
section 7.12 GPU-accelerated ECSs.
2018-11-19 This issue is the tenth official release.

l Added section 6.2 Spot ECSs because spot ECSs have been
released in the CN South region for OBT.
l Added newly released E3 ECSs in section 7.7 Large-Memory
ECSs.
l Terminated Hi3 ECSs in section 7.11 Ultra-high Performance
Computing ECSs.
2018-10-29 This issue is the ninth official release.

l Modified description in section 7.8 Disk-intensive ECSs, allowing
you to attach up to 60 disks to an ECS.
l Modified description in section 7.9 Ultra-high I/O ECSs, allowing
you to attach up to 60 disks to an ECS.
l Modified description in section 7.12 GPU-accelerated ECSs,
allowing PI1 ECSs of flavors pi1.2xlarge.4, pi1.4xlarge.4, and
pi1.8xlarge.4 to support automatic recovery.
2018-08-13 This issue is the eighth official release.

l Added the billing description for PI1 ECSs in section 7.12 GPU-
accelerated ECSs.

2018-08-03 This issue is the seventh official release.

l 7.5 General-Entry ECSs
l 7.7 Large-Memory ECSs
l Modified description in section 7.13 FPGA-accelerated ECSs, in
which an ECS equipped with FPGAs is still being billed after the
ECS is stopped.
2018-07-10 This issue is the sixth official release.

l Added OBT flavors fp1.16xlarge.11.dev and fp1c.16xlarge.11.dev
in section 7.13 FPGA-accelerated ECSs.
l Added flavors c3.3xlarge.2, c3.6xlarge.2, c3.3xlarge.4, and
c3.6xlarge.4 in section 7.4 General Computing-Plus ECSs.
l Added flavors m3.3xlarge.8 and m3.6xlarge.8 in section 7.6
Memory-optimized ECSs.
l Added flavors h3.3xlarge.2, h3.6xlarge.2, h3.3xlarge.4, and
h3.6xlarge.4 in section 7.10 High-Performance Computing ECSs.
2018-07-02 This issue is the fifth official release.

l Added network QoS.
l Officially released I3 ECSs for commercial use in section 7.9 Ultra-
high I/O ECSs.
l Added three types of PI1 flavors in section 7.12 GPU-accelerated
ECSs.
l Added network QoS in section 7.1 ECS Types.
2018-06-11 This issue is the fourth official release.

l Modified description in sections 7.8 Disk-intensive ECSs and 7.9
Ultra-high I/O ECSs, allowing an I3 or D2 ECS to be attached with
up to 24 VBD disks and 30 SCSI disks.
l Added notes on using D2 ECSs in section 7.8 Disk-intensive ECSs.
l Added newly released C3ne, M3ne, Sn3, and Hi3 ECSs.
2018-05-25 This issue is the third official release.

l Added the g1.2xlarge.8 flavor in section 7.12 GPU-accelerated
ECSs.

2018-04-05 This issue is the second official release.

l Added the virtualization type for each ECS flavor.
l 7.13 FPGA-accelerated ECSs
2018-01-26 This issue is the first official release.

Ecs Productdesc

Uploaded by

Copyright:

Available Formats

You might also like

Ecs Productdesc

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Ecs Productdesc

Uploaded by

Copyright:

Available Formats

Elastic Cloud Server

HUAWEI TECHNOLOGIES CO., LTD.

Trademarks and Permissions

Huawei Technologies Co., Ltd.

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. i

7 ECS Types and Specifications...................................................................................................18

8 Accessing and Using ECSs.........................................................................................................81

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. ii

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. iii

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 1

Figure 1-1 ECS architecture

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 2

2 Regions and AZs

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 3

EVS Disk Types

EVS Disk Device Types

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 4

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 5

4 Network and Security

4.2 User Encryption

Use either of the following methods to create an encrypted image:

l Create an encrypted image using an existing encrypted ECS.

EVS Disk Encryption

l When creating an ECS, you can encrypt added data disks.

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 6

Figure 4-1 Data encryption process

Table 4-1 Keys

Default CMK A master key automatically generated by the l Supports viewing

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 7

l For Windows OSs, download and install Cloudbase-Init.

After Cloud-Init or Cloudbase-Init is installed in an image, Cloud-Init or Cloudbase-Init

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 8

4.4 Project and Enterprise Project

Differences Between Projects and Enterprise Projects

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 9

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 10

Table 5-1 Image types

Shared A private image shared by another user.

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 11

Conversion Between Images and ECSs

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 12

Table 6-1 ECS statuses

Starting Intermediate The ECS is between the Stopped and SHUTOFF

Running Stable The ECS is running properly. ACTIVE

Stopping Intermediate The ECS is between the Running ACTIVE

Stopped Stable The ECS has been properly stopped. SHUTOFF

Restarting Intermediate The ECS is being restarted. REBOOT

Resizing Intermediate The ECS has received a resizing RESIZE

Verifying Intermediate The ECS is verifying the modified VERIFY_RESIZE

Issue 19 (2019-04-25) Copyright © Huawei Technologies Co., Ltd. 13

Status Status Description API Status

Deleting Intermediate The ECS is being deleted. ACTIVE,

Deleted Intermediate The ECS has been deleted. An ECS DELETED

Faulty Stable An exception has occurred on the ERROR

Reinstalling Intermediate The ECS has received a request to SHUTOFF

Reinstalling Stable The ECS received a request to SHUTOFF

Changing Intermediate The ECS received a request to change SHUTOFF

OS Change Stable The ECS has received a request to SHUTOFF