Updated on 2024-04-15 GMT+08:00

Disk-intensive ECSs

Overview

Disk-intensive ECSs are delivered with local disks for high storage bandwidth and IOPS. In addition, local disks are more cost-effective in massive data storage scenarios. Disk-intensive ECSs have the following features:

  • They use local disks to provide high sequential read/write performance and low latency, improving file read/write performance.
  • They provide powerful and stable computing capabilities, ensuring efficient data processing.
  • They provide high intranet performance, including high intranet bandwidth and packets per second (PPS), meeting requirements for data exchange between ECSs during peak hours.

D3 ECSs use Intel® Xeon® Scalable processors to offer powerful and stable computing performance. Equipped with proprietary 25GE high-speed intelligent NICs and local SAS disks, D3 ECSs offer ultra-high network bandwidth, PPS, and local storage.

Table 1 Disk-intensive ECS features

Type

Compute

Disk Type

Network

D3

  • vCPU to memory ratio: 1:8 or 1:10
  • Number of vCPUs: 4 to 56
  • Intel® Xeon® Scalable Processor
  • Basic/Turbo frequency: 3.0 GHz/3.4 GHz
  • Ultra-high I/O
  • General Purpose SSD
  • High I/O
  • Extreme SSD
  • Ultra-high PPS throughput
  • An ECS with higher specifications has better network performance.
  • Maximum PPS: 5,000,000
  • Maximum intranet bandwidth: 40 Gbit/s

Specifications

Table 2 D3 ECS specifications

Flavor

vCPUs

Memory

(GiB)

Max./Assured Bandwidth

(Gbit/s)

Max. PPS

(10,000)

Max. NIC Queues

Max. NICs

Local Disks

(GiB)

Virtualization

d3.xlarge.8

4

32

2.5/2.5

50

2

3

2 × 1,675

KVM

d3.2xlarge.8

8

64

5/5

100

2

4

4 × 1,675

KVM

d3.4xlarge.8

16

128

10/10

120

4

8

8 × 1,675

KVM

d3.6xlarge.8

24

192

15/15

160

6

8

12 × 1,675

KVM

d3.8xlarge.8

32

256

20/20

200

8

8

16 × 1,675

KVM

d3.12xlarge.8

48

384

32/32

220

16

8

24 × 1,675

KVM

d3.14xlarge.10

56

560

40/40

500

16

8

28 × 1,675

KVM

Notes on Using D3 ECSs

  • If the host where a D3 ECS resides becomes faulty, the ECS cannot be restored through live migration.
    • If the host is faulty or subhealthy, you need to stop the ECS for hardware repair.
    • In case of system maintenance or hardware faults, the ECS will be redeployed (to ensure HA) and cold migrated to another host. The local disk data of the ECS will not be retained.
  • D3 ECSs do not support specifications modification.
  • D3 ECSs do not support local disk snapshots or backups.
  • D3 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 D3 ECS.
    • Both EVS disks and local disks can be used as data disks of a D3 ECS.
    • A maximum of 60 disks (including VBD, SCSI, and local disks) can be attached to a D3 ECS. Among the 60 disks, the maximum number of SCSI disks is 30, and the VBD disks (including the system disk) is 24. For details, see Can I Attach Multiple Disks to an ECS?

      The maximum number of disks attached to an existing D3 ECS remains unchanged.

  • You can modify the fstab file to set automatic disk mounting at ECS start.
  • The local disk data of a D3 ECS may be lost if an exception occurs, such as physical server breakdown or local disk damage. If your application does not use the data reliability architecture, it is a good practice to use EVS disks to build your ECS.
  • When a D3 ECS is deleted, its local disk data will also be automatically deleted, which can take some time. As a result, a D3 ECS takes a longer time than other ECSs to be deleted. Back up the data before deleting such an ECS.
  • Do not store service data in local disks for a long time. Instead, store it in EVS disks. To improve data security, use a high availability architecture and back up data in a timely manner.
  • Local disks can only be purchased during ECS creation. The quantity and capacity of your local disks are determined according to the specifications of your ECS.

Application Scenario

  • Applications: Massively parallel processing (MPP) database, MapReduce and Hadoop distributed computing, and big data computing
  • Features: Suitable for applications that require large volumes of data to process, high I/O performance, and rapid data switching and processing.
  • Application scenarios: Distributed file systems, network file systems, and logs and data processing applications