Alibaba Cloud disks are block-level data storage resources for Elastic Compute Service (ECS). Alibaba Cloud disks provide low latency, high performance, high durability, and high reliability. Alibaba Cloud disks use a distributed triplicate mechanism to ensure 99.9999999% (nine 9's) data durability for ECS instances. If service disruptions due to hardware failures occur within a zone, data within the zone is copied to an available disk in another zone to ensure data durability and availability.

Disk categories

Disks are classified into the following categories based on their performance:
  • ESSD AutoPL disks: You can configure the burst performance and provisioned performance of ESSD AutoPL disks based on your business requirements. ESSD AutoPL disks inherit the features and performance of enhanced SSDs (ESSDs) and provide the capability of decoupling disk capacity from disk performance. For more information, see ESSD AutoPL disks.
    We recommend that you use ESSD AutoPL disks in the following scenarios:
    • Scenarios to which ESSDs are applicable, such as large-sized online transactional processing (OLTP) databases, NoSQL databases, and Elasticsearch, Logstash, and Kibana (ELK) distributed logs.
    • Scenarios in which business requires disk performance to increase without disk capacity expansion.
    • Scenarios in which business workloads greatly fluctuate and require disks that can burst their performance to handle spiky workloads.
  • ESSDs: ESSDs are based on the next-generation distributed block storage architecture and utilize 25 Gigabit Ethernet and remote direct memory access (RDMA). Each ESSD has low one-way latency and can deliver up to 1,000,000 random read/write IOPS. For more information, see ESSDs.

    We recommend that you use ESSDs for scenarios such as online transactional processing (OLTP) databases, NoSQL databases, and Elasticsearch, Logstash, and Kibana (ELK) distributed logs.

  • Standard SSDs: Standard SSDs are high-performance disks that provide consistent high random IOPS and high data reliability.

    We recommend that you use standard SSDs for scenarios such as I/O-intensive applications, small and medium-sized relational databases, and NoSQL databases.

  • Ultra disks: Ultra disks are cost-effective and provide medium random IOPS and high data reliability.

    We recommend that you use ultra disks as system disks for scenarios such as development and testing.

  • Basic disks: Basic disks are the previous generation of disks and are unavailable for purchase.

The following table describes the performance of disks of different categories.

Item ESSD AutoPL disk ESSD Standard SSD Ultra disk Basic disk
PL3 PL2 PL1 PL0
Capacity range per disk (GiB) 40~32,768 1261~32,768 461~32,768 20~32,768 40~32,768 20~32,768 20~32,768 5~2,000
Maximum IOPS 1,000,000 1,000,000 100,000 50,000 10,000 25,000 5,000 Several hundreds
Maximum throughput (MB/s) 4,096 4,000 750 350 180 300 140 30~40
Formula for calculating the IOPS per disk
  • Baseline performance: min{1,800 + 50 × Capacity, 50,000}
  • Provisioned performance: min{Provisioned IOPS, 50,000}
  • Burst performance: min{IOPS supported by the instance type, 1,000,000}
min{1,800 + 50 × Capacity, 1,000,000} min{1,800 + 50 × Capacity, 100,000} min{1,800 + 50 × Capacity, 50,000} min{1,800+12 × Capacity, 10,000} min{1,800 + 30 × Capacity, 25,000} min{1,800 + 8 × Capacity, 5,000} None
Formula for calculating the throughput per disk (MB/s)
  • Baseline performance: min{120 + 0.5 × Capacity, 350}
  • Provisioned performance: min{16 KB × Provisioned IOPS/1,024, Maximum throughput per disk}
  • Burst performance: min{Throughput supported by the instance type, 4 GB/s}
min{120 + 0.5 × Capacity, 4,000} min{120 + 0.5 × Capacity, 750} min{120 + 0.5 × Capacity, 350} min{100 + 0.25 × Capacity, 180} min{120 + 0.5 × Capacity, 300} min{100 + 0.15 × Capacity, 140} None
Average one-way random write latency in milliseconds (block size = 4 KB) 0.2 0.2 0.2 0.2 0.3~0.5 0.5~2 1~3 5~10
API parameter value cloud_auto cloud_essd cloud_essd cloud_essd cloud_essd cloud_ssd cloud_efficiency cloud

For more information about disk performance, see EBS performance.

Disks are classified into system disks and data disks based on their purposes.
  • System disks contain operating systems and can be created only along with instances. The lifecycle of a system disk is the same as that of the instance to which the system disk is attached.
  • Data disks are used to store application data and can be created separately or along with instances.
Note When a disk is created, the disk capacity displayed in the ECS console includes the capacity occupied by the operating system, and the remaining available capacity may be less than the disk capacity displayed in the ECS console. For example, if the capacity of a system disk displayed in the ECS console is 40 GiB, the remaining available capacity may be less than 40 GiB because the operating system occupies some of the disk capacity.

Limits

A disk can be attached only to a single ECS instance within the same zone.

The limits described in the following table also apply.

Item Requirement or limit Adjust the quota
Permissions to create pay-as-you-go disks To create disks within the Chinese mainland, you must first complete real-name verification. N/A
Maximum number of pay-as-you-go disks You can view the resource quota in the ECS console. For more information, see View and increase resource quotas. N/A
Maximum number of system disks on a single instance 1 N/A
Maximum number of data disks on a single instance 64
Note You can attach a maximum of 16 data disks to an instance when you create the instance. If the instance requires more data disks, attach more data disks after the instance is created. The maximum number of disks that can be attached to an instance varies with instance types. For more information, see Instance family.
N/A
Capacity of all pay-as-you-go ultra disks within an account You can view the resource quota in the ECS console. For more information, see View and increase resource quotas. N/A
Capacity of all pay-as-you-go standard SSDs within an account You can view the resource quota in the ECS console. For more information, see View and increase resource quotas. N/A
Capacity of all pay-as-you-go enhanced SSDs (ESSDs) within an account You can view the resource quota in the ECS console. For more information, see View and increase resource quotas. N/A
Capacity of a single basic disk 5 GiB~2,000 GiB N/A
Capacity of a single standard SSD 20 GiB~32,768 GiB N/A
Capacity of a single ultra disk 20 GiB~32,768 GiB N/A
Capacity of a single ESSD
  • PL0 ESSDs: 40 GiB to 32,768 GiB
  • PL1 ESSDs: 20 GiB to 32,768 GiB
  • PL2 ESSDs: 461 GiB to 32,768 GiB
  • PL3 ESSDs: 1,261 GiB to 32,768 GiB
N/A
Capacity of a single ESSD AutoPL disk 40 GiB~32,768 GiB N/A
Capacity of a single local standard SSD 5 GiB~800 GiB N/A
Capacity of all local standard SSDs on an instance 1,024 GiB N/A
Capacity of a single system disk
  • Windows Server: 40 GiB to 500 GiB
  • Red Hat: 40 GiB to 500 GiB
  • CoreOS and FreeBSD: 30 GiB to 500 GiB
  • Linux distributions excluding CoreOS: 20 GiB to 500 GiB
N/A
Permissions to attach new local disks to instances that are equipped with local disks New local disks cannot be attached to instances that are already equipped with local disks. N/A
Permissions to change configurations of instances that are equipped with local disks Only bandwidth configurations of instances that are equipped with local disks can be changed. N/A
Mount points of system disks /dev/vda N/A
Mount points of data disks /dev/vd[b-z] N/A

Billing

For information about the billing of disks, visit the Pricing tab on the Elastic Compute Service product page.

Disks support the subscription and pay-as-you-go billing methods. For more information, see Subscription and Pay-as-you-go.

  • Disks created along with subscription instances or separately created for subscription instances use the subscription billing method.
  • Disks created along with pay-as-you-go instances or separately created use the pay-as-you-go billing method. Storage capacity units (SCUs) can be used to offset the bills of pay-as-you-go disks.

After a disk is created, you can change its billing method. For information about, see Change the billing methods of a disk.

Related operations

The following table describes the operations that you can perform on disks.

Operation References
Attach an idle pay-as-you-go disk to an ECS instance
  1. Attach a data disk
  2. Format the data disk based on the operating system. For more information, see the following topics:
Create and use a data disk
  1. Create a disk
  2. Attach a data disk
  3. Format the data disk based on the operating system. For more information, see the following topics:
Encrypt data stored on a disk For more information about encryption, see Encryption overview.
For more information about how to encrypt disks, see the following topics:
Resize a system disk or data disk

For more information about resizing, see Overview.

Replace the operating system of an instance Replace the operating system of an instance by using a public image
Back up data stored on a disk
Restore a disk to its initial state Re-initialize a system disk
Restore a disk to its state at a specific point in time Roll back a disk by using a snapshot
Detach a damaged system disk from an instance and attach the disk back to the instance after the disk is repaired Detach or attach a system disk
Release an instance but retain data stored on its system disk
Release a subscription disk that is no longer needed to reduce costs
  1. Change the billing methods of a disk
  2. Detach a data disk
  3. Release a disk
Release a pay-as-you-go disk that is no longer needed to reduce costs
  1. Detach a data disk
  2. Release a disk