Help Center/ Elastic Volume Service/ User Guide/ Overview/ Disk Types and Performance
Updated on 2022-12-20 GMT+08:00
View PDF
Share

Disk Types and Performance

EVS disks are classified based on the disk I/O performance. EVS disks differ in performance and price. Choose the disk type most appropriate for your applications.

EVS Performance

EVS performance metrics include:
  • IOPS: Number of read/write operations performed by an EVS disk per second
  • Throughput: Amount of data read from and written into an EVS disk per second
  • Read/write I/O latency: Minimum interval between two consecutive read/write operations on an EVS disk
    Single-queue access latencies of different types of EVS disks are as follows:
    • High I/O: 1 ms to 3 ms
    • Ultra-high I/O: 1 ms

Table 1 EVS performance data

Parameter

High I/O

Ultra-high I/O

IOPS per GiB/EVS disk

6

50

Max. IOPS/EVS disk

5,000

33,000

Baseline IOPS/EVS disk

1,200

1,500

IOPS limit/EVS disk

Min. (5,000, 1,200 + 6 x Capacity)

Min. (33,000, 1,500 + 50 x Capacity)

IOPS burst limit/EVS disk

5,000

16,000

Max. throughput

150 MiB/s

350 MiB/s

API name

NOTE:

This API name indicates the value of the volume_type parameter in the EVS API. It does not represent the type of the underlying hardware device.

SAS

SSD

Typical application scenarios

Mainstream applications requiring high performance and high reliability, such as large-scale development and test environments, web server logs, and enterprise applications. Typical enterprise applications include SAP applications, Microsoft Exchange, and Microsoft SharePoint.

Read/write-intensive applications that require ultra-high I/O and throughput, such as distributed file systems used in HPC scenarios or NoSQL and relational databases used in I/O-intensive scenarios. Typical databases include MongoDB, Oracle, SQL Server, MySQL, and PostgreSQL databases.

Calculating Disk IOPS Limit

To calculate the IOPS limit of a disk, obtain the smaller value of the following two values:

  • Max. IOPS/disk
  • Baseline IOPS/disk + IOPS per GiB x Disk capacity
The following example uses an ultra-high I/O EVS disk with a maximum IOPS of 33,000.
  • If the disk capacity is 100 GiB, the disk IOPS limit is calculated as follows:

    Disk IOPS limit = Min. (33,000, 1,500 + 50 x 100)

    The disk IOPS limit is 6,500, the smaller value between 33,000 and 6,500.

  • If the disk capacity is 1,000 GiB, the disk IOPS limit is calculated as follows:

    Disk IOPS limit = Min. (33,000, 1,500 + 50 x 1,000)

    The disk IOPS limit is 33,000, the smaller value between 33,000 and 51,500.

Disk Burst Capability and Principles

The burst capability allows a small-capacity disk to surpass the disk IOPS limit within a certain period of time. The IOPS limit indicates the performance of a single disk.

The burst capability is suitable for improving the server startup speed. Normally, system disks have small capacities. For example, if a 50-GiB ultra-high I/O disk does not have the burst capability, its IOPS limit can reach only 4,000 (1,500 + 50 x 50). However, if the disk has the burst capability, its IOPS limit can burst up to 16,000.

The following example uses an ultra-high I/O EVS disk with the IOPS burst limit of 16,000.
  • If the disk capacity is 100 GiB, the disk IOPS limit is 6,500. In this case, the disk maximum IOPS can reach 16,000 in a certain duration.
  • If the disk capacity is 1,000 GiB, the disk IOPS limit is 33,000. In this case, the disk IOPS limit already exceeds its IOPS burst limit (16,000), and the disk does not need the burst capability.

The burst IOPS consumption and reservation principles are described as follows:

The burst capability is implemented based on a token bucket. The number of initial tokens in the bucket is calculated as follows:

Number of initial tokens = Burst duration x IOPS burst limit

In the following example, a 100-GiB ultra-high I/O EVS disk is used, and the fixed burst duration is 1800s. Therefore, the number of initial tokens is 28,800,000 (1,800 x 16,000).
  • Token production rate: This rate equals the disk IOPS limit, which is 6,500 tokens/s.
  • Token consumption rate: This rate is calculated based on the I/O usage. Each I/O request consumes a token. The maximum consumption rate is 16,000 tokens/s, which is the larger value between the disk burst IOPS and IOPS limit.

Consumption principles

When the token consumption rate is greater than the production rate, the number of tokens decreases accordingly, and eventually the disk IOPS will be consistent with the token production rate (the IOPS limit). In this example, the disk can burst for approximately 3,032 seconds [28,800,000/(16,000 - 6,500)].

Reservation principles

When the token consumption rate is smaller than the production rate, the number of tokens increases accordingly, enabling the disk to regain the burst capability. In this example, if the disk is suspended for approximately 4,431 seconds (28,800,000/6,500), the token bucket will be filled up with tokens.

As long as there are tokens in the token bucket, the disk will have the burst capability.

Figure 1 shows the token consumption and reservation principles. The blue bars indicate the disk IOPS usage, the green dashed line represents the IOPS limit, the red dashed line indicates the IOPS burst limit, and the black curve indicates the changes of the number of tokens.
  • When the number of tokens is greater than zero, the disk IOPS can exceed 6,500 and has the capability to reach 16,000, the IOPS burst limit.
  • When the number of tokens is zero, the disk does not have the burst capability, and the maximum IOPS is 6,500.
  • When the disk IOPS is less than 6,500, the number of tokens starts to increase, and the disk can regain the burst capability.
Figure 1 Burst capability diagram
Parent topic: Overview