No relevant resource is found in the selected language.

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies. Read our privacy policy>Search

Reminder

To have a better experience, please upgrade your IE browser.

upgrade

FusionCloud 6.3.1.1 Solution Description 04

Rate and give feedback:
Huawei uses machine translation combined with human proofreading to translate this document to different languages in order to help you better understand the content of this document. Note: Even the most advanced machine translation cannot match the quality of professional translators. Huawei shall not bear any responsibility for translation accuracy and it is recommended that you refer to the English document (a link for which has been provided).
Local Disk, EVS Disk and Local Pass-through Disk

Local Disk, EVS Disk and Local Pass-through Disk

Definition

  • A local disk refers to a disk residing on the local host of the ECS to provide non-persistent storage. This type of storage provides high I/O throughput and low latency but cannot be used for persistent data storage.

    An ECS loses its local disk data after it is rebuilt on another host. Local disks cannot be live migrated, but can be cold migrated. Cold migration does not cause data loss, but takes a long time because disk files need to be copied from the source to the destination node during the migration.

  • Elastic Volume Service (EVS) is a virtual block storage service that provisions block storage to Elastic Cloud Servers (ECSs) and Bare Metal Servers (BMSs) from storage backends. Users can create EVS disks online and attach them to ECSs. Users can use EVS disks the same way they use traditional hard disks on servers. EVS disks deliver higher data reliability and I/O throughput and are easy to use. They can be used for file systems, databases, or other system software and applications that require block storage resources. EVS disks provide persistent storage, meaning that the data stored on them does not get lost when ECS instances are started, stopped, or migrated.

    EVS disks are categorized as Virtual Block Device (VBD) or Small Computer System Interface (SCSI), depending on whether advanced SCSI commands are supported.

  • A local pass-through disk allows an ECS to have direct access to the disk space on its host. Local pass-through disks offer high read/write speeds and low latency and are suitable for scenarios that require high I/O performance and rapid data switching and processing to handle massive data sets.

    Currently, ECSs that use local pass-through disks are as follows:

    • Ultra-high I/O ECSs: They use high-performance local NVMe SSDs as data disks. They do not support flavor changes (online or offline), cold migration, live migration, HA, ECS snapshot, cloning, memory reuse, or user-defined CPU QoS settings.
    • Disk-intensive ECSs: They use pass-through HDDs as data disks. They do not support live migration, cold migration, HA, cloning, or ECS snapshot, but they support memory reuse and user-defined CPU QoS settings. A disk-intensive ECS cannot be changed into another type of ECS by changing its flavor.

The total number of system and data disks cannot exceed 60. Table 18-1 lists the categories of local disks, EVS disks and local pass-through disks and the quantity of disks that can be attached.

Table 18-1 Disk type description

Category

Disk Type

Purpose

Description

Local disk

HDD

Used as the system disk and data disk (Region Type II and III).

When used as data disks, only one local HDD can be attached to an ECS.

The performance of local disks varies with the load on the physical host and single points of failure (SPOFs) may exist. Local disks are suitable for systems that run only for a short period of time and have relatively low stability and reliability standards.

You are advised to configure data redundancy at the application layer and synchronize or back up important data from local disks to other ECSs or EVS disks in a timely manner, ensuring data availability.

EVS disk

SCSI disk

Used only as data disks.

A maximum of 59 such disks can be attached.

EVS disks of this type support transparent SCSI command transmission and allow the ECS OS to directly access the underlying storage media. SCSI EVS disks support advanced SCSI commands (such as SCSI-3 persistent pre-lock) in addition to basic SCSI read and write commands. They can be used in cluster scenarios where data security is enhanced by using the SCSI lock mechanism, such as the Windows MSCS cluster.

VBD disk

Used as both the system disk and data disks.

The number of disks that can be attached to an ECS depends on Disk Device Type set for the ECS image when the image was registered on Service OM. For details, see Table 18-2.

EVS disks of this type support only basic SCSI read/write commands. They are mostly used in common scenarios like OA and testing, or common Linux clusters such as RHCS.

Local pass-through disk

NVMe SSD

Used only as data disks.

A maximum of eight NVMe SSDs can be used to create an ultra-high I/O ECS.

Ultra-high I/O ECSs use high-performance local NVMe SSDs as data disks to provide high storage IOPS and low read/write latency. Disks of this type can be used for high-performance relational databases, NoSQL databases (such as Cassandra and MongoDB), and ElasticSearch.

Pass-through HDD

Used only as data disks.

A maximum of 59 pass-through HDDs can be used to create a disk-intensive ECS.

Disk-intensive ECSs use pass-through HDDs as data disks to provide a higher sequential reading performance and a lower latency, improving file read and write performance. Disks of this type are suitable for scenarios that require high I/O performance and rapid data switching and processing to handle massive data sets. The scenarios include MapReduce computing, Hadoop distributed computing, large data warehouse, distributed file system, data processing, and log processing.

NOTE:
  • If you create an ECS earlier than FusionSphere Service 6.3.1, a maximum of 12 disks can be attached to your ECS.
  • If the number of disks that can be attached to an ECS is less than the number that you specify, some drive letters have been pre-occupied by the system.
Table 18-2 Relationship between the total number of attached VBD disks and the disk device type

Disk Device Type

Total VBD Disks

ide

4

virtio

24

NOTE:

If Boot Mode for the image is set to UEFI during ECS creation:

  • During online disk attachment, the mount point must be between vda and vdp. A maximum of 16 disks (including system disks) can be attached.
  • If the mount point exceeds vdp, for example, vdq, you must shut down the ECS, attach the target disk, and then start the ECS. Such a process is an offline disk attachment process.

scsi

60

Translation
Download
Updated: 2019-10-23

Document ID: EDOC1100063247

Views: 73723

Downloads: 192

Average rating:
This Document Applies to these Products
Related Version
Related Documents
Share
Previous Next