problem description : customer want to get the information about Hot Spare policy in RAID 2.0 configuration.
Right now SSD Hot Spare Capacity = 6.316 TB, but capacity of entire ssd disk is 6.651 TB
Main question why HS capacity less then entire ssd (where is 300 GB)
problem analysis :
The capacity of a storage system is used to store service data and system data. To ensure that the capacity for service data is sufficient, plan the capacity for system data properly.
For details about the available capacity plan and purchased capacity, contact your local Huawei representative office or Huawei authorized distributor.
The capacity for storing system data refers to the file system capacity, hot spare capacity, and coffer disk capacity. The space overhead consumed by the storage system makes the actual available capacity smaller than the capacity provided by the storage system.
The space overhead consumed by the storage system comprises several parts:
· Capacity used by parity data or mirrored data in a RAID group
Table 1 lists the disk utilization of different RAID levels.
Table 1 Disk utilization of different RAID levels
· 2Da: The disk utilization is about 50%.
· 4D: The disk utilization is about 25%.
RAID 3 supports flexible configurations. Specifically, a RAID 3 policy allows data block and parity block policies ranging from 2D+1P to 13D+1P. The following examples show disk utilization rates of several configurations commonly used by RAID 3:
· 4D + 1Pb: The disk utilization is about 80%.
· 2D + 1P: The disk utilization is about 66.67%.
· 8D + 1P: The disk utilization is about 88.89%.
For a flexibly configured RAID policy xD+yP, the disk utilization is [x/(x + y)] × 100%.
RAID 5 supports flexible configurations. Specifically, a RAID 5 policy allows data block and parity block policies ranging from 2D+1P to 13D+1P. The following examples show disk utilization rates of several configurations commonly used by RAID 5:
· 2D + 1P: The disk utilization is about 66.67%.
· 4D + 1P: The disk utilization is about 80%.
· 8D + 1P: The disk utilization is about 88.89%.
For a flexibly configured RAID policy xD+yP, the disk utilization is [x/(x + y)] × 100%.
RAID 6 supports flexible configurations. Specifically, a RAID 6 policy allows data block and parity block policies ranging from 2D+2P to 26D+2P. The following examples show disk utilization rates of several configurations commonly used by RAID 6:
· 2D + 2P: The disk utilization is about 50%.
· 4D + 2P: The disk utilization is about 66.67%.
· 8D + 2P: The disk utilization is about 80%.
· 16D + 2P: The disk utilization is about 88.89%.
For a flexibly configured RAID policy xD+yP, the disk utilization is [x/(x + y)] × 100%.
· (2D + 1P) x 2: The disk utilization is about 66.67%.
· (4D + 1P) x 2: The disk utilization is about 80%.
· (8D + 1P) x 2: The disk utilization is about 88.89%.
a: D indicates the data block.
b: P indicates the parity block.
· Capacity used by hot spare space
To prevent data loss or performance deterioration caused by a member disk failure, the storage system employs hot spare space to take over data from the failed member disk. The supported hot spare policies are as follows:
· High
The capacity of one disk is used as hot spare space if the number of disks at a storage tier equals to or fewer than 12. The hot spare space non-linearly increases as the number of disks increases. When the number of disks at a storage tier reaches 175, the storage tier uses the capacity of one disk in every 100 disks as the hot spare space.
· Low
The capacity of one disk is used as hot spare space if the number of disks at a storage tier equals to or fewer than 25. The hot spare space non-linearly increases as the number of disks increases. When the number of disks at a storage tier reaches 175, the storage tier uses the capacity of one disk in every 200 disks as the hot spare space.
· None (not supported by 18000, 18000F series storage systems)
The system does not provide hot spare space.
Table 2 describes how hot spare space changes with the number of disks. The hot spare space changes at a storage tier are used as an example here. The hot spare space changes at different types of storage tiers are the same.
Table 2 Changes of hot spare space
Number of Disks of Which Capacity Is Used as Hot Spare Space in High Hot Spare Policya
Number of Disks of Which Capacity Is Used as Hot Spare Space in Low Hot Spare Policya
a: Huawei storage systems use RAID 2.0+ virtualization technology. Hot spare capacity is provided by member disks in each disk domain. Therefore, the hot spare capacity is expressed in number of disks in this table.
For example, if a disk domain is composed of 12 SSDs and the high hot spare policy is used, the hot spare space occupies the capacity of one SSD and the capacity is provided by member disks in the disk domain. If a disk domain is composed of 13 SSDs and the high hot spare policy is used, the hot spare space occupies the capacity of two SSDs.
· For 18000 and 18000F series storage systems, the high hot spare policy is used by default. You can only run the change disk_domain general command on the CLI to modify the hot spare policy.
· When you are creating a disk domain, ensure that the disks used to provide hot spare space are sufficient.
· Hot spare space can be used for the current disk domain only.
· Table 2 lists common capacity changes of the hot spare space. The number of disks supported by a storage system and the capacity of their hot spare space are based on actual specifications.
· Capacity used by coffer disks
Part of the coffer disk space can be used to store critical system data, including user configuration data and system logs. The rest of the coffer disk space can be used to store service data. For details about capacity used by coffer disks, see the "Coffer Disk" of the corresponding model and version in the Product Description.
· Capacity used by file systems and volume management software on the application server
File systems and volume management software of multiple types on the application server may occupy a portion of space in the storage system. The actually occupied capacities depend on the deployment of applications on the application server.
· WriteHole capacity
WriteHole is used to resolve inconsistent data stripe verification caused by certain operations before I/Os are delivered to disks. Each disk reserves a 256 MB space as WriteHole capacity.
· Capacity used by system information.
The system information occupies 577 MB per disk.
· Metadata capacity
Each disk reserves 0.6% of its total capacity as metadata capacity, and reserves 2% as metadata backup capacity.
· Reserved space for improving system performance and disk balance
Each disk reserves 1% of its total capacity to improve system performance and disk balance. When 1% of the disk total capacity is smaller than 2 GB, 2 GB of space is reserved.
· Integrated capacity
When disks are being formatted, if the size of a sector is 520 bytes, the sector uses 8 bytes to store parity data. If the size of a sector is 4160 bytes, the sector uses 64 bytes to store parity data. The integrated capacity usage is about 98.46% (512/520 or 4096/4160).
Without considering the hot spare capacity consumption, you can use the following formula to calculate RAID 2.0+ disk capacity usage: RAID 2.0+ disk capacity usage = [1 – Metadata space – (1 – Metadata space) × Metadata backup space] × (1 – Disk space reserved for load balancing) x Integrated capacity usage = [1 – 0.6% – (1 – 0.6%) × 2%] × (1 – 1%) × 98.46% ≈ 94.95%
The disk capacity defined by disk manufacturers is different from that calculated by operating systems. As a result, the nominal capacity of a disk is different from that displayed in the operating system.
· Disk capacity defined by disk manufacturers: 1 GB = 1,000 MB, 1 MB = 1,000 KB, 1 KB = 1,000 bytes.
· Disk capacity calculated by operating systems: 1 GB = 1,024 MB, 1 MB = 1,024 KB, 1 KB = 1,024 bytes.
The preceding formulas are for reference only. The disk capacity displayed on the DeviceManager prevails.
