Understanding Hard Drive Types, RAID and RAID Controllers on Dell PowerEdge and Blade Chassis Servers

Table of Contents:

1. Types of Hard Drive
2. What is a RAID?
3. RAID Solutions Available
4. Understanding Configuration
   
    

Types of Hard Drives

Dell PERC (PowerEdge RAID Controller) and other controllers can support a variety of hard drive types. There are four main types used in Dell 9th generation servers and up. There are specific configuration limitations, and the specifics should be checked for the type of controller used. In addition, the types cannot be mixed in the same RAID set. There is also transfer differences referred to as SATA 1, 2, or 3. They may also be seen as 3Gb/s or 6Gb/s. To get the maximum speed the hard drive, backplane, cables, and controller all have to support the set rate. In most cases, the higher specification is backwards compatible to the lowest common speed. Example - plugging a 6Gb/s hard drive into a 3Gb/s backplane will result in the speed being 3Gb/s.

 

1. Serial ATA (SATA): SATA drives are base hard drives in Dell PowerEdge servers. Serial ATA was designed to replace the older parallel ATA (PATA) standard (often called by the old name IDE), offering several advantages over the older interface: reduced cable size and cost (7 conductors instead of 40), native hot swapping, faster data transfer through higher signaling rates, and more efficient transfer through a I/O queuing protocol. On some systems without a controller, these can be cabled instead to the onboard SATA connections on the motherboard. On smaller servers with a controller, they can still be cabled because these systems will not have a backplane. Cabled hard drives are not hot swappable.
   
    
2. Near Line SAS: Near Line SAS are enterprise SATA drives with a SAS interface, head, media, and rotational speed of traditional enterprise-class SATA drives with the fully capable SAS interface typical for classic SAS drives. This provides better performance and reliability over SATA. Basically it is a hybrid between SATA and SAS.
   
    
3. Serial Attached SCSI (SAS): SAS is a communication protocol used in Enterprise hard drives and tape drives. SAS is a point-to-point serial protocol that replaces the older based parallel SCSI bus technology (SCSI). It uses the standard SCSI command set. These have extra connections through the top of the SATA connection. These are the top end in performance for electromechanical drives.
   
    
4. Solid-State Drive (SSD): An SSD is a data storage device that uses integrated circuit assemblies as memory to store data persistently. SSD technology uses electronic interfaces compatible with traditional block input/output (I/O) hard disk drives. SSDs do not employ any moving mechanical components, which distinguishes them from traditional magnetic disks such as hard disk drives, which are electromechanical devices containing spinning disks and movable read/write heads. Compared with electromechanical disks, SSDs are typically less susceptible to physical shock, are silent, and have lower access time and latency. Typically because of these features, SSD drives can be the fastest I/O in the market today in standard hard drive form factor.
   
    

Back to Top

---

What is a RAID?

A RAID is a group of independent physical disks that provides high performance by increasing the number of drives used for saving and accessing data. A RAID disk subsystem improves I/O performance and data availability. The physical disk group appears to the host system either as a single storage unit or multiple logical units. Data throughput improves because several disks are accessed simultaneously. RAID systems also improve data storage availability and fault tolerance. Data loss caused by a physical disk failure can be recovered by rebuilding missing data from the remaining physical disks containing data or parity. RAID is not a backup solution. It does not replace a good data backup solution for data retention and security.
 

The different RAID levels:

• RAID 0 uses disk striping to provide high data throughput, especially for large files in an environment that requires no data redundancy.
• RAID 1 uses disk mirroring so that data written to one physical disk is simultaneously written to another physical disk. RAID 1 is good for small databases or other applications that require small capacity, but also require complete data redundancy.
• RAID 5 uses disk striping and parity data across all physical disks (distributed parity) to provide high data throughput and data redundancy, especially for small random access.
• RAID 6 is an extension of RAID 5 and uses an additional parity block. RAID 6 uses block-level striping with two parity blocks distributed across all member disks. RAID 6 provides protection against double disk failures, and failures while a single disk is rebuilding. If you are using only one array, deploying RAID 6 is more effective than deploying a hot spare disk.
• RAID 10, a combination of RAID 0 and RAID 1, uses disk striping across mirrored disks. It provides high data throughput and complete data redundancy. RAID 10 can support up to eight spans, and up to 32 physical disks per span.
• RAID 50 is a combination of RAID 0 and RAID 5 where a RAID 0 array is striped across RAID 5 elements. RAID 50 requires at least six disks.
• RAID 60 is a combination of RAID 0 and RAID 6 where a RAID 0 array is striped across RAID 6 elements. RAID 60 requires at least eight disks.

RAID Terminology
 

• RAID 0:  RAID 0 allows you to write data across multiple physical disks instead of just one physical disk. RAID 0 involves partitioning each physical disk storage space into 64 KB stripes. These stripes are interleaved in a repeated sequential manner. The part of the stripe on a single physical disk is called a stripe element. For example, in a four-disk system using only RAID 0, segment 1 is written to disk 1, segment 2 is written to disk 2, and so on. RAID 0 enhances performance because multiple physical disks are accessed simultaneously, but it does not provide data redundancy (Figure 1 (English only)). 

  
Figure 1: RAID 0

Fault Tolerance – None
Advantage – Improved performance, Additional storage
Disadvantage – Should not be used for critical data Data Loss will occur with any drive failure.


 

RAID 1

With RAID 1, data written to one disk is simultaneously written to another disk. If one disk fails, the contents of the other disk can be used to run the system and rebuild the failed physical disk. The primary advantage of RAID 1 is that it provides 100 percent data redundancy. Because the contents of the disk are completely written to a second disk, the system can sustain the failure of one disk. Both disks contain the same data at all times. Either physical disk can act as the operational physical disk (Figure 2 (English only)).

Note: Mirrored physical disks improve read performance by read load balance.

 
Figure 2: RAID 1

Fault Tolerance – Disk errors, Single disk failure
Advantage – High read performance, Fast recovery after drive failure, Data redundancy
Disadvantage – High disk overhead, Limited capacity

 

RAID 5 and 6

Parity Data Parity data is redundant data that is generated to provide fault tolerance within certain RAID levels. In the event of a drive failure the parity data can be used by the controller to regenerate user data. Parity data is present for RAID 5, 6, 50, and 60. The parity data is distributed across all the physical disks in the system. If a single physical disk fails, it can be rebuilt from the parity and the data on the remaining physical disks. RAID level 5 combines distributed parity with disk striping, as shown below (Figure 3 (English only)). Parity provides redundancy for one physical disk failure without duplicating the contents of entire physical disks.  RAID 6 combines dual distributed parity with disk striping (Figure 4 (English only)). This level of parity allows for two disk failures without duplicating the contents of entire physical disks.
 
RAID 5
 
Figure 3: RAID 5

Fault Tolerance – Disk errors, Single disk failures
Advantage – Efficient use of drive capacity, High read performance, Med-to-High write performance
Disadvantage – Disk failure medium impact, Longer re-build due to parity re-calculation


 
RAID 6
 
Figure 4: RAID 6

Fault Tolerance – Disk errors, Dual disk failures
Advantage – Data redundancy, High read performance
Disadvantage – Write performance decrease due to dual parity calculations, Extra cost due to 2 disk equivalent devoted to parity




 
RAID 10:  RAID 10 requires two or more mirrored sets working together. Multiple RAID 1 sets are combined to form a single array. Data is striped across all mirrored drives. Since each drive is mirrored in RAID 10, no delay is encountered because no parity calculation is done. This RAID strategy can tolerate the loss of multiple drives as long as two drives of the same mirrored pair do not fail. RAID 10 volumes provide high data throughput and complete data redundancy (Figure 5 (English only)).

 
Figure 5: RAID 10

Fault Tolerance – Disk errors, One disk failure per mirrored set
Advantage – High read performance, Supports largest RAID group of 192 drives
Disadvantage – Most expensive


Back to Top

---

RAID Solutions Available per Controller Card

The RAID levels supported by each PERC (PowerEdge Raid Controller Card) is listed in KB article: List of PowerEdge RAID Controller (PERC) types for Dell EMC systems
 

Understanding Configuration

At time of system purchase, most systems come pre-configured with the RAID type you selected and are functional out of box. Typically in this situation no customer action is required since it is configured and working. If after receiving the unit a change is required, the RAID level may be able to be changed through software or controller interface without data loss depending on the controller itself, the original RAID type, and the type you are looking to go to. Not all migrations are supported. If the migration is not possible it will require a complete wipe out of the hard drives and re-creation from scratch.

Warning – It is strongly recommended that to create a verified backup of your data before making or attempting any changes. Any failure could result in data loss. RAID Level Migration (Example for the H700/H800 controller).
      
 

  -

-