1. Chapter 3 Presented by: Anupam Mittal

2.  Data protection: Concept of RAID and its Components Data Protection: RAID - 2

3. After completing this chapter, you will be able to:  Describe what is RAID and the needs it addresses  Describe the concepts upon which RAID is built  Define and compare RAID levels  Recommend the use of the common RAID levels based on performance and availability considerations  Explain factors impacting disk drive performance Data Protection: RAID - 3

4.  Performance limitation of a single drive disk drive ◦ Limited Capacity ◦ Limited access speed  An individual drive has a certain life expectancy ◦ Measured in MTBF ◦ Example - If the MTBF of a drive is 750,000 hours, and there are 100 drives in the array, then the MTBF of the array becomes 750,000 / 100, or 7,500 hours  RAID was introduced to mitigate this problem  RAID provides: ◦ Increase capacity ◦ Higher availability ◦ Increased performance Data Protection: RAID - 4

5. RAID Arrays - 5 RAID Controller RAID Array Host

6. Data Protection: RAID - 6 RAID Controller Hard Disks Logical Array Physical Array RAID Array Host

7.  Hardware (usually a specialized disk controller card) ◦ Controls all drives attached to it ◦ Array(s) appear to host operating system as a regular disk drive ◦ Provided with administrative software  Software ◦ Runs as part of the operating system ◦ Performance is dependent on CPU workload ◦ Does not support all RAID levels Data Protection: RAID - 7

8.  0 Striped array with no fault tolerance  1 Disk mirroring  3 Parallel access array with dedicated parity disk  4 Striped array with independent disks and a dedicated parity disk  5 Striped array with independent disks and distributed parity  6 Striped array with independent disks and dual distributed parity  Nested RAID (i.e., 1 + 0, 0 + 1, etc.) Data Protection: RAID - 8

9. © 2008 EMC Corporation. All rights reserved. RAID Arrays - 9 RAID Redundancy: Parity Parity Disk 0 8 4 1 9 5 2 10 6 3 11 7 0 1 2 3 8 9 10 11 4 5 6 7 RAID Controller Host

10. © 2008 EMC Corporation. All rights reserved. RAID Arrays - 10 Parity Calculation Parity Data 4 2 3 5 14 5 + 3 + 4 + 2 = 14 The middle drive fails: 5 + 3 + ? + 2 = 14 ? = 14 – 5 – 3 – 2 ? = 4 RAID Array

11. © 2008 EMC Corporation. All rights reserved. Lecture 8, 9, 10  Different RAID levels and their suitability for different application environments: RAID 0, RAID 1 RAID Arrays - 11

12. Data Protection: RAID - 12 Stripe 1 Stripe 2 Strips Strip 1Strip 2Strip 3 Stripe Strips Stripes Strip 3 Strip 2 Strip 1 Stripe 1

13. Data Protection: RAID - 13 1 9 5 2 10 6 3 11 7 0 Host RAID Controller

14. Data Protection: RAID - 14 Block 1 Block 0 Host Block 0 RAID Controller

15. Data Protection: RAID - 15 Block 3 Block 2 Block 1 Host RAID 0 Block 0 Block 3 Block 2 Block 1 Block 0 RAID 1 RAID Controller

16. Data Protection: RAID - 16 RAID Controller Block 3 Block 2 Block 1 RAID 0 Block 0 RAID 1 Block 3 Block 2 Block 1 Block 0 Block 3 Block 2 Block 1 Block 0 Host

17. Data Protection: RAID - 17 Host Block 3 Block 1 RAID 1 Block 0 Block 1 RAID 0 Block 2 RAID Controller

18. Data Protection: RAID - 18 Host RAID Controller RAID 1 Block 0 RAID 0 Block 2 Block 3 Block 1 Block 0 Block 2

19.  Benefits are identical under normal operations  Rebuild operations are very different ◦ RAID 1+0 uses a mirrored pair – only 1 disk is rebuilt if a disk fails ◦ RAID 0+1 if a single drive fails, the entire stripe is faulted  RAID is 0+1 is a poorer solution and is less common RAID Arrays - 19

20. RAID Arrays - 20 Parity Disk 0 8 4 1 9 5 2 10 6 3 11 7 0 1 2 3 8 9 10 11 4 5 6 7 RAID Controller Host

21. Data Protection: RAID - 21 Parity Disk 1 9 5 3 11 7 0 0 1 2 3 4 5 6 7 4 6 1 7 18 Host RAID Controller Parity calculation 4 + 6 + 1 + 7 = 18 The middle drive fails: 4 + 6 + ? + 7 = 18 ? = 18 – 4 – 6 – 7 ? = 1 ?

22. Data Protection: RAID - 22 Host RAID Controller Block 1 Block 2 Block 3 P 0 1 2 3 Block 0 Block 3 Block 2 Block 1 Block 0 Parity Generated

23. © 2008 EMC Corporation. All rights reserved. RAID Arrays - 23 RAID 4 – Striping with Dedicated Parity Disk RAID Controller P 0 1 2 3Block 0 Block 4 Block 1 Block 5 Block 2 Block 6 Block 3 Block 7 P 0 1 2 3 P 4 5 6 7 Parity Generated Block 0 P 0 1 2 3 Host

24. Data Protection: RAID - 24 Host Block 0 P 0 1 2 3 Block 7 RAID Controller P 0 1 2 3Block 0Block 4Block 0 Block 1 Block 5 Block 2 Block 6 Block 3 Parity Generated Block 0 P 0 1 2 3 Block 4 P 4 5 6 7 Block 4 P 4 5 6 7Block 4 Parity Generated

25.  Two disk failures in a RAID set leads to data unavailability and data loss in single-parity schemes, such as RAID-3, 4, and 5  Increasing number of drives in an array and increasing drive capacity leads to a higher probability of two disks failing in a RAID set  RAID-6 protects against two disk failures by maintaining two parities ◦ Horizontal parity which is the same as RAID-5 parity ◦ Diagonal parity is calculated by taking diagonal sets of data blocks from the RAID set members  Even-Odd, and Reed-Solomon are two commonly used algorithms for calculating parity in RAID-6 Data Protection: RAID - 25

26.  Hardware (usually a specialized disk controller card) ◦ Controls all drives attached to it ◦ Performs all RAID-related functions, including volume management ◦ Array(s) appear to the host operating system as a regular disk drive ◦ Dedicated cache to improve performance ◦ Generally provides some type of administrative software  Software ◦ Generally runs as part of the operating system ◦ Volume management performed by the server ◦ Provides more flexibility for hardware, which can reduce the cost ◦ Performance is dependent on CPU load ◦ Has limited functionality RAID Arrays - 26

27.  Comparison of RAID Levels Data Protection: RAID - 27

28. RAID Min Disks Storage Efficiency % CostRead PerformanceWrite Performance 02100Low Very good for both random and sequential read Very good 1250High Good Better than a single disk Good Slower than a single disk, as every write must be committed to two disks 33 (n-1)*100/n where n= number of disks Moderate Good for random reads and very good for sequential reads Poor to fair for small random writes Good for large, sequential writes 53 (n-1)*100/n where n= number of disks Moderate Very good for random reads Good for sequential reads Fair for random write Slower due to parity overhead Fair to good for sequential writes 64 (n-2)*100/n where n= number of disks Moderate but more than RAID 5 Very good for random reads Good for sequential reads Good for small, random writes (has write penalty) 1+0 and 0+1 450HighVery goodGood Data Protection: RAID - 28 RAID Comparison

29.  Small (less than element size) write on RAID 3 & 5  Ep = E1 + E2 + E3 + E4 (XOR operations)  If parity is valid, then: Ep new = Ep old – E4 old + E4 new (XOR operations) ◦ 2 disk reads and 2 disk writes  Parity Vs Mirroring ◦ Reading, calculating and writing parity segment introduces penalty to every write operation ◦ Parity RAID penalty manifests due to slower cache flushes ◦ Increased load in writes can cause contention and can cause slower read response times Data Protection: RAID - 29 E p new RAID Controller 2 XOR E p new E p old E 4 old E 4 new +-= E 4 old E p old E 4 new P0D1D2D3D4

30.  Total IOPS at peak workload is 1200  Read/Write ratio 2:1  Calculate IOPS requirement at peak activity for ◦ RAID 1/0 ◦ RAID 5 Data Protection: RAID - 30

31. Data Protection: RAID - 31 RAID Controller

32. Key points covered in this chapter:  What RAID is and the needs it addresses  The concepts upon which RAID is built  Some commonly implemented RAID levels Data Protection: RAID - 32

33.  What is a RAID array?  What benefits do RAID arrays provide?  What methods can be used to provide higher data availability in a RAID array?  What is the primary difference between RAID 3 and RAID 5?  What is advantage of using RAID 6?  What is a hot spare? Data Protection: RAID - 33