Disk Scheduling

1
Disk Scheduling

• CS3450
• Chapter 11.5 - 11.6

2
Memory Hierarchy
3
Magnetic disk
Track
Sector
Read write head
Spindle
4
Disk Performance Parameters

• Access time
• sum of seek time and rotational delay
• the time it takes to get in position to read or
  write
• Data transfer occurs as the sector moves under
  the head
• Data transfer for an entire file is faster when
  the file is stored in the same cylinder and in
  adjacent sectors

5
Disk Scheduling Policies

• Seek time is the reason for differences in
  performance
• For a single disk there will be a number of I/O
  requests
• If requests are selected randomly, we will get
  the worst possible performance

6
Disk Scheduling Policies

• First-in, first-out (FIFO)
• process request sequentially
• fair to all processes
• approaches random scheduling in performance if
  there are many processes

7
FCFS
Illustration shows total head movement of 640
cylinders.
8
Disk Scheduling Policies

• Priority
• goal is not to optimize disk use but to meet
  other objectives
• short batch jobs may have higher priority
• provide good interactive response time

9
Disk Scheduling Policies

• Last-in, first-out
• good for transaction processing systems
• the device is given to the most recent user so
  there should be little arm movement
• possibility of starvation since a job may never
  regain the head of the line

10
Disk Scheduling Policies

• Shortest Service Time First
• select the disk I/O request that requires the
  least movement of the disk arm from its current
  position
• always choose the minimum Seek time

11
SSTF (Cont.)
12
Disk Scheduling Policies

• SCAN
• arm moves in one direction only, satisfying all
  outstanding requests until it reaches the last
  track in that direction
• direction is reversed

13
SCAN (Cont.)
14
Disk Scheduling Policies

• C-SCAN
• restricts scanning to one direction only
• when the last track has been visited in one
  direction, the arm is returned to the opposite
  end of the disk and the scan begins again

15
C-SCAN (Cont.)
16
Disk Scheduling Policies

• N-step-SCAN
• segments the disk request queue into subqueues of
  length N
• subqueues are process one at a time, using SCAN
• new requests added to other queue when queue is
  processed
• FSCAN
• two queues
• one queue is empty for new request

17
Stable-Storage Implementation

• Write-ahead log scheme requires stable storage.
• To implement stable storage
• Replicate information on more than one
  nonvolatile storage media with independent
  failure modes.
• Update information in a controlled manner to
  ensure that we can recover the stable data after
  any failure during data transfer or recovery.

18
RAIDRedundant Array of Independent Disks

• Set of physical disk drives viewed by the os as a
  single logical drive
• Data are distributed across the physical drives
  of an array
• Redundant disk capacity is used to store parity
  information, which guarantees data recoverability
  in case of a disk failure.

19
RAID 0 (non-redundant)
strip 0
strip 1
strip 2
strip 3
strip 4
strip 5
strip 6
strip 7
strip 9
strip 10
strip 11
strip 8
strip 13
strip 15
strip 12
strip 14
20
Raid 0

• Characteristics/Advantages
• Implements a striped disk array, the data is
  broken down into blocks and each block written to
  a separate disk drive
• High Transaction and transfer rate
• No parity calculation overhead
• simple design/ easy to implement

• Disadvantages
• Not a True RAID not fault tolerant
• failure of one drive will result in all data in
  an array being lost
• should not be used for critical environments

Recommended uses Non-critical applications
requiring high bandwidth Image Editing,
Pre-press Applications
21
Data Mapping for RAID Level 0 Array
Physical Disk 0
Physical Disk 1
Physical Disk 2
Physical Disk 3
strip 0
strip 1
strip 2
strip 3
strip 4
strip 5
strip 6
strip 7
strip 8
strip 9
strip 10
strip11
strip 12
strip 13
strip 14
strip 15
22
RAID 1 (mirrored)
23
Raid 1Mirroring and Duplexing

• Characteristics/Advantages
• Each strip is mapped to two separate drives
  (mirrored)
• Read request serviced by disk with minimum seek
  time
• Write request can be done to both disk in
  parallel. No Parity computation penalty
• 100 redundancy of data
• Medium Transaction and transfer rate
• Simplest true RAID design

• Disadvantages
• COST (twice the disk space)
• High I/0 Rate if mostly read request. No
  improvement for write request.
• Software implementation can load the CPU/Server
  degrading throughput at high activity levels
  hardware implementation preferred

Recommended uses Accounting, Payroll, Any
application requiring very high availability
24
RAID 2 (redundancy through Hamming code)
f2(b)
f1(b)
f0(b)
b2
b1
b0
b2
25
Raid 2

• Disadvantages
• Very High ratio of ECC disk to data disk
• low transaction rate
• Only effective choice in an environment of high
  disk errors. Considered overkill and not
  implemented

• Characteristics/Advantages
• All member disks participate in every I/0
  request. Strips are very small (work or byte)
• Hamming code used to store bits across all disk
• High Transfer rate

Recommended uses Not Implemented
26
RAID 3 (bit-interleaved parity)
P(b)
b2
b1
b0
b2
27
Raid 3

• Disadvantages
• Only one I/0 request can be executed at a time.
• Low Transaction rates

• Characteristics/Advantages
• All member disks participate in every I/0
  request. Strips are very small (work or byte)
• Simple parity used to store bits across all disk
  (requires only a single redundant disk.)
• High Data transfer rates. Parallel transfer of
  data from all data disk. Good for moving very
  large sequential files in a timely manner

Recommended uses Video production, Image/video
Editing. Any application requiring very high
throughput
28
RAID 4 (block-level parity)
block 0
block 1
block 2
block 3
P(0-3)
block 4
block 5
block 6
block 7
P(4-7)
block 9
block 10
block 11
block 8
P(8-11)
block 13
block 15
block 12
block 14
P(12-15)
29
Raid 4

• Disadvantages
• Parity disk becomes a bottleneck for write
  operations
• Medium/low Data transfer Rate

• Characteristics/Advantages
• Each member disk operates independently. So
  separate I/0 request can be done in parallel.
• Strips are large
• Each entire block is written on a data disk.
  Parity for same
• High transaction rate

Recommended uses Not Implemented
30
RAID 5 (block-level distributed parity)
block 0
block 1
block 2
block 3
P(0-3)
block 5
block 4
block 6
P(4-7)
block 7
block 9
block 10
block 11
P(8-11)
block 8
block 12
P(12-15)
block 13
block 14
block 15
P(16-19)
block 16
block 17
block 18
block 19
31
Raid 5

• Characteristics/Advantages
• Each member disk operates independently. So
  separate I/0 request can be done in parallel.
• Organized as RAID 4 only RAID 5 distributes
  parity strips across all disk
• Avoids the bottleneck of RAID 4
• High Transaction rate

• Disadvantages
• Disk failure time consuming/difficult compared to
  RAID level1
• medium/low Transfer Rates

Recommended uses High request rate,
read-intensive, data lookupInternet servers,
Database servers WWW, file , application servers
32
RAID LEVELS