IO System

1
Chapter 8

• 11/12/08

2
IO System

• Storage
• Must be dependable
• Networks
• Must tolerate faults in communications by
  including mechanisms to detect and recover form
  faults.
• Peripherals
• Extremely Diverse

3
I/O Systems

• Emphasis is placed on dependability and cost.
• Processors and memory emphasize performance and
  cost.
• I/O System performance must keep pace with
  processor performance.
• I/O can become a bottleneck.

4
(No Transcript)
5
I/O performance

• Complex
• Access Latency
• Throughput
• Depends on many aspects of the system.
• Device characteristics
• Connection between device and rest of system
• Memory hierarchy
• Operating system
• Etc.
• I/O benchmarks are primitive compared to
  processor benchmarks.

6
(No Transcript)
7
(No Transcript)
8
Transferring data between a device and memory

• Polling
• I/O interrupts
• DMA
• Special DMA controller handles transfers
• Processor sets up DMA
• DMA controller starts operation, arbitrates the
  bus, and interrupts processor when DMA is
  complete.

9
Disk Storage

• Nonvolatile Data is not lost when power turned
  off.
• Consists of platters (1-4) each with two
  recordable disk surfaces, and R/W heads.
• Platters are rotated at 5400-15,000 RPM.
• Each dist is divided into tracks.
• Tracks are divided into sectors.

10
(No Transcript)
11
Answer Second. Track Seek time.
12
(No Transcript)
13
Disk manufactures report minimum, maximum and
average seek time. The first two are easy to
measure. Average is open to wide interpretation
because it depends on seek distance. The standard
is Sum of the time for all possible seeks
divided by number of possible seeks. Actual
average may be considerably less.
14
(No Transcript)
15
Transfer time time to transfer a block of bits.
Function of sector size, rotation speed and
recording density. 30 80 MB/sec
typical. However, most disk controllers have a
built-in cache that stores sectors as they are
passed over. Resulting in higher transfer
rates. Today most disk transfers are multiple
sectors lengths. Controller time Overhead
imposed by controller in performing disk
I/O. Disk I/O time consists of the above times
plus any wait time because other processes are
using the disk.
16
(No Transcript)
17
(No Transcript)
18
(No Transcript)
19
Replace large disk with many small disks.
20
(No Transcript)
21
RAID

• RAID 0 Spread data over multiple drives.
• Called striping improves performance but no
  redundancy.
• RAID 1 Mirrors or shadows data to redundant
  drive.
• RAID 2-6 Incorporates error correction
  techniques.

22
Error detection and correction.

• Single error correction. HD 3.
• P1 D3 ? D5 ? D7
• 2 3 4 5 6 7 P2 D3 ? D6 ? D7
• P1 P2 D3 P4 D5 D6 D7 P4 D5 ? D6 ? D7
• 0 0 0 1 1 1 1 C4 P4 ? D5 ?
  D6 ? D7
• 0 1 1 0 0 1 1 C2 P2 ? D3 ?
  D6 ? D7
• 1 0 1 0 1 0 1 C1 P1 ? D3 ?
  D5 ? D7

23
RAID 6

• Allows for the simultaneous loss of two drives.
• Much better data protection than RAID 5.
• Implementation is based on Galois Field (GF)
  mathematics.
• Object is to achieve Maximum Distance Separable
  (MDS) coding.
• There are two implementations
• Reed-Solomon PQ
• Double Parity

24
(No Transcript)
25
GF - mathematics

• A GF is a set of values that contains a finite
  number of elements.
• For example GF(28) contains 28-1 elements.
• GF is closed under addition, subtraction,
  multiplication, and division operations.
• These operations are defined differently than the
  corresponding operations normal arithmetic.
• Addition is bitwise XOR.
• Subtraction same as addition.
• Multiplication and division are more complicated,
  and are typically accomplished by adding or
  subtracting gflogs.

26
P and Q Parity blocks
27
Problem 8.1
System A 1500 I/O operations per second. System
B 1000 I/O operations per second. Both systems
use a 500 MIPS processor. Each transaction
requires 5 I/O operations and each I/O operation
requires 10,000 instructions. Ignoring response
time and assuming the transactions may be
arbitrarily overlapped, what is the maximum
transaction-per-second rate that each machine can
sustain? Each transaction requires 5 X 10,000
50K inst. CPU limit 500M/50K 10,000
trans/sec I/0 limit for A is 1500/5 300
trans/sec I/O limit for B is 1000/5 200
trans/sec Therefore, I/O limits both systems.
28
Buses

• A bus is a shared communication link, which uses
  one set of wires to connect multiple subsystems.
• Advantages
• Versatile
• Low cost
• Disadvantage
• Communication bottleneck
• A bus generally consists of data, and control
  lines.
• Control lines are used to signal request and
  acknowledgments, and to indicate what type of
  information is on the data lines.
• Data lines carry information between the source
  and destination. These lines are often separated
  into address and data.

29
Bus Transactions

• A sequence of bus operations that includes a
  request and may include a response, either of
  which may carry data.
• May require several bus operations to complete.
• Includes two parts sending address and sending or
  receiving data.

30
Processor-memory bus

• Connects processor and memory.
• Short
• High speed
• Matched to memory system to maximize
  memory-processor bandwidth.

31
I/O Buses

• Can connect many types of I/O devices.
• Can be long.
• Wide range of data bandwidths.
• Provides a way of extending the machine and
  adding new peripherals.

32
Backplane Bus

• Allows processor, memory and I/O to exist on a
  single bus.

33
Synchronous Bus

• Contains a clock as part of the control lines,
  and uses a fixed protocol for communicating that
  is relative to the clock.
• Every device must run at the clock rate.
• Because of clock skew synchronous busses can not
  be long.
• Processor-memory buses tend to be synchronous.

34
Asynchronous Buses

• Not clocked.
• Uses handshaking.
• Can accommodate wide variety of devices.
• Can be long.
• Frequently used in I/O buses.
• USB and Firewire are asynchronous buses.

35
(No Transcript)
36
data
address
37
(No Transcript)