Slides 5 - USC Upstate: Faculty

Download Report

Transcript Slides 5 - USC Upstate: Faculty

SCSC 311 Information Systems
hardware and software
Overview of Storage Devices

Storage devices consist of
 Storage medium: device or substance holds data
 Read/write mechanism: read/write data to/from the
storage medium
e.g. RAM, HD, magnetic tape, CD, USB flash memory …

Device controller: provides the interface between the
storage devices and system bus

Two main types:
 Primary storage devices:
Support immediate execution of programs

Secondary storage devices
Provide long-term storage of programs and data
Chapter Objectives




Storage device Characteristics
Primary storage
Magnetic storage
Optical storage
Different types of storage
devices
Q: Why do we need so many different type of storage devices?
Storage Hierarchy


Different storage devices have different characteristics.
No single storage device fits in all purpose  find an optimal mix of
cost and performance for a particular purpose.
 a crucial decision to be made in the process of procurement of
computer systems.
Five Characteristics of Storage Devices
1.
Speed
2.
Volatility
3.
Access method
4.
Portability
5.
Cost and capacity
Characteristic 1: Speed

Access time
 the time required to execute one complete read/write operation
 For some devices: access time is constant regardless storage
location. (e.g. RAM)
 For others: access time varies with storage location. (e.g. HD)
Average access time

Primary storage speed
 Typically faster than secondary storage speed by a factor of 10^5
 measured in nanoseconds (ns)
 Very important to overall system performance
(Recall: wait state in Ch4)

Secondary storage speed

measured in milliseconds (ms)
 Important to some applications
Characteristic 1: Speed

Storage device speed is decided by


Access time
The unit of data transfer to/from the storage device
 For primary storage: a word
 For secondary storage: a block


512 bytes is typical block size
Data transfer rate = 1 / access time x unit of data transfer
e.g. a primary storage device with 50 ns access time, and word size is 4
bytes  data transfer rate = ?
e.g. a typical hard disk with 50 ms access time, and block size is 512 bytes
 data transfer rate = ?
Characteristic 2: Volatility

Primary storage are generally volatile


Cannot reliably hold data for long periods
Secondary storage are generally nonvolatile

Hold data without loss over long periods of time
Characteristic 3:
Access Method

The physical structure determines the ways in which data can be
accessed.

Serial access (linear)



Random access (direct access)



Access time depends on the current position of read/write
mechanism and the position of the desired data item.
Usually hold backup copies of data, e.g. magnetic tape
Is not restricted to any specific order when accessing data
Access time may or may not be constant, e.g. RAM, HD
Parallel access


simultaneously access multiple storage locations
e.g. RAM, HD in some OS
Characteristic 4: Portability

Removable storage media with standardized formats
e.g., compact disc, tape, USB flash memory

Typically results in slower access speeds
Why?
Ans: Usually high-speed access requires tight control of
environmental factor.
e.g. In a HD, sealed enclosures minimize / eliminate dust and air
density variations.
Characteristic 5: Cost and Capacity

Cost increases:



With improved speed, volatility, or portability
As access method changes
serial  random  parallel access
Cost vs. other characteristics


Primary storage: expensive, high speed and combination of
parallel/random access methods
Secondary storage: less expensive, slower, and capacity is
greater
Summary: Characteristics & Cost
Index

Storage device Characteristics

Primary storage

Magnetic storage
Optical storage

Storing Electrical Signals


Data are represent as digital electrical signals in
computer system
Digital electrical signals can be stored directly or
indirectly


Storing signal directly:
using battery, capacitor
Storing signal indirectly:
using its energy to alter the state of a device, and an
inverse process regenerates an equivalent electrical signal
Storing Electrical Signals Directly

Directly storing electrical power
 by devices such as batteries and capacitors
 Trade off between access speed and volatility

Battery



stable
slow to accept / regenerate electrical current
Capacitor


charge / discharge faster
lose charge quickly  need to recharge frequently
An electrochemical cell
Storing Electrical Signals Indirectly



Indirectly storing electrical power
 Uses energy to alter the state of a device, such as a mechanical
switch, or a magnetic field;
 Inverse the process regenerates equivalent electrical signal
Early computers use rings of ferrous material as primary memory
(core memory)
 Storing data via the polarity of the magnetic field they contain.
Modern computers use memory implemented with semiconductors
(RAM and ROM)
Random Access Memory (RAM)


Primary storage must closely match CPU speed and
word size to avoid wait states
Characteristics of RAM




Microchip implementation using semiconductors
To read and write with equal speed
Random access to stored bytes, words, or larger data
units
Basic memory types:

Static RAM (SRAM) – implemented entirely with
transistors


flip-flop circuit (next slide)
Dynamic RAM (DRAM) – uses transistors & capacitors
(Details on how SRAM and DRAM work are not required.)
Static RAM (SRAM)
•A flip-flop circuit
• 2 transistor to store one bit, and 2 - 4 transistors perform
read/write
• requires a continuous supply of electrical power to maintain
position.
Dynamic RAM (DRAM)

DRAM needs 1 transistors & 1 capacitors per bit
 stores each bit in a separate capacitor.
 As real-world capacitors are not ideal and hence leak
electrons, the information eventually fades unless the
capacitor charge is refreshed periodically (thousands
time / sec)

Less complex than SRAM
 have higher density than SRAM
 Less expensive than SRAM

Slower than SRAM
 Required refresh cycles
 Less efficient circuitry for accessing individual bit
access time: CPU (0.2 ns) vs. SRAM 5 ns vs. DRAM 50 ns.
Improve RAM Performance
To bridge the performance gap between memory and CPU,
three technologies are used:



Read-ahead memory access
 Activating the read/write circuitry need extra time
 Programs usually access memory sequentially
 Activating the read/write circuitry for location n+1 during or
after an access to location n
Synchronous read operations (SDRAM)
Write/read operation are broken into steps  pipelining multiple
write/read operations
On-chip memory caches
Enhanced DRAM (EDRAM) – Puts a small amount of SRAM in DRAM, as
cache
Nonvolatile Memory (NVM)

NVM: random access memory with long-term or permanent data
retention

NVM is slower than RAM
e.g. NVM is used to store system BIOS,
e.g. NVM is used to store programs and data (Firmware) in portable devices
(handheld computers and cell phones …)

Three generations of NVM

ROM: the content is permanent put into it

EPROM (Erasable programmable ROM)

EEPROM (Electronically Erasable programmable ROM)
Common NVM

Flash RAM is the most common NVM





Competitive with DRAM in capacity and read performance
Relatively slow write speed
Limited number of write cycles (wear out)
Primary used for secondary storage and for firmware that
isn’t frequently updated.
Other NVM technologies are under development:
Ferroelectric RAM, Polymer memory, … (not required)
Memory Packaging
Memory circuits are embedded in chips  groups of chips are packed
on a small circuit board

Dual in-line packages (DIPs)
 Early RAM and ROM circuits were packaged in DIPs
 Difficult to install on a circuit board

Single in-line memory module (SIMM)
 Standard RAM package in late 1980s
 easy to install

Double in-line memory module (DIMM)
 A newer packaging standard
 SIMM with independent electrical contacts on both sides of the module.
Memory Access

Physical organization of memory: a sequence of contiguous memory
cells

Big endian vs. little endian

Addressable memory: the highest numbered storage byte can be
(self-study)
Computer manufactures made different design decision
 Big endian: the most significant byte at the lowest memory address
 Little endian: the other way around
represent
 Physical memory is usually smaller than addressable memory
 Addressable memory is determined by the number of bits used to
represent an address
Q: If 32 bits are used to represent an address, what is the addressable
memory?
Memory Allocation


Memory allocation: describes the assignment of specific memory
addresses to system software, application programs, and data
The program’s offset: the difference between the first address in
physical memory and the address of the first program instruction

Programmer can describe addresses in a program in two
ways


Absolute addressing
Relative addressing
Absolute addressing vs. Relative addressing

Absolute addressing

Programmer describes memory address that refers to
actual physical memory address
Q: What’re some disadvantages of absolute addressing?

Relative addressing (a.k.a. Indirect addressing )


Each program are written as if the first programm
instruction is at address 0.
CPU converts this relative address into physical address
through the program offset


Offset register holds the offset value.
OS updates offset register for each executing program.
Relative addressing for Multiple Programs
Index

Storage device Characteristics


Primary storage
Magnetic storage

Optical storage
Magnetic Storage

The duality of magnetism and electricity

Converts electrical signals into magnetic charges, and
captures magnetic charge on a storage medium



Polarity of magnetic charge represents bit values zero and
one
Later regenerates electrical current from stored magnetic
charge
Q: How does magnetic storage device work?
(next slide …)
Principles of Magnetic Storage
• Components
• Write operation
• Read operation
Characteristics of Magnetic Storage
Coercivity and Areal Density

Coercivity: the ability of a substance or magnetic storage medium
to accept and hold magnetic charges.

Areal density: a function of the length and width of an individual
bit area.
Magnetic Tape





Ribbon of plastic with a coercible (usually metallic oxide)
surface coating
Mounts in a tape drive for reading and writing
Relatively slow serial access
Compounds magnetic leakage; wraps upon itself
Susceptible to stretching, friction, temperature variations
Magnetic Tape


Two approaches to recording data (details are not required)
(a) Linear recording, (b) Helical scanning
Several formats and standards (e.g., DDS [DAT], AIT, Mammoth,
DLT, LTO)
Magnetic Disk

In magnetic disk, flat, circular platter with metallic coating
that is rotated beneath read/write heads



Random access device; read/write head can be moved to
any location on the platter
Common types: Hard disks & floppy disks
Cost performance leader for general-purpose
on-line secondary storage
Components of a Disk Drive
Tracks, Sectors and Cylinder
To increase capacity per platter, disk manufacturers
divide tracks into zones and vary the sectors per track
in each zone.
Magnetic Disk Access Time

Disk Access Steps:
1.
2.
3.

Switch among read/write heads
Position the heads over a track
Wait for the desired sector to rotate beneath the heads
Disk Delay:
1.
Head-to-head switching time: HTH (All heads share on set of
circuit.)
2.
3.
Track-to-track seek time: TTT
Rotational delay
Most important performance numbers




Average access delay: (e.g. p196)
 For a large number of random accesses, the expected HTH switch time
is the switching time of half of the number of recording surfaces.
 The expected TTT seek time is the movement time over half of the
tracks.
 The expected rotation delay is time needed to rotate half of a track.
Average access time:
Average access time =
average access delay + the time reading a sector
Sequential access time = the time reading a sector
How to minimize average access time
 Organize related data in sequential sectors of the same a track
 Equivalently positioned tracks on multiple platters
 De-fragmentation
Index

Storage device Characteristics

Primary storage

Magnetic storage

Optical storage
Optical Storage Devices



In optical storage devices, bit values are stored as
variations in light reflection
 reflecting a laser off of a recording surface and
detecting changes in the reflected light compared to
the original light.
 Higher areal density and longer data life than
magnetic storage
Standardized and relatively inexpensive
Uses: low performance requirements, high capacity
requirements, portable and in standardized format
• Optical storage devices read data by shining laser beam on the disc.
• Reflecting a laser off of a recording surface and detecting changes in
the reflected light compared to the original light.
• Photoelectric cell is positioned at a complementary angle to intercept
reflected laser light.
CD-ROM




Read-only; data permanently embedded in durable
polycarbonate disc
Bit values represented as flat areas (lands) and concave
dents (pits) in the reflective layer
Data recorded in single continuous track that spirals
outward from center of disc
Popular medium for distributing software and large data
sets
CD-R and Magneto-Optical (self study)

CD-R




Uses a laser that can be switched between high and low
power and a laser-sensitive dye embedded in the disc
Relatively cheap
Common uses: create music CDs on home computers,
back up data from other storage devices, create archives of
large data sets, and manufacture small quantities of
identical CDs
Magneto-Optical


Utilize both optical and magnetic technologies.
Technology peaked in the mid 1990s. It is waning.
Phase-Change Optical Discs and DVD
(self study)

Phase-Change Optical Discs




Enables nondestructive writing to optical storage media
Materials change state easily from non-crystalline
(amorphous), to crystalline, and then back again
Example: CD-RW
DVD: improves on CD and CD-RW technology



Increased track and bit density: smaller wavelength lasers
and more precise mechanical control
Improved error correction
Multiple recording sites and layers
Technologies and Storage formats for Optical Storages
(details are not required)