Chapter 5

Data Storage Technology

2005 IS112

Chapter goals

Describe the distinguishing characteristics of primary and secondary storage

Describe the devices used to implement primary storage

Describe the memory allocation schemes Compare and contrast secondary storage

technology alternatives

Goals cont.

Describe factors that determine storage device performance Choose appropriate secondary storage technologies and devices Explore storage devices and their technologies Outlines characteristics common to all storage devices Explains the technology strengths and weaknesses of primary

storage and secondary storage

Storage types

Primary storage – memory or RAM Holds instructions and data for currently executing

programs Volatile – requires electricity to maintain data

Secondary storage – electromagnetic or optical devices Non-volatile storage devices with large capacities

Storage device components

Storage devices are comprised of Storage medium Read/write mechanism Device controller – interface between the storage

device and the system bus (discussed in chapter 6)

Storage device characteristics

Speed

Speed of primary storage (RAM) directly impacts performance of entire system

RAM extends the limited capacity of CPU registers The CPU continually moves data and instructions

between registers and RAM If a read/write to RAM takes more than one CPU

cycle, then CPU must wait for information RAM is faster than secondary storage by a factor of

105 or more

Speed cont.

Speed is also an issue for secondary storage Called “access time” or “seek time” Access time is defined as time to complete one read

or write operation Access time for disk or tape storage can vary

depending on location of information, therefore access time is expressed as an average

Access times

Primary storage – expressed in nanoseconds (billionths of a second)

Secondary storage – expressed in milliseconds (thousandths of a second)

Data transfer rate

Complete measure of data access speed consists of access time and the unit of data transfer to/from the storage device Access time plus how much data is transferred

Data transfer unit for primary storage is based on word size (usually 32 bit)

Data transfer unit

Data transfer unit (amount of data moved at a time) for secondary storage varies depending on the device

Unit is called a “block” Block size is stated in bytes “Sector” is data transfer unit for magnetic and

optical devices Common sector/block size is 512 bytes

Data transfer rate

Expressed in terms of bytes/second Access time combined with data transfer unit

Data transfer rate describes how much data can be transferred between devices over a period of time

Volatility

Volatile – storage device is volatile if it cannot reliable hold data for long periods of time

Non–volatile – storage device is non-volatile if it can reliably store data for long periods of time

Computer systems need a combination of volatile and non-volatile storage devices

Access method

Physical structure of storage device’s read/write mechanism determines the way(s) data can be accessed Serial access Random access Parallel access

Serial access

Stores and retrieves data items in a linear or sequential order

Slowest access method Tape typically used for backup purposes

Random access

Also called a direct access device Can directly access data stored on the device All primary storage and disk storage devices

are direct access Parallel access – with multiple read/write

heads, can simultaneously access more than one storage location

Portability

Data can be made portable by storing it on a removable storage medium or device.

Portable devices typically have slower access speed than permanently installed devices and those with non-removable media.

Cost and capacity

An increase in speed, permanence or portability generally comes at increased cost if all other factors are held constant.

Storage Device Characteristics

Primary storage devices

Random access memory (RAM) is a generic term for storage device that Microchip implementation using semiconductors Ability to read and write with equal speed Random access to stored bytes, words, or larger

data units

Primary Storage Devices

Critical performance characteristics Access speed Data transfer unit size

Must closely match CPU speed and word size to avoid wait states

Storing Electrical Signals

Directly By devices such as batteries and capacitors Trade off between access speed and volatility

Indirectly Uses energy to alter the state of a device; inverse

process regenerates equivalent electrical signal Modern computers use memory implemented

with semiconductors (RAM and NVM)

Random Access Memory

Characteristics Microchip implementation using

semiconductors Ability to read and write with equal speed Random access to stored bytes, words, or

larger data units

SRAM vs. DRAM

Static RAM – implemented with transistors Requires continuous supply of electricity to preserve data

Dynamic RAM – uses transistors and capacitors Require a fresh infusion of power thousands of times per

second. Each refresh operation is called a refresh cycle

Random Access Memory

To bridge performance gap between memory and microprocessors Read-ahead memory access Synchronous read operations On-chip memory caches

Nonvolatile Memory

Random access memory with long-term or permanent data retention

Usually relegated to specialized roles and secondary storage; slower write speeds and limited number of rewrites

Generations of devices (ROM, EPROM, and EEPROM)

Nonvolatile Memory

Flash RAM (most common NVM) Competitive with DRAM in capacity and read

performance Relatively slow write speed Limited number of write cycles

NVM technologies under development Ferroelectric RAM Polymer memory

SRAM vs. DRAM

Static RAM – implemented with transistors Requires continuous supply of electricity to preserve data

Dynamic RAM – uses transistors and capacitors Require a fresh infusion of power thousands of times per

second. Each refresh operation is called a refresh cycle

Read only memory

ROM – random access memory device that can store data permanently or semi-permanently

Typically used to store BIOS (basic input output services)

Instructions stored in ROM is called firmware

Memory packaging

CPU Memory Access

Management of RAM is critical to performance of computer

Organization, access, and management or RAM is done by the operating system

How memory is accessed is large factor in performance of RAM

Physical memory organization Main memory of any computer is a sequence of

contiguous memory cells Addressable memory – highest number storage byte

that can be represented Determined by the number of bits used to represent an

address If 32 bits used to represent and address, highest address is

232 = 4,294,967,296, or 4 GB Physical memory – actual memory installed, usually

less than addressable memory

Memory addressing & allocation Memory allocation is the assignment or reservation

of memory segments for system software, application programs, and data

Memory allocation is the responsibility of the operating system

Common scheme is to place OS in low memory and applications in high memory This can be demonstrated with C++ program

Memory allocation

Absolute vs. relative addressing Some programming languages (C, C++)

allow instructions that reference explicit memory locations BRANCH to location # STO to location #

Absolute addressing describes memory address operands that refer to actual physical memory locations

Problems with absolute addressing If a program refers to a physical memory

address in the code, then OS loses ability to re-arrange application locations in memory

Instead, programs use relative addressing

Relative addressing

Instructions that refer to memory use a combination of registers to compute addresses

When OS loads application into memory, OS loads starting point of application into one register

Instruction in application that refers to memory location is using an offset (i.e. distance from beginning of application)

OS adds offset to starting point to calculate physical memory location

Segmented memory

Each application has unique starting address

Magnetic storage

Uses magnetism to store binary information onto a storage medium that can store magnetic information

Least expensive medium for secondary storage Can be portable Retains data without electricity Over longer periods of time will eventually lose

information

Read/write in magnetic device

Magnetic decay and leakage

Primary disadvantage is loss of data over time

Magnetic Decay – the tendency of magnetically charges particles to lose their charge over time

Magnetic Leakage – a decrease in the strength of individual bit charges

Magnetic storage

Organization of tracks and sectors

Optical mass storage devices

Advantages: Higher recording density Longer data life Retain data for decades Not subject to problems of magnetic decay and leakage

Optical storage

Optical storage devices store bit values as variations in light reflection.

Storage medium is a surface of highly reflective material.

The read mechanism consists of a low-power laser and a photoelectric cell.

Storing binary information

Examples of optical devices

Chapter summary

A typical computer system has primary and secondary storage devices

The critical performance characteristics of primary storage devices are their access speed and the number of bits that can be accessed in a single read or write operation

Summary cont.

Programs generally are created as through they occupied contiguous primary storage locations starting at the first location

Magnetic storage storage devices store data bits as magnetic charges

Optical discs store data bits as variations in light reflection