Search in the document preview
Lecture - 5 External Memory
Computer Architecture Course Code: CSE360
Types of External Memory • Magnetic Disk
• Optical —CD-ROM —CD-Recordable (CD-R) —CD-R/W —DVD
• Magnetic Tape
Magnetic Disk • A disk is a circular platter constructed of non-
magnetic material, called substrate, coated with magnetizable material (iron oxide…rust)
• Traditionally, substrate has been an aluminium • Now, glass substrate have been introduced
—Improved surface uniformity – Increases disk reliability
—Reduction in surface defects – Reduces read/write errors
—Lower flight heights (See later) —Better stiffness —Better shock/damage resistance
Read and Write Mechanisms • Recording & retrieval of data via conductive coil called a head • In many systems, there are two heads, a read head and a write
head • During read/write, head is stationary, platter rotates • Write
— Electricity flowing through coil produces magnetic field — Electric pulses sent to write head — Resulting magnetic patterns are recorded on surface below,
with different patterns for positive and negative currents • Read (traditional)
— Magnetic field moving relative to coil produces current in the coil
— Coil is the same for read and write • Read (contemporary)
— Different read mechanism, requires separate read head, positioned close to write head
— The read head consists of a partially shielded magneto resistive (MR) sensor
— The MR material has an electrical resistance that depends on direction of magnetic field
— By passing current through MR sensor, resistance changes are detected as voltage signals
— The MR design allows high frequency operation which equates to higher storage density and speed
Inductive Write MR Read
• Inductive Write — An electric current in the wire induces a magnetic field, which
in turn magnetizes a small area of the recording medium. — Reversing the direction of current reverses the direction of
magnetization on the recoding medium • MR Read
— As discussed in previous slide
Data Organization and Formatting • The head is a small device capable of reading from or
writing to a portion of the platter • This gives organization of data on the platter in a
concentric set of rings, called tracks (there are thousands of tracks per surfaces)
• Adjacent tracks are separated by gaps which prevents or reduces errors due to misalignment of head or simplify interference of magnetic fields
• Reducegap to increase capacity • Data are transferred to or from the disk in sectors • There are hundreds of sectors per track, these may be
either fixed or variable length • In most contemporary systems, fixed length sectors are
used, with 512 bytes being the universal sector size • To avoid imposing unreasonable precision on system,
adjacent sectors are separated by intratrack (intersector) gaps
Disk Data Layout
Disk Velocity • A bit near centre of rotating disk travels a fixed (such as
read-write head) point slower than a bit on outside of disk • Need to compensate for the variation in speed so that head
can read all bits at the same rate • This can be done by increasing spacing between bits in
different tracks • The information can then be scanned at the same rate by
rotating disk at fixed speed, known as constant angular velocity (CAV) — Disk is divided into pie-shaped sectors and concentric
tracks — Individual blocks of data can be directly addressed by
track and sector — To move the head from its current location to a specific
address, it only takes short movement of the head to a specific track and short wait for given sector
— Waste of space on long outer tracks – Lower data density (the amount of data stored on long outer tracks
is same as what can be stored on short inner tracks)
Disk Layout Methods Diagram
• To increase density, modern hard disk systems use a technique known as multiple zone recording, in which the surface is divided into number of concentric zones (16 is typical) — Each zone has fixed bits per track — Zones farther from centre contain more bits (more
sectors) — This allows greater storage capacity at the expense of
somewhat more complex circuitry
Finding Sectors • Some means is needed to locate sector
positioned within a track • Clearly, there must be some starting point
on the track and a way of identifying the start and end of each sector
• Thus, the disk is formatted with some extra data used only by disk drive and not available to user
Winchester Disk Format Seagate ST506
• Each track contains 30 fixed-length sectors of 600 bytes each. - Each sector holds 512 bytes of data plus control information useful
to the disk controller - The ID field a unique identifier or address used to locate a particular
sector - The SYNCH byte is a special bit pattern that delimits the
beginning of the field - The track number identifies a track on a surface - The head number identifies a head (because disk has multiple
surfaces) - The ID and data fields each contain error-detecting code.
Physical Characteristics of Disk Systems
Fixed/Movable Head Disk • The head may be either fixed or movable
with respect to the radial direction of the platter
• Fixed head —One read write head per track —Heads mounted on fixed ridged arm (rare
today) • Movable head
—One read write head per side —Mounted on a movable arm (because, the
head must be able to be positioned above any track)
Removable or Not • The disk itself is mounted in a disk drive, which
consists of arm, a spindle that rotates the disk and electronics needed for I/O of binary data
• Removable disk —Can be removed from drive and replaced with
another disk —Provides unlimited storage capacity —Easy data transfer between systems —e.g. Floppy disk
• Nonremovable disk —Permanently mounted in the drive —e.g. hard disk in a personal computer is a
Sides • For most disks, the magnetizable coating
is applied to both sides of platter, which is then referred to as double sided.
• Some less expensive disk systems use single-sided disks
Multiple Platter • Some disk drives accommodate multiple platters stacked
vertically a fraction of an inch apart. • Multiple-platter disks employ a movable head, with
one read-write head per platter surface • All of the heads are mechanically fixed so that all are
at the same distance from the centre of the disk and move together
• Thus, at any time, all of the heads are positioned over tracks that are of equal distance from the centre of the disk
• The set of all the tracks in the same relative position on the platter is referred to as a cylinder.
• Data is striped by cylinder — reduces head movement — Increases speed (transfer rate)
Multiple Platters • The read-write head has
been positioned a fixed distance above the platter, allowing air gap
• The head actually comes into physical contact with the physical medium during read or write operation (e.g. this mechanism is used with the floppy disk)
• The narrower the head is, the closer it to the platter surface
• Narrower head means narrower tracks, therefore greater data density
• The closer the head to the disk, the greater the risk of error from imperfections
• To push the technology further, Winchester disk was developed (see later)
Tracks and Cylinders • All of the shaded
tracks are part of one cylinder
Floppy Disk • 8”, 5.25”, 3.5” • Small capacity
—Up to 1.44Mbyte (2.88M never popular) • Slow • Universal • Cheap • Obsolete?
Winchester Hard Disk (1) • Developed by IBM in Winchester (USA) • Winchester heads are used in sealed-unit drive with
aerodynamic head design • One or more platters (disks) • They are designed to operate closer to the disk’s
surface (very small head to disk gap) than conventional rigid disk heads, thus allowing greater data density
• The resulting noncontact system can be engineered to use narrower heads that operate closer to the platter’s surface than conventional rigid disk heads.
• Getting more robust
Winchester Hard Disk (2) • Universal (Winchester disk is commonly found in
personal computers an workstations, where it is referred to as a hard disk)
• Cheap • Fastest external storage • Getting larger all the time
—250 Gigabyte now easily available
Disk Performance Parameters: Speed • When the disk drive is operating, the disk is rotating at constant
speed. To read or write, the head must be positioned at the desired track and at the beginning of the desired sector on that track.
• Seek time — On a movable-head system, the time it takes to position the
head at the track is known as seek time • (Rotational) latency
— Once the track is selected, the disk controller waits until the appropriate sector rotates to line up with the head. The time it takes for the beginning of the sector to reach the head is known as rotational delay.
• Access time The sum of the seek time, if any, and the rotational delay equals
the access time (Access time = Seek + Latency), which is the time it takes to get into position to read or write.
• Transfer rate Once the head is in position, the read or write operation is then
performed as the sector moves under the head; this is the data transfer portion of the operation and the time for the transfer is the transfer time.
Timing of Disk I/O Transfer
• The actual disk I/O operation depend on the computer system, operating system, and nature of I/O channel and disk controller hardware.
• In addition to access time and transfer time, there are several queuing delays associated with I/O operation.
• When a process issues an I/O request, it must wait first for the device to be available.
• At that time, the device is assigned to the process. • If the device shares a single I/O channel or a set of I/O channels
with other disk drivers, there may be an additional wait for the channel to be available.
• At that point, the seek is performed to begin disk access.
RAID • Redundant Array of Independent Disks • Redundant array of inexpensive disks • 7 levels in common use • RAID is a set of physical disk drives viewed by the
operating system 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.
• A parity bit is a bit that is added to a group of source bits to ensure that the number of set bits (i.e., bits with value 1) in the outcome is even or odd. It is a very simple scheme that can be used to detect single or any other odd number (i.e., three, five, etc.) of errors in the output.
RAID 0 • No redundancy • Data striped across all disks
• Increase speed —Multiple data requests probably not on
same disk —Disks seek in parallel —A set of data is likely to be striped across