Chapter 121 MassStorage Systems

1
Chapter 12-1 Mass-Storage Systems
2
Chapter 12 Mass-Storage Systems

• Overview of Mass Storage Structure will spent
  lots of time here.
• Disk Attachment
• Disk Scheduling
• Disk Management
• Swap-Space Management
• RAID Structure
• Disk Attachment
• Stable-Storage Implementation
• Tertiary Storage Devices
• Operating System Issues
• Performance Issues

3
Overview of Mass Storage Structures
4
Limited Objectives

• We can view a file system as possessing three
  components
• A user / programmer interface to the file system
• The internal data structures and algorithms used
  by the operating system to implement this
  interface and access the data, and
• The secondary and tertiary storage structures
  themselves, which will be covered a couple of
  lectures in the future.
• Here we first describe the physical structure of
  secondary storage devices and the resulting
  effects on the uses of these devices

5
Overview of Mass Storage Structure

• Magnetic disks provide bulk of secondary storage
  of modern computers
• Drives rotate at 60 to 200 times per second
• Transfer rate is rate at which data flow between
  drive and computer
• Positioning time (random-access time) is time to
  move disk arm to desired cylinder (seek time) and
  time for desired sector to rotate under the disk
  head (rotational delay latency)
• Disk consists of a central spindle with platters
  attached.
• Data is recorded on the top and bottom surface of
  each platter except the top surface of the top
  platter and the bottom surface of the bottom
  platter (for dust).
• The read/write heads float over the surface of
  the platters and all arms move with the arm
  assembly together in unison.
• The set of tracks that are carved out via each
  arm position forms a cylinder..
• Each track may contain hundreds of sectors,
  depending on the size of the sectors. Modern
  disks have thousands of cylinders.
• See next slide.

6
Moving-head Disk Machanism
Discuss
7
Disk Access

• The disk spins at a high speed somewhere
  between 60 and 200 revolutions per second, but
  these speeds vary with time as technologies are
  constantly changing
• A disk read traditionally consists of three
  components1. Seek time this is the movement
  of the arm to the correct cylinder
• 2. Head select - negligible
• 3. Rotational delay (latency) generally, half
  the speed of rotation until the desired sector
  / logical block moves under the read/write head.
  
• 4. Data transfer time - copying the data from
  the disk into the I/O controller unit.
• Oftentimes, head select is not counted, because
  it is done electronically. But the head must be
  selected so that it is decided which head is
  going to read/write which surface!

8
Disk Head Crashes

• The read/write heads float over a surface, as
  mentioned.
• But a head crash can result from disk head making
  contact with the disk surface. This will ruin
  your entire day although it is much more unlikely
  nowadays.
• This can happen if power is abruptly pulled,
  although, again, more modern devices store some
  power so that they can gracefully degrade
• Some disks are removable that this allows other
  disks (disk packs) to be mounted on the same disk
  drive.
• Some are permanent disks in an organization.
• These are generally faster and have more
  capacity.
• Floppy Disks inexpensive, removable magnetic
  disks where the head sits directly on the disk
  surface.
• Floppies rotate much more slowly and have much
  less capacity than hard disks. Nominal capacity
  of a 3.5 floppy is 1.4 MB or 2.8MB.

9
More on Disks

• Disk Drives are attached to computer via I/O
  buses.
• Buses are the vehicle that support data transfer
  and are driven by special processors called I/O
  Disk Controllers generally at either end of the
  bus.
• A Host controller is located at the computer end
  of the bus disk controller on the other end.
  In between generally some kind of ribbon cable
  of varying channels.
• The host controller uses the bus to talk to a
  specific disk controller built into a disk
  drive itself (or storage array later this
  chapter).
• The computer places a specific read or write I/O
  command into the host controller, typically using
  memory-mapped I/O ports, which also points to the
  area of memory from which / to which data is to
  be accessed..
• The host controller then sends the I/O command to
  a disk controller.
• The disk controller operates the disk drive
  hardware to accommodate the commands that this
  disk controller executes.
• Note these are usually called commands vice
  instructions. Much tradition here

10
Disk Controller Commands and more

• In IBM jargon, we used to use the language
• CSW channel status word
• CCW a channel command word
• CAW a channel address word.
• These were 64 bit words executed interpretively
  by the disk controllers.
• They contain many fields of information including
  memory addresses, status information, specific
  commands (read, write, ) and much more.
• The interested student is encouraged to look
  these up.
• They are very interesting to see the formats of
  these commands.
• Disk controllers will typically have a built in
  cache to facilitate disk transfers both to the
  disk itself and from the disk to the host
• data transfer from the cache to the disk surface
  and
• data transfer from the cache to the host
• depending on whether we are reading or writing.
• Important to note that disk controllers are
  themselves small computers (mentioned in the
  past) that possess very specialized hardware to
  be able to interpret the commands sent to it via
  a limited instruction set.

11
Bus Architectures

• Typical buses that are available include
• 1. an (enhanced) integrated drive electronics
  (EIDE) bus,
• 2. an advanced technology attachment (ATA) bus,
• 3. a serial ATA (SATA) bus,
• 4. SCSI buses
• 5. a universal serial bus (USB) bus, a
• 6. fiber channel (FC) bus and
• Lets look at some of the details of these at
  this time before we continue

12
EIDE Bus Architecture

• EIDE (Enhanced Integrated Drive Electronics) is
  the current standard for inexpensive, high
  performance hard disks used in PCs.
• EIDE stands for Enhanced IDE and it is a
  registered name own by hard disk manufacturer
  Western Digital. They also own the name "IDE".
• IDE is older technology and is pretty limited.
• Other companies like Seagate, IBM, Quantum and
  Maxtor use the term ATA, which stands for
  Advanced Technology Attachment. But it is all the
  same. (There are, however, different protocols
  behind the terms. )
• You can think of EIDE as a bus - which has a host
  controller - which controls the bus, to which one
  may connect up to four units.
• All Pentium system boards since 1995 have this
  EIDE host controller built into the chip set.
• This allows the hard disk and other EIDE units to
  be connected directly to the system board

13
EIDE and SCSI disks

• Most modern computers automatically come with
  EIDE (enhanced IDE) built into the main board.
• This is perfectly adequate for personal
  workstations.
• A high performance SCSI controller can be added
  to a new system for an extra couple of hundred
  dollars.
• These provide for much higher performance and
  capability.
• IDE and SCSI disks operate at the same speed, but
  SCSI has advantages for a multitasking server
  because it allows many devices to be performing
  operations at the same time.
• In particular, a group of attached disks may all
  be transmitting / receiving at the same time thus
  significantly improving overall performance.
• This is particularly important in architectures
  such as RAID ahead.

14
EIDE and SCSI disks The Two Main Technologies.

• IDE, as mentioned, is older technology and is
  very limited.
• IDE can only support disks, while EIDE supports a
  variety of devices
• IDE can only support two devices (single cable),
  while EIDE can support four devices as mentioned.
  (two cables).
• SCSI (Small Computer System Interface) provides a
  standard interface for all types of computers.
• The IDE disk and the ISA bus are peculiar to
  IBM-compatible Intel-compatible PCs.
• SCSI, however, is much more versatile, and is
  used by Macintosh computers, RISC workstations,
  minicomputers, and even some mainframes.
• SCSI has always supported a mixture of disks,
  tapes, and CD-ROM drives.
• EIDE disks are limited in size when compared to
  the capacity of SCSI disks.
• On a SCSI bus, each device is a "peer" of the
  other devices.

15
More on Buses

• A computer is full of busses -- highways that
  take information and power from one place to
  another.
• Example when you plug an MP3 player or digital
  camera into your computer, you're probably using
  a universal serial bus (USB) (ahead) port.
• Your USB port is good at carrying the data and
  electricity required for small electronic devices
  that do things like create and store pictures and
  music files.
• But this bus isn't big enough to support a whole
  computer, a server or lots of devices
  simultaneously. (more ahead on USB
  devices/ports)
• To support a number of devices, we would need
  something like a SCSI.
• SCSI originally stood for Small Computer System
  Interface, but it's really outgrown the "small"
  designation.
• SCSI a fast bus that can connect lots of devices
  to a computer at the same time, including hard
  drives, scanners, CD-ROM/RW drives, printers, and
  tape drives.

16
SCSI is an ultra-fast, high-power communications
bus that connects up to 15 devices to your
computer.
17
Control Card and Connector
SCSI devices usually connect to a controller card
like this one
18
EIDE and SCSI disks The Two Main Technologies.

• An IDE disk must be mounted inside the computer.
• There is no provision for the IDE ribbon cable to
  run to external devices.
• Internal SCSI SCSI devices can also be
  internal.
• They are connected to each other and to the
  adapter card using a flat ribbon cable or a round
  bundled cable. .
• External SCSI SCSI devices, however, can also
  be external to the computer.
• They can be mounted in individual boxes, or can
  be mounted together in larger tower enclosures.
• This makes SCSI devices much more flexible to a
  variety of architectures, as we shall see ahead.

19
USB Serial Bus

• In information technology, a Universal Serial Bus
  (USB) is a serial bus standard that interfaces
  many different kinds of devices to a host
  computer.
• USB was designed to allow many peripherals to be
  connected using a single standardized interface
  socket and to improve the plug and play
  capabilities by allowing hot swapping that is,
  by allowing devices to be connected and
  disconnected without rebooting the computer or
  turning off the device.
• We nowadays do this all the time plugging in
  and removing external devices via our USB ports.
• Other convenient features include providing power
  to low-consumption devices without the need for
  an external power supply and allowing many
  devices to be used without requiring manufacturer
  specific, individual device drivers to be
  installed
• Consider our jump drives, ipods, and a host of
  other devices.

20
USB Serial Bus

• USB is intended to help retire all legacy
  varieties of serial and parallel ports.
• USB can connect many computer peripherals such as
  mice, keyboards, PDAs, joysticks, scanners,
  digital cameras, printers, flash drives and more!
  
• For many such devices, USB has become the
  standard connection method.
• USB was originally designed for personal
  computers.
• But it has become commonplace on other devices
  such as PDAs and video game consoles, and as a
  bridging power cord between a device and an AC
  adapter plugged into a wall plug for charging
  purposes.
• As of 2008, there are about 2 billion USB devices
  in the world.
• Interesting, other technologies, like serial-ATA
  (SATA), are largely replacing USBs in new
  systems, but SCSI is still in use.

21
The most common USB Plug.
22
Fiber Channel Bus (FC)

• Fibre Channel, or FC, is a gigabit-speed network
  technology primarily used for storage networking.
  
• Fibre Channel is standardized in the T11
  Technical Committee of the International
  Committee for Information Technology Standards
  (INCITS), an American National Standards
  Institute (ANSI)accredited standards committee.
• It started use primarily in the supercomputer
  field, but has become the standard connection
  type for storage area networks (SAN) in
  enterprise storage.
• We are going to discuss storage area networks
  later in this chapter.
• Despite common connotations of its name, Fibre
  Channel signaling can run on both
• twisted pair copper wire and
• fiber-optic cables.
• Fibre Channel Protocol (FCP) is a transport
  protocol (similar to TCP used in IP networks)
  which predominantly transports SCSI commands over
  Fibre Channel networks.

23
Magnetic Tapes

• Was the primary early secondary-storage medium
  for many years.
• Relatively permanent and holds large quantities
  of data
• Access time slow, but again, can store huge
  quantities of data.
• Random access 1000 times slower than disk
• Mainly used for backup, storage of
  infrequently-used data, transfer medium between
  systems
• Used for archiving history tapes, and more.
• Please note that in years past, these constituted
  a primary storage medium for files as long as
  they were sequential!!
• Kept in spools and wound or rewound past
  read-write head
• Once data under head, transfer rates comparable
  to disk
• 20-200GB typical storage

24
Used extensively in the mid-60s and early
70s. Still backup / recovery Tapes are still
widely used.
25
Disk Structure
26
Disk Structure

• Unlike years ago, disks are structured
  differently with different technologies.
• Two major types of technologies
• Have lots of similarities, but
• Have major differences too.
• They are
• Constant linear velocity (CLV) disks and
• Constant angular velocity (CAV) disks.
• Their organizations / way they store data is
  different.

27
Disk Structure Commonalities

• Disks store data as large, one-dimensional arrays
  of blocks.
• The term logical blocks is now used in place of
  what used to be called (and definitely still is
  in some sectors) physical blocks.
• We will go with the more modern terminology, but
  be careful.
• We will distinguish where appropriate.
• Most common logical block size is 512 bytes (.5
  K)
• Other sizes available for low level formatting.
• Sector 0 is traditionally the first sector on the
  first track of the outermost cylinder and mapping
  proceeds from this sector, this track, this
  cylinder to the rest of the tracks on that
  cylinder before moving to the next cylinder.
• We can convert a logical block into the old-style
  disk address that address a cylinder number, a
  track number in that cylinder, and a record /
  sector number on that track.

28
Disk Structure Commonalities

• But life is not simple and we cannot always do a
  direct mapping that is, we dont always have
  sector 0, sector 1, etc. through tracks,
  cylinders, etc. without a hitch!
• Manufacturing of disks usually includes defective
  sectors (or even tracks).
• They come from the manufacturer that way and
  defects are normally identified via low-level
  formatting normally done at the factory.
• Then too, the number of sectors per track may not
  be a constant on some kind of drives.

29
Constant Linear Velocity (CLV) Drives

• CD-ROM and DVD-ROM drives use the CLV approach.
• This is referred to as a constant linear velocity
  drive.
• Here, the density of each track is uniform.
• This means that the same amount of storage is
  available on each track no matter where the track
  is on the disk.
• Now, as tracks are located away from the center
  of the disk, they are clearly longer (if we
  opened them up and spread them out) than other
  tracks.
• Result is that there are more sectors per track
  as we move outward, but the density of the bits
  is uniform.
• Because of this, (your textbook) tracks in the
  outermost cylinders can hold 40 more data
  (additional sectors) than tracks in the inner
  cylinders!
• The same rate of data is moving under the
  read/write heads to keep transfer speeds uniform.

30
Constant Linear Velocity drives - more

• An interesting twist to this
• Constant Linear Velocity Storage (CLV) is a
  driving scheme in which the linear velocity of
  the disk is kept constant.
• This requires that the angular velocity of the
  disk be larger when the reading or writing tracks
  closer to the axis.
• This is necessary so that the same number of bits
  pass under a read/write head per unit time.
• The advantage of this technique is that the
  read/write speed is constant.
• Downside But, as mechanical stability puts an
  upper limit on the angular velocity (and not the
  linear velocity) using the same linear velocity
  throughout, means that we are using less than the
  maximal angular velocity at outer tracks and this
  means that full potential of the drive is not
  used.
• Lots of devices use CLV drives. These are
  necessary to keep a constant data rate. .
• Interestingly, mechanically, the motor speed
  actually decreases from 495 to 212 rpm as the
  read head moves away from the center, to keep the
  disc moving past the read head at a CLV of 1.2
  meters/sec.

31
Constant Angular Velocity (CAV) drives

• In contrast to the constant linear velocity (CLV)
  drives, we have the constant angular velocity
  (CAV) drives.
• Here, unlike the CLV drives, the disk rotation
  speed stays constant, but as a result, the
  density of the bits moving under the read/write
  heads decreases as we proceed from inner tracks
  to outer tracks.
• But since the disk rotation speed stays constant,
  the data transfer rate remains constant.
• Newer Technologies As technology has
  progressed, the number of sectors per track has
  been increasing, and now the outermost tracks
  often have several hundred sectors per track.
• Further, the number of cylinders / disk is on the
  upswing.
• Large disks have tens of thousands of cylinders!

32
Constant Angular Velocity drives more

• A drive or disc operating in CAV mode maintains a
  constant angular velocity, contrasted with a
  constant linear velocity (CLV).
• When playing back music, a compact disc (CD)
  employs CLV to maintain a constant data rate.
• As mentioned, the motor speed decreases from 495
  to 212 rpm as the read head moves away from the
  center to keep the disc moving past the read head
  at a constant linear velocity.
• CAV was used in the LaserDisc format for
  interactive titles, as well as special editions
  of certain films. CAV allowed for perfect still
  frames, as well as random access to any given
  frame on a disc.
• Playing time, however, was cut in half from 60
  minutes to 30 minutes.
• More on CAVs
• High speed CD and DVD drives use CAV.
• CAV is used with Nintendo GameCube Game Disc and
  Wii Optical Disc.
• To accommodate the higher data transfer rates and
  random access requirements of modern CD-ROM
  drives, CAV systems are used. This is because
  seek performance would be greatly affected during
  random access by the requirement to continually
  modulate the disc's rotation speed to be
  appropriate for the read head's position.

33
End of Chapter 12.1