1. Disk Structure
Each surface is composed of a group of concentric circles called tracks. Each track is divided into a group of sectors. Each sector contains an equal number of data bits (usually 512 bytes ); the data is encoded in the magnetic material on the slice. The slices are separated by some gaps, which do not contain data spaces. The gap storage is used to identify the formatting bit of the slice.
Note: spindle (spindle), platter (disc), cylinder (cylinder)
2. disk capacity
(Slice size × average slice of each track × number of tracks of each plane × number of sides of each disk × Number of disks of each disk)
3. For units related to DRAM and SRAM capacity, K = 2 10 , M = 2 20 , G = 2 30 , For disk and network I/O device capacity related units, usually K = 10 3 , M = 10 6 , G = 10 9 .
4. All reading and writing headers are located on the same cylinder at any time.
Note: spin, cushion, and radially)
The read/write head at the end of the drive arm is flying on a thin cushion about 0.1 microns on the disk surface at a speed of about 80 km/h. The disk reads and writes data in blocks of the sector size.
5. The access time to the slice consists of three main parts: Seek time, rotational latency, and transfer time ).
1) track time (seek Time): to read the content of a target slice, the drive arm first locates the read/write header on the track containing the target slice. The time required is the seek time, which is about equal to the maximum rotation time.
2) Rotation time: After the desired track is located, the drive waits for the first position of the target sector to rotate to the read/write header.
TMax Rotation= 1/Maximum Rotation Rate
TAVG Rotation= (1/2) × TMax Rotation.
3) Transfer Time
Tavg transfer = (1/Maximum Rotation Rate) × (1/the average number of sectors per track ).
6. The structure of modern disks is complex. There are multiple disk surfaces with different record areas. To hide such complexity for the operating system, modern disks simplify their construction into a sequence of logical blocks of B sector size, numbered 0, 1, 2,... B-1. The disk has a small hardware/firmware device called a disk controller, which maintains the ing between the logical block number and the actual (physical) disk sector.
When the operating system wants to perform (executed) an I/O operation such
Reading a disk sector into main memory, it sends a command toDisk Controller
Asking it to read a participant logical block number. Firmware on the Controller
PerformsFast tableLookup that translatesThe logical block numberInto(Surface,
Track, Sector) TripleThat uniquely identifies the corresponding physical sector.
Hardware on the Controller interprets this triple to move the heads to the appropriate
Cylinder, waits for the sector to pass under the head, gathers up the bits sensed by
Head into a small buffer on the controller, and copies them into main memory.
Computer Systems: A programmer's perspective >