Click Here!
home account info subscribe login search My ITKnowledge FAQ/help site map contact us


 
Brief Full
 Advanced
      Search
 Search Tips
To access the contents, click the chapter and section titles.

Oracle Performance Tuning and Optimization
(Publisher: Macmillan Computer Publishing)
Author(s): Edward Whalen
ISBN: 067230886x
Publication Date: 04/01/96

Bookmark It

Search this book:
 
Previous Table of Contents Next


Chapter 13
System Processors

This chapter gives a brief overview of how system processors work and how performance is affected by various aspects of the computer hardware architecture. Of course, you cannot “tune” your CPUs, but you should look at how the hardware works to better understand the system.

This chapter first looks at the various components of computer hardware and then looks at some of these components in more detail. It is important to remember how the components react with each other to understand why you favor certain components such as memory.

Overview of Computer Architecture

Your computer system is made up of hundreds and thousands of individual components all working in harmony to process data. Each of these components has its own job to perform; each has its own performance characteristics.

The brain of the system is the Central Processing Unit (CPU), which actually processes all the calculations and instructions that run on the computer. The job of the rest of the system is to keep the CPU busy with instructions to process. A well-tuned system runs at maximum performance if the CPU or CPUs are busy 100 percent of the time.

So how does the system keep the CPUs as busy as possible? In general, the system is made up of different layers, or tiers, of progressively slower components. Because the faster components are typically the most expensive, you must perform a balancing act between speed and cost efficiency.

The following sections look at the performance tiers.

CPU and Cache

The CPU and the CPU cache are the fastest components of the system. The cache is very high-speed memory used to store recently used data and instructions so that it can provide quick access if this data is used again in a short time. Most CPU hardware designs actually have a cache built into the CPU chip. This internal cache is known as a Level 1 (or L1) cache. Typically, an L1 cache is very small—on the order of 8 to 16 kilobytes in size.

When a certain piece of data is wanted, the hardware first looks in the L1 cache. If the data is there, the hardware processes that data immediately. If the data is not available in the L1 cache, the hardware looks in the L2 cache, which is external to the CPU chip. The L2 cache is located very close to the CPU chip because speed is important. The L2 cache is connected to the CPU chips on the same side of the memory bus as the CPU. To get to main memory, you need to use the memory bus, which affects the speed of the memory access.

Although the L2 cache is twice as slow as the L1 cache, it is usually much larger. Its larger size provides a better chance of getting a “cache hit.” Typical L2 caches range from 128K to 4M in size.

Slower yet is the speed of the system memory. It is probably five times slower than the L2 cache. The size of system memory can range from 4M for a small desktop PC up to 2 to 4 gigabytes for large server machines. Some supercomputers have even more system memory than that.

If data or instructions have not been found in any of the system caches or the system memory, an I/O is done through the I/O bus. Any I/Os generated outside of system memory are at least 50 times slower than access from memory. Depending on the storage device and the data being accessed, the access time may even be slower than that.

If data is not available on the system’s local disks and must be acquired through a local area network (LAN), accesses are even slower. In the world of the CPU, cache, and memory, it takes an eternity to get data from over a network.

Suppose that it takes 1 second to get a piece of data from the L1 cache in the CPU chip. It takes approximately 2 seconds to get that data from the L2 cache. If the data is not available in the L2 cache and must be retrieved from main system memory, it can take up to 10 seconds to retrieve that data. If the data is not in system memory and you have to go to disk, it can take from 8 to 10 minutes to retrieve the data. If you have to get that data from another machine on the network, it can take up to a half hour or more (see Figure 13.1).


Figure 13.1  Powers of 10.

As you can see from the time line, there is an enormous difference between retrieving data from the L1 cache and retrieving data from the disk. This is why we spend so much time trying to take advantage of the SGA in memory. This is also why hardware vendors spend so much time designing CPU caches and fast memory busses.

Now look at some of these components and at the different types of computers and architectures.

CPU Design

The CPU is the brains of the computer. This is where most of the instruction processing happens. Although some intelligent devices such as disk controllers can process some instructions, the instructions these devices can handle are limited to the control of data moving to and from the devices.

The CPU works off of the system clock and executes instructions based on clock signals. The clock rate and type of CPU determine how fast these instructions are executed.

The CPU usually falls into one of two groups of processors: Complex Instruction Set Computer (CISC) or Reduced Instruction Set Computer (RISC), as described following.

CISC Processors

CISC processors (such as the type of processors Intel builds) are by far the most popular processors sold today. CISC processors are more traditional and offer a large instruction set to the program developer. Some of these instructions can be quite complicated; most instructions require several clock cycles to complete.

CISC processors are very complex and difficult to build. Because these CPU chips contain millions of internal components, the components are extremely close together. The physical closeness causes problems because there is no room for error. Each year, technology allows more complex and faster chips to be built but eventually, physics will limit what can be done.

CISC processors carry out a wide range of tasks and can sometimes perform two or more instructions at a time in parallel. CISC processors perform most tasks such as RDBMS processing very well.


Previous Table of Contents Next


Products |  Contact Us |  About Us |  Privacy  |  Ad Info  |  Home

Use of this site is subject to certain Terms & Conditions, Copyright © 1996-2000 EarthWeb Inc.
All rights reserved. Reproduction whole or in part in any form or medium without express written permission of EarthWeb is prohibited.