Clusters Part 1 Definition of and motivation for clusters

1
Clusters Part 1 - Definition of and motivation
for clusters

• Lars Lundberg
• The slides in this presentation cover Part 1
  (Chapters 1-4) in Pfisters book

2
Introduction

• There are three ways of doing anything faster
• Work harder (increased processor speed)
• Work smarter (better algorithms)
• Get help (parallel processing)
• This course is about clusters, and they are one
  way of getting help, i.e. one way of obtaining
  parallel processing

3
Work harder

• The processor speed is increasing with a factor
  of two every 9-18 months (depending on who you
  ask)

4
Getting help

• Parallel processing occurs on many level, e.g.,
  instruction parallelism inside the processor
  (superscalar).
• We are focusing on parallelism that is visible in
  the program in the form of multiple processes or
  threads.
• It is cost-effective to build a large computer
  based on a (large) number of cheap
  microprocessors.
• It is relatively easy to build the multiprocessor
  hardware, but much more difficult to build good
  parallel software.
• Massive multiprocessors can potentially solve
  challenging problems, e.g., global weather
  simulation, full system simulation of cars and
  airplanes.

5
Lowly Parallel Processing

• The current market for massively parallel
  multiprocessors is small, but it is increasingly
  interesting to connect a small number (e.g. 2-16)
  of computers in a cluster.
• There are at least two reasons for this
• Microprocessors are getting faster, i.e. many
  problems can be solved without the aid of
  massively parallel computers.
• Availability (i.e. non-stop operation) is
  becoming increasingly important.

6
Availability

• It is (almost) always desirable to build systems
  that will not stop working, and cluster
  technology makes it possible to obtain high
  availability for a reasonable cost.
• In its simplest form cluster availability is
  obtained by having two computers. One active
  (primary) computer and one stand-by (secondary)
  computer if the primary computer fails you
  simply switch to the secondary computer.

7
Availability continued

• Instead of having one stand-by computer that
  just sits getting dusty almost all the time, we
  use both, and if either fails move all the work
  to one until you fix the one that died.
• We have now started to do (lowly) parallel
  processing across those two computers.
• In order to obtain higher availability we may
  want to use more than just two computers.

8
Motivation for Clusters

• Based on the discussion on the previous slides
  we conclude that the primary reason for using
  clusters is availability and not processing
  capacity. At least from an industrial
  perspective.
• However, people from academia are generally
  interested in clusters because they provide
  inexpensive massively parallel computes, i.e.
  clusters are popular in both industry and
  academia but for different reasons.

9
Cluster Example - BreweryIf one system goes
down (e.g. Manufacturing) then this task is
picked up by another system (e.g. Administration)
Administration
Shared disk
Shared disk
Manufacturing
Shared disk
Distribution
10
Cluster Example - Office EnvironmentIf the
active server fail the work will be picked up by
the standby server. The standby servers disk is
consistent with the active servers disk at all
times.
Standby server
Active server
11
Cluster Example - Web-severSome popular Internet
sites need more than one server in order to
handle all incoming requests. In that case one
can send allrequests to a dispatcher and let the
dispatcher distribute the load among a number of
servers.When serving the the Olympics in Nagano
IBM had this kind of configuration with 53
servers.
12
Cluster Example - Our Beowolf clusterThis is
the system that you will use in the laboratory
exercises.
Internet
Front-end (king)
Clients
13
Database cluster productsThe database server
processes are equivalent to the clients.
Clients
...
DB server
DB server
DB server
Disk
14
The standard reasons for using parallel and
distributed systems in general

• Performance (always important)
• Availabilty (in most cases the most important
  reason for using clusters)
• Price/performance (clusters consist of standard
  computers, which generally have good
  price/performance ratio)
• Incremental Growth (one can incrementally extend
  the system by adding more computers)
• Scaling (there is no upper limit on the number of
  computers in cluster, as opposed to the maximum
  number of processors in an SMP)
• Scavenging (turn the idle time on organizations
  computers into something useful)

15
Trends that promote clusters

• Very high-performance microprocessors, i.e. the
  need for massive parallelism is decreasing
• The communication technology is improving
  rapidly, e.g. fiber channels, Gbit networks etc.
• Standard tools and protocols for distributed
  computing, e.g. TCP/IP
• The need for high availability is increasing

16
Problems with cluster systems

• Lack of single system image software. The
  important exception in parallel processing is the
  SMP. This is probably a major reason why SMPs
  have been relatively successful
• Limited exploitation. Only a limited number of
  software products currently support clusters
• Consequently, the problem with clusters is not
  hardware it is software.

17
The Need for High Availability

• There are a number of reasons why availability
  is becoming increasingly important
• The Internet if your site is down you will lose
  customers immediately
• Remote accesses from employees I.e, people
  working from their homes and sales personnel
  downloading presentations and price lists
• Centralized server resources and thin clients
  Reduced maintanance cost.
• Etc.

18
Definition of a Cluster

• A cluster is a type of parallel system that
• Consists of a collection of interconnected whole
  computers,
• and is used as a single unified computing
  resource
• A whole computer could be a uni-processor or a
  SMP.

19
Clusters versus SMPs

• Clusters are composed of whole computers, SMPs
  are composed of processors
• Compared to a SMP it is easier to obtain high
  availabilty in clusters
• Compared to a SMP it is easier to incrementally
  increase the size of a cluster
• SMPs are easier to maintain from a system
  administrators point of view
• On a SMP you will often get away with only one
  license for your favorite software

20
Clusters versus distributed systems

• The nodes in a distributed system have their own
  identity from the outside the cluster nodes are
  anonymous
• The computers in a distributed system often have
  dedicated roles, e.g. servers and clients the
  computers in a cluster are usually equal.
• A cluster can be one node in a distributed system

21
System Size

• Due to the rapid growth in processor speed,
  neither parallel nor distributed systems are
  particularly interesting if they cannot scale to
  thousands of processors/computers.
• Clusters on the other hand are interesting (for
  availability reasons) also for systems with ten
  or less computers.