CS457 - System Performance Evaluation - Winter 2010


Public Service Announcements

  1. This lecture and the previous one are based on this example.
  2. Assignment 1 deadline moved to 20 January.

Lecture 5 - Performance Metrics

The Textbook's Categories

1. Goal(s)

An Example System

Description

2. Services

External requests

Requests to secondary servers

Requests to primary server, all the above plus

Requests to load balancer

Internal requests

Requests to secondary servers

Requests to primary servers, all the above plus

3. Metrics

Possible metrics

Always remember Goodhart's law.

Response Time, Throughput and Utilization

For request i:

Draw a time line

Throughput is the number of requests processed per unit time. For stable systems,

4. Parameters

System Parameters

Things that could change in the system and that would change measured values:

  1. service capacity
  2. network delays
  3. resource management strategy
  4. scheduling algorithm
  5. load balancing algorithm
  6. time between failure for servers

Workload Parameters

Things that might change in the workload and that would change measured values:

  1. arrival rate of requests
  2. service requirement per request

5. Factors

Things that we will actually study

Metrics

  1. Response time to requests
  2. Catalogue freshness
  3. System utilization
  4. System downtime

System factors

  1. service capacity per server
  2. number of servers
  3. time between failures for servers
  4. downtime per failure for servers

Workload factors

  1. Arrival rate of user requests
  2. Arrival rate of catalogue requests


Return to: