CS457 - System Performance Evaluation - Winter 2010

Public Service Announcements

1. The next two lectures are based on this example.
2. Assignment 1 deadline moved to 20 January.
3. Microsoft power: 30 MWatt

Lecture 4 - Abstraction from the Other Direction

A Typical System: E-Commerce Again

1. Goal(s)

• Provide merchandise information and process sales. Assume
  • Separate data system(s) for
    • fulfilment
    • payment processing
    • catalogue maintenance
    • etc.
  • Undifferentiated user requests
• Zero down time
• Easily scalable
• Vary response user to user
• Accommodate dynamic catalogue

A Possible System

1. N identical servers:
   • `identical' means
     • same hardware
     • same software
     • same connectivity
   • one is primary
     • interacts with external non-user requests
   • other servers are secondary
     • receive non-user state changes from primary
   • servers can fail
     • new primary is needed
       => secondary servers need all the state of primary server
2. Users
   • each connected to a home server that does all the transactions
   • each home server is one of a server set
     • each server in the server set has all the user state of the home server
     • home server failure means new server from server set
   • activities
     • browse catalogue
     • interact with shopping cart
     • purchase what's in shopping cart
3. Load balancer
   • initial assignment of home server
   • assignment of home server on redirection
4. External state (catalogue data)
   • updated initially on primary
   • distributed from primary to secondaries
   • synchronized by primary
5. User state (shopping cart contents)
   • updated at home server
   • transmitted to primary server
   • distributed to esrver set

We have abstracted away

1. server architecture: a server is a server
2. communication properties: a message is a message
3. external state: an update is an update
4. users: sources of uncorrelated requests

2. Services

External requests

Requests to secondary servers

• user requests
  • browse
  • add/remove from cart
  • purchase
  all these requests have exogenous arrival rates
• primary server assignment

Requests to primary server, all the above plus

• external requests, such as catalogue updates

Requests to load balancer

• user requests
  • login to system
• system requests
  • redirect user

Internal requests

Requests to secondary servers

• as home servers
  • catalogue updates from primary
  • assignment and re-assignment from load balancer
• as server set servers
  • shopping cart updates from primary

Requests to primary servers, all the above plus

• shopping cart updates from home servers
• home and server set updates from load balancer

3. Metrics

Possible metrics

• Load balancing
  • response time to user requests
    • mean
    • variability, such as standard deviation
    • percentiles
    • tails
    The above list applies to all response times.
  • response time for home server re-assignment
  • system utilization
• Consistency
  • response time to catalogue updates
• Uptime
  • response time for primary server re-assignment
  • availability: uptime / ( uptime + downtime )

Always remember Goodhart's law.

Return to:

• Bill Cowan's lecture notes for CS457 in W10
• Bill Cowan's Winter 2010 CS457 page
• Bill Cowan's CS457 page
• Bill Cowan's teaching page
• Bill Cowan's home page