Lecture 11: Multi-Core Processing

Question 1

What are our CPU Scheduling strategies for multi-core systems?

Answer 1

1) Asymmetric Multi-Processing

2) Symmetric Multi-Processing

Question 2

List the components in Asymmetric Multi-Processing

Answer 2

1) 1 CPU = Master CPU (“Control Plan”)

2) Remaining CPU’s = Slave CPUs (“Data or Code Plane)

Question 3

What does the Master CPU do and not do in Asymmetric Multi-Processing?

Answer 3

Does: All decisions with regards to:
1) Scheduling (Ready Queue to Running)
2) I/O Processing (from Running to I/O Queue)
3) System Activities
Doesn’t: Run actual code / processes themselves

Question 4

What are the advantages of Asymmetric Multi-Processing?

Answer 4

1) No sharing: only one processor accesses the system data structures (Queues)
2) Good Load Balancing

Question 5

List the components in Symmetric Multi-Processing

Answer 5

All CPUs = Master CPUs (no slave CPUs).

Question 6

Describe the behaviour of Symmetric Multi-Processing:

Answer 6

1) Here, each processor is self-scheduling
2) All processors share a common ready queue or each processor may have its own private queue of ready processes
3) Whether there is a common ready queue or private ready queues, there is a scheduler for each processor that examines the ready queue and dispatches the CPU to a specific process for execution

Question 7

What are the advantages or disadvantages of Asymmetric Multi-Processing?

Answer 7

Disadvantage: Sharing can cause issues –> each processor may update common queue or specific PCBs in queue
Advantage: Obvious performance increase - more CPUs in the multi-CPU system, we observe a directly proportional increase in system performance

Question 8

What are the challenges for Multi-Processing Systems?

Answer 8

1) Processor Affinity

2) Load Balancing

Question 9

Define: Processor Affinity

Answer 9

Process biasness towards a processor due to PCB information already being written into that particular CPU’s cache. (Reading/writing PCBs to caches is an expensive process and it is desirable to keep it minimized)
- higher the processor affinitiy, the lower load balancing we get

Question 10

Define: Load Balancing

Answer 10

Evenly spread out CPU Utilization across all CPUs in the multi-processing system. Better load balancing = desirable

Question 11

This applies to both systems: T or F: a process can move from the I/O queue back to the running state / processor

Answer 11

False; it always has to go through the Ready Queue to get back to a processor for processing

Question 12

In Asymmetric Multi-Processing: T or F; All CPUs must communicate with each other

Answer 12

False; Only Master communicates with the Slaves

Question 13

In Symmetric Multi-Processing: T or F; All CPUs must communicate with each other

Answer 13

True; otherwise they will lose their synchronization.

Question 14

What happens to the cache when a process leaves the running state?

Answer 14

The contents of the cache memory must be invalidated due to the fact that the next time the process is scheduled, it may be scheduled to another processor

Question 15

Is the contents of the cache memory being invalidated desirable?

Answer 15

Not really since read/write operations to memory (cache) are slow and, thus, not desirable. Thus, it would be better if the PCB info was allowed to stay in the cache and for the process to return to the same processor (this is processor affinity / process biasness)

Question 16

What is the phrase used to describe minimizing the act of invalidating the cache when a process goes to I/O queue, possibly resulting the process to go to another CPU?

Answer 16

Avoiding migration by utilizing process affinity.

Question 17

Summary of Single-Core VS. Multi-Core Systems:

Answer 17

1) Multi-Core vastly more complex than Single-Core
2) Clear performance gains in Multi-core
3) Difference between ASP and SMP is Sharing and Load Balancing / Process Afinity