Title: FINDING THE OPTIMAL QUANTUM SIZE Revisiting the M/G/1 Round-Robin Queue
1FINDING THE OPTIMAL QUANTUM SIZERevisiting the
M/G/1 Round-Robin Queue
- VARUN GUPTA
- Carnegie Mellon University
2M/G/1/RR
Incomplete jobs
Poisson arrivals
Jobs served for q units at a time
3M/G/1/RR
Incomplete jobs
Poisson arrivals
Jobs served for q units at a time
4M/G/1/RR
Incomplete jobs
Completed jobs
Poisson arrivals
Jobs served for q units at a time
- arrival rate ?
- job sizes i.i.d. S
- load
-
Squared coefficient of variability (SCV) of job
sizes C2 ? 0
5M/G/1/RR
q ? 0
q ?
M/G/1/FCFS
M/G/1/PS
? Preemptions cause overhead (e.g. OS
scheduling)
? Variable job sizes cause long delays
preemption overheads
job size variability
small q
large q
6GOAL Optimal operating q for M/G/1/RR with
overheads and high C2
effect of preemption overheads
SUBGOAL Sensitivity Analysis Effect of q and C2
on M/G/1/RR performance (no switching overheads)
- PRIOR WORK
- Lots of exact analysis Wolff70, Sakata et
al.71, Brown78 - ? No closed-form solutions/bounds
- ? No simple expressions for interplay of q and C2
7Outline
- Effect of q and C2 on mean response time
- Approximate analysis
- Bounds for M/G/1/RR
- Choosing the optimal quantum size
No preemption overheads
Effect of preemption overheads
8Approximate sensitivity analysis of M/G/1/RR
- Approximation assumption 1
- Service quantum Exp(1/q)
- Approximation assumption 2
- Job size distribution
9Approximate sensitivity analysis of M/G/1/RR
- Monotonic in q
- Increases from ETPS ? ETFCFS
- Monotonic in C2
- Increases from ETPS ? ETPS(1?q)
10Outline
- Effect of q and C2 on mean response time
- Approximate analysis
- Bounds for M/G/1/RR
- Choosing the optimal quantum size
11M/G/1/RR bounds
- Assumption job sizes ? 0,q,,Kq
THEOREM
Lower bound is TIGHT ES iq
Upper bound is TIGHT within (1?/K) Job sizes ?
0,Kq
12Outline
- Effect of q and C2 on mean response time
- Approximate analysis
- Bounds for M/G/1/RR
- Choosing the optimal quantum size
13Optimizing q
- Preemption overhead h
-
- Minimize ETRR upper bound from Theorem
Common case
14Mean response time
h0
service quantum (q)
Job size distribution H2 (balanced means) ES
1, C2 19, ? 0.8
15Mean response time
1
h0
service quantum (q)
Job size distribution H2 (balanced means) ES
1, C2 19, ? 0.8
16Mean response time
2.5
1
h0
service quantum (q)
Job size distribution H2 (balanced means) ES
1, C2 19, ? 0.8
17Mean response time
5
2.5
1
h0
service quantum (q)
Job size distribution H2 (balanced means) ES
1, C2 19, ? 0.8
187.5
Mean response time
5
2.5
1
h0
service quantum (q)
Job size distribution H2 (balanced means) ES
1, C2 19, ? 0.8
1910
7.5
Mean response time
5
2.5
1
h0
service quantum (q)
Job size distribution H2 (balanced means) ES
1, C2 19, ? 0.8
20Outline
- Effect of q and C2 on mean response time
- Approximate analysis
- Bounds for M/G/1/RR
- Choosing the optimal quantum size
21Conclusion/Contributions
- Simple approximation and bounds for M/G/1/RR
- Optimal quantum size for handling highly
variable job sizes under preemption overheads
22Bounds Proof outline
- Di mean delay for ith quantum of service
- D D1 D2 ... DK
- D is the fixed point of a monotone linear system
- DT APDTb
f10
f20
D2
Sufficient condition for upper bound DT ?
APDTb for all P
Sufficient condition for lower bound DT ?
APDTb for all P
D
D
D
D1
23Optimizing q
- Preemption overhead h
- q qh, ES ? ES (1h/q), ? ? ES
-
Heavy traffic
Small overhead