exact analysis of some split-merge queues
TRANSCRIPT
Exact Analysis of Some Split-Merge Queues
Lester LipskyComputer Science & Engineering
University of Connecticut
Pierre FioriniCF Search
Portsmouth, NH
Contents• Introduction
– Synchronized Queues• Fork-Join Queues• Split-Merge Queues
• Related Work– Research Strategies– Harrison & Zertal (2003)– Lebrecht & Knottenbelt (2007)– Tsimashenka & Knottenbelt (2014)
• Background– Order Statistics
• Homogenous• Heterogeneous
– Matrix Exponential Distributions• Matrix Exponential Functions• Homogenous Order Statistics• Heterogeneous Order Statistics• Joint Distributions
– M/G/1 Queues• PK Formula• Stationary Queue Length
Distribution• Response Time Distribution
• Examples of Split-Merge Queues– Homogeneous Split–Merge
Queues– Heterogeneous Split–Merge
Queues– Split–Merge Queues with
Subtask Failure & Repair– Split–Merge Queues with a
Variable Number of Subtasks
Introduction – Split-Merge Queues
• On arrival a job is split into n sub-tasks which are serviced in parallel. • Only when all the tasks finish servicing and have rejoined can the
next job start• A type of “synchronized” queue
Introduction – Fork-Join Queues
• Incoming jobs are split on arrival for service by numerous servers and joined before departure
• Jobs can arrive at any time• Exact results only exist for N = 2
𝑇=12− 𝜌8
𝑥1− 𝜌
Nelson, R. & Tantawi, A. N. (1988).
Introduction – Difference Between Fork-Join & Split-Merge Queues
• FJ – new jobs can arrive at any time
• SM – new jobs can only arrive after the last subtask finishes service
• This means SM provide upper-bound response time for FJ queues
• SM queues are “more synchronized”
• Most researchers have used the EMOS (Expected Maximum Order Statistic) technique for the service time distribution
• Usually computed via numerical integration
• They have applied this to the M/G/1 queue and used the PK Formula to generate performance measures
Related Work – Research Strategies
𝑅E[max ( 𝑋1 , 𝑋 2,…, 𝑋𝑛)2]
1−𝜌
Related Work - Harrison & Zertal (2003)
• “Queueing Models with Maxima of Service Times”
• Found recursive way to compute the moments of o.s.– Identical + Non-Identical– Exact for exponential– Approximate for non-
exponential
• Applied results to analyze performance of RAID subsystems (exponential) for M/G/1 queues
Related Work - Lebrecht & Knottenbelt (2007)
• “Response Time Approximations in Fork-Join Queues”
• A response time approximation of the fork-join queue is presented using EMOS
• Used to model performance of RAID
• Used various distributions for M/G/1 queues & heterogeneous servers
Related Work – Tsimashenka & Knottenbelt (2014)
• “Trading off Subtask Dispersion and Response Time in Split-Merge Systems”
• Describe a methodology for managing the trade off between subtask dispersion and task response time
• That is, the time between the arrival of the first and last subtasks originating from a given task in the output buffer– The “Range”
• Used M/G/1 queue to generate performance measures
ContributionsResearch Queueing
ModelsHomogenous
Order StatisticsHeterogeneous Order Statistics
Stationary Queue Length Distribution
Response Time Distribution
Unreliable SM Queues
Variable Subtasks
Harrison & Zertal (2003)
M/G/1 (PK Formula)
Exact for Exponential, Approximations
Exact for Exponential, Approximations
No results No results No results No results
Lebrecht & Knottenbelt (2007)
M/G/1 (PK Formula)
Numerical Integration
Approximations & Numerical Integration
No results No results No results No results
Tsimashenka & Knottenbelt (2014)
M/G/1 (PK Formula)
Not discussed Numerical Integration
No results No results No results No results
Fiorini & Lipsky (2015)
M/G/1, M/G/1/N, M/G/1//N, M/G/C, M/G/C//N, G/G/1//N
Markov Chain Markov Chain Explicit ME representation
Explicit ME representation
ME rep ME rep
Background – Homogenous Order Statistics
F(x)X1
X2
X3
X4 X5
X(1)≤ X(2) ≤ X(3) ≤ X(4) ≤ X(5)
Randomly sample F(x)
Order sample by size…Parent Distribution
o.s. Distributions
Background – Homogenous Order Statistics
Background – Homogenous Order Statistics
• Interested in the Extremes• Maximum• Minimum
Background – Homogenous Order Statistics
Background – Heterogeneous Order Statistics
F1(x)X1
X2
X3
X4 X5
X(1)≤ X(2) ≤ X(3) ≤ X(4) ≤ X(5)
Randomly sample Fi(x)
Order sample by size…
F2(x)
Fn(x)Parent Distribution
Non-Identical o.s. Distributions
Background – Heterogeneous Order Statistics
Let X1, X2, X3, … be the order statistics
The joint distribution is (Bapet & Beg 1989)
Background – LAQTAny arbitrary pdf can be represented by an m-dimensional vector-matrix pair < p, B >
Let X be a matrix-exponential (ME) r.v. greater than or equal to 0. The cdf is
Let density function is
Moments can be computed by
Background – LAQT (M/G/1)For the open M/G/1 queue, the stationary queue length probabilities are given by
where
Background – LAQT (M/G/1)For the open M/G/1 queue, the mean queue length can be calculated by
or
Background – LAQT (M/G/1)For the open M/G/1 queue, the response time distribution can be calculated by
• Intuition…– Think of 4 tasks (i.e., “r.v.’s”) running concurrently…
• The 1st task finishes at t1
• The 2nd finishes at t2
– The maximum happens at X(4)
ME Order Statistics - Max
X(1)
X(2)
X(3)
X(4)
t1 t2 t3 t4
ME Order StatisticsState Transition Diagram
max{B1, B2, B3, B4} 𝑩1⊕𝑩2⊕𝑩3⊕𝑩4
𝑩1⊕𝑩2 𝑩3⊕𝑩4𝑩1⊕𝑩3𝑩1⊕𝑩4𝑩2⊕𝑩3𝑩2⊕𝑩4
𝑩1 𝑩2 𝑩3 𝑩4
𝑩4
𝑩3 𝑩3
𝑩3𝑩2 𝑩3
𝑩4 𝑩2𝑩1𝑩2
𝑩3 𝑩4
𝑩2
𝑩2 𝑩2𝑩1
𝑩1
𝑩1𝑩3𝑩3 𝑩3
𝑩4 𝑩4 𝑩4
𝑩1
𝑩4
𝑩3
𝑩1
ME Order Statistics – Markov Chainmax{B1, B2, B3, B4}
𝑩=¿
ME Order Statistics - Max
Let X1, X2,…, Xn be independent (and possibly non-identical) ME distributed r.v.’s having CDF
ME Order Statistics - Max
ME Order Statistics - Max
Need to construct the M & P matrices…
ME Order Statistics - Max
ME Order Statistics - Max
• Examples…
– Homogeneous split-merge queues – Heterogeneous split-merge queues – Split-Merge queues with unreliable subtasks– Variable number of subtasks
Examples of Split-Merge Queues
• In this example, all subtasks are iid and have the same parent distribution,
• For now, we assume the following:– n = 2 subtasks (but, n can by any number)
– Subtasks are exponentially distributed with parameter m
Homogeneous Split-Merge Queues
Homogeneous Split-Merge Queues
• Process rate matrix
• Service time matrix
• Density function, which is maximum of 2 exp r.v. with rate µ
Homogeneous Split-Merge Queues• Mean response time (using the
PK Formula for M/G/1 queues)
• Response time distribution (pdf)
Split-Merge vs. Fork-Join (n = 2)
(Nelson & Tantawi, 1988)
(Fiorini & Lipsky, 2015)
Mean upper-bound for FJ Queue, n = 2
• Upper-Bound Response Time Distribution for Fork-Join queues where n = 2
Split-Merge vs. Fork-Join (n = 2)
• Here we assume all subtasks are iid and have different parent distributions,
• We assume the following:– n = 2 subtasks (but, n can by any number)– Subtasks are exponentially distributed, where
Heterogeneous Split-Merge Queues
Heterogeneous Split-Merge Queues
• Process rate matrix
• Service time matrix
• Density function of maximum o.s. of 2 non-identical exponential r.v.’s
Heterogeneous Split-Merge Queues
• Mean response time (using the PK Formula) for M/G/1 queue
• Suppose a subtask fails at rate a and is repaired at rate b
• Assume when subtask is in upstate, it completes at rate m
• The generator of this process is
Unreliable Split-Merge Queues
• For n = 2, we have
Unreliable Split-Merge Queues
• The mean response time turns out to be (using the PK formula) for the M/G/1 queue
Unreliable Split-Merge Queues
• Other modeling factors…
– Subtasks can have different failure rates, – Subtasks can have different repair rates, – Subtasks can be a mixture of subtasks that fail and
those that don’t– Subtasks can have different recovery polices • prd, prs, etc.
Unreliable Split-Merge Queues
Split-Merge Queues with Variable Number of Forked Subtasks
• There is an a1p1 vector probability of 1 task being forked, a2p2 vector probability of 2 tasks, and so on…
Split-Merge Queues with Variable Number of Forked Subtasks
SummaryResearch Queueing
ModelsHomogenous
Order StatisticsHeterogeneous Order Statistics
Stationary Queue Length Distribution
Response Time Distribution
Unreliable SM Queues
Variable Subtasks
Harrison & Zertal (2003)
M/G/1 (PK Formula)
Exact for Exponential, Approximations
Exact for Exponential, Approximations
No results No results No results No results
Lebrecht & Knottenbelt (2007)
M/G/1 (PK Formula)
Numerical Integration
Approximations & Numerical Integration
No results No results No results No results
Tsimashenka & Knottenbelt (2014)
M/G/1 (PK Formula)
Not discussed Numerical Integration
No results No results No results No results
Fiorini & Lipsky (2015)
M/G/1, M/G/1/N, M/G/1//N, M/G/C, M/G/C//N, G/G/1//N
Markov Chain Markov Chain Explicit ME representation
Explicit ME representation
ME rep ME rep
• Study performance bounds of homogenous and heterogeneous fork-join queues– Use split-merge queues– Heavy-Tails?– Not well understood
• Unreliable split-merge queues– Subtasks can have different failure rates, – Subtasks can have different repair rates, – Subtasks can be a mixture of subtasks that fail and those that don’t– Subtasks can have different recovery polices
• prd, prs, etc.
Future Work
Questions???