CPU U%liza%on Control in Distributed Real‐Time Systems Chenyang Lu Department of Computer Science and Engineering IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management
Highlight Common class of compu6ng problems MIMO: mul6‐input (knobs), mul6‐output (objec6ves) Coupling between objec6ves. Constraints on knobs. Model Predic6ve Control Op6miza6on + Predic6on + Feedback IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 2
Why CPU U%liza%on Control? Overload protec6on CPU over‐u6liza6on system crash Meet response 6me requirement CPU u6liza6on < bound meet deadlines IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 3
Challenge: Uncertain%es Execu6on 6mes? Unknown sensor data or user input Request arrival rate? Aperiodic events Bursty service requests Disturbance? Denial of Service aYacks Control‐theore6c approach Robust u6liza6on control in face of workload uncertainty IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 4
End‐to‐End Tasks Distributed Real‐Time Systems Periodic task T i = sequence of subtasks {T ij } on different processors All the subtasks of a task run at a same rate Task rate can be adjusted Within a range Higher rate higher u6lity T 1 T 11 T 12 T 13 T 3 Remote Invocation T 2 Subtask P 2 P 3 P 1 IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 5
Problem Formula%on B i : U6liza6on set point of processor P i (1 ≤ i ≤ n) u i (k): U6liza6on of P i in the k th sampling period r j (k): Rate of task T j (1 ≤ j ≤ m) in the k th sampling period n ∑ ( B i − u i ( k )) 2 min { r j ( k )|1 ≤ j ≤ n } i = 1 subject to rate constraint: R min,j ≤ r j (k) ≤ R max,j (1 ≤ j ≤ m) IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 6
Single‐Input‐Single‐Output (SISO) Control Single Processor Sensor Inputs {r(k+1)} Set point Application Controller Actuator U s = 69% Middleware u(k) Task Rates R 1 : [1, 5] Hz Monitor OS R 2 : [10, 20] Hz Processor C. Lu, X. Wang, and C. Gill, Feedback Control Real-Time Scheduling in ORB Middleware, IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS'03), May 2003. IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 7
New in Distributed Systems Need to control u6liza6on of mul6ple processors U6liza6on of different processors are coupled with each other due to end‐to‐end tasks Replica6ng a SISO controller on all processors does not work! Constraints on task rates T 1 T 11 T 12 T 13 T 3 T 2 P 2 P 3 P 1 IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 8
EUCON: Mul%‐Input‐Mul%‐Output Control Measured Output Distributed System (m tasks, n processors) Utilization UM UM Monitor Model Predictive Rate Controller Modulator RM RM Feedback Loop Control Remote Invocation Input Subtask C. Lu, X. Wang and X. Koutsoukos, Feedback Utilization Control in Distributed Real-Time Systems with End-to-End Tasks, IEEE Transactions on Parallel and Distributed Systems, 16(6): 550-561, June 2005. IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 9
Control Theore%c Methodology 1. Derive a dynamic model of the system 2. Design a controller 3. Analyze stability IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 10
Dynamic Model: One Processor ∑ u i ( k ) = u i ( k − 1) + g i c jl Δ r j ( k − 1) T jl ∈ S i S i : set of subtasks on P i c jl : es6mated execu6on 6me of T il g i : u6liza6on gain of P i ra6o between actual and es6mated change in u6liza6on models uncertainty in execu6on 6mes IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 11
Dynamic Model: Mul%ple Processors u ( k ) = u ( k -1) + GF Δ r ( k -1) G: diagonal matrix of u6liza6on gains F : subtask alloca6on matrix models the coupling among processors f ij = c jl if task T j has a subtask T jl on processor P i f ij = 0 if T j has no subtask on P i T 1 T 11 T 22 T 3 T 2 T 21 T 31 P 1 P 2 IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 12
Model Predic%ve Control Suitable for coupled MIMO control problems with constraints. Compute input to minimize cost over a future interval. Cost func6on: tracking error and control cost. Predict cost based on a system model and feedback. Compute input subject to constraints. Op6miza6on + Predic6on + Feedback IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 13
Cost Func%on Cost P M − 1 2 2 ∑ ∑ V ( k ) = u ( k + i ) − ref ( k + i ) Δ r ( k + i ) − Δ r ( k + i − 1) + i = 1 i = 0 Tracking Error Control Cost Reference trajectory: exponen6al convergence to B − T s i T ref ref ( k + i ) = B − e ( B − u ( k )) IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 14
Model Predic%ve Controller At the end of each sampling period Compute inputs in future sampling periods Δ r (k), Δ r (k+1), ... Δ r (k+M‐1) to minimize the cost func6on Cost is predicted using (1) feedback u(k‐1) (2) approximate dynamic model Apply Δ r (k) to the system At the end of the next sampling period Shid 6me window and re‐compute Δ r (k+1), Δ r (k+2), ... Δ r (k+M) based on feedback IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 15
EUCON Controller Constrained op6miza6on solver Desired trajectory for Difference from u (k) to converge to B reference trajectory IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 16
Stability Analysis Stability: u6liza6on of all processors converge to set points Derive stability condi6on range of G Tolerable varia6on of execu6on 6mes Provides analy6cal assurance despite uncertainty IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 17
Stable System execu6on 6me factor = 0.5 (actual execu6on 6mes = ½ of es6mates) IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 18
Unstable System execu6on 6me factor = 7 (actual execu6on 6mes = 7 6mes es6mates) IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 19
Stability Stability condi6on tolerable range of execu6on 6mes Analy6cal assurance on u6liza6ons despite uncertainty Overes%ma%on Predicted of execu%on bound for %mes prevents stability oscilla%on actual execution time / estimation IM 2009: Recent Advances in the Applica6on of Control Theory to Network and Service Management 20
Recommend
More recommend