1 / 34

H.J. Siegel Tony Maciejewski Purdue University

Viktor Prasanna USC. Richard Freund Noemix. Adapting MSHN Scheduling Technology for HiPer-D. H.J. Siegel Tony Maciejewski Purdue University. Viktor Prasanna USC. Richard Freund Noemix. Adapting MSHN Scheduling Technology for HiPer-D. H.J. Siegel Tony Maciejewski Purdue University

shawna
Download Presentation

H.J. Siegel Tony Maciejewski Purdue University

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Viktor Prasanna USC Richard FreundNoemix Adapting MSHN Scheduling Technology for HiPer-D H.J. Siegel Tony Maciejewski Purdue University

  2. Viktor Prasanna USC Richard FreundNoemix Adapting MSHN Scheduling Technology for HiPer-D H.J. Siegel Tony Maciejewski Purdue University Colorado State University

  3. Viktor Prasanna USC Richard FreundNoemix Adapting MSHN Scheduling Technology for HiPer-D • MSHN: Management System for Heterogeneous Networks • apply the techniques, knowledge, and expertise we developed in MSHN for mapping applications to heterogeneous platforms to the HiPer-D environment • work in collaboration with DeSiDeRaTa and HiPer-D teams • DeSiDeRaTa dynamically modifies existing HiPer-D mappings to avoid QoS violations using real-time feedback • our focus: derive initial HiPer-D mapping • done off-line – more time than dynamic mapper • use estimated predictions about HiPer-D (no feedback) H.J. Siegel Tony Maciejewski Purdue University Colorado State University

  4. One Example HiPer-D Subsystem (SUN) Ensemble TCP Land Attack Engagement Server TCP (SGI) Fire Sim 21 Ensemble CFF Broker Tacfire Gun Sim Ensemble Land Picture Deconflict Server Ensemble TCP OTH Data Server CORBA (TAO) Air Track Picture Display Components ALT Data Server (NT) NDDS

  5. HiPer-D System-Wide Attributes • continuously executing applications • QoS constraints for a system-wide mapping • for each subsystem • throughput • end-to-end latency • target platform • collection of heterogeneous COTS machines and networks • standard operating systems and network protocols

  6. Our Proposed Goal for the Initial Mapping • find an initial mapping of all HiPer-D applications onto the machines in the hardware platform • to be used when HiPer-D is first booted up • based on estimated predicted computation and communication times • derived off-line (static mapping) – more time for derivation than a dynamic (on-line) mapping • maximize the allowable increase in workload(e.g., targets) until a dynamic reallocation of resources is required to avoid a QoS violation in any subsystem • finding an optimal solution to the problem is intractable • need heuristic approaches

  7. Pluggable Algorithms (Heuristics) • select a pluggable algorithm (heuristic) • depends on • heterogeneous suite of machines • quality of mapping vs. off-line heuristic execution time • heuristics being investigated • local optimization: “2-phase greedy” • mixed integer programming based • global optimization: • genetic algorithm (GA) • simulated annealing (SA)

  8. Research Tasks to Create Heuristics • characterized and modeledthe continuously executing HiPer-D applications and the hardware platform(static information, no real-time feedback) • computation and communication time • particular machine selection • machine multi-tasking and network sharing • application workload • non-periodic (asynchronous) nature • context switching and background loads • limited profiling information available

  9. Research Tasks to Create Heuristics (cont’d) • quantifiedthe performance goal using the model • designing and developing heuristics for allocating the applications so as to optimize the performance goal • leverage heterogeneity • evaluating performance of heuristics using simulations • will integrate into HiPer-D

  10. Hardware Platform Model Hi-Level Overview • collection of heterogeneous machines • each with full-duplex connection to a non-blocking switch • collection of sensors and actuators • each with a half-duplex connection to the switch • sensor features • data output rate - the# of data sets produced per time unit • tactical load - the # of “tracks” per data set

  11. application sensor sensor 1 actuator 1 actuator sensor 2 sensor 3 actuator 2 Application Model Concepts • a directed acyclic graph • nodes are applications, arcs are data transfers • continuously executing, pipelined applications

  12. Z Ysends picture of battlefield to Z Y S P Q R Modeling Multiple Input Applications • discriminating applications - do not produce an output unless a particular input is present • Z is a discriminating application • generates output only if certain sensor data received from radar • combining applications - produce an output when all inputs arrive • S is a combining application • P, Q, and R solve pieces of a large computation, and Scombines the pieces to form the final answer

  13. path 1 path 2 path 3 path 4 = discriminating app. Paths Overview • group of applications that together perform one job • a “path” begins at a sensor • ends at an actuator or a discriminating application • paths are important because QoS constraints are defined on paths

  14. end-to-end latency Real-Time QoS Constraints for a Path • end-to-end latency- the time elapsed between the instant the sensor produces an input and the instant the path delivers its own output • must be no larger than a specified value • throughput - the number of data sets that the path can process in unit time • must be no smaller than a specified value • assumed equal to the sensor data rate

  15. Verifying Constraints • computation stage • a set of applications • communication stage • a set of data transfers • path • sequence of computation and communication stages • throughput constraint • execution time for any comp. stage  1/(sensor data rate) • execution time for any comm. stage  1/(sensor data rate) • the end-to-end latency constraint • the sum of execution times for ALL stages in a given path  that path’s maximum allowed end-to-end latency

  16. Quantifying the Allowable Increase in Load • let the maximum allowable increase in the tactical load be abbreviated as “MAIT” • MAIT for a system = min(system wide MAIT for throughput constraint, system wide MAIT for latency constraint) • different procedures required to find the MAIT values for throughput and latency constraints • assume that a mapping is given

  17. MAIT for the Latency Constraint • solve on a path-by-path basis • let  be the initial tactical load for the sensor for this path (load  was basis for the mapping) • solve for  in the next equation to find MAIT for the latency constraint for a path • set the maximum allowed path latency =  execution times for all comp. stages in the path given sensor tactical load +  execution times for all comm. stages in the path given sensor tactical load  • repeat the calculation above for all paths • system wide MAIT for latency = min of ( – )/ over all paths

  18. MAIT for the Throughput Constraint • solve on a path-by-path basis • recall  is the initial tactical load for the sensor for this path (load  was basis for the mapping) • solve for  in the next equation to find MAIT for the throughput constraint for a path • 1/(max. output rate from the sensor) = max(max(computation time for any application in the path given sensor tactical load ),max(communication time for any data transfer in the path given sensor tactical load )) • repeat the calculation above for all paths • system wide MAIT for throughput = min of ( – )/ over all paths

  19. Two-Phase Greedy Heuristic • origins in the Min-min heuristic • first discussed in Ibarra and Kim, J. of ACM, ’77 • from prior MSHN work • performed comparably to GA and SA in some different environments • faster heuristic than GA and SA • experiment to determine its performance in the HiPer-D environment

  20. Two-Phase Greedy: Simplified Overview • 1st phase: for each unmapped application individually, find machine that maximizes allowable increase in workload for throughput constraint (without allowing any QoS violations) • based on applications mapped so far • 2nd phase: select the single application/machine pair from 1st phase that maximizes the allowable increase in workload for the latency constraint and map the application • based on applications mapped so far and average values for unmapped applications • repeat both phases for all unmapped applications

  21. Variations on Two-Phase Greedy Approach • base: 1st phase: throughput constraint, 2nd phase: latency constraint • variations • 1st phase: latency, 2nd phase: throughput • 1st phase: latency, 2nd phase: latency • 1st phase: throughput, 2nd phase: throughput • simulations: best is function of relative tightness of constraints • “lower” bounds - a single phase greedy • map applications in random order • either use just throughput or use just latency • upper bounds – use best machine, unlimited machines, no communications(unattainable)

  22. Mixed Integer Programming (MIP) Approach • based on well-researched mathematical techniques for optimization • mathematical programming formulation based on models of the latency and throughput of applications • applicable to several objective functions • uses QoS requirements as constraints • directly solvable if the formulation is linear • use heuristics to convert non-linear problems into linear problems • solution • globally optimized • satisfies all constraints

  23. Paths MIP Formulation optimize MIP Solver objective function subject to Linearization Heuristics • latency requirements • throughput requirements • mapping constraints Solution MIP Approach Overview Subsystem Application model Target Platform

  24. MIP Formulation • issue • direct formulation of the MIP problem is non-linear • product of two variables in a single term • solution • use heuristics to estimate one of the variables • linearize the formulation • for example • latency of an application impacted by the number of applications mapped on each machine (N) • estimating N • Capability Based Heuristic (CBH) • Uniformly Allocated Heuristic (UAH)

  25. CBH UAH 100 80 60 40 20 3 4 5 number of machines Preliminary Simulation Results • objective: avg % of optimal value (12 applications, 10 cases)

  26. Status and Impact • status • the heuristics are being implemented and evaluated • integration as pluggable HiPer-D algorithms to occur • impact • provide effective initial allocation of resources to HiPer-D applications • simulation tool for “what if” studies of resources available versus manageable load • possible to compare off-line versus on-line resource allocation heuristics for the same HiPer-D system state

  27. Proposed Post Quorum Work • applying our heuristics to the entire HiPer-D system and evaluating their performance • developing application task-profiling procedures • predict computation and communication times • predict impact of workload changes • refining our current models to have more accurate approximations of impact of • multitasking • bandwidth sharing • workload varying in different ways at different sensors

  28. Proposed Post Quorum Work (cont’d) • understanding the performance of heuristics when the estimated computation and communication times differ from the actual times • evaluate robustness of current heuristics • design alternate heuristics for robustness • using our heuristics for determining the relative strengths and weaknesses of existing or proposed hardware environments

  29. Summary of Notes for Quorum Assessment • Our Specific Program Goal • original MSHN: resource management system that exploits heterogeneity • MSHN for HiPer-D: initial resource allocation generated off-line • Technical Approach (How?) • original MSHN: Scheduling Advisor; Client Library; Resource Status Server: Resource Requirements Database • MSHN for HiPer-D: model computation and communication; heuristics for mapping continuous, communicating, aperiodic applications

  30. Summary of Notes for Quorum Assessment (cont’d) • Scope of Solution (Metrics) • original MSHN: makespan; FISC – Flexible Integrated System Capability (priorities, deadlines, versions, security,…) • MSHN for HiPer-D: % allowable increase in workload w/o dynamic remapping • Open Problems/Extensions • original MSHN:build prototype into full working system • MSHN for HiPer-D: application profiling; impact of multitasking; heuristic robustness; use as system evaluator

  31. t-1 hij  dij sij aij max 0  i < Ij p (pj) rij dijsijaij  4 j =0 æ ç ç è ö ÷ ÷ ø FISC Measure – Collective Value of Applications • priorities: p(pj) - weight • required descendant: rij - output generated • completed by firm deadline:if yes dij = 1, elsedij = 0 • required security: sij = 1 if minimum met, else sij = 0 • required application specific QoS: aij = 1 if minimum met, else aij = 0 • versions: hij - normalized worth (%) • deadlines: dij - % (based on eijd,sijd, fijd, m) • variable security: sij - % satisfied • variable application specific QoS: aij- % satisfied

  32. t-1 j =0 max 0  i < Ij p (pj) rij dijsijaij  chjhij  cdj dijcsjsij cajaij chjcdjcsjcaj chjhij  cdj dijcsjsij cajaij chjcdjcsjcaj æ ç ç è ö ÷ ÷ ø FISC with Weighted Coefficients • relative importance among attributes for task j: • chj(versions), cdj(deadline), csj (security), and caj(application specific QoS) • set by user, policy maker, or application developer • all coefficients  0, and chjcdjcsjcaj > 0 •  1 • if hij = dij=sij= aij = 100%, fraction = 1

  33. Summary of Notes for Quorum Assessment (cont’d) • Scope of Solution (Metrics) • original MSHN: makespan; FISC – Flexible Integrated System Capability(priorities, deadlines, versions, security,…) • MSHN for HiPer-D: % allowable increase in workload w/o dynamic remapping • Open Problems/Extensions • original MSHN:build prototype into full working system • MSHN for HiPer-D: application profiling; impact of multitasking; heuristic robustness; use as system evaluator

More Related