250 likes | 262 Views
This presentation discusses the Governor framework, an explicit and quantified approach towards performance impact control in resource scavenging applications. It provides an extensible and user-level implementation that allows for control over the impact on native workloads. The framework is evaluated with two types of scavenging applications, and performance results are discussed.
E N D
Governor: Autonomic Throttling for Aggressive Idle Resource Scavenging Jonathan Strickland (1) Vincent Freeh (1) Xiaosong Ma (1 & 2) Sudharshan Vazhkudai (2) (1) Department of Computer Science, NC State Univ. (2) Mathematics and Computer Science Division, Oak Ridge National Laboratory International Conference on Autonomic Computing 2005
Presentation Roadmap • Introduction • Model and approach • System implementation • Performance results • Conclusion and future work International Conference on Autonomic Computing 2005
Aggregating Desktop Computer Resources • Personal computers pervasive • Easily updated and well equipped • Under-utilized • Consolidate scattered resources by resource scavenging (resource stealing) • Computing resources • Condor, Entropia • SETI@home, Folding@home • Creating massive compute power • Storage resources • Farsite, Kosha, FreeLoader • Aggregate distributed spaces into shared storage (Courtesy: SETI@home) (Courtesy: Folding@home) International Conference on Autonomic Computing 2005
Impact on Workstation Owners • Foremost concern of resource donors • Security and privacy impact • Virtual machine/sandbox solutions • Performance impact • Existing approaches often too conservative • “Stop” approach • Stop scavenging when user activity detected • Unable to utilize small pieces of idle time • Does not overlap scavenging with native workload • Priority-based approach • Works for cycle-stealing • Implicit, “best-effort” • Range and granularity limited by operating system International Conference on Autonomic Computing 2005
Objectives and Contributions • Goal: systematic performance impact control framework • Contributions: Governor • Explicit, quantified approach toward performance impact control • Extensible framework for arbitrary scavenging applications and native workloads • User-level, OS-independent implementation • Evaluation with two types of scavenging applications International Conference on Autonomic Computing 2005
Presentation Roadmap • Introduction • Model and approach • System implementation • Performance results • Conclusion and future work International Conference on Autonomic Computing 2005
System Entities • Active on donated workstations • Resource scavenging application (scavenger) • Native workload • Governor process • Controls execution of scavenger • Limits impact on native workload to target level α(e.g., 20%) International Conference on Autonomic Computing 2005
Performance Impact • Performance impact • Caused by resource scavenging application on workstation owner’s native workload • Metrics: slow-down factor (Timescavenged – Timeoriginal) / Timeoriginal • May not reflect resource owner perceived impact • Main approach: resource throttling • Throttle level (β, 0<=β<1) Timescavenging / Timetotal • Major challenge: to select appropriate β value International Conference on Autonomic Computing 2005
Impact Benchmarking • Characterize scavenger S against system resources • Native workload as combination of resource consumption components • Resource vector R = (r1, r2, …, rn) • Benchmark vector B = (B1, B2, …, Bn) • Measure S’ impact onBiwith various throttle levels • Store impact curve • Calculate target throttle level βiwith given impact level α International Conference on Autonomic Computing 2005
Native Workload Monitoring • Native workloads typically complex and dynamic • Online workload monitoring • Activate corresponding βwhen non-trivial native resource consumption detected • Resource trigger vector Т = (τ1, τ2, …, τn) • For each resource Ri • βi’= • Overall β = min (β1’ , β2’ , … βn’ ) • Picking most restrictive βacross resources βi, if consumption ≥ τi 1, if consumption < τi International Conference on Autonomic Computing 2005
Governor Architecture 0. impact benchmarking User target system resources Resource vectors (b1, b2 , ...) (t1, t2 , ...) 1. monitor resource activity scavenger 3. throttle scavenger 2.compute overall b • Adaptive • Extensible and generic Governor International Conference on Autonomic Computing 2005
Presentation Roadmap • Introduction • Model and approach • System implementation • Performance results • Conclusion and future work International Conference on Autonomic Computing 2005
Dynamic Throttling Mechanism I I I … β=0.3 β=0.6 0.2 β=0.5 Scavenger phases Monitoring phases • Fixed throttle interval “I” • 1 second in our implementation • Within each I, Governor • Runs scavenger application for β*I • Monitors native workload during (1-β)*I • Adjust βfor next I International Conference on Autonomic Computing 2005
Resource Usage Monitoring and Triggers • At beginning and end of each monitoring phase (1-β)*I • Monitor resource usage • CPU: /proc/stat (cycles) • Disk: /proc/partitions (blocks) • Network: /proc/net/dev (bytes) • Triggers (τarray) International Conference on Autonomic Computing 2005
Presentation Roadmap • Introduction • Model and approach • System implementation • Performance results • Conclusion and future work International Conference on Autonomic Computing 2005
Applications, Benchmarks, and Configurations • Scavenger applications • SETI@home • Search for signals in slices of radio telescope data • Computation-intensive • FreeLoader • Prototype for aggregating storage in LAN environments • I/O- and network-intensive • Single-resource benchmarks • CPU: EP from NAS benchmark suite • I/O: large sequential file read • Network: repeated downloading with wget • Linux workstation • 2.8GHz Pentium 4, 512MB memory, 80GB disk International Conference on Autonomic Computing 2005
Impact Benchmarking Results SETI FreeLoader International Conference on Autonomic Computing 2005
Multi-resource Workload: Kernel Compile Impact on native workload Impact on scavenger app. International Conference on Autonomic Computing 2005
Synthetic Composite Workload • Simulate common intermittent user activities • Short sleep time between operations • Writing 80MB data to file • Browsing arbitrary directories in search of file • Compressing data written previously and send via networks • Browsing more directories • Removing files written • Takes about 150 seconds without concurrent user load International Conference on Autonomic Computing 2005
Composite Exec. Time and Impact • Combine impact benchmarking results with real-time monitoring of composite workload • Governor closely approximates target performance impact (α) International Conference on Autonomic Computing 2005
Comparison with Priority Based Method (SETI@home) International Conference on Autonomic Computing 2005
Comparison with Priority Based Method (FreeLoader) International Conference on Autonomic Computing 2005
Presentation Roadmap • Introduction • Model and approach • System implementation • Performance results • Conclusion and future work International Conference on Autonomic Computing 2005
Conclusion and Future Work • Governor: extensible framework for quantitative performance impact control • Contains actual performance impact • Proactively consume idle resources • Self-adaptive • OS-independent and low-overhead • Future work • Connect impact control with user interfaces • Studying memory resource throttling • Evaluating with more scavengers International Conference on Autonomic Computing 2005
Resource Utilization and β for Composite International Conference on Autonomic Computing 2005