200 likes | 333 Views
Online Feedback-based Estimation of Dynamic Page Service Time. Ashwini Kumar Kaushik Veeraraghavan Benjamin Wester Kang Shin. Motivation. Dynamic pages Increasingly prevalent Pages difficult to cache Service time applications Differentiated QoS (prioritizing requests) Load balancing
E N D
Online Feedback-based Estimation of Dynamic Page Service Time Ashwini Kumar Kaushik Veeraraghavan Benjamin Wester Kang Shin
Motivation • Dynamic pages • Increasingly prevalent • Pages difficult to cache • Service time applications • Differentiated QoS (prioritizing requests) • Load balancing • Virtual host services • Estimates: credit card payment times 2
Idea • History • Maintain records of past service times • Predict based on existing records • Assume a correlation between past and future • What is the invariant property? • What system state can we store to track it? • We explore three estimators and their design 3
Outline • Motivation • Design & Implementation • Evaluation • Conclusion and Future Work 4
History • Maintain per-URL fixed-size history table • Data depends on the estimator used • Tag incoming requests • Update history when request processing finishes 5
Sirocco 7
Outline • Motivation • Design & Implementation • Evaluation • Conclusion and Future Work 9
Evaluation • How close are our estimators? • Load patterns • Steady load: httperf • 50ms / request • Changing load: SURGE 10
Average Estimator (steady) • Request takes ~35ms to complete • Estimator should not be too responsive 11
Average Estimator (changing) • Each point averages 20 requests • Vertical bars indicate the addition of a handling thread 12
Average Estimator • How to read the graph: • Enters system: t = 5.4s • Estimated service time: 1.6s • Real service time: 4.9s 13
Average Estimator • History becomes out-of-date • Base estimation on the current state of the system 14
STQ Estimator • It’s better than the Average Estimator… • Inaccurate around a thread change 15
STQ Estimator • Estimations will be inaccurate unless the estimator knows about the coming change in the number of threads • After a change, recently-completed requests show a mixed view of system state and will pollute the history 16
STQT Estimator • Overshoots target because of a polluted history • Fix: Integrate request times across the thread change 17
Outline • Motivation • Design & Implementation • Evaluation • Conclusion and Future Work 18
Concluding Remarks • Takeaways • Don’t adapt to transient delays • Use current state along with the history • Be aware of underlying changes • Future Directions • Extrapolate requests’ service times • URL service time as a distribution 19