Graduated QoS by Decomposing Bursts: Don't Let the Tail Wag Your Server

The growing popularity of hosted storage services and shared storage infrastructure in data centers is driving the recent interest in resource management and QoS in storage systems. The bursty nature of storage workloads raises significant performance and provisioning challenges, leading to increased infrastructure, management, and energy costs. We present a novel dynamic workload shaping framework to handle bursty workloads, where the arrival stream is dynamically decomposed to isolate its bursts, and then rescheduled to exploit available slack. We show how decomposition reduces the server capacity requirements dramatically while affecting QoS guarantees minimally. We present an optimal decomposition algorithm RTT and a recombination algorithm Miser, and show the benefits of the approach by performance evaluation using several storage traces.

[1]  Arif Merchant,et al.  Façade: Virtual Storage Devices with Performance Guarantees , 2003, FAST.

[2]  Walter Willinger,et al.  On the self-similar nature of Ethernet traffic , 1993, SIGCOMM '93.

[3]  Maria E. Gomez,et al.  On the impact of workload burstiness on disk performance , 2001 .

[4]  Evgenia Smirni,et al.  Scheduling for performance and availability in systems with temporal dependent workloads , 2008, 2008 IEEE International Conference on Dependable Systems and Networks With FTCS and DCC (DSN).

[5]  Anand Sivasubramaniam,et al.  Storage performance virtualization via throughput and latency control , 2005, 13th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems.

[6]  Alma Riska,et al.  Long-Range Dependence at the Disk Drive Level , 2006, Third International Conference on the Quantitative Evaluation of Systems - (QEST'06).

[7]  Harrick M. Vin,et al.  Start-time fair queueing: a scheduling algorithm for integrated services packet switching networks , 1996, SIGCOMM '96.

[8]  Ness B. Shroff,et al.  Admission control for statistical QoS: theory and practice , 1999, IEEE Netw..

[9]  Antony I. T. Rowstron,et al.  Everest: Scaling Down Peak Loads Through I/O Off-Loading , 2008, OSDI.

[10]  Scott Shenker,et al.  Analysis and simulation of a fair queueing algorithm , 1989, SIGCOMM 1989.

[11]  Bruce S. Davie,et al.  Deploying IP and MPLS QoS for Multiservice Networks: Theory & Practice , 2007 .

[12]  Walter Willinger,et al.  On the Self-Similar Nature of Ethernet Traffic ( extended version ) , 1995 .

[13]  Qi Zhang,et al.  Load Unbalancing to Improve Performance under Autocorrelated Traffic , 2006, 26th IEEE International Conference on Distributed Computing Systems (ICDCS'06).

[14]  Peter J. Varman,et al.  pClock: an arrival curve based approach for QoS guarantees in shared storage systems , 2007, SIGMETRICS '07.

[15]  Mor Harchol-Balter,et al.  Size-based scheduling to improve web performance , 2003, TOCS.

[16]  Wei Jin,et al.  Interposed proportional sharing for a storage service utility , 2004, SIGMETRICS '04/Performance '04.

[17]  QUTdN QeO,et al.  Random early detection gateways for congestion avoidance , 1993, TNET.

[18]  Prashant J. Shenoy,et al.  Cello: A Disk Scheduling Framework for Next Generation Operating Systems* , 1998, SIGMETRICS '98/PERFORMANCE '98.

[19]  Willy Zwaenepoel,et al.  Cluster reserves: a mechanism for resource management in cluster-based network servers , 2000, SIGMETRICS '00.

[20]  Hui Zhang,et al.  WF/sup 2/Q: worst-case fair weighted fair queueing , 1996, Proceedings of IEEE INFOCOM '96. Conference on Computer Communications.

[21]  Analysis and Simulation of a Fair Queuing Algorithm , 2008 .