srcmap energy proportional storage using dynamic
play

SRCMap: Energy Proportional Storage using Dynamic Consolidation - PowerPoint PPT Presentation

Motivation Design Evaluation Conclusions & Future Work SRCMap: Energy Proportional Storage using Dynamic Consolidation Akshat Verma 1 Ricardo Koller 2 Luis Useche 2 Raju Rangaswami 2 1 IBM Research, India 2 School of Computing and


  1. Motivation Design Evaluation Conclusions & Future Work SRCMap: Energy Proportional Storage using Dynamic Consolidation Akshat Verma 1 Ricardo Koller 2 Luis Useche 2 Raju Rangaswami 2 1 IBM Research, India 2 School of Computing and Information Sciences College of Engineering and Computing FAST Conference, 2010 1 / 21

  2. Motivation Design Evaluation Conclusions & Future Work ◮ Current power density of data centers is 100 W/sq.ft & increasing 15-20% per year. ◮ Storage consume 10-25% of computing equipment. ◮ Storage load low (10-30%), but still peak power consumed. ◮ CPUs are more energy proportionality than storage. ◮ Consolidation is a well known technique for energy proportionality in virtualized servers. 2 / 21

  3. Motivation Design Evaluation Conclusions & Future Work Storage Consolidation? Can we use a storage virtualization layer to design a practical energy proportional storage system? ◮ Storage virtualization I/O indirection useful for consolidation. Challenge Moving logical volumes from one device to another is prohibitively expensive. 3 / 21

  4. Motivation Design Evaluation Conclusions & Future Work Background: Storage Virtualization 4 / 21

  5. Motivation Design Evaluation Conclusions & Future Work Outline 1. Motivation 2. Design 3. Evaluation 4. Conclusions & Future Work 5 / 21

  6. Motivation Design Evaluation Conclusions & Future Work Workloads mail Our department mail server. web-vm Virtual machine hosting two web-servers: CS web-mail & online course management. homes NFS server that serves the home directories for our research group. Block traces collected downstream of an active page cache for three weeks. 6 / 21

  7. Motivation Design Evaluation Conclusions & Future Work Observations Observation 1 The active data set is only a small fraction of total storage used. (about 1.5-6.5%) Observation 2 There is a significant variability in I/O load. (5-6 orders of magnitude) Observation 3 More that 99% of the working set consist of really popular & recently accessed data. 7 / 21

  8. Motivation Design Evaluation Conclusions & Future Work Overview 8 / 21

  9. Motivation Design Evaluation Conclusions & Future Work Our Approach Initialization Sample Characterize the logical volume to find the working set. Replicate Create multiple working-set replicas in various physical volumes’ scratch space. Consolidate Based on I/O workload intensity, activate a sub-set of physical volumes and serve workloads either from original copies or working set replicas on these active disks. Every H hours 9 / 21

  10. Motivation Design Evaluation Conclusions & Future Work Goals → Solutions Goal Solution Fine grained proportionality Multiple replica targets. Low space overhead Instead of entire volumes, only working-sets are replicated. Reliability Coarse-grained consolidation intervals. (hours) Workload Adaptation Update working set replicas with new data that lead to read misses. Heterogeneity support Performance-power ratio ac- counted for in the replica place- ment benefit function. 10 / 21

  11. Motivation Design Evaluation Conclusions & Future Work SRCMap work-flow Event Response Initialization Detect working-sets of logical volumes & create replicas . Every H hours Identify what volumes and replicas to activate the next H hours . Change in workload Same as initialization. 11 / 21

  12. Motivation Design Evaluation Conclusions & Future Work Replica Placement ◮ Replication benefit based on: 1. Working set stability 2. Average load 3. Power efficiency of primary physical volume. 4. Working set size ◮ Assign space with priorities based on benefit. ◮ Update replica creation benefit as additional replicas are created. ◮ Algorithm executes until scratch spaces are full. 12 / 21

  13. Motivation Design Evaluation Conclusions & Future Work Active Replica Identification ◮ Calculate predicted aggregate workload IOPS. ◮ Compute minimum number of volumes to serve the aggregate IOPS. ◮ Identify replicas for inactive volumes. ◮ The number of active disks is incremented by one in case no active replica has been identified for some inactive volume. 13 / 21

  14. Motivation Design Evaluation Conclusions & Future Work Workloads & Configuration ◮ 8 workloads to independent data volumes. ◮ Mix of web-servers of our CS department, and file server, SVN, and WiKi for our research group. ◮ H = 2. Change active replicas every 2 hours. ◮ Two minute disk time-outs. ◮ Working sets & replicas based on three week workload history. ◮ We report results of replaying the next 8 most active hours in the traces. ◮ We assume an oracle for estimation of load during each consolidation interval. 14 / 21

  15. Motivation Design Evaluation Conclusions & Future Work Storage test-bed ◮ One machine with 8 SATA ports. ◮ Intel P4 HT 3GHz, 1GB memory. ◮ Trace played back using btreplay . ◮ Dedicated power supply for disks connected to power meter. ◮ Watts up? PRO power meter: measures power every second with resolution of 0.1W. 15 / 21

  16. Motivation Design Evaluation Conclusions & Future Work Power 70 60 Baseline - On Watts 50 SRCMap 40 30 20 6 # Disks On 4 2 0 0 1 2 3 4 5 6 7 8 Hour ◮ Power consumption measured every second & active disks every 5 seconds. Disks off Power Saved 4.33 23.5 (35.5%) 16 / 21

  17. Motivation Design Evaluation Conclusions & Future Work Response time 1 1 0.95 0.95 P(Response Time < x) P(Response Time < x) 0.9 0.9 0.85 0.85 0.8 0.8 0.6 0.6 0.4 0.4 SRCMap 0.2 0.2 Baseline - On 0 0 10 -1 10 0 10 1 10 2 10 3 10 4 Response Time (msec) ◮ After 1ms, Baseline - On demonstrate better performance. ◮ 8% of requests with latencies ≥ 10ms. ◮ 2% of requests with latencies ≥ 100ms. ◮ Synchronization I/Os issued at beginning of each interval. ◮ Replaying without sync I/Os follows Baseline-On more closely. 17 / 21

  18. Motivation Design Evaluation Conclusions & Future Work Energy proportionality 60 25.65 + 0.393*x ◮ One point for each 2-hour 55 interval in 24-hour 50 Power (Watts) duration. 45 40 ◮ Load Factor : Load 35 relative to the assumed 30 volume maximum load 25 capacity. 0 10 20 30 40 50 60 70 80 90 Load factor (%) SRCMap is able to achieve close to N-level proportionality for a system with N physical volumes. 18 / 21

  19. Motivation Design Evaluation Conclusions & Future Work Conclusions ◮ We proposed and evaluate SRCMap, a storage virtualization solution for energy proportional storage. ◮ SRCMap establishes the feasibility of energy proportional storage systems. ◮ SRCMap meets all goals we set out to achieve energy proportional storage: � Low space overhead � Reliability � Workload adaptation � Heterogeneity support � Fine grain energy proportionality 19 / 21

  20. Motivation Design Evaluation Conclusions & Future Work Future Work ◮ Models to predict I/O workload intensity. ◮ Models that estimate the performance impact of storage consolidation. ◮ Investigate the presence of workload correlation for better workload estimation and consolidation decision. ◮ Optimizing the scheduling of synchronization I/Os to minimize impact on foreground requests. 20 / 21

  21. Motivation Design Evaluation Conclusions & Future Work http://dsrl.cs.fiu.edu/projects/srcmap/ Questions? 21 / 21

  22. Motivation Design Evaluation Conclusions & Future Work Related Work ◮ Singly redundant schemes: Spin down volumes with redundant data during low load. ◮ Geared RAIDs: Redundancy on several disks and each disk spun down represents a gear shift. ◮ Caching systems: Cache of popular data on additional storage. ◮ Write Offloading: Increase disk idle periods by redirecting writes to alternate locations.

  23. Motivation Design Evaluation Conclusions & Future Work Other Methods SRCMap(L0) Caching-1 90 Power (Watts) Replication Caching-2 60 30 Remaps 2 0 Load 90 0 0 2 4 6 8 10 12 14 16 18 20 22 24 Hour

Recommend


More recommend