Unistore: Project Updates Presenter: Wei Xie Project Members: Jiang Zhou, Mark Reyes, Jason Noble, David Cauthron and Yong Chen Data-Intensive Scalable Computing Laboratory(DISCL) Computer Science Department Texas Tech University We are grateful to the Nimboxx and the Cloud and Autonomic Computing site at Texas Tech University for the valuable support for this project

Unistore Overview To build a unified storage architecture (Unistore) for Cloud storage systems with the co-existence and efficient integration of heterogeneous HDDs and SCM (Storage Class Memory) devices Prototype development based on Sheepdog and/or Ceph Data distribution management and workload characterization Data Placement Component Characterization Component I/O Pattern Random/Sequential Read/write Hot/cold Workloads Access patterns guide ----- Meeting Notes (4/8/15 14:37) ----- Objective slide. ----- Meeting Notes (4/8/15 15:09) ----- unitore: design, idea implement on sheepdog title change to unistore objective and design Prototype developement based on sheepdog distributed store for vm. Component reflect objective. Placement Algorithm Modified Consistent Hash Devices Characteristics Bandwidth Throughput Replication Algorithm Pattern-directed Replication

Project Updates 2 new papers completed and submitted: Pattern-directed Replication Scheme to ICPP2016 SUORA to SC16 2 new papers under preparation: Version consistent hash Tiered-CRUSH: in preparation for SoCC16 Simulation code and prototype developed to evaluate the proposed schemes Proposed schemes improve the performance of heterogeneous storage systems and maintain the balanced storage utilization

Tiered-CRUSH CRUSH (algorithm used in Ceph) ensures data placed across multiple independent locations to improve data availability Tiered-CRUSH integrates storage tiering into the CRUSH data placement Access frequency of object recorded per volume, hotter data more likely to be placed on faster tiers Implemented in a benchmarks tool compiled with the CRUSH library functions Simulation showed that data distribution uniformity can be maintained Simulation shows 1.5 to 2X improvement in overall bandwidth in our experimental settings

Version Consistent Hashing Scheme Build versions into the virtual nodes Avoid data migration when adding nodes or node fails Maintain efficient data lookup Data lookup algorithm Performance improvement: v1: 1,2 v2: 4,1 v3: 4,6 v4: 4,6 Lookup locations: {4, 6, 1, 2}

Pattern-directed Replication Trace object I/O requests when executing applications Trace analysis, correlation finding and object grouping Reorganize objects for replication in the background for better performance

Conclusions Tiered-CRUSH algorithm achieves better IO performance and higher data availability at the same time for heterogeneous storage system Version consistent hashing scheme for improving manageability of data center PRS for high performance data replication by reorganizing the placement of data replications

On-going/Future Work Implement/evaluate the proposed schemes in Sheepdog (currently simulation-based) Instrument Sheepdog with Lttng framework for more flexible tracing capability

http://cac.ttu.edu/, http://discl.cs.ttu.edu/ Thank You Please visit: http://cac.ttu.edu/, http://discl.cs.ttu.edu/ Acknowledgement: The CAC@TTU is funded by the National Science Foundation under grants IIP-1362134 and IIP-1238338.

Please take a moment to fill out your L.I.F.E. forms. http://www.iucrc.com Select “Cloud and Autonomic Computing Center” then select “IAB” role. What do you like about this project? What would you change? (Please include all relevant feedback.)