A comparison of Flashcache with IQ-Twemcached

Person-to-person cloud service providers such as Facebook use Host-side (HsC) and Application-side (AsC) caches to enhance performance. Using Facebook's Flashcache as the representative of HsC and IQ-Twemcached as the representative of AsC, this study quantifies their tradeoffs using both a read-heavy and a write-heavy workload. Obtained results show Flashcache provides significant benefit for I/O intensive workloads, e.g., read-heavy workloads when the application working set does not fit in memory. IQ-Twemcached is most suitable for those workloads that fully utilize the CPU of the server hosting the database management system. For some workloads, the performance enhancement observed with the two caches deployed together is several folds higher than the sum of the performance benefit realized by each cache individually.

[1]  Shahram Ghandeharizadeh,et al.  A Mid-Flight Synopsis of the BG Social Networking Benchmark , 2013, WBDB.

[2]  Xiaoyun Zhu,et al.  VFRM: Flash Resource Manager in VMware ESX Server , 2014, 2014 IEEE Network Operations and Management Symposium (NOMS).

[3]  Steve Byan,et al.  Mercury: Host-side flash caching for the data center , 2012, 012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST).

[4]  Shahram Ghandeharizadeh,et al.  Expedited Benchmarking of Social Networking Actions with Faster Data Load Techniques , 2013 .

[5]  E. Hensbergen.  Dynamic Policy Disk Caching for Storage Networking , 2006 .

[6]  Shahram Ghandeharizadeh,et al.  A comparison of two physical data designs for interactive social networking actions , 2013, CIKM.

[7]  Michael J. Franklin.  Client Data Caching: A Foundation for High Performance Object Oriented Database Systems , 1996, The Kluwer international series in engineering and computer science.

[8]  Shahram Ghandeharizadeh,et al.  Cache augmented database management systems , 2013, DBSocial '13.

[9]  Donald Kossmann,et al.  On the Design and Scalability of Distributed Shared-Data Databases , 2015, SIGMOD Conference.

[10]  Tony Tung,et al.  Scaling Memcache at Facebook , 2013, NSDI.

[11]  M. Tamer Özsu,et al.  An Adaptive Data-Shipping Architecture for Client Caching Data Management Systems , 2004, Distributed and Parallel Databases.

[12]  Janet L. Wiener,et al.  Open data challenges at Facebook , 2015, 2015 IEEE 31st International Conference on Data Engineering.

[13]  Sandy Irani,et al.  A demonstration of KOSAR: an elastic, scalable, highly available SQL middleware , 2014, Middleware.

[14]  Carlo Curino,et al.  OLTP-Bench: An Extensible Testbed for Benchmarking Relational Databases , 2013, Proc. VLDB Endow..

[15]  David J. DeWitt,et al.  A Study of Three Alternative Workstation-Server Architectures for Object Oriented Database Systems , 1990, VLDB.

[16]  Private Communications , 2001 .

[17]  Samuel Madden,et al.  Transactional Consistency and Automatic Management in an Application Data Cache , 2010, OSDI.

[18]  Shahram Ghandeharizadeh,et al.  Strong consistency in cache augmented SQL systems , 2014, Middleware.

[19]  Jonathan Goldstein,et al.  MTCache: transparent mid-tier database caching in SQL server , 2004, Proceedings. 20th International Conference on Data Engineering.

[20]  J. T. Robinson,et al.  On optimistic methods for concurrency control , 1979, TODS.

[21]  Samuel Madden,et al.  A Trigger-Based Middleware Cache for ORMs , 2011, Middleware.

[22]  Hamid Pirahesh,et al.  DBCache: middle-tier database caching for highly scalable e-business architectures , 2003, SIGMOD '03.

[23]  Margo I. Seltzer,et al.  Flash Caching on the Storage Client , 2013, USENIX Annual Technical Conference.

[24]  Sandy Irani,et al.  Memory Hierarchy Design for Caching Middleware in the Age of NVM , 2015 .

[25]  Shahram Ghandeharizadeh,et al.  An Evaluation of Alternative Physical Graph Data Designs for Processing Interactive Social Networking Actions , 2014, TPCTC.

[26]  Shahram Ghandeharizadeh,et al.  BG: A Benchmark to Evaluate Interactive Social Networking Actions , 2013, CIDR.

[27]  Michael J. Franklin,et al.  Client Data Caching , 1996 .

[28]  Goetz Graefe,et al.  The five-minute rule twenty years later, and how flash memory changes the rules , 2007, DaMoN '07.

[29]  Nikolas Ioannou,et al.  Flash-Conscious Cache Population for Enterprise Database Workloads , 2014, ADMS@VLDB.