Easy Freshness with Pequod Cache Joins

Pequod is a distributed application-level key-value cache that supports declaratively defined, incrementally maintained, dynamic, partially-materialized views. These views, which we call cache joins, can simplify application development by shifting the burden of view maintenance onto the cache. Cache joins define relationships among key ranges; using cache joins, Pequod calculates views on demand, incrementally updates them as required, and in many cases improves performance by reducing client communication. To build Pequod, we had to design a view abstraction for volatile, relationless key-value caches and make it work across servers in a distributed system. Pequod performs as well as other in-memory key-value caches and, like those caches, outperforms databases with view support.

[1]  Douglas Crockford,et al.  The application/json Media Type for JavaScript Object Notation (JSON) , 2006, RFC.

[2]  E. F. CODD,et al.  A relational model of data for large shared data banks , 1970, CACM.

[3]  Eddie Kohler,et al.  Cache craftiness for fast multicore key-value storage , 2012, EuroSys '12.

[4]  Jennifer Widom,et al.  View maintenance in a warehousing environment , 1995, SIGMOD '95.

[5]  Werner Vogels,et al.  Dynamo: amazon's highly available key-value store , 2007, SOSP.

[6]  Parag Agrawal,et al.  Asynchronous view maintenance for VLSD databases , 2009, SIGMOD Conference.

[7]  Sanghyun Park,et al.  A self-managing data cache for edge-of-network web applications , 2002, CIKM '02.

[8]  Frederick Reiss,et al.  TelegraphCQ: Continuous Dataflow Processing for an Uncertain World , 2003, CIDR.

[9]  Tao Yang,et al.  Class-based cache management for dynamic Web content , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[10]  Burton H. Bloom,et al.  Space/time trade-offs in hash coding with allowable errors , 1970, CACM.

[11]  V. S. Subrahmanian,et al.  Maintaining views incrementally , 1993, SIGMOD Conference.

[12]  Amir Shaikhha,et al.  DBToaster: higher-order delta processing for dynamic, frequently fresh views , 2012, The VLDB Journal.

[13]  Michael Stonebraker,et al.  OLTP through the looking glass, and what we found there , 2008, SIGMOD Conference.

[14]  Inderpal Singh Mumick,et al.  Maintenance of Materialized Views: Problems, Techniques, and Applications , 1999, IEEE Data Eng. Bull..

[15]  Sriram Padmanabhan,et al.  DBProxy: a dynamic data cache for web applications , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).

[16]  Surajit Chaudhuri,et al.  Maintenance of Materialized Views: Problems, Techniques, and Applications. , 1995 .

[17]  F. E..  A Relational Model of Data Large Shared Data Banks , 2000 .

[18]  Hui Ding,et al.  TAO: Facebook's Distributed Data Store for the Social Graph , 2013, USENIX Annual Technical Conference.

[19]  Hicham G. Elmongui,et al.  Lazy Maintenance of Materialized Views , 2007, VLDB.

[20]  Surajit Chaudhuri,et al.  Automated Selection of Materialized Views and Indexes in SQL Databases , 2000, VLDB.

[21]  Hans-Arno Jacobsen,et al.  PNUTS: Yahoo!'s hosted data serving platform , 2008, Proc. VLDB Endow..

[22]  Letizia Tanca,et al.  What you Always Wanted to Know About Datalog (And Never Dared to Ask) , 1989, IEEE Trans. Knowl. Data Eng..

[23]  Arun Iyengar,et al.  A scalable system for consistently caching dynamic Web data , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[24]  Per-Åke Larson,et al.  Computing Queries from Derived Relations , 1985, VLDB.

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

[26]  Luping Ding,et al.  Dynamic Materialized Views , 2007, 2007 IEEE 23rd International Conference on Data Engineering.

[27]  Rada Chirkova,et al.  Materialized Views , 2012, Found. Trends Databases.

[28]  Michael Hammer,et al.  Specifying queries as relational expressions , 1974, SIGPLAN '73.

[29]  Jingren Zhou,et al.  Partially Materialized Views , 2005 .

[30]  Raghu Ramakrishnan,et al.  Feeding frenzy: selectively materializing users' event feeds , 2010, SIGMOD Conference.

[31]  Frank Wm. Tompa,et al.  Eeciently Updating Materialized Views , 1986 .

[32]  Frank Wm. Tompa,et al.  Maintaining materialized views without accessing base data , 1988, Inf. Syst..

[33]  Frank Wm. Tompa,et al.  Efficiently updating materialized views , 1986, SIGMOD '86.

[34]  Hosung Park,et al.  What is Twitter, a social network or a news media? , 2010, WWW '10.

[35]  Wilson C. Hsieh,et al.  Bigtable: A Distributed Storage System for Structured Data , 2006, TOCS.

[36]  Yuan Yu,et al.  Dryad: distributed data-parallel programs from sequential building blocks , 2007, EuroSys '07.

[37]  Gang Luo,et al.  Partial Materialized Views , 2007, 2007 IEEE 23rd International Conference on Data Engineering.