Mime: a high performance parallel storage device with strong recovery guarantees

Mime is a shadow-writing disk storage architecture that uses late binding of data to disk locations to improve performance. This results in a simple design with strong atomicity guarantees and a rich set of transaction-like capabilities.The shadowing system in Mime is designed to avoid synchronous updates of metadata during normal operation. Instead, metadata is recovered using an efficient combination of logging and inverted indices. Mime can be used to transparently improve the performance and failure characteristics of existing file systems. The extensions that it makes to typical storage semantics, together with its high performance offer ways to simplify file system implementations. You must love Mime ... —Richard Wagner, Siegfried, Scene I

[1]  Irving L. Traiger,et al.  The Recovery Manager of the System R Database Manager , 1981, CSUR.

[2]  Scott D. Carson,et al.  A system for adaptive disk rearrangement , 1990, Softw. Pract. Exp..

[3]  A. J. Kondoff.  The MPE XL data management system exploiting the HP precision architecture for HP's next generation commercial computer systems , 1988, Digest of Papers. COMPCON Spring 88 Thirty-Third IEEE Computer Society International Conference.

[4]  Andreas Reuter,et al.  Performance analysis of recovery techniques , 1984, TODS.

[5]  J. Wilkes.  DataMesh-parallel storage systems for the 1990s , 1991, [1991] Digest of Papers Eleventh IEEE Symposium on Mass Storage Systems.

[6]  J. Wilkes.  DataMeshTM — scope and objectives : a commentary , 1989 .

[7]  Mary Baker,et al.  Non-volatile memory for fast, reliable file systems , 1992, ASPLOS V.

[8]  Michael J. Carey,et al.  A recovery algorithm for a high-performance memory-resident database system , 1987, SIGMOD '87.

[9]  Chris Ruemmler,et al.  Disk Shuffling , 1991 .

[10]  Sanjeev Setia,et al.  Optimal Write Batch Size in Log-Structured File Systems , 1994, Comput. Syst..

[11]  Michael Stonebraker,et al.  Implementation techniques for main memory database systems , 1984, SIGMOD '84.

[12]  Kwok-Yan Lam.  An implementation for small databases with high availability , 1991, OPSR.

[13]  Evangelos P. Markatos,et al.  Implementation Issues for the Psyche Multiprocessor Operating System , 1989, Comput. Syst..

[14]  Ruby B. Lee.  Precision architecture , 1989, Computer.

[15]  Samuel J. Leffler,et al.  The design and implementation of the 4.3 BSD Unix operating system , 1991, Addison-Wesley series in computer science.

[16]  Gail E. Kaiser,et al.  Concurrency control in advanced database applications , 1991, CSUR.

[17]  Michael B. Jones,et al.  A simple and efficient implementation of a small database , 1987, SOSP '87.

[18]  Michael Stonebraker,et al.  Transaction Support in Read Optimizied and Write Optimized File Systems , 1990, VLDB.

[19]  Mendel Rosenblum,et al.  The design and implementation of a log-structured file system , 1991, SOSP '91.

[20]  John Wilkes,et al.  UNIX Disk Access Patterns , 1993, USENIX Winter.

[21]  Cyril U. Orji,et al.  Distorted mirrors , 1991, [1991] Proceedings of the First International Conference on Parallel and Distributed Information Systems.

[22]  Partha Dasgupta,et al.  The Clouds distributed operating system: functional description, implementation details and related work , 1988, [1988] Proceedings. The 8th International Conference on Distributed.