@inproceedings{1ba9e4cab1794a4cb545adbde01ada24,
title = "Phoenix: Making data-intensive grid applications fault-tolerant",
abstract = "A major hurdle facing data intensive grid applications is the appropriate handling of failures that occur in the grid-environment. Implementing the fault-tolerance transparently at the grid-middleware level would make different data intensive applications fault-tolerant without each having to pay a separate cost and reduce the time to grid-based solution for many scientific problems. We analyzed the failures encountered by four real-life production data intensive applications: NCSA image processing pipeline, WCER video processing pipeline, US-CMS pipeline and BMRB BLAST pipeline. Taking the result of the analysis into account, we have designed and implemented Phoenix, a transparent middleware-level fault-tolerance layer that detects failures early, classifies failures into transient and permanent and appropriately handles the transient failures. We applied our fault-tolerance layer to a prototype of the NCSA image processing pipeline and considerably improved the failure handling and report on the insights gained in the process.",
author = "George Kola and Tevfik Kosar and Miron Livny",
year = "2004",
doi = "10.1109/GRID.2004.51",
language = "English",
isbn = "0769522564",
series = "Proceedings - IEEE/ACM International Workshop on Grid Computing",
publisher = "IEEE Computer Society",
pages = "251--258",
booktitle = "Proceedings - Fifth IEEE/ACM International Workshop on Grid Computing",
address = "United States",
note = "5th IEEE/ACM International Workshop on Grid Computing, GRID 2004 ; Conference date: 08-11-2004 Through 08-11-2004",
}