Filters








7 Hits in 7.1 sec

Towards Scalable Checkpoint Restart: A Collective Inline Memory Contents Deduplication Proposal

Bogdan Nicolae
2013 2013 IEEE 27th International Symposium on Parallel and Distributed Processing  
This paper contributes with a novel collective memory contents deduplication scheme that attempts to identify and eliminate duplicate memory pages before they are saved to storage.  ...  For a large class of applications that run for a long time and are tightly coupled, Checkpoint-Restart (CR) is the only feasible method to survive failures.  ...  This paper contributes with a collective inline deduplication technique that identifies and eliminates duplicate memory contents at page level granularity both locally and between different application  ... 
doi:10.1109/ipdps.2013.14 dblp:conf/ipps/Nicolae13 fatcat:ciyjjh3pdraavbfonxz44y6j4e

The design and implementation of a multi-level content-addressable checkpoint file system

Abhishek Kulkarni, Adam Manzanares, Latchesar Ionkov, Michael Lang, Andrew Lumsdaine
2012 2012 19th International Conference on High Performance Computing  
In this paper, we describe the design and implementation of cento, a multilevel, content-addressable checkpoint file system for large-scale HPC systems. cento achieves in-flight checkpoint data reduction  ...  across all compute nodes through compression and elimination of duplicate blocks over a series of checkpoints.  ...  Acknowledgment This work was supported, in part, by a grant from the Lilly Endowment; National Science Foundation NSF ANI-0330620 and EIA-0202048; and U.S. Department of Energy DE-FC02-06ER25750.  ... 
doi:10.1109/hipc.2012.6507514 dblp:conf/hipc/KulkarniMILL12 fatcat:iowg66kb55f2zpjnzx5afep3fq

Support for configuration and provisioning of intermediate storage systems

Lauro Beltrão Costa
2014
By relying on the target application's characteristics, the proposed mechanisms can accelerate the exploration of the configuration space. [...]  ...  These platforms typically offer a centralized persistent backend storage system.  ...  The disadvantage of content-based boundaries is the high cost of analyzing all the data content in order to define the chunks. Inline data deduplication.  ... 
doi:10.14288/1.0165568 fatcat:5t2jmzj4ifc5pio3jaxzyvv5t4

Storage system tracing and analysis

Dutch T. Meyer
2015
This thesis describes a methodology to facilitate the collection, analysis, and publication of large traces of file system activity and structure so that organizations can perform regular analysis of their  ...  One reason for this deficiency is that studying clusters of storage systems operating at scale requires large data repositories that are difficult to collect, manage, and query.  ...  Periodically, the commit log is collapsed into a checkpoint to save space, and any stale entries are collected.  ... 
doi:10.14288/1.0166682 fatcat:whuaexcrtzgvrc67kdlit4g2sa

Composing and Decomposing OS Abstractions [article]

James Litton
2020
PTx is a new high-level abstraction for persistence built on top of NVRAM, a new form of persistent byte addressable memory, whereas lwCs are a new OS abstraction that enables fine-grained intra-process  ...  Operating systems (OSes) provide a set of abstractions through which hardware resources are accessed.  ...  keys during a system restart.  ... 
doi:10.13016/auaf-1su4 fatcat:q66e6dyuyvgiredlohinka2nf4

Pipelined XSLT Transformations

Ari Nordström
Proceedings of Balisage: The Markup Conference 2020   unpublished
This paper is a commercial for pipelined XSLT transformations, hoping to convince the reader to move to a liberating step-by-step approach to write your transformations rather than continuing to endure  ...  It all runs in XProc, but knowing XProc is not a requirement (even though it's fun in its own right); XSLT is enough to enjoy pipelined XSLTs.  ...  from a crash (or forceful restart).  ... 
doi:10.4242/balisagevol25.nordstrom01 fatcat:2d76lampg5hmndytvcocqyqmsy

Mining big data streams for multiple concepts

Christian Bockermann, Technische Universität Dortmund, Technische Universität Dortmund
2015
Restart of nodes and replay of data for fault-tolerance 5. Deduplication of messages for exactly-once semantics.  ...  Using a volatile in-memory buffering, the buffer content is lost upon failure of the broker. Such a broker is easy to implement and handles failure in a gap recovery manner (cf. Section 2.3.2.2).  ...  The package is based around a central ImageRGB data structure, which provides access to a single, decorded video frame in bitmap form.  ... 
doi:10.17877/de290r-16437 fatcat:ltjowwtrb5drhj7k7yotbiitke