The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Neste artigo, propomos um novo sistema de arquivos denominado Ad-hoc Filesystem que tem como alvo redes sem fio ad-hoc. Ad-hoc Filesystem é um sistema de arquivos sem servidor que gera automaticamente espaço compartilhado temporário entre várias máquinas móveis quando elas se reúnem em um intervalo comunicável. O espaço gerado está disponível gratuitamente para as máquinas participantes e pode ser utilizado para qualquer trabalho temporário. O projeto do sistema de arquivos Ad-hoc é fortemente motivado pelas recentes tecnologias de rede sem fio e pelos avanços das técnicas de rede ad-hoc. No entanto, visar uma rede tão instável nos obriga a um design completamente diferente dos sistemas de arquivos existentes. Projetamos um protótipo inicial de sistema de arquivos Ad-hoc e avaliamos os resultados da simulação. Nosso projeto é fortemente baseado na suposição de que as pessoas que desejam trabalhar juntas formariam um grupo estável em um intervalo, e a replicação de dados em duas máquinas diferentes seria suficiente para fornecer um nível adequado de disponibilidade. Conseqüentemente, o Ad-hoc Filesystem distribui arquivos entre várias máquinas e os duplica, a fim de manter os arquivos disponíveis mesmo que algumas das máquinas participantes saiam arbitrariamente do alcance de comunicação. As entradas do diretório são mantidas como um mecanismo de estado suave mantido pela troca de pacotes de transmissão. Os resultados da simulação mostram que o uso de transmissão para manter o estado do sistema dificilmente afeta o desempenho geral do sistema, e otimizações tais que atrasar as respostas com transmissão e detectar outros pacotes promiscuamente durante o atraso reduzem significativamente a sobrecarga. Além disso, o resultado indica que nossa estratégia que mantém duas réplicas para cada dado promete fornecer disponibilidade. Embora investigações adicionais baseadas em implementação real continuem sendo um trabalho importante, acreditamos que o protótipo tem uma contribuição para concretizar a possibilidade de sistemas de arquivos ad-hoc, sintetizando vários trabalhos anteriores em áreas como sistemas de arquivos de rede, replicação de servidores e redes sem fio ad-hoc.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Kinuko YASUDA, Tatsuya HAGINO, "Design and Concept of Ad-hoc Filesystem" in IEICE TRANSACTIONS on Communications,
vol. E84-B, no. 4, pp. 920-929, April 2001, doi: .
Abstract: In this paper, we propose a new filesystem named Ad-hoc Filesystem which targets ad-hoc wireless networks. Ad-hoc Filesystem is a serverless filesystem which automatically generates temporary shared space among multiple mobile machines when they gather in a communicable range. The generated space is freely available for participating machines and can be used for any temporary work there. The design of Ad-hoc Filesystem is strongly motivated by the recent wireless network technologies and advances of ad-hoc network techniques. However, targeting such an unstable network forces us a completely different design from existing filesystems. We have designed an initial prototype of Ad-hoc Filesystem and have evaluated the simulation results. Our design is strongly based on an assumption such that people who wish to work together would form a stable group in a range, and replicating data on two different machines would be enough to provide a proper level of availability. Hence, Ad-hoc Filesystem distributes files among multiple machines and duplicates them, in order to keep the files available even if some of participating machines arbitrarily leave the communication range. The directory entries are kept as a soft-state mechanism maintained by exchanging broadcast packets. The simulation results show that using broadcast to maintain system state hardly affects the overall system performance, and optimizations such that delaying replies with broadcast and sensing other packets promiscuously during the delay reduce the overhead significantly. Also the result indicates that our strategy that keeps two replicas for each data is promising to provide availability. Although further investigation based on real implementation remains important work, we believe that the prototype has a contribution to realize the possibility of ad-hoc filesystem by synthesizing number of previous works in areas such as network filesystems, server replication and ad-hoc wireless networks.
URL: https://global.ieice.org/en_transactions/communications/10.1587/e84-b_4_920/_p
Copiar
@ARTICLE{e84-b_4_920,
author={Kinuko YASUDA, Tatsuya HAGINO, },
journal={IEICE TRANSACTIONS on Communications},
title={Design and Concept of Ad-hoc Filesystem},
year={2001},
volume={E84-B},
number={4},
pages={920-929},
abstract={In this paper, we propose a new filesystem named Ad-hoc Filesystem which targets ad-hoc wireless networks. Ad-hoc Filesystem is a serverless filesystem which automatically generates temporary shared space among multiple mobile machines when they gather in a communicable range. The generated space is freely available for participating machines and can be used for any temporary work there. The design of Ad-hoc Filesystem is strongly motivated by the recent wireless network technologies and advances of ad-hoc network techniques. However, targeting such an unstable network forces us a completely different design from existing filesystems. We have designed an initial prototype of Ad-hoc Filesystem and have evaluated the simulation results. Our design is strongly based on an assumption such that people who wish to work together would form a stable group in a range, and replicating data on two different machines would be enough to provide a proper level of availability. Hence, Ad-hoc Filesystem distributes files among multiple machines and duplicates them, in order to keep the files available even if some of participating machines arbitrarily leave the communication range. The directory entries are kept as a soft-state mechanism maintained by exchanging broadcast packets. The simulation results show that using broadcast to maintain system state hardly affects the overall system performance, and optimizations such that delaying replies with broadcast and sensing other packets promiscuously during the delay reduce the overhead significantly. Also the result indicates that our strategy that keeps two replicas for each data is promising to provide availability. Although further investigation based on real implementation remains important work, we believe that the prototype has a contribution to realize the possibility of ad-hoc filesystem by synthesizing number of previous works in areas such as network filesystems, server replication and ad-hoc wireless networks.},
keywords={},
doi={},
ISSN={},
month={April},}
Copiar
TY - JOUR
TI - Design and Concept of Ad-hoc Filesystem
T2 - IEICE TRANSACTIONS on Communications
SP - 920
EP - 929
AU - Kinuko YASUDA
AU - Tatsuya HAGINO
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Communications
SN -
VL - E84-B
IS - 4
JA - IEICE TRANSACTIONS on Communications
Y1 - April 2001
AB - In this paper, we propose a new filesystem named Ad-hoc Filesystem which targets ad-hoc wireless networks. Ad-hoc Filesystem is a serverless filesystem which automatically generates temporary shared space among multiple mobile machines when they gather in a communicable range. The generated space is freely available for participating machines and can be used for any temporary work there. The design of Ad-hoc Filesystem is strongly motivated by the recent wireless network technologies and advances of ad-hoc network techniques. However, targeting such an unstable network forces us a completely different design from existing filesystems. We have designed an initial prototype of Ad-hoc Filesystem and have evaluated the simulation results. Our design is strongly based on an assumption such that people who wish to work together would form a stable group in a range, and replicating data on two different machines would be enough to provide a proper level of availability. Hence, Ad-hoc Filesystem distributes files among multiple machines and duplicates them, in order to keep the files available even if some of participating machines arbitrarily leave the communication range. The directory entries are kept as a soft-state mechanism maintained by exchanging broadcast packets. The simulation results show that using broadcast to maintain system state hardly affects the overall system performance, and optimizations such that delaying replies with broadcast and sensing other packets promiscuously during the delay reduce the overhead significantly. Also the result indicates that our strategy that keeps two replicas for each data is promising to provide availability. Although further investigation based on real implementation remains important work, we believe that the prototype has a contribution to realize the possibility of ad-hoc filesystem by synthesizing number of previous works in areas such as network filesystems, server replication and ad-hoc wireless networks.
ER -