1998
DOI: 10.1109/71.737697
|View full text |Cite
|
Sign up to set email alerts
|

On coordinated checkpointing in distributed systems

Abstract: Abstract-Coordinated checkpointing simplifies failure recovery and eliminates domino effects in case of failures by preserving a consistent global checkpoint on stable storage. However, the approach suffers from high overhead associated with the checkpointing process. Two approaches are used to reduce the overhead: First is to minimize the number of synchronization messages and the number of checkpoints, the other is to make the checkpointing process nonblocking. These two approaches were orthogonal in previou… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
3
0
8

Year Published

2002
2002
2009
2009

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 110 publications
(11 citation statements)
references
References 23 publications
(81 reference statements)
0
3
0
8
Order By: Relevance
“…One way to achieve this consistency is through coordinated checkpointing [15]. In coordinated checkpointing, once the decision to checkpoint is made, the program does not progress unless all the checkpoints of all the processes are saved.…”
Section: Application-level Checkpointingmentioning
confidence: 99%
“…One way to achieve this consistency is through coordinated checkpointing [15]. In coordinated checkpointing, once the decision to checkpoint is made, the program does not progress unless all the checkpoints of all the processes are saved.…”
Section: Application-level Checkpointingmentioning
confidence: 99%
“…Porém, a suspensão da aplicação reduz o desempenho do sistema. Na tentativa de se obter um desempenho melhor para a aplicação, os protocolos síncronos não-bloqueantes permitem que todos os processos gravem checkpoints a cada construção consistente sem suspender as atividades da computação [9,7,8,30]. Cao e Singhal propuseram um novo tipo de checkpoint, chamado de checkpoint mutável, que é facilmente manipulado pois pode ser salvo em memória não-estável [7,8].…”
Section: Abordagens Para Checkpointgunclassified
“…Cao e Singhal introduzem o conceito de z-dependência para expressar uma relação de dependência entre processos em dois intervalos de checkpoints [9].…”
Section: Z-dependênciaunclassified
See 2 more Smart Citations