Total Recall

Total Recall

TotalRecall is peer-to-peer storage system that is capable to automatically manage its availability in dynamic changing environment. It is able to perform availability prediction based on empirical results. It has redundancy management feature, which is able to choose between replication, erasure code, and hybrid techniques based on system condition. It is able to repair itself (dynamic repair) automatically when hosts leave the system and decreasing redundancy. However, TotalRecall is not symmetry. It introduces three types of host in its implementation: master host, storage host and client host.

TotalRecall’s lazy repair with erasure code is is suitable for Volunteer Computing environment since it is claimed to have good performance for highly dynamic and highly unavailable environment. However, the paper that describes TotalRecall does not really mention about the security aspect of this storage system except of the usage of erasure code to protect the data. Overall, it has potential for Volunteer Computing environment if the security aspect of TotalRecall is designed and implemented fully.


Peer-to-peer nature of Total Recall implies high scalability. It offers flexibility for the system administrator to specify availability target. Able to handle highly dynamic and highly unavailable environment by using lazy repair with erasure code technique


Security aspect of TotalRecall is not really designed and implemented fully

Volunteer Computing Suitability

Total Recall’s lazy repair with erasure code is suitable and has potential to be used in Volunteer Computing system as long as the security aspect of Total Recall is designed and implemented fully.

decentralized_storage_systems/total_recall.txt · Last modified: 2012/04/23 00:58 by julia
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 3.0 Unported
Recent changes RSS feed Donate Powered by PHP Valid XHTML 1.0 Valid CSS Driven by DokuWiki