1112.6128 (Stefano Gallozzi)
Stefano Gallozzi
In the immediate future holographic technology will be available to store a
very large amount of data in HVD (Holographic Versatile Disk) devices. This
technology make extensive use of the WORM (Write-Once-Read-Many) paradigm: this
means that such devices allow for a simultaneous and parallel reading of
millions of volumetric pixels (i.e. voxels). This characteristic will make
accessible wherever the acquired data from a telescope (or satellite) in a
quite-simultaneous way.
With the support of this new technology the aim of this paper is to identify
the guidelines for the implementation of a distributed RAID system, a sort of
"storage block" to distribute astronomical data over different geographical
sites acting as a single remote device as an effect of a property of
distributed computing, the abstraction of resources. The end user will only
have to take care on connecting in a opportune and secure mode (using personal
certificates) to the remote device and will have access to all (or part) of
this potential technology.
A Storage-Block+Services engineered on such a platform will allow rapid
scalability of resources, creating a "network-distributed cloud" of services
for an instrument or a mission. It is recommended the use of a dedicated
grid-infrastructure within each single cloud to enhance some critical tasks and
to speed-up services working on the redundant, encrypted and compressed
scientific data. The power, the accessibility, the degree of parallelism and of
redundancy will only depend on the number of distributed storage-blocks: the
higher this amount, the greater will be throughput of the IT-system. A
storage-block of this kind is a meeting point between two technologies and two
antithetical computing paradigms: the Grid-Computing and Cloud-Computing.
View original:
http://arxiv.org/abs/1112.6128
No comments:
Post a Comment