![](bg5.png)
delete the data and modify the ASN’s location in-
formation.
Update: When users need to update their data, they
send their update command to the DSC. If the data
that need to be updated are stored in the ASN, the
system will compare the ASN with the DSC. If the
load of the DSC is lighter, the DSC will deal with
the update request. Otherwise, the ASN will do it.
After the ASN modify the data, it should update the
use frequency of the data in the DSC. Then the data
synchronization will happen between the ASN and
the DSC. Whether or not the data modification op-
eration happens in the ASN or DSC, the system will
check the metadata of the data according to the pre-
set strategies.
4 VMS MIGRATION
When the DSC adjusts the underlying storage archi-
tecture, data migration has two kinds, one is data
migrate from P2P storage network to Master-Slave
storage network, the other is contrary. For the first
kinds, when a common VPN needs to migrate to
Master-Slave storage network, the node only needs
to exit the P2P storage network and join the Master-
Slave storage network as a new node. Then the
VMN of the corresponding Master-Slave storage
network updates the related metadata information of
each data block in the migrated node and the meta-
data of the use frequency and the location informa-
tion of the ASN will be reserved in the virtual man-
agement node. The system will delete the original
routing table of this node which is used in the P2P
storage network, but the data information of users
will not be deleted. So these data can be visited both
from the P2P storage network and the Master-Slave
storage network. For the second kinds, when the
VSNs of the Master-Slave storage network needs to
migrate to the P2P storage network, the node only
needs to exit the Master-Slave storage network and
join the P2P storage network as a new node. Then
the system will initialize the routing table. Besides,
the use frequency and the ASN’s location informa-
tion in the metadata will be copied into this route
table from the VMN.
5 CONCLUSIONS
The main research content of this paper is that we
have presented a open cloud storage architecture
model which can dynamically configure the underly-
ing storage architecture and process the hotspot data
through ASNs. At last, We have discussed the con-
sistency and migration problems of cloud storage
system.
For the future work, we plan to research our pro-
posed architecture in the following two ways, (1)
building the model of the ASNs and simulating with
Cloudsim (Buyya.etc, 2009) and neural network, and
(2) building the model of the underlying storage
architecture and simulating through the P2P simula-
tion tools such as P2Psim (Montresor.etc, 2009).
ACKNOWLEDGEMENTS
We thank Mrs. Ning Wang and Mr. Ming Chen for
their helpful discussions. This work was supported
by the National High-Tech Research and Develop-
ment Plan of China under Grant No.2009AA01A402,
the Natural Science Foundation of Hubei Province
of China under Grant No.2010CDB01601, and the
Fundamental Research Funds for the Central Uni-
versities of China under Grant No.
HUST2010MS065.
REFERENCES
Ghemawat, S., Gobioff, H., Leung, S., 2003. "The Google
file system," ACM SIGOPS Operating Systems Review,
vol. 37, no.5, pp. 29-43.
Decandia, G., Hastorun, D., Jampani, M., .etc, 2007. "Dy-
namo: Amazon's highly available key-value store," in
Operating Systems Review (ACM), pp. 205-220.
Harnik, D., Naor, D., Segall, I., 2009. "Low power mode
in cloud storage systems," in IEEE International Sym-
posium on Parallel & Distributed Processing, pp. 1-8.
Abu-Libdeh, H., Princehouse, L., etc, 2010. "RACS: A
case for cloud storage diversity," in the 1st ACM Sym-
posium on Cloud Computing, pp. 229-239.
Bowers, K., Juels, A., Oprea, A., 2009. "HAIL: A high-
availability and integrity layer for cloud storage," in
the ACM Conference on Computer and Communica-
tions Security, pp. 187-198.
Pallis, G., Vakali, A., 2006. "Insight and perspectives for
Content Delivery Networks," Communications of the
ACM, vol. 49,no.1, pp. 101-106.
Barham, P., Dragovic, B., Fraser, K., Hand, S., .etc, 2003.
"Xen and the art of virtualization," in Operating Sys-
tems Review (ACM), pp. 164-177.
Buyya, R., Ranjan, R., Calheiros, R., 2009. "Modeling and
simulation of scalable cloud computing environments
and the cloudsim toolkit: Challenges and opportuni-
ties," in International Conference on High Perform-
ance Computing and Simulation, pp. 1-11.
Montresor, A., Jelasity, M., 2009. "Peersim: A scalable
p2p simulator," in IEEE P2P'09 - 9th International
Conference on Peer-to-Peer Computing, pp. 99-100.
CLOSER 2011 - International Conference on Cloud Computing and Services Science
524