Weighted distributed hash tables

@inproceedings{Schindelhauer2005WeightedDH,
  title={Weighted distributed hash tables},
  author={Christian Schindelhauer and Gunnar Schomaker},
  booktitle={SPAA '05},
  year={2005}
}
We present two methods for weighted consistent hashing also known as weighted distributed hash tables. [...] Key Method By using node copies and different partitions of the hash space, the balance of this scheme approximates the fair weight relationship with high probability. The second method, called the Logarithmic Method, uses a logarithmic weighted distance between the peers and the data to find the corresponding node. For distributing one data element it provides perfect weighted balance.Expand
Atributed consistent hashing for heterogeneous storage systems
TLDR
An attributed consistent hashing (attributedCH) is proposed, which overcomes the deficiency of existing consistent hashing algorithms well and is particularly suitable for heterogeneous storage systems.
Hierarchical Consistent Hashing for Heterogeneous Object-Based Storage
TLDR
The evaluation based on the Sheepdog, a distributed objectbased storage system, confirms that HiCH can improve the performance of storage systems, and also make better utilization of heterogeneous storage devices.
SPREAD: an adaptive scheme for redundant and fair storage in dynamic heterogeneous storage systems
TLDR
A strategy called SPREAD is presented that solves the problem of designing an adaptive hash table for redundant data storage in a system of storage devices with arbitrary capacities and preserves (a) for every storage device within a (1 ± ε) factor with high probability.
Data Distribution Algorithm Using Time Based Weighted Distributed Hash Tables
  • Rongling Lang, Z. Deng
  • Computer Science
    2008 Seventh International Conference on Grid and Cooperative Computing
  • 2008
TLDR
From the simulation results, it is concluded that such multi-parameters selection related to the network ensured the data could be fairly distributed to the storage nodes.
3 nuts : A Locality-Aware Peer-to-Peer Network Combining Random Networks , Search Trees , and DHTs
Categorizing peer-to-peer networks from an algorithmic point of view the two extremes of the spectrum are unstructured networks and networks based on plain distributed hash tables (DHT). Unstructured
Weighted Load Balancing in Distributed Hash Tables
TLDR
A new way of using Distributed Hash Tables (DHTs) to create a distributed storage in P2P-networks is introduced to introduce the lowest overheads possible and allowing for fair load balancing, even if nodes contributing storage capacities of arbitrary/different sizes form the network.
Attributed Consistent Hashing for Heterogeneous Storage System
Cloud-scale storage system is an important building block of the cloud infrastructure. It demands the flexibility to distribute data and provide high I/O performance. Consistent hashing algorithm is
SAN Optimal Multi Parameter Access Scheme
  • C. Schindelhauer, Gunnar Schomaker
  • Computer Science
    International Conference on Networking, International Conference on Systems and International Conference on Mobile Communications and Learning Technologies (ICNICONSMCL'06)
  • 2006
TLDR
An efficient solution for providing parallel access to multiple hard disks for popular content and an efficient and elegant hash table data structure for utilizing the full capacity of each data server are described.
Reliable and randomized data distribution strategies for large scale storage systems
TLDR
The Random Slicing strategy is presented, which incorporates lessons learned from table-based, rule- based, and pseudo-randomized hashing strategies and is able to provide a simple and efficient strategy that scales up to handle exascale data.
DHHT-RAID: A Distributed Heterogeneous Scalable Architecture for Dynamic Storage Environments
  • Gunnar Schomaker
  • Computer Science
    21st International Conference on Advanced Information Networking and Applications (AINA '07)
  • 2007
TLDR
This work presents the new scalable DHHT-RAID strategy, which features all RAID levels at any time, coexistent, with embedded autonomous rebalancing, and without massive time consuming re-stripes neither administrative intensive offset tables nor manual reallocations, and it allocates the approximately maximal capacity.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 20 REFERENCES
Consistent hashing and random trees: distributed caching protocols for relieving hot spots on the World Wide Web
TLDR
A family of caching protocols for distrib-uted networks that can be used to decrease or eliminate the occurrence of hot spots in the network, based on a special kind of hashing that is called consistent hashing.
Compact, adaptive placement schemes for non-uniform requirements
TLDR
This paper presents two strategies based on hashing that achieve all of the goals above and gives a list of applications demonstrating that they can be used efficiently for distributed data management, web caches, and adaptive random graphs, which may be of interest for peer-to-peer networks.
Simple Load Balancing for Distributed Hash Tables
TLDR
This paper suggests the direct application of the “power of two choices” paradigm, whereby an item is stored at the less loaded of two (or more) random alternatives, and considers how associating a small constant number of hash values with a key can be extended to support other load balancing strategies, including load-stealing or load-shedding, as well as providing natural fault-tolerance mechanisms.
Accessing Nearby Copies of Replicated Objects in a Distributed Environment
TLDR
A simple randomized algorithm for accessing shared objects that tends to satisfy each access request with a nearby copy is designed, based on a novel mechanism to maintain and distribute information about object locations, and requires only a small amount of additional memory at each node.
Koorde: A Simple Degree-Optimal Distributed Hash Table
TLDR
Koorde is a new distributed hash table (DHT) based on Chord 15 and the de Bruijn graphs 2 that meets various lower bounds, such as O(log n) hops per lookup request with only 2 neighbors per node.
Pastry: Scalable, distributed object location and routing for large-scale peer-to-
TLDR
Experimental results obtained with a prototype implementa tion on a simulated network of up to 100,000 nodes confirm Pastry’s scalability, its ability to selfconfigure and adapt to node failures, and its good network loc ality properties.
Load Balancing in Structured P2P Systems
TLDR
This paper explores the space of designing load-balancing algorithms that uses the notion of “virtual servers” and presents three schemes that differ primarily in the amount of information used to decide how to re-arrange load.
Chord: A scalable peer-to-peer lookup service for internet applications
TLDR
Results from theoretical analysis, simulations, and experiments show that Chord is scalable, with communication cost and the state maintained by each node scaling logarithmically with the number of Chord nodes.
Efficient, distributed data placement strategies for storage area networks (extended abstract)
TLDR
This paper investigates the problem of evenly distributing and efficiently locating data in dynamically changing SANs and presents placement strategies capable of locating blocks efficiently and that are able to quickly adjust the data placement to insertions or removals of disks or data blocks.
Pastry: Scalable, Decentralized Object Location, and Routing for Large-Scale Peer-to-Peer Systems
TLDR
Experimental results obtained with a prototype implementation on an emulated network of up to 100,000 nodes confirm Pastry's scalability and efficiency, its ability to self-organize and adapt to node failures, and its good network locality properties.
...
1
2
...