A fault-scalable service can be configured to tolerate increasing numbers of faults without significant decreases in performance. The Query/Update (Q/U) protocol is a new tool that enables construction of fault-scalable Byzantine faulttolerant services. The optimistic quorum-based nature of the Q/U protocol allows it to provide better throughput and fault-scalability than replicated state machines using agreement-based protocols. A prototype service built using the Q/U protocol outperforms the same service built using a popular replicated state machine implementation at all system sizes in experiments that permit an optimistic execution. Moreover, the performance of the Q/U protocol decreases by only 36 % as the number of Byzantine faults tolerated increases from one to five, whereas the performance of the replicated state machine decreases by 83%.

As peer-to-peer and widely distributed storage systems proliferate, the need to perform efficient erasure coding, instead of replication, is crucial to performance and efficiency. Low-Density Parity-Check (LDPC) codes have arisen as alternatives to standard erasure codes, such as Reed-Solomon codes, trading off vastly improved decoding performance for inefficiencies in the amount of data that must be acquired to perform decoding. The scores of papers written on LDPC codes typically analyze their collective and asymptotic behavior. Unfortunately, their practical application requires the generation and analysis of individual codes for finite systems. This paper attempts to illuminate the practical considerations of LDPC codes for peer-to-peer and distributed storage systems. The three main types of LDPC codes are detailed, and a huge variety of codes are generated, then analyzed using simulation. This analysis focuses on the performance of individual codes for finite systems, and addresses several important heretofore unanswered questions about employing LDPC codes in real-world systems. 1

Storage clusters consisting of thousands of disk drives are now being used both for their large capacity and high throughput. However, their reliability is far worse than that of smaller storage systems due to the increased number of storage nodes. RAID technology is no longer sufficient to guarantee the necessary high data reliability for such systems, because disk rebuild time lengthens as disk capacity grows. In this paper, we present FAst Recovery Mechanism (FARM), a distributed recovery approach that exploits excess disk capacity and reduces data recovery time. FARM works in concert with replication and erasure-coding redundancy schemes to dramatically lower the probability of data loss in large-scale storage systems. We have examined essential factors that influence system reliability, performance, and costs, such as failure detections, disk bandwidth usage for recovery, disk space utilization, disk drive replacement, and system scales, by simulating system behavior under disk failures. Our results show the reliability improvement from FARM and demonstrate the impacts of various factors on system reliability. Using our techniques, system designers will be better able to build multi-petabyte storage systems with much higher reliability at lower cost than previously possible.

As storage systems scale to thousands of disks, data distribution and load balancing become increasingly important. We present an algorithm for allocating data objects to disks as a system as it grows from a few disks to hundreds or thousands. A client using our algorithm can locate a data object in microseconds without consulting a central server or maintaining a full mapping of objects or buckets to disks. Despite requiring little global configuration data, our algorithm is probabilistically optimal in both distributing data evenly and minimizing data movement when new storage is added to the system. Moreover, our algorithm supports weighted allocation and variable levels of object replication, both of which are needed to permit systems to efficiently grow while accommodating new technology. 1

Abstract Peer-to-peer (P2P) networks have become a powerful means for online data exchange. Currently, users are primarily utilizing these networks to perform exact-match queries and retrieve complete files. However, future more data intensive applications, such as P2P auction networks, P2P job-search networks, P2P multi-player games, will require the capability to respond to more complex queries such as range queries involving numerous data types including those that have a spatial component. In this paper, a distributed quadtree index that adapts the MX-CIF quadtree is described that enables more powerful accesses to data in P2P networks. This index has been implemented for various prototype P2P applications and results of experiments are presented. Our index is easy to use, scalable, and exhibits good load-balancing properties. Similar indices can be constructed for various multi-dimensional data types with both spatial and non-spatial components. This work was supported in part by the National Science Foundation under grants EIA-99-00268, EIA-00-91474, and CCF-05-15241 as well as Microsoft Research.

Abstract not found

Structured peer-to-peer (P2P) systems are considered as the next generation application backbone on the Internet. An important problem of these systems is load balancing in the presence of non-uniform data distributions. In this paper we propose a completely decentralized mechanism that in parallel addresses a local and a global load balancing problem: (1) balancing the storage load uniformly among peers participating in the network and (2) uniformly replicating different data items in the network while optimally exploiting existing storage capacity. Our approach is based on the P-Grid P2P system which is our variant of a structured P2P network. Problem (1) is solved by directly adapting the search structure to the data distribution. This may result in an unbalanced search structure, but we will show that the expected search cost in P-Grid in number of messages remains logarithmic under all circumstances.

NOTE: NCA’s page limit is rather severe: 8 pages. As a result, the final paper is pretty much a hatchet job of the original submission. I would recommend reading the technical report version of this paper, because it presents the material with some accompanying tutorial material, and is easier to read. The technical report is available at:

Scalable Distributed Data Structures (SDDS) need scalable availability. This can be provided through replication, which is storage intensive, or through the use of Erasure Correcting Codes (ECC) to provide redundancy, which is more complicated. We calculate availability under both strategies and show that redundancy through use of an ECC implies significantly less overhead. We

In this paper we present and evaluate uncoordinated on-line algorithms for simultaneous storage and replication load-balancing in DHT-based peer-to-peer systems. We compare our approach with the classical balls into bins model, and point out the similarities but also the differences which call for new loadbalancing mechanisms specifically targeted at P2P systems. Some of the peculiarities of P2P systems, which make our problem even more challenging are that both the network membership and the data indexed in the network is dynamic, there is neither global coordination nor global information to rely on, and the load-balancing mechanism ideally should not compromise the structural properties and thus the search efficiency of the DHT, while preserving the semantic information of the data (e.g., lexicographic ordering to enable range searches).