Proceedings ArticleDOI
Using idle disks in a cluster as a high-performance storage system
J.S. Hansen,R. Lachaize +1 more
- pp 415-424
TLDR
The software support for sharing of disks in clusters, where the disks are distributed across the nodes in the cluster, thereby allowing them to be combined into a high-performance storage system, is described.Abstract:
In many clusters today, the local disks of a node are only used sporadically. This paper describes the software support for sharing of disks in clusters, where the disks are distributed across the nodes in the cluster, thereby allowing them to be combined into a high-performance storage system. Compared to centralized storage servers, such an architecture allows the total I/O capacity of the cluster to scale up with the number of nodes and disks. Additionally, our software allows customizing the functionality of the remote disk access using a library of code modules. A prototype has been implemented on a cluster connected by a Scalable Coherent Interface (SCI) network and performance measurements using both raw device access and a distributed file system show that the performance is comparable to dedicated storage systems and that the overhead of the framework is moderate even during high load. Thus, the prospects are that clusters sharing disks distributed among the nodes will allow both the application processing power and total I/O capacity of the cluster to scale up with the number of nodes.read more
Citations
More filters
Patent
Systems and methods for path-based management of virtual servers in storage network environments
TL;DR: In this article, the authors analyze the service and performance levels associated with virtual machines in a storage network environment for compliance with a resource capacity policy and identify virtual machines with resource consumptions that violate the resource capacity policies.
Patent
Methods and systems for predictive change management for access paths in networks
TL;DR: In this paper, a configuration change can be specified and pre-validated according to the access path policy, before the actual changes are implemented, so that root causes for resulting access path violations can be detected and remedied before the changes are made.
Patent
Methods and systems for history analysis for access paths in networks
TL;DR: In this paper, a method and system for constructing and analyzing an access path event history in a network is provided, where inconsistencies in the physical and logical access paths when making changes in the network are detected and analyzed.
Patent
Methods and systems for validating accessibility and currency of replicated data
TL;DR: In this article, a replicated-data policy for replicating data is defined, and access paths between network devices or between applications running on the network devices are monitored, for example, by a replicated data monitor.
References
More filters
Journal ArticleDOI
The click modular router
TL;DR: On conventional PC hardware, the Click IP router achieves a maximum loss-free forwarding rate of 333,000 64-byte packets per second, demonstrating that Click's modular and flexible architecture is compatible with good performance.
Journal ArticleDOI
Myrinet: a gigabit-per-second local area network
N.J. Boden,Danny Cohen,R.E. Felderman,A.E. Kulawik,Charles L. Seitz,Jakov Seizovic,Wen-King Su +6 more
TL;DR: The Myrinet local area network employs the same technology used for packet communication and switching within massively parallel processors, but with the highest performance per unit cost of any current LAN.
Proceedings ArticleDOI
The Click modular router
TL;DR: The Click IP router can forward 64-byte packets at 73,000 packets per second, just 10% slower than Linux alone, and is easy to extend by adding additional elements, which are demonstrated with augmented configurations.
Proceedings Article
GPFS: A Shared-Disk File System for Large Computing Clusters
Frank B. Schmuck,Roger L. Haskin +1 more
TL;DR: GPFS is IBM's parallel, shared-disk file system for cluster computers, available on the RS/6000 SP parallel supercomputer and on Linux clusters, and discusses how distributed locking and recovery techniques were extended to scale to large clusters.
Proceedings ArticleDOI
Petal: distributed virtual disks
TL;DR: The design, implementation, and performance of Petal is described, a system that attempts to approximate this ideal in practice through a novel combination of features.