RAID level selection for heterogeneous disk arrays

Thomasian, Alexander; Xu, Jun

doi:10.1007/s10586-010-0129-4

Cited by 12 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the volume of data and access rate a VA is allocated as multiple Virtual Disks (VDs) on different disks. The VA RAID level is determined by its size and data access intensity, e.g., VAs with high access rates to read and write small data blocks are assigned as RAID1, while VAs with RAID5 can process large reads and writes more efficiently [106].…”

Section: Simulation For Reliability Modelingmentioning

confidence: 99%

Mirrored and hybrid disk arrays and their reliability

Thomasian¹

2018

Cluster Comput

Self Cite

View full text Add to dashboard Cite

Basic mirroring (BM) classified as RAID level 1 replicates data on two disks, thus doubling disk access bandwidth for read requests. RAID1/0 is an array of BM pairs with balanced loads due to striping. When a disk fails the read load on its pair is doubled, which results in halving the maximum attainable bandwidth. We review RAID1 organizations which attain a balanced load upon disk failure, but as shown by reliability analysis tend to be less reliable than RAID1/0. Hybrid disk arrays which store XORed instead of replicated data tend to have a higher reliability than mirrored disks, but incur a higher overhead in updating data. Read request response time can be improved by processing them at a higher priority than writes, since they have a direct effect on application response time. Shortest seek distance and affinity based routing both shorten seek time. Anticipatory arm placement places arms optimally to minimize the seek distance. The analysis of RAID1 in normal, degraded, and rebuild mode is provided to quantify RAID1/0 performance. We compare the reliability of mirrored disk organizations against each other and hybrid disks and erasure coded disk arrays. RAID reliabilities can be compared with a shortcut reliability analysis method.

show abstract

Section: Simulation For Reliability Modelingmentioning

confidence: 99%

Mirrored and hybrid disk arrays and their reliability

Thomasian¹

2018

Cluster Comput

Self Cite

View full text Add to dashboard Cite

show abstract

“…Existing facilities in our Information Center provide a good operating environment and hardware platform for data integration, among of which the RAID 5 (Redundant Arrays of Independent Disks) storage system consists of 24 pieces of 1TB hard drives and is equipped with optical fiber switches to ensure the data safety and the data accessing speed. Disk Array (Chandy 2008, Thomasian andXu 2011) is a combination of two or more disks, with the same types, capacity and interface, managed by a disk array card. Disk Array selectively distributes data into multiple disks, which improves not only data accessibility, but also data accessing speed and fault tolerance, thereby avoiding disastrous consequences caused by disk failure.…”

Section: Hardware Optimizationmentioning

confidence: 99%

Automated Data Processing and Integration of Large Multiple Data Sources in Geohazards Monitoring

Liu

et al. 2017

IJGE

View full text Add to dashboard Cite

The development of geohazard information management system has greatly promoted the wireless automation monitoring technology for geohazards. More monitoring instruments are increasingly used in geohazard monitoring. Consequently, the types of monitoring data become more and more complicated, and massive amount of monitoring data are collected, which raises new demands in data storage and retrieval. In order to meet the requirements of data processing in geohazard monitoring, this paper presents a method of geohazard monitoring data processing, realizing the heterogeneous data integration, data access optimization, and abnormal data processing. Having analyzed the wireless automation monitoring process and the features of geohazard monitoring data, we defined the data integration standards of multiple data sources. Based on this, we developed a Geohazard Monitoring Data Integration System, with optimization in both hardware and software. This system allows automatic integration of large monitoring data from multiple sources. It has important significance for geohazard monitoring and early warning. A Geohazard Monitoring Data Analyzing System based on the monitoring data integrated by this system and data mining technology is developed to fully explore the hidden values of Big Data. Through field tests in Guizhou province with 92 sets of monitoring equipment and 5 types of databases, this method is proven to meet the system requirements with satisfactory performance.

show abstract

“…A fraction f 1 of all allocation requests are for RAID1 and a fraction f 5 = 1 − f 1 are for RAID5. These fractions may follow the observed pattern or are based on classification as in [2,25]. We also use the notation RAID5:RAID1=3:1 implying f 5 = 0.75.…”

Section: Virtual Allocation Requestsmentioning

confidence: 99%

Data Allocation in a Heterogeneous Disk Array - HDA with Multiple RAID Levels for Database Applications

Thomasian,

2015

Preprint

Self Cite

View full text Add to dashboard Cite

We consider the allocation of Virtual Arrays (VAs) in a Heterogeneous Disk Array (HDA). Each VA holds groups of related objects and datasets such as files, relational tables, which has similar performance and availability characteristics. We evaluate single-pass data allocation methods for HDA using a synthetic stream of allocation requests, where each VA is characterized by its RAID level, disk loads and space requirements. The goal is to maximize the number of allocated VAs and maintain high disk bandwidth and capacity utilization, while balancing disk loads. Although only RAID1 (basic mirroring) and RAID5 (rotated parity arrays) are considered in the experimental study, we develop the analysis required to estimate disk loads for other RAID levels. Since VA loads vary significantly over time, the VA allocation is carried out at the peak load period, while ensuring that disk bandwidth is not exceeded at other high load periods. Experimental results with a synthetic stream of allocation requests show that allocation methods minimizing the maximum disk bandwidth and capacity utilization or their variance across all disks yield the maximum number of allocated VAs. HDA saves disk bandwidth, since a single RAID level accommodating the most stringent availability requirements for a small subset of objects would incur an unnecessarily high overhead for updating check blocks or data replicas for all objects. The number of allocated VAs can be increased by adopting the clustered RAID5 paradigm, which exploits the tradeoff between redundancy and bandwidth utilization. Since rebuild can be carried out at the level of individual VAs, prioritizing rebuild of VAs with higher access rates can improve overall performance.

show abstract

RAID level selection for heterogeneous disk arrays

Cited by 12 publications

References 24 publications

Mirrored and hybrid disk arrays and their reliability

Mirrored and hybrid disk arrays and their reliability

Automated Data Processing and Integration of Large Multiple Data Sources in Geohazards Monitoring

Data Allocation in a Heterogeneous Disk Array - HDA with Multiple RAID Levels for Database Applications

Contact Info

Product

Resources

About