LiU: Hiding Disk Access Latency for HPC Applications with a New SSD-Enabled Data Layout

Huang, Daixin; Zhang, Xuechen; Shi, Wei; Zheng, Mai; Jiang, Song; Qin, Feng

doi:10.1109/mascots.2013.19

Cited by 10 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(iii) For content like video, user-perceived latency depends on how soon the application can have enough chunks to get started. Retrieval delay for other chunks can be hidden by the time it takes for the application to consume the head; there is a similar idea in file layout for solid state disks [10].…”

Section: A Ccndn: Descriptionmentioning

confidence: 99%

CCndnS: A strategy for spreading content and decoupling NDN caches

Rezazad

Tay

2015

2015 IFIP Networking Conference (IFIP Networking)

View full text Add to dashboard Cite

Many proposals for information-centric networking (ICN) share the idea of in-network caching. This idea has four issues: (1) Memory capacity can be wasted through caching redundant copies and unpopular content. (2) Memory latency is high because the caches must be large. (3) Traffic filtering can result in high miss rates in the core and load imbalance. (4) Performance coupling among caches makes modeling their behavior intractable.CCndnS is a caching strategy for Named Data Networking that segments each file and spreads them among the caches, thus addressing the above issues: (1) It reduces redundant copies and cache pollution by unpopular content. (2) It reduces the number of futile checks on caches, thus reducing the delay from memory accesses. (3) It increases hit rates in the core without reducing hit rates at the edge (thus improving overall hit rates) and balances the load among caches. (4) It decouples the caches, so there is a simple analytical performance model for the network of caches.The efficacy of CCndnS and the accuracy of the model are validated with simulations using an Abilene-like topology.

show abstract

Section: A Ccndn: Descriptionmentioning

confidence: 99%

CCndnS: A strategy for spreading content and decoupling NDN caches

Rezazad

Tay

2015

2015 IFIP Networking Conference (IFIP Networking)

View full text Add to dashboard Cite

show abstract

“…iBridge [8] introduces a scheme which uses SSDs to host fragments, thereby alleviates the speed gap between access fragments and large files. LiU [9] studies how to place different partitions of a file to HDDs and SSDs to relieve I/O latency of HDDs. CARL [5] studies how to divide a large file and place different partitions to PFS and SSDs to improve read performance.…”

Section: Related Workmentioning

confidence: 99%

Exploring Memory Hierarchy to Improve Scientific Data Read Performance

Zhang

Tang

Zou

et al. 2015

2015 IEEE International Conference on Cluster Computing

View full text Add to dashboard Cite

Improving read performance is one of the major challenges with speeding up scientific data analytic applications. Utilizing the memory hierarchy is one major line of researches to address the read performance bottleneck. Related methods usually combine solide-state-drives(SSDs) with dynamic random-access memory(DRAM) and/or parallel file system(PFS) to mitigate the speed and space gap between DRAM and PFS. However, these methods are unable to handle key performance issues plaguing SSDs, namely read contention that may cause up to 50% performance reduction. In this paper, we propose a framework that exploits the memory hierarchy resource to address the read contention issues involved with SSDs. The framework employs a general purpose online read algorithm that able to detect and utilize memory hierarchy resource to relieve the problem. To maintain a near optimal operating environment for SSDs, the framework is able to orchastrate data chunks across different memory layers to facilitate the read algorithm. Compared to existing tools, our framework achieves up to 50% read performance improvement when tested on datasets from real-world scientific simulations.

show abstract

“…New storage devices such as solid state drives (SSDs) have been widely deployed in the HPC environment because of their near-zero seek latency and superior performance (especially for random accesses) [34] [6] [10] [40] [11]. However, SSDs are much more expensive than HDDs.…”

Section: Introductionmentioning

confidence: 99%

Optimizing the SSD Burst Buffer by Traffic Detection

Shi

Liu

et al. 2020

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

Currently, HPC storage systems still use hard disk drive (HDD) as their dominant storage device. Solid state drive (SSD) is widely deployed as the bu er to HDDs. Burst bu er has also been proposed to manage the SSD bu ering of bursty write requests. Although burst bu er can improve I/O performance in many cases, we nd that it has some limitations such as requiring large SSD capacity and harmonious overlapping between computation phase and data ushing phase.In this paper, we propose a scheme, called SSDUP+ 1 . SSDUP+ aims to improve the burst bu er by addressing the above limitations. First, in order to reduce the demand for the SSD capacity, we develop a novel method to detect and quantify the data randomness in the write tra c. Further, an adaptive algorithm is proposed to classify the random writes dynamically. By doing so, much less SSD capacity is required to achieve the similar performance as other burst bu er schemes. Next, in order to overcome the di culty of perfectly overlapping the computation phase and the ushing phase, we propose a pipeline mechanism for the SSD bu er, in which data bu ering and ushing are performed in pipeline. In addition, in order to improve the I/O throughput, we adopt a tra c-aware ushing strategy to reduce the I/O interference in HDD. Finally, in order to further improve the performance of bu ering random writes in SSD, SSDUP+ transforms the random writes to sequential writes in SSD by storing the data with a log structure. Further, SSDUP+ uses the AVL tree structure to store the sequence information of the data.We have implemented a prototype of SSDUP+ based on OrangeFS and conducted extensive experiments. e experimental results show that our proposed SSDUP+ can save an average of 50% SSD space, while delivering almost the same performance as other common burst bu er schemes. In addition, SSDUP+ can save about 20% SSD space compared with the previous version of this work, SSDUP, while achieving 20%-30% higher I/O throughput than SSDUP.

show abstract

LiU: Hiding Disk Access Latency for HPC Applications with a New SSD-Enabled Data Layout

Cited by 10 publications

References 11 publications

CCndnS: A strategy for spreading content and decoupling NDN caches

CCndnS: A strategy for spreading content and decoupling NDN caches

Exploring Memory Hierarchy to Improve Scientific Data Read Performance

Optimizing the SSD Burst Buffer by Traffic Detection

Contact Info

Product

Resources

About