Rigorous Modeling of Disk Performance for Real-Time Applications

Park, Sangsoo; Shin, Hyundong

doi:10.1007/978-3-540-24686-2_30

Cited by 5 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of works characterized the behavior of SSDs through mathematical modeling or via simulation [18]. Yang et al [19] and Tao et al [20] used simulation method to determine page size, the address allocation policies, and parallelism.…”

Section: Related Workmentioning

confidence: 99%

Power Consumption Signature: Characterizing an SSD

Yoo

Lee

Won

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYSSDs consist of non-mechanical components (host interface, control core, DRAM, flash memory, etc.) whose integrated behavior is not well-known. This makes an SSD seem like a black-box to users. We analyzed power consumption of four SSDs with standard I/O operations. We find the following: (a) the power consumption of SSDs is not significantly lower than that of HDDs, (b) all SSDs we tested had similar power consumption patterns which, we assume, is a result of their internal parallelism. SSDs have a parallel architecture that connects flash memories by channel or by way. This parallel architecture improves performance of SSDs if the information is known to the file system. This paper proposes three SSD characterization algorithms to infer the characteristics of SSD, such as internal parallelism, I/O unit, and page allocation scheme, by measuring its power consumption with various sized workloads. These algorithms are applied to four real SSDs to find: (i) the internal parallelism to decide whether to perform I/Os in a concurrent or an interleaved manner, (ii) the I/O unit size that determines the maximum size that can be assigned to a flash memory, and (iii) a page allocation method to map the logical address of write operations, which are requested from the host to the physical address of flash memory. We developed a data sampling method to provide consistency in collecting power consumption patterns of each SSD. When we applied three algorithms to four real SSDs, we found flash memory configurations, I/O unit sizes, and page allocation schemes. We show that the performance of SSD can be improved by aligning the record size of file system with I/O unit of SSD, which we found by using our algorithm. We found that Q Pro has I/O unit of 32 KB, and by aligning the file system record size to 32 KB, the performance increased by 201% and energy consumption decreased by 85%, which compared to the record size of 4 KB.

show abstract

Section: Related Workmentioning

confidence: 99%

Power Consumption Signature: Characterizing an SSD

Yoo

Lee

Won

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Consequently, an intensive work had been achieved to model and optimize Inputs/Outputs execution on HDDs [9,16,22,13,15,23,24]. These optimizations were validated and their efficiency is proven.…”

Section: Introductionmentioning

confidence: 99%

Exploiting the Fine Grain SSD Internal Parallelism for OLTP and Scientific Workloads

Zertal¹

2014

2014 IEEE Intl Conf on High Performance Computing and Communications, 2014 IEEE 6th Intl Symp on Cyberspace Safety and Security

View full text Add to dashboard Cite

Solid State Disks (SSDs) are promising data storage devices in term of performance and energy consumption comparing to Hard Drive Disks (HDDs). They are more and more used, even in On-Line Transaction Processing (OLTP) systems and for scientific data with hard constraints on response time. Consequently, parallel execution and parallel access to data are capital to fulfil this performance requirement. The SSD internal structure provides a potential for parallel access at different levels which can be exploited to match the concurrency naturally present in both OLTP and scientific applications. In this paper, the SSD behaviour is analysed considering two degrees of internal parallelism associated to inter-Dies (degree 1) and interPlanes (degree 2) parallelisms and compared to a sequential scheme (degree 0) as a reference. The study is conducted using representative workloads for both OLTP and scientific applications. The obtained results are significant and show the important performance gain of exploiting the internal SSD parallelism (up to ×44 for OLTP). The gain is less important for scientific applications due to their requests size distributions and the interleaving of read/write streams. In conjunction with priority and preemption scheduling strategies, an additional impact is observed, which can be very modest or a factor of ×10 according to the context, with a significant impact only if priority is associated to preemption.

show abstract