Digital Library[ Search Result ]
Study of Effective Valid Page Tracking Methods in Mobile Flash Storage without DRAM
http://doi.org/10.5626/JOK.2025.52.5.357
Mobile systems, commonly use flash-based storage devices like Universal Flash Storage (UFS). These devices are designed with a small form factor and operate under limited power and budget constraints, often lacking large internal DRAM. As a result, they rely on small SRAM to run the Flash Translation Layer (FTL). This limitation makes it difficult to manage metadata, such as address mapping tables and the Valid Page Bitmap related to garbage collection (GC), within SRAM. Managing the Valid Page Bitmap in flash memory poses challenges due to performance degradation from significant metadata I/O overhead. This paper proposes an efficient method for tracking valid pages within specific blocks by managing L2P segment bitmaps per block. This approach minimizes the metadata access overhead during valid page tracking, leading to improved performance. Evaluation results indicate up to an 83% reduction in latency for finding valid pages compared to existing methods, particularly with a 128KB I/O unit.
Managing DISCARD Commands in F2FS File System for Improving Lifespan and Performance of SSD Devices
Jinwoong Kim, Donghyun Kang, Young Ik Eom
http://doi.org/10.5626/JOK.2024.51.8.669
The DISCARD command is an interface that helps improve the lifespan and performance of SSDs by informing the SSD devices about invalid file system blocks. However, in the F2FS file system, the DISCARD command is only sent to the SSD during idle time, which limits the potential for improving lifespan and performance. In this paper, we propose an EPD scheme to efficiently transfer DISCARD commands during short idle times, as well as a seg-ment allocation scheme called PSA, which replaces DISCARD commands with overwrite commands. To evaluate the effectiveness of these proposed schemes, we conducted several experiments using various workloads to verify the lifespan and performance of real SSD devices. The results showed that the proposed schemes can improve the write amplification factor (WAF) by up to 40% and throughput by up to 160%, when compared to the traditional F2FS file system.
Optimized Design of Filesystems for Unikernel
Kyeong Woon Cho, Hyo Kyeong Ban
http://doi.org/10.5626/JOK.2024.51.5.389
Unikernel is a special-purpose kernel optimized for single applications and services. Compared to general-purpose kernels, its advantages include fast boot time, small memory footprint, high performance, and security. Unikernel applications attempt to maintain compatibility with the runtime environment of the general-purpose kernel and are used in binary or source-compatible form with legacy applications. Most existing unikernel projects implemented filesystem APIs with a priority on running applications rather than performance optimizations. Accordingly, it is a common practice to deploy a general-purpose file system naively or to introduce a host filesystem dependent method. In this paper, we discuss the design of unikernel file systems taking into account the purpose of unikernel, i.e., ensuring optimized performance with minimal system resources while maintaining security. Specifically, we analyze the performance and memory requirements for file systems supported by major unikernels through micro-benchmarks and suggest file system design guidelines to provide optimized performance and security.
Storage Trie Optimization Based on Ethereum Transaction Data
http://doi.org/10.5626/JOK.2024.51.2.110
Interest in blockchain has grown with the increased usage of Ethereum, thus the blockchain state data has exploded, making it difficult for users to participate in the network. In this paper, we propose a method of optimizing the storage trie, which accounts for a significant portion of state data, based on pas transaction data of real Ethereum. By deleting storage trie that never appeared during 1 million blocks from a massive 14 million block storage tire, we reduced the storage space by 19.6%, which is 10.8GB. Based on the research results of this paper, it is expected that we can propose a more effective storage trie optimization based on data.
CSDVirt: An Emulator for Computational Storage Device
Ilkueon Kang, Jaehoon Shim, Jin-Soo Kim
http://doi.org/10.5626/JOK.2024.51.1.1
Since Computational Storage Device (CSD) concept was proposed, various forms of CSDs have been presented in both academia and industries. The standardization of CSD interfaces is currently undergoing, but they are still in a very early stage. As a result, the existing CSD proposals lack uniformity in interfaces and internal device architectures. This has led to significant engineering efforts for CSD research. In this paper, we propose CSDVirt to facilitate the CSD research and provide an environment similar to actual devices. CSDVirt is an emulator that offers CSD functionalities using NVMeVirt. With CSDVirt, the characteristics of various workloads on CSDs can be evaluated easily.
Addressing Write-Warm Pages in OLTP Workloads
Kyong-Shik Lee, Mijin An, Sang-Won Lee
http://doi.org/10.5626/JOK.2023.50.11.1002
One of the most important purposes of buffer management policies is to cache frequently accessed data in the buffer pool to minimize disk I/O. However, even if frequently referenced pages are effectively stored, a small number of pages can still result in excessive disk I.O. This is because of write-warm pages, which are repeatedly fetched and evicted from the buffer pool. In this paper, we introduce a “(Write-)Warm Page Thrashing” problem and confirm the existence of write-warm pages. Specifically, we found that 10% of flushed pages accounted for 41% of writes. This could degrade the performance, particularly for flash memory devices with slow write speeds. Therefore, a new buffer management policy is required to detect and prevent such thrashing problem.
Integrated Host-SSD Mapping Table Cache Management Techniques for Improving Performance of a Mobile Storage Device
Yoona Kim, Inhyuk Choi, Sungjin Lee, Jihong Kim
http://doi.org/10.5626/JOK.2023.50.11.924
As the size of a storage device gradually increases, the demand for on-device memory capacity required for managing the address mapping translation of a NAND flash-based storage device increases. The on-device memory capacity of a mobile storage device, Universal Flash Storage (UFS), does not increase due to H/W and cost constraints, making it challenging to manage the increased address translation table. To resolve the problem, Host Performance Booster (HPB), which borrows host-side DRAM memory to load portions of the address translation table was introduced. In this paper, we demonstrate that the HPB-enabled system does not work in an integrated manner with the device-side SRAM, therefore wasting the given memory resource. We propose integrated mapping table management techniques that consider the distinctive features of each cache layer. By adopting these techniques, we aim to minimize wasted cache resources, reduce storage latency, and prevent unnecessary degradation of the storage lifetime. Based on the evaluation results, the cache hit ratio is improved by 5% while the wasted memory resource is reduced by 95%, and the number of device-side garbage collections is reduced by 43% compared to the baseline scheme.
ESP: Improving Performance and Lifetime of High-Capacity 3D Flash Storage Using an Erase-Free Subpage Programming Technique
http://doi.org/10.5626/JOK.2023.50.1.1
Recent high-capacity 3D NAND flash devices have large page sizes. Although large pages are useful in increasing flash capacity, they can degrade both the performance and lifetime of flash storage systems when small writes are dominant. We propose a new NAND programming scheme, called erase-free sub-page programming (ESP), which allows the same page to be programmed multiple times for small writes without the intervention of the erase operation. By avoiding internal fragmentation, the ESP scheme reduces the overhead of garbage collection for large-page NAND storage. Based on the proposed ESP scheme with an adaptive retention management technique, we implemented an ESP-aware FTL(subFTL) and performed comprehensive evaluations using various benchmarks and workloads. The experimental results showed that an ESP-aware FTL could improve the IOPS and lifetime by up to 74% and 177%, respectively.
LSM Tree Compaction Offloading Using NVMe-oF
Sungho Moon, Hera Koo, Hyeongjun Jeon, Beomseok Nam
http://doi.org/10.5626/JOK.2022.49.7.569
NVMe-over-Fabrics (NVMe-oF) is drawing attraction in the industry as an alternative to disaggregated storage by providing fast access to remote NVMe SSDs through NVMe commands. In this paper, we propose RocksDB-oF, an LSM-Tree-based key-value store optimized for disaggregated storage using NVMe-oF. RocksDB-oF alleviated the Write Stall problem by offloading compaction from the computing node onto the storage node in consideration of the characteristics of NVMe-oF. In addition, a file system that uses Storage Performance Development Kit (SPDK) effectively solves the file system consistency problem of two nodes accessing the same NVMe SSD at the same time. Experimentally, in a disaggregated storage environment with NVMe-oF, RocksDB-oF showed higher write throughput than legacy RocksDB.
New Flash Commands for Building Flash Storage Systems with Plausible Deniability
Geonhee Cho, Myungsuk Kim, Jihong Kim
http://doi.org/10.5626/JOK.2022.49.2.120
Traditional encryption cannot defend against coercive attackers who compel the user to hand over decryption keys as it cannot hide the existence of the ciphertext. To solve this problem, there have been studies on a deniable storage solution that applies plausible deniability, a characteristic that allows the user to deny the existence of sensitive data, to a storage device. The hidden volume mechanism is being used in various deniable storage solutions due to its relatively low-performance overhead compared to other mechanisms, and has recently evolved to defend against multiple-snapshot attacks. However, the existing hidden volume mechanism fundamentally requires a dummy random data pool to hide the ciphertext. Due to the existence of dummy random data stored in the storage device, the plausible deniability characteristic is exposed, which can reveal the intention to hide the data. This study proposes a flash chip-level access control command set that simultaneously supports data sanitization and plausible deniability, and using this, we propose a hidden volume-based deniable storage solution that supports plausible deniability characteristics without dummy random data.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr