Sooyong Kang

Performance Trade-Offs in Using NVRAM Write Buffer for Flash Memory-Based Storage Devices

While NAND flash memory is used in a variety of end-user devices, it has a few disadvantages, such as asymmetric speed of read and write operations, inability to in-place updates, among others. To overcome these problems, various flash-aware strategies have been suggested in terms of buffer cache, file system, FTL, and others. Also, the recent development of next-generation nonvolatile memory types such as MRAM, FeRAM, and PRAM provide higher commercial value to non-volatile RAM (NVRAM). At todays prices, however, they are not yet cost-effective. In this paper, we suggest the utilization of small-sized, next-generation NVRAM as a write buffer to improve the .overall performance of NAND flash memory-based storage systems. We propose various block-based NVRAM write buffer management policies and evaluate the performance improvement of NAND flash memory-based storage systems under each policy. Also, we propose a novel write buffer-aware flash translation layer algorithm, optimistic FTL, which is designed to harmonize well with NVRAM write buffers. Simulation results show that the proposed buffer management policies outperform the traditional page-based LRU algorithm and the proposed optimistic FTL outperforms previous log block-based FTL algorithms, such as BAST and FAST.

LRU-WSR: integration of LRU and writes sequence reordering for flash memory

Most mobile devices are equipped with a NAND flash memory even if it has characteristics of not-in-place update and asymmetric I/O latencies among read, write, and erase operations: write/erase operations are much slower than a read operation in a flash memory. For the overall performance of a flash memory system, the buffer replacement policy should consider the above severely asymmetric I/O latencies. However, existing LRU buffer replacement algorithm cannot deal with the above problem. This paper proposes the LRU-WSR buffer replacement algorithm that enhances LRU by reordering writes of not-cold dirty pages from the buffer cache to flash storage. The enhanced LRU-WSR algorithm focuses on reducing the number of write/erase operations as well as preventing serious degradation of buffer hit ratio. The experimental results show that the LRU-WSR outperforms other algorithms including LRU, CF-LRU, and FAB1.

Deduplication in SSDs: Model and quantitative analysis

In NAND Flash-based SSDs, deduplication can provide an effective resolution of three critical issues: cell lifetime, write performance, and garbage collection overhead. However, deduplication at SSD device level distinguishes itself from the one at enterprise storage systems in many aspects, whose success lies in proper exploitation of underlying very limited hardware resources and workload characteristics of SSDs. In this paper, we develop a novel deduplication framework elaborately tailored for SSDs. We first mathematically develop an analytical model that enables us to calculate the minimum required duplication rate in order to achieve performance gain given deduplication overhead. Then, we explore a number of design choices for implementing deduplication components by hardware or software. As a result, we propose two acceleration techniques: sampling-based filtering and recency-based fingerprint management. The former selectively applies deduplication based upon sampling and the latter effectively exploits limited controller memory while maximizing the deduplication ratio. We prototype the proposed deduplication framework in three physical hardware platforms and investigate deduplication efficiency according to various CPU capabilities and hardware/software alternatives. Experimental results have shown that we achieve the duplication rate ranging from 4% to 51%, with an average of 17%, for the nine workloads considered in this work. The response time of a write request can be improved by up to 48% with an average of 15%, while the lifespan of SSDs is expected to increase up to 4.1 times with an average of 2.4 times.

VSSIM: Virtual machine based SSD simulator

In this paper, we present a virtual machine based SSD Simulator, VSSIM (Virtual SSD Simulator). VSSIM intends to address the issues of the trace driven simulation, e.g. trace re-scaling, accurate replay, etc. VSSIM operates on top of QEMU/KVM with software based SSD module. VSSIM runs in realtime and allows the user to measure both the host performance and the SSD behavior under various design choices. VSSIM can flexibly model the various hardware components, e.g. the number of channels, the number of ways, block size, page size, planes per chip, program, erase, read latency of NAND cells, channel switch delay, and way switch delay. VSSIM can also facilitate the implementation of the SSD firmware algorithms. To demonstrate the capability of VSSIM, we performed a number of case studies. The results of the simulation study deliver an important guideline in the firmware and hardware designs of future NAND based storage devices. Followings are some of the findings: (i) as the page size increases, the performance benefit of increasing the channel parallelism against increasing the way parallelism becomes less significant, (ii) due to the bi-modality in IO size distribution, FTL should be designed to handle multiple mapping granularity, (iii) hybrid mapping does not work in four or more way SSD due to severe log block fragmentation, (iv) as a performance metric, the Write Amplification Factor can be misleading, (v) compared to sequential write, random write operation can be benefited more from the channel level parallelism and therefore in multi-channel environment, it is beneficial to categorize larger fraction of IO as random. VSSIM is validated against commodity SSD, Intel X25M SSD. VSSIM models the sequential IO performance of X25M within 3% offset.

Adaptive delay-based congestion control for high bandwidth-delay product networks

The design of an end-to-end Internet congestion control protocol that could achieve high utilization, fair sharing of bottleneck bandwidth, and fast convergence while remaining TCP-friendly is an ongoing challenge that continues to attract considerable research attention. This paper presents ACP, an Adaptive end-to-end Congestion control Protocol that achieves the above goals in high bandwidth-delay product networks where TCP becomes inefficient. The main contribution of ACP is a new form of congestion window control, combining the estimation of the bottleneck queue size and a measure of fair sharing. Specifically, upon detecting congestion, ACP decreases the congestion window size by the exact amount required to empty the bottleneck queue while maintaining high utilization, while the increases of the congestion window are based on a “fairness ratio” metric of each flow, which ensures fast convergence to a fair equilibrium. We demonstrate the benefits of ACP using both ns-2 simulation and experimental measurements of a Linux prototype implementation. In particular, we show that the new protocol is TCP-friendly and allows TCP and ACP flows to coexist in various circumstances, and that ACP indeed behaves more fairly than other TCP variants under heterogeneous round-trip times (RTT).

Parity Cloud Service: A Privacy-Protected Personal Data Recovery Service

As more and more data are generated in an electronic format, the necessity of data recovery service became larger and the development of more efficient data backup and recovery technology has been an important issue during the past decade. While lots of effective backup and recovery technologies, including data dedeplication and incremental backup, have been developed for enterprise level data backup service, few works have been done for efficient personal data recovery service. Since the privacy protection is a crucial issue for providing a personal data recovery service, a plain data backup-based recovery service is not adequate for public service. Users are not expected to upload their critical data to the internet backup server until they can fully trust the service provider in terms of the privacy protection. In this paper, we propose a novel data recovery service framework on cloud infrastructure, a Parity Cloud Service (PCS) that provides a privacy-protected personal data recovery service. The proposed framework does not require any user data to be uploaded to the server for data recovery. Also the necessary server-side resources for providing the service are within a reasonable bound.

Embedded NAND flash file system for mobile multimedia devices

In this work, we present a novel mobile multimedia file system, MNFS, which is specifically designed for NAND flash memory. Our design specifically addresses the needs of devices such as MP3 players, personal media players (PMPs), digital camcorders, etc. The file system has three novel features important in mobile multimedia applications: (1) predictable and uniform write latency, (2) quick file system mount, and (3) a small memory footprint. We implemented the proto-type file system on an embedded platform. In our experiments, MNFS exhibits uniform I/O latency for sequential write operation. It is mountable within 0.2 seconds and available with only 34 Kbytes of heap memory for a 128 Mbytes volume. The mounting time is 30 times faster compared to that of YAFFS, which is a well known file system for NAND flash memory, and the heap memory usage is only 5% of the YAFFS usage.

Transmission of video streams with constant bandwidth allocation

Encoded video streams present numerous problems in bandwidth allocation, multiplexing and admission control as a result of their Variable Bit Rate (VBR) characteristics. In particular, as video signals show a large range of variability, peak rate allocation results in very low bandwidth utilization. However, other allocation schemes tend to cause cell loss, delay and delay jitter, which make it difficult to guarantee quality of service (QoS). It is therefore necessary to develop a scheme that has no cell loss while guaranteeing QoS and achieving high bandwidth utilization at the same time. In this article, we propose a new scheme to accomplish this, which employs a 2-phase smoothing technique before transmitting VBR signal to produce an on-off signal with fixed bandwidth. Hence, it is possible to allocate a constant bandwidth for each stream, which results in high bandwidth utilization and a guaranteed deterministic QoS.

Building Concept Network-Based User Profile for Personalized Web Search

This paper presents a novel way of building the user profile of concept network for personalized search. The user profile is defined as a concept network, in which each concept is approximately represented with the formal concept analysis (FCA) theory. We assume that a concept, called ‘session interest concept’, subsume a user’s query intention during a query session and it can reflect the user’s preference. Whenever a user issues his/her query, a session interest concept is generated. Then, new concepts are merged into the current concept network (i.e., a user profile) in which recent user preferences are accumulated. According to FCA, a session interest concept is defined as a pair of extent and intent where the extent covers a set of documents selected by the user among the search results and the intent covers a set of keyword features extracted from the selected documents. And, in order to make a concept network grow, we need to calculate the similarity between a new concept and existing concepts, and to this end, we use a reference concept hierarchy called Open Directory Project. The user profile of concept network is eventually used to expand a user’s initial query. The empirical results show that our approach improves the accuracy of search results in terms of personal preference.

IO Workload Characterization Revisited: A Data-Mining Approach

Over the past few decades, IO workload characterization has been a critical issue for operating system and storage community. Even so, the issue still deserves investigation because of the continued introduction of novel storage devices such as solid-state drives (SSDs), which have different characteristics from traditional hard disks. We propose novel IO workload characterization and classification schemes, aiming at addressing three major issues: (i) deciding right mining algorithms for IO traffic analysis, (ii) determining a feature set to properly characterize IO workloads, and (iii) defining essential IO traffic classes state-of-the-art storage devices can exploit in their internal management. The proposed characterization scheme extracts basic attributes that can effectively represent the characteristics of IO workloads and, based on the attributes, finds representative access patterns in general workloads using various clustering algorithms. The proposed classification scheme finds a small number of representative patterns of a given workload that can be exploited for optimization either in the storage stack of the operating system or inside the storage device.