SWShenggang Wan

Shenggang Wan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shenggang Wan has a total of 25 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    ABS: An Availability-Balanced Data Placement Strategy to Improve Overall Data Availability in Decentralized Storage

    by Weichen Huang, Shenggang Wan

    Decentralized storage systems rely on heterogeneous edge nodes and therefore often suffer from weak availability guarantees. Although redundancy mechanisms such as replication and erasure coding can improve data availability, the overall data availability still depends heavily on how replicas or coded blocks are placed across nodes with different availability levels. Existing placement approaches can be broadly divided into two categories: random strategies and greedy strategies. Random strategies ignore node heterogeneity, while greedy strategies tend to over-rely on a limited number of highly available nodes and decline as data loading proceeds. In this article, we develop an availability analysis model for decentralized storage under both replication and erasure coding. We find that, in most cases, balancing availability across data items helps improve the overall data availability. Based on these insights, we propose ABS, an A vailability- B alanced placement S trategy. ABS uses grouped bidirectional matching to balance the data-item availabilities. More specifically, under replication, it steers each data item toward the standard value; under erasure coding, it adopts a variance-greedy final selection rule. We further incorporate several complementary techniques to optimize read efficiency, load balance, and migration cost. Prototyping and simulation-based experiments show that ABS consistently outperforms random and greedy baselines in average data availability under both replication and erasure coding settings.

  • Open Access

    Boosting Burst I/O Performance under Heterogeneous Hybrid Storage Workloads via DUal I/O IssuE Thresholds

    by Yongjun Pan, Le Yu, Jiali Liu, Jiayi Cheng, Bingyi Cai, Shenggang Wan

    I/O schedulers are the key component to maintain high quality of services under homogeneous hybrid storage workloads, e.g., multiple concurrently running sustained workloads. However, the long hardware queue for I/O requests under I/O schedulers, which is utilized to exploit the substantial parallelism of underlying storage devices, induces unbearable I/O latency for the latency-sensitive burst workloads, particularly under heterogeneous hybrid storage workloads, i.e., concurrently running burst and sustained workloads. Based on our dedicated observation that limited slots in the hardware queue are sufficient to maintain a high throughput for the throughput-sensitive sustained workloads consisting of oversized I/O requests, we propose a novel I/O scheduling framework DUET that deploys DUal I/O issuE Thresholds to boost the I/O performance of burst workloads under heterogeneous hybrid workloads. Specifically, DUET utilizes a high threshold to limit the total amount of data requested by the sustained workloads in the hardware queue when only sustained workloads are actively running. According to our observation, a proper high threshold not only ensures a high throughput for sustained workloads, but also significantly reduces the queuing time for the I/O requests of upcoming burst workloads. To further reduce the I/O latency of burst workloads, DUET adopts a low threshold when sustained and burst workloads are simultaneously present. Through adjusting this low threshold, we can conveniently tradeoff throughput of sustained workloads against I/O latency of burst workloads. Results from prototyping experiments demonstrate the effectiveness and efficiency of DUET.

  • Open Access

    Data Deduplication Based on Content Locality of Transactions to Enhance Blockchain Scalability

    by Chenglong Yi, Jintong Liu, Shenggang Wan, Juntao Fang, Bin Sun, Liqiang Zhang

    Blockchain is a promising infrastructure for the internet and digital economy, but it has serious scalability problems, that is, long block synchronization time and high storage cost. Conventional coarse-grained data deduplication schemes (block or file level) are proved to be ineffective on improving the scalability of blockchains. Based on comprehensive analysis on typical blockchain workloads, we propose two new locality concepts (economic and argument locality) and a novel fine-grained data deduplication scheme (transaction level) named Alias-Chain. Specifically, Alias-Chain replaces frequently used data, for example, smart contract arguments, with much shorter aliases to reduce the block sizes, which results in both shorter synchronization time and lower storage cost. Furthermore, to solve the potential consistency issue in Alias-Chain, we propose two complementary techniques: one is generating aliases from history blocks with high consistency, and the other is speeding up the generation of aliases via a specific algorithm. Our simulation results show: (1) the average transfer and SC-call transaction (a transaction used to call the smart contracts in the blockchain) sizes can be significantly reduced by up to 11.03% and 79.44% in native Ethereum, and up to 39.29% and 81.84% in Ethereum optimized by state-of-the-art techniques; and (2) the two complementary techniques well address the inconsistency risk with very limited impact on the benefit of Alias-Chain. Prototyping-based experiments are further conducted on a testbed consisting of up to 3200 miners. The results demonstrate the effectiveness and efficiency of Alias-Chain on reducing block synchronization time and storage cost under typical real-world workloads.


  • Open Access

    gPPM: A Generalized Matrix Operation and Parallel Algorithm to Accelerate the Encoding/Decoding Process of Erasure Codes

    by Shiyi Li, Qiang Cao, Shenggang Wan, Wen Xia, Changsheng Xie

    Erasure codes are widely deployed in modern storage systems, leading to frequent usage of their encoding/decoding operations. The encoding/decoding process for erasure codes is generally carried out using the parity-check matrix approach. However, this approach is serial and computationally expensive, mainly due to dealing with matrix operations, which results in low encoding/decoding performance. These drawbacks are particularly evident for newer erasure codes, including SD and LRC codes. To address these limitations, this article introduces the Partitioned and Parallel Matrix ( PPM ) algorithm. This algorithm partitions the parity-check matrix, parallelizes encoding/decoding operations, and optimizes calculation sequence to facilitate fast encoding/decoding of these codes. Furthermore, we present a generalized PPM ( gPPM ) algorithm that surpasses PPM in performance by employing fine-grained dynamic matrix calculation sequence selection. Unlike PPM, gPPM is also applicable to erasure codes such as RS code. Experimental results demonstrate that PPM improves the encoding/decoding speed of SD and LRC codes by up to 210.81%. Besides, gPPM achieves up to 102.41% improvement over PPM and 32.25% improvement over RS regarding encoding/decoding speed.


  • Open Access

    Boosting the Performance of Degraded Reads in RS-coded Distributed Storage Systems

    by Tian Xie, Juntao Fang, Shenggang Wan, Changsheng Xie, Xubin He

    Reed-Solomon (RS) codes have been increasingly adopted by distributed storage systems in place of replication,because they provide the same level of availability with much lower storage overhead. However, a key drawback of those RS-coded distributed storage systems is the poor latency of degraded reads, which can be incurred by data failures or hot spots,and are not rare in production environments. To address this issue, we propose a novel parallel reconstruction solution called APLS. APLS leverages all surviving source nodes to send the data needed by degraded reads and chooses light-loaded starter nodes to receive the reconstructed data of those degraded reads. Hence, the latency of the degraded reads can be improved.Prototyping-based experiments are conducted to compare APLS with ECPipe, the state-of-the-art solution of improving the latency of degraded reads. The experimental results demonstrate that APLS effectively reduces the latency, particularly under heavy or medium workloads.

  • Data Representation Aware of Damage to Extend the Lifetime of MLC NAND Flash Memory

    by Bin Zhou, Ting Ye, Shenggang Wan, Xubin He, Weijun Xiao, Changsheng Xie

    Multilevel cell (MLC) NAND flash memory uses the voltages of the memory cells to represent bits, but high voltages cause much more damage on the cells than low voltages. Free space in MLC can be leveraged to reduce the usage of the high voltages and thus extend the lifetime of MLC. However, limited by the conventional data representation rule that represents bits by the voltage of one single cell, the high voltages are used in a high probability. To fully explore the potential of the free space on reducing the usage of high voltages without changing the total density of MLC, we propose a novel data representation aware of damage, named DREAM. DREAM uses the low voltage combinations of multiple cells instead of the voltage of one single cell to represent bits. It enables to represent the same bits through flexibly replacing the high voltages in some cells with the low voltages in other cells when free space is available. Hence, high voltages which cause more damage are less used and the lifetime of the MLC memory is extended. In addition, complementary techniques are proposed to mitigate performance loss induced by DREAM. Theoretical analysis and simulation results demonstrate the effectiveness and efficiency of DREAM.


  • A-Cache: Asymmetric Buffer Cache for RAID-10 Systems Under a Single-Disk Failure to Significantly Boost Availability

    by Bin Zhou, Hong Jiang, Qiang Cao, Shenggang Wan, Changsheng Xie

    The RAID-10 architecture has been widely deployed in commercial and industrial storage environments over the past two decades due to its high reliability, availability, and performance. However, during the recovery process of a single disk failure, which accounts for more than 99.75% of the disk failure scenarios, it is still at a high risk of data loss and suffers from a degradation of user I/O performance, which result from the severe interference between the user and recovery I/Os. Based on our observations and analyses, we find highly asymmetric disk bandwidth utilization and disk I/O interference during the recovery process of the RAID-10 systems under the single faulty-disk condition. Motivated by the fact that this asymmetry can be leveraged to significantly and simultaneously speed up the recovery and user I/O performances. As a result, we propose a novel asymmetric buffer cache management scheme, called A-Cache, to mitigate this asymmetry by allocating cache space asymmetrically between the disks that do not participate in the recovery process and those that do. To verify the effectiveness of the A-cache, we have integrated A-Cache into the popular cache algorithms LRU, named A-LRU. The evaluation of our prototype system demonstrates that A-LRU is able to significantly speed up the recovery speed and average user I/O latency under various typical configurations, compared to the original LRU, without any additional hardware cost.


  • Design and Evaluation of a Risk-Aware Failure Identification Scheme for Improved RAS in Erasure-Coded Data Centers

    by Weichen Huang, Juntao Fang, Shenggang Wan, Changsheng Xie, Xubin He

    Data reliability and availability, and serviceability (RAS) of erasure-coded data centers are highly affected by data repair induced by node failures. In a traditional failure identification scheme, all chunks share the same identification time threshold, thus losing opportunities to further improve the RAS. To solve this problem, we propose RAFI, a novel risk-aware failure identification scheme. In RAFI, chunk failures in stripes experiencing different numbers of failed chunks are identified using different time thresholds. For those chunks in a high-risk stripe, a shorter identification time is adopted, thus improving the overall data reliability and availability. For those chunks in a low-risk stripe, a longer identification time is adopted, thus reducing the repair network traffic. Therefore, RAS can be improved simultaneously. We also propose three optimization techniques to reduce the additional overhead that RAFI imposes on management nodes and to ensure that RAFI can work properly under large-scale clusters. We use simulation, emulation, and prototyping implementation to evaluate RAFI from multiple aspects. Simulation and prototype results prove the effectiveness and correctness of RAFI, and the performance improvement of the optimization techniques on RAFI is demonstrated by running the emulator.


  • Isolation: Inexpensively separating cold data via garbage collection to improve the lifetime and performance of NAND flash SSDs

    by Bin Zhou, Shenggang Wan, Changsheng Xie

    Summary: An effective way to mitigate the lifetime and performance problems of NAND flash SSDs induced by garbage collection is separating the cold data and hot data. However, all existing solutions do this separation from the viewpoint of the hot data and thus suffer from expensive cost on monitoring the update behaviors of workloads. Different from the conventional wisdom, we propose to do the separation from the viewpoint of the cold data, which is rooted on the following two dedicated observations. First, the data migrated by garbage collection demonstrate a cold property compared with the other data. Second, it is inexpensive to separate the former data from the latter data. In the proposed method, named Isolation, we inexpensively separate the cold data via garbage collection. More specifically, through writing the data migrated by garbage collection (cold data) to dedicated blocks and writing the other data (hot data) to other blocks, the separation is done naturally. To evaluate Isolation, we conduct extensive trace‐driven simulations under seven typical workloads. The simulation results demonstrate the effectiveness and efficiency of Isolation. In most cases, Isolation can reduce the number of erasures and average I/O response time up to 47.3% and 80.1%, respectively. Existing approaches integrated with Isolation can further reduce the number of erasures and average I/O response time up to 7.8%‐18.5% and 10.7%‐41.4%, respectively.