Log-structured storage has emerged as a prevalent paradigm in the storage domain. However, the out-of-place update mechanism generates a substantial number of invalid data blocks, and the garbage collection (GC) mechanism employed to reclaim these blocks exacerbates write amplification. Although numerous existing schemes have made significant progress in mitigating write amplification, they often incur considerable performance and memory overheads. To address this issue, we present NatSep, a novel data placement scheme that reduces write amplification while safeguarding system performance and minimizing memory overhead. The core of NatSep lies in leveraging Native Information to characterize data hotness, with the following key design components: Firstly, NatSep meticulously defines the temperature regions and implements a strict rollback-style, unidirectional linear growth writing mode for each region. Secondly, NatSep adopts a more stringent GC selection strategy, for GC within a region, it strictly retrieves from the head of each region, and for GC between regions, there are priorities. Thirdly, NatSep manages each hotness temperature region independently and establishes dynamically allocated regions for adjacent temperature regions. The experimental results demonstrate that NatSep exhibits outstanding performance advantages compared with the current state-of-the-art data placement schemes. In detail, the throughput of NatSep has increased by 26 %, the memory overhead has been reduced by 50.8 %, and the performance has been improved by$\mathbf{2 0. 6} \boldsymbol{\%}$.

Emerging Zoned Namespace (ZNS) provides hosts with fine-grained, performance-predictable storage management. ZNS organizes the address space into zones composed of fixed-size, sequentially written, non-overwritable blocks, making it suitable for log-structured file systems. However, our experimental analysis reveals that ZNS’s write restrictions introduce notable persistence overhead. Firstly, out-of-place updates of data blocks require frequent small modifications to file metadata blocks, which are typically much smaller than a block, to record the latest logical block address. Secondly, some files, such as databases’ Write-Ahead Logging files, frequently execute synchronous small writes, with I/O sizes typically smaller than a logical block. The persistence of these file metadata and file data requires writing back the entire block even if it is only partially updated. This significantly increases the I/O latency and potentially reduces device lifespan. This article proposes exZNS , an innovative extension of ZNS, designed to provide both regular zones and byte-loggable zones . By exposing the persistent write buffer of the opened zones on the device to the application, the byte-loggable zone allows for appending at byte granularity through a new set of APIs. To reduce the persistence overhead described above, we built exBlzFS , a novel high-performance file system for exZNS. exBlzFS selectively records the partial updates of metadata blocks to the byte-loggable zone to ensure metadata persistence, and persists file data to the byte-loggable zone at byte granularity to absorb the frequent small writes. Evaluations show that exBlzFS increases the IOPS of RocksDB by 42.7% and 76.3%, and reduces the device’s write traffic by 86% and 94%, compared with BlzFS and F2FS, respectively. 1

This paper proposes a two-layer structure Internet-distributed energy management strategy (ID-EMS) for connected plug-in hybrid electric vehicles (PHEVs) to deal with two significant challenges in the real-time global optimization process. One is that the traffic flow information from the commercial intelligent transportation system (ITS) is insufficient to accurately predict future driving conditions, which is alleviated by introducing the computer vision-based detection method for traffic flow density. The other is the conflict between global optimality and real-time capability, which the algorithm complexity analysis solves. Namely, the maximum problem size of the global optimization under a given computing power is derived to ensure real-time capability. Finally, an Internet-distributed vehicle-in-the-loop (ID-VIL) simulation platform is introduced to evaluate the proposed ID-EMS’s feasibility through an on-road driving experiment. Some extreme conditions, such as heavy calculation load and network failure, are also tested.

The fast app launch is crucial to users' experience and it is one of the eternal pursuits of manufacturers. Page fault is a critical factor leading to long app launch latency. Prefetching is the current method of reducing page faults during app launch. Before app launch, prefetching all demanded pages of the target app can speed up the app launch effectively, but it always uses the memory of several hundred MB, leading to low memory and slowing other apps' launch. Prefetching during application launch uses memory effectively, however, current methods are not aware of the order of pages accessed, causing noticeable accessing-prefetching order inversions, which results in limited acceleration of app launch. In order to accelerate the application launch effectively with little memory usage, we propose a Two-Phase Prefetching schema (TPP), which performs prefetching via two phases: 1) Before the app launch, to increase the efficiency of memory usage in prefetching, TPP prefetches few critical pages with app prediction, which is based on Long Short-Term Memory (LSTM) with high accuracy. 2) During app launch, TPP prefetches the rest of the critical pages via an order-aware sliding window method, resolving the accessing-prefetching order inversions and significantly reducing the app launch latency. We evaluate TPP on Google Pixel 3, compared to the state-of-the-art method, TPP reduces the application launch time by up to 52.5%, and 37% on average, and the data prefetched before the target application started is only 1.31 MB on average.

As SSD failures seriously lead to data loss and service interruption, proactive failure prediction is often used to improve system availability. However, the unidimensional SMART-based prediction models hardly predict all drive failures. Some other features applied in data centers and enterprise storage systems are not readily available in consumer storage systems (CSS). To further analyze related failures in production SSD-based CSS, we study nearly 2.3 million SSDs from 12 drive models based on a dataset of SMART logs, trouble tickets, and error logs. We discover that SMART, Firmware Version, WindowsEvent, and BlueScreenof Death (SFWB) are closely related to SSD failures. We further propose a multidimensional-based failure prediction approach (MFPA), which is portable in algorithms, SSD vendors, and PC manufacturers. Experiments on the datasets show that SFWB-based MFPA achieves a high true positive rate (98.18%) and low false positive rate (0.56%), which is 4% higher and 86% lower than the SMART-based model. It is robust and can con-tinuously predict for 2–3 months without iteration, substantially improving the system availability.

Emerging Zoned Namespace (ZNS) SSDs provide hosts with fine-grained, performance-predictable storage management. The ZNS SSD divides its address space into zones, and each zone must be written sequentially and cannot be overwritten. However, the write constraint results in frequent small modifications of file metadata to record the latest logical block addresses of the updated data blocks, increasing the overhead of fsync() system call. We comprehensively analyze the metadata overhead of fsync on a real ZNS SSD and find that (1) the update size of most metadata blocks (e.g., tens of bytes) is far less than the IO unit of the zone (e.g., 4 KiB), and frequent fsyncs cause severe metadata write amplification; (2) metadata block IOs significantly increase the fsync latency, decreasing the throughput of workloads.To reduce the metadata overhead of fsync, we build the byte-loggable zone based on the persistent write cache of the opened zone, a novel extension of ZNS, which can be appended at byte granularity instead of block. Based on the byte-loggable zone, we present BlzFS, a high-performance and crash-consistent file system for ZNS SSD. Firstly, BlzFS maintains the update ranges of the metadata block by the update bitmap. Secondly, BlzFS ensures the persistence and consistency of metadata by logging the partial updates of metadata blocks to the device’s byte-loggable zone. Finally, BlzFS restores metadata consistency by replaying the metadata update log and scanning the list of recent allocated metadata blocks. In the evaluation, BlzFS shows a 33.5%∼96.1% reduction in metadata write traffic and a 1.37×∼1.91× throughput improvement compared with the original ZNS storage system.

The Zoned Namespace (ZNS) emerges as a new storage interface with advantages such as low garbage collection overhead and low over-provisioning cost. However, it is vulnerable to fragmentation due to its out-of-place updates and the multi-threaded writing behaviors of applications. Fragmentation splits I/O requests and causes resource conflicts within the device, degrading I/O performance. Most defragmentation tools need to read the entire contents of the file from the SSD to the host memory and then rewrite the data to contiguous space in the SSD. The host-level migration operations prolong the elapsed time of defragmentation and excessive write operations for data migration even reduce the device lifetime.Our experiments discover that defragmenting data with a low degree of fragmentation or cold data provides little performance gain. With the observation, we propose a new defragmentation tool called InDeF to reduce the defragmentation overhead. InDeF combines the degree of logical and physical fragmentation and access hotness to filter out the fragments that have little impact on I/O performance for reducing the write traffic of the SSD. To take advantage of the internal flash chip parallelism, InDeF offloads the data migration on the SSD, decreasing the elapsed time of defragmentation. Evaluation results show that InDeF decreases the elapsed time of defragmentation by 91.6%∼94.2% and the amount of data migration by 38.1%∼66.7% compared with conventional defragmentation tools.

Because the increasing power density is limited by the thermal constraint, multi-core integrated systems have stepped into the dark silicon era recently, meaning not all parts of the system can be powered on at the same time. Dark silicon effects are, especially severe for 3-D microprocessors due to the even higher power density caused by the stacked structures, which greatly limit the system performances. In this article, we propose a greedy based core-cache co-optimization algorithm to optimize the performance of 3-D microprocessors in dark silicon at runtime. The new method determines many runtime settings of the 3-D system on the fly, including the active core and cache bank positions, active cache bank number, and the voltage/frequency (V/f) level of each active core, which optimizes the performance of the 3-D microprocessor under thermal constraint. Because the core-cache settings are co-optimized in the 3-D space and the power budgets are computed dynamically according to the running state of the 3-D microprocessor, the new method leads to a higher system performance compared with the existing methods. Experiments on two 3-D microprocessors show the greedy-based core-cache co-optimization algorithm outperforms the state-of-the-art 3-D dark silicon microprocessor performance optimization method by achieving a higher processing throughput with guaranteed thermal safety.