Data migration strategies (DMS) improve the overall performance of hybrid memory systems by migrating frequently accessed (hot) data to faster memory. However, designing an efficient DMS is challenging since the key metrics of DMS -hot data selection, migration granularity, and migration frequency -are sensitive to access patterns of workloads. Most existing strategies focus on only one of these metrics and often overlook the crucial impact of access patterns, resulting in sub-optimal performance and unnecessary migration traffic. In this paper, we propose AdaptHM, a fully access-pattern-aware Adaptive data migration strategy for Hybrid Memory systems. AdaptHM achieves adaptability on all three metrics through its unique multi-level data framework. First, AdaptHM adopts a group-level competition policy to select hot blocks, which responds faster to access patterns than threshold-based policies. Second, AdaptHM enables segment-level dynamic migration granularity by decoupling migration from remapping, which shows better access pattern resilience than existing schemes with fixed-size global migration granularity. Third, AdaptHM adjusts the migration frequency at set-level by periodically assessing the migration benefit, avoiding unnecessary migrations. Experimental results demonstrate that AdaptHM improves the performance by an average of 12.78% and reduces energy consumption by up to 37.24% compared to the state-of-the-art scheme.

Emerging Zoned Namespace (ZNS) SSDs divide address space into sequentially written zones and transfer garbage collection (GC) to the host, thereby providing more stable performance, increased capacity, and extended device lifespan. However, the sequential write constraint poses some problems for file system design on ZNS devices, particularly leading to bottlenecks in multi-threaded performance for concurrent write requests. Through comprehensive experiments, we analyze the scalability issues of existing POSIX file systems on NVMe ZNS SSDs and identify the root causes: (1) current file systems generally fail to simultaneously utilize the throughput of multiple zones, and (2) their methods for concurrent writing within a single zone are inefficient. To fully exploit the concurrent performance of ZNS SSDs, we propose SchInFS, a novel multi-head logging ZNS SSD file system that integrates the functions of the block I/O scheduler. Firstly, SchInFS employs a multi-head logging design to leverage the throughput of multiple zones concurrently. Secondly, it provides an independent merge queue for each log, facilitating efficient cross-thread write blocks. Finally, SchInFS uses a Block I/O Submission Controller (BSC) to ensure the timely submission of requests and ordered writing within a single zone. Evaluation on real devices demonstrates the effectiveness of SchInFS, showcasing a substantial improvement in the concurrency performance of ZNS SSDs by up to 71.94% compared to current ZNS SSD file systems.

Hybrid storage systems can fully leverage the advantages of multiple devices to achieve better performance. However, current systems are designed primarily for a slow disk with an expensive fast device at high costs. They ignore device features and workload status while placing data. The issue of cache pollution is affecting their data hotness identification. Besides, inconsistent load status in multiple devices is overlooked during migration. These shortcomings constrain the overall performance of the system.To solve this, we propose HyF2FS, a hybrid storage filesystem based on F2FS. HyF2FS features a cache-tiering integrated architecture that stores hot data and metadata in an accelerator while asynchronously migrating cold data to the SSD, which provides cost-effective opportunities to optimize device parallelism. HyF2FS uses multidimensional scores to place data on the appropriate device to achieve high bandwidth. To improve data hotness identification, HyF2FS proposes two-level counters. Besides, a migration window is employed to minimize the impact of migration on foreground I/O. By implementing these scheduling algorithms, HyF2FS can fully exploit the parallelism of both fast and slow devices. Experimental results demonstrate significant improvements in throughput (116%-244%) and latency reduction (49%-64%) compared to F2FS and other hybrid storage systems.

The space–air–ground-integrated network (SAGIN) can enhance the performance of the Internet of Vehicles (IoV). However, the basic hardware differences among communication systems are large, which leads to communication difficulties between different communication systems. To effectively manage multiple communication networks (satellite networks, air networks, and terrestrial networks) and computing resources in IoV, this article proposes a SAGIN-IoV edge–cloud architecture based on software-defined networking (SDN) and network function virtualization (NFV). In addition, we construct an optimization model based on SAGIN-IoV’s service requirements, and propose an improved algorithm. Experimental results show that the improved algorithm can effectively optimize the resource scheduling problem of SAGIN-IoV.

In the traditional cloud-based Internet of Vehicles (IoV) architecture, it is difficult to guarantee the low latency requirements of the current intelligent transportation system (ITS). As a supplement to cloud computing, fog computing can effectively alleviate the bottlenecks of cloud computing bandwidth and computing resources and improve the quality of service (QoS) of the IoV. However, as a distributed system that operates near users, fog computing has a complicated network structure. In the complex and dynamic IoV environment, to effectively manage these computing resources with different attributes and provide high-quality services, it is necessary to design an efficient architecture and a resource allocation algorithm. Therefore, on the basis of fog-cloud computing and software-defined networking (SDN), a novel 5G IoV architecture is designed. In addition, after fully considering the service requirements of the IoV, a model of four objectives is constructed, and a many-objective optimization algorithm is proposed. The experiment results show that the proposed algorithm outperforms the other state-of-the-art algorithms.