Failures in a large distributed storage system are often critical, leading to unexpected I/Os that are required to restore the system's health and ensure availability. With the advent of NVMe-oF, the disaggregation of compute and storage resources presents an opportunity to minimize the negative impact of the compute failure by reattaching the storage resources. However, despite advances in hardware, modern distributed storage systems have not yet fully adapted to the disaggregated architecture. There are four main reasons: (1) lack of awareness of recoverable failure events in the disaggregated architecture, (2) incorrect availability management with respect to the NVMe-oF fault domains, (3) unnecessary data rebalance I/Os for uniform distribution triggered even after the failure is recovered, (4) load imbalance caused by asymmetric deployment of compute resources after blind relocation for recovery. To address these challenges, we introduceNVMe-oF-R, a resilient disaggregated distributed storage architecture for fast recovery.NVMe-oF-Rcomprises three techniques: (1)NVMe-oF adapter, which detects recoverable failure events and orchestrates relocation; (2)DCRUSH, a data placement strategy that considers the NVMe-oF based disaggregation architecture; and (3)Relocater, which efficiently relocates failed compute resources and fixes stragglers that arise after recovery. We implementNVMe-oF-Ratop the storage orchestration layer in a CRUSH-based distributed storage system, Ceph. Our experimental results demonstrate thatNVMe-oF-Rcan eliminate unnecessary recovery traffic and reduce recovery time by more than 50%.

The deep learning-based satellite image analysis and retraining systems are getting emerging technologies to enhance the capability of the sophisticated analysis of terrestrial objects. In principle, to apply the explainable DNN model for the process of satellite image analysis and retraining, we consider a new acceleration scheduling mechanism. Especially, the conventional DNN acceleration schemes cause serious performance degradation due to computational complexity and costs in satellite image analysis and retraining. In this article, to overcome the performance degradation, we propose cooperative scheduling schemes for explainable DNN acceleration in analysis and retraining process. For the purpose of it, we define the latency and energy cost modeling to derive the optimized processing time and cost required for explainable DNN acceleration. Especially, we show a minimum processing cost considered in the proposed scheduling via layer-level management of the explainable DNN on FPGA-GPU acceleration system. In addition, we evaluate the performance using an adaptive unlabeled data selection scheme with confidence threshold and a semi-supervised learning driven data parallelism scheme in accelerating retraining process. The experimental results demonstrate that the proposed schemes reduce the energy cost of the conventional DNN acceleration systems by up to about 40% while guaranteeing the latency constraints.

Since the concept of Software-Defined Networking (SDN) and Network Function Virtualization (NFV) has been proposed, service providers leverage the concepts to provide their services efficiently. Mobile CORD (M-CORD) is a platform to provide 5G network services using containerized VNFs in Multi-access Edge Clouds (MECs) at the central offices of telcos. However, current M-CORD does not include network and resource monitoring functions. In this paper, we present the design and implementation of a monitoring system to help efficient management and operation of the M-CORD platform configured in multi-site. Through this monitoring system, we can monitor the computing resource usages and data traffic load of each VNF container in M-CORD. We conducted experiments on our multi-cluster testbed to evaluate our monitoring system in terms of CPU and memory usage. As a result, our proposed monitoring system has a slight increase in CPU and memory usage, but it was able to perform M-CORD monitoring functions well.

In order to manage data center networks, distributed SDN controllers such as ONOS controller have been researched and used. In this paper, we propose simple live distributed controller migration scheme and design the orchestrator for this scheme. This scheme basically transfers an distributed SDN controller from the overloaded physical machine to the under-loaded physical machine. According to experimental results, a data center network is broken without our scheme when computing load increases. On the other hands, our proposed scheme reduces an average delay as well as avoids a breakdown of the data center network.