Search

With in-memory databases (IMDBs), where all data sets reside in main memory for fast processing speed, logging and checkpointing are essential for achieving persistence in data. Logging of IMDBs has evolved to reduce run-time overhead to suit the systems, but this causes an increase in recovery time. Checkpointing technique compensates for these problems with logging, but existing schemes often incur high costs due to reduced system throughput, increased latency, and increased memory usage. In this paper, we propose a checkpointing scheme using validity tracking-based compaction (VTC), the technique that tracks the validity of logs in a file and removes unnecessary logs. The proposed scheme shows extremely low memory usage compared to existing checkpointing schemes, which use consistent snapshots. Our experiments demonstrate that checkpoints using consistent snapshot increase memory footprint by up to two times in update-intensive workloads. In contrast, our proposed VTC only requires 2% additional memory for checkpointing. That means the system can use most of its memory to store data and process transactions.

High-performance storage devices, such as Non-Volatile Memory express Solid-State Drives (NVMe SSDs), have been widely adopted in data centers. Especially, multiple storage devices provide higher I/O performance compared with a single device. However, the performance can be reduced in the case of workloads with mixed read and write requests (e.g., key-value stores) even though multiple storage devices are adopted. This is because read requests can be blocked until the processing for write requests is finished. In this article, we propose an I/O isolation scheme to improve the performance of the key-value store for multiple SSDs. In our scheme, we classify files of the key-value store and deploy files to the separated storage devices according to the characteristics of each file. Thus, read/write operations are performed in different storage devices. In addition, we propose two different device mapping methods, namely fixed and adaptive device mapping to deploy files to the proper device. We implement our scheme in RocksDB with multiple storage devices (six NVMe SSDs) and extend our scheme on an open-channel SSD, which reveals internal hardware architecture to verify the effectiveness of read/write isolation within a single storage device. The experimental results demonstrate that our scheme improves performance by up to 29% and 26% in the open-channel SSD and multiple storage devices, respectively, compared with the existing scheme.

The emerging computational storage drives (CSDs) provide new opportunities by moving data computation closer to the storage. Performing computation within storage drives enables data pre/post-processing without expensive data transfers. Moreover, large amounts of data can be processed in parallel thanks to the nature of the field-programmable gate array (FPGA) included in CSDs. In a CSD, there are several implementation techniques that support parallel processing, each of which provides a different degree of parallelism. However, without sufficient understanding of the parallel processing techniques of CSD, it can lead to overhead due to misuse rather than benefiting from task offloading. Thus, to exploit the best performance of CSDs, it is important to properly adjust the degree of parallelism of each implementation technique. In this paper, we focus on the study of the differences in CSD performance according to various combinations of parallel processing techniques. To investigate the performance differences, we implement and offload the data verification algorithm to the CSD and analyze the performance and resource utilization. The experimental results show that implementing the data verification algorithm with a sufficient understanding of CSD’s parallel processing techniques can improve the performance by up to 20 times. Moreover, even with the same degree of parallelism, the performance can differ by 59% depending on the combination of implementation techniques. These results imply that proper orchestration of different implementation techniques leads to better performance and efficient resource utilization.

As flash-based solid-state drive (SSD) becomes more prevalent because of the rapid fall in price and the significant increase in capacity, customers expect better data services than traditional disk-based systems. However, the order of magnitude performance provided and new characteristics of flash require a rethinking of data services. For example, backup and recovery is an important service in a database system since it protects data against unexpected hardware and software failures. To provide backup and recovery, backup/recovery tools or backup/recovery methods by operating systems can be used. However, the tools perform time-consuming jobs, and the methods may negatively affect run-time performance during normal operation even though high-performance SSDs are used. To handle these issues, we propose an SSD-assisted backup/recovery scheme for database systems. Our scheme is to utilize the characteristics (e.g., out-of-place update) of flash-based SSD for backup/recovery operations. To this end, we exploit the resources (e.g., flash translation layer and DRAM cache with supercapacitors) inside SSD, and we call our SSD with new backup/recovery functionality BR-SSD. We design and implement the functionality in the Samsung enterprise-class SSD (i.e., SM843Tn) for more realistic systems. Furthermore, we exploit and integrate BR-SSDs into database systems (i.e., MySQL) in replication and redundant array of independent disks (RAID) environments, as well as a database system in a single BR-SSD. The experimental result demonstrates that our scheme provides fast backup and recovery but does not negatively affect the run-time performance during normal operation.

Solid-state drives (SSDs) have accelerated the architectural evolution of storage systems with several characteristics (e.g., out-of-place update) compared with hard disk drives (HDD). Out-of-place update of SSDs naturally can support transaction mechanism which is commonly used in systems to provide crash consistency. Thus, transactional functionality has been recently implemented inside solid-state drives (SSDs). However, this approach must be re-evaluated for enterprise storage with a standard interface to investigate their benefits in a more realistic and standard fashion. In this article, we explore the implications and challenges of transactional SSDs with different experiments. To evaluate the potential benefit of transactional SSDs, we design and implement the transactional functionality in a Samsung enterprise-class and SATA-based SSD (i.e., SM843TN) called TxSSD. We modify the local file systems (i.e., ext4 and btrfs) and a distributed parallel file system (i.e., Lustre) to utilize TxSSDs. Our modified file systems with TxSSDs provide crash consistency without redundant writes. We evaluate our file systems by using multiple micro and macro benchmarks. We analyze the performance results and demonstrate that TxSSDs may generate an overhead for supporting transactional functionality inside SSD.

Distributed ledger technology faces scalability problems due to a long commit time despite recent successes for cryptocurrency. Small group consensus studies have improved this scalability of distributed ledgers. However, they still have problems of the consensus process itself. For example, most blockchain systems perform serialized block proposal and consensus processing, guarantee the finality with high overhead, and handle byzantine nodes inefficiently. To address these problems, we propose a consensus system, named graph learning byzantine fault tolerance (GL BFT), which offers high parallelism and low latency under Byzantine fault. To do this, we enable a parallel pipelined agreement by separating the block proposal and the consensus process. Second, we devise two techniques of merging blocks and commit learning to guarantee the finality with little overhead. Finally, we present a path learning approach which chooses optimal paths to handle Byzantine fault. The proposed GL BFT can achieve instant finality with low message overhead among a small group of nodes even if Byzantine nodes exit. Also, we evaluate its performance on an open source blockchain protocol. Experimental results show that our design reduces data traffic required by the consensus up to 30%, one transaction is finalized within a few seconds, and optimal performance is maintained.

Popular deep learning frameworks like PyTorch utilize GPUs heavily for training, and suffer from out-of-memory (OOM) problems if memory is not managed properly. In this paper, we propose a modification that utilizes CUDA Unified Memory (UM) to expand GPU memory to the available host memory space so that practicality for the programmer can increase, and OOM memory errors will not result for any workload. We also pinpoint performance issues that result from our modifications to the framework, and outline future plans like reducing redundant memory copies, prefetching, and memory advising techniques to improve upon our design. Our implementation shows that PyTorch UM performance overheads are minimal when the data footprint is below GPU memory capacity.

Recently, graphic processing unit (GPU) multitasking has become important in many platforms since an efficient GPU multitasking mechanism can enable more GPU-enabled tasks running on limited physical GPUs. However, current GPU multitasking technologies, such as NVIDIA Multi-Process Service (MPS) and Hyper-Q may not fully utilize GPU resources since they do not consider the efficient use of intra-GPU resources. In this paper, we present smCompactor, which is a fine-grained GPU multitasking framework to fully exploit intra-GPU resources for different workloads. smCompactor dispatches any particular thread blocks (TBs) of different GPU kernels to appropriate stream multiprocessors (SMs) based on our profiled results of workloads. With smCompactor, GPU resource utilization can be improved as we can run more workloads on a single GPU while their performance is maintained. The evaluation results show that smCompactor improves resource utilization in terms of the number of active SMs by up to 33% and it reduces the kernel execution time by up to 26% compared with NVIDIA MPS.

Many cloud services perform periodic database backup to keep the data safe from failures such as sudden system crashes. In the database system, two techniques are widely used for data backup and recovery: a physical backup and a logical backup. The physical backup uses raw data by copying the files in the database, whereas the logical backup extracts data from the database and dumps it into separated files as a sequence of query statements. Both techniques support a full backup strategy that contains data of the entire database and incremental backup strategy that contains changed data since a previous backup. However, both strategies require additional I/O operations to perform the backup and need a long time to restore a backup. In this paper, we propose an efficient backup and recovery scheme by exploiting write-ahead logging (WAL) in database systems. In the proposed scheme, for backup, we devise a backup system to use log data generated by the existing WAL to eliminate the additional I/O operations. To restore a backup, we utilize and optimize the existing crash recovery procedure of WAL to reduce recovery time. For example, we divide the recovery range and applying the backup data for each range independently via multiple threads. We implement our scheme in MySQL, a popular database management system. The experimental result demonstrates that the proposed scheme provides instant backup while reducing recovery time compared with the existing schemes.