Search

A crash-consistency mechanism of database application (hereinafter DBMS for short) imposes an enormous burden on the journaling process of the file system (e.g., JBD2) in that it employs regular files on the file system to persistently preserve the application’s journal data with synchronous system calls. Unfortunately, much of the previous research is impractical in real-world scenarios because they require changing a lot of source lines of code in multiple software layers of the software stack or using special hardware (e.g., the transactional flash storage or NVM technologies). In this paper, we propose a new journal mode of DBMS, called S-WAL, which compresses the raw data journaled by the database to alleviate both the redundant journaling operations and harmful write amplification. We believe that S-WAL is a practical way to support application-level crash consistency on the existing mobile devices because only a few lines of DBMS code need to be changed, without the need to employ special hardware. We demonstrate the effectiveness of S-WAL by running four popular mobile applications on the latest smartphone. Our evaluation results show that S-WAL considerably outperforms existing journal modes of DBMS in all cases. In the best case, S-WAL reduces the elapsed time by up to $7.5\times$ more than the PERSIST mode and by up to 51% more than the traditional WAL mode.

Solid-state drives (SSDs), composed of NAND flash memories, are replacing hard disk drives (HDDs) rapidly. In addition, storage class memories (SCMs) bridge the bandwidth gap between DRAM and NAND flash, thus introducing SCM to SSD further improves the solid storage performance. Different from schemes that use SCM to store file system metadata or logical to physical mapping tables, two architectures 1) use SCM as a write-back non-volatile memory (NVM) based cache, 2) use SCM as a storage device are presented in this paper. Since SCM chip latency varies due to memory device and circuit design, three SSD data management algorithms are evaluated under five SCM chip design scenarios to provide useful design guidelines of SCM/NAND flash hybrid SSD. SCM interface and capacity requirement are also analyzed. From the experimental results, less than 10% of the SCM/NAND flash capacity ratio is enough for SCM chips with 500 ns read and 5 μs write latency to boost NAND flash-only SSD speed by over 10 times when workloads own high IO skew1.

As the number of file I/O intensive mobile applications increase, in-memory file systems have gained attention. In-memory file systems provide a fast access to file data, but the main memory of the corresponding mobile devices often suffers due to its capacity limit. To provide mobile applications with more free space, the swap mechanism has been an essential technique for the overcoming of this space insufficiency; however, the existing swap mechanism is inadequate for the file I/O of mobile applications. In this study, a new in-memory file system is devised to improve the current swap mechanism in the legacy in-memory file system, whereby strip-based layouts with separated file-swap partitions are used and unnecessary file- I/O overheads are eliminated. To evaluate the proposed in-memory file system, experiments with the file-I/O benchmark were conducted. The experiment results show that, compared to the current swap scheme, the proposed swap scheme improves the overall performance by ten times on average1.

Car digital video recorders (DVRs) store realtime audio/video data at flash memory storage device. Car DVR should handle a large amount of high quality multimedia data with high reliability. However, current file systems are vulnerable to sudden-power-offs and flash memory errors. This paper proposes flash-aware cluster allocation techniques and a flash-aware journaling technique. The flash-aware cluster allocation techniques can reduce the probability of file system corruptions and file fragmentations. The flash-aware journaling technique can ensure the file system consistency without significant overheads. Experiments on a simulator and a real system showed that the proposed techniques can prevent file fragmentations and file system corruptions, and they can improve the write performance and lifetime of SD card significantly.

Recent consumer devices such as smartphones, smart TVs and tablet PCs adopt NAND flash memory as storage device due to its advantages of small size, reliability, low power consumption, and high performance. The unique characteristics of NAND flash memory require an additional software layer, called flash translation layer (FTL), between traditional file systems and flash memory. In order to reduce the garbage collection cost, FTLs generally try to separate hot and cold data. Previous hot and cold separation techniques monitor the storage access patterns within storage device, or exploit file system hints from host system. This paper proposes a novel clustered page-level mapping, called CPM, which can separate hot and cold data efficiently by allocating different flash memory block groups to different logical address regions. CPM can reduce the FTL map loading overhead during garbage collection and it does not require any high-cost monitoring overhead or host hint. This paper also proposes a K-associative version of CPM, called K-CPM, which allows different logical address regions to share a physical block group in order to achieve high block utilizations. Experimental results show that CPM improves the storage I/O performance by about 54% compared with a previous page-level mapping FTL, and K-CPM further improves the performance by about 19.4% compared with CPM1.

In recent years, ensuring the reliability of databases in battery-powered mobile devices such as smartphones and tablets has gained in importance, since most mobile applications use a lightweight embedded database. Write-ahead logging (WAL) has been one of the representative techniques in embedded databases to ensure their reliability. However, this technique causes additional data write overhead. Besides, the file system provides its own reliability technique and this may therefore cause duplicate overhead. Both types of overhead lead to the performance degradation of mobile applications and have an adverse effect on the user experience. This paper proposes an efficient in-memory write-ahead logging (IMWAL) technique for the embedded databases of mobile devices adopting nonvolatile random access memory (NVRAM). When a write operation for the embedded database is invoked, IMWAL assures that the new data in a mobile application are all written to the NVRAM as a write-ahead data log. This data log is reused to update the embedded database file by remapping the memory address and therefore it reduces the additional writes. With IMWAL, write operations can resume even after crashes occur in the mobile devices and ensure the reliability of the embedded database with performance improvement. To evaluate the proposed technique, it is implemented on the in-memory file system of a real mobile platform. Its performance is evaluated against original WAL-on mode and WAL-off mode with various experiments, including various benchmarks and real mobile application workloads. The results show that IMWAL performs 14% faster than the original WAL technique for embedded databases in real mobile devices on average1.

Journaling techniques are widely used to guarantee file system consistency of battery-powered mobile devices such as smartphones and tablets. In a journaling file system, system recovery is facilitated by first writing updated data blocks to a journal area and then periodically writing them to their home locations. However, these duplicated writes degrade the performance and shorten the lifetime of NAND flash storage in mobile devices. In particular, a lightweight database library, which is mainly used to manage application data in mobile devices, is a major cause of excessive journaling because it frequently triggers the costly file synchronization to guarantee the atomicity of transactional execution and thus generates a significant amount of synchronous random write traffic. This paper presents a novel journaling scheme, called Delta Journaling (DJ), to resolve this problem efficiently by using small-sized nonvolatile random access memory (NVRAM). DJ is based on a unique update pattern found in mobile devices, where file system updates are mostly very small. By exploiting the byteaddressable and the nonvolatile characteristics of NVRAM, DJ stores a journal block as a compressed delta in the smallsized NVRAM only when the compressed delta is small enough. Experimental results show that DJ outperforms a traditional journaling file system by up to 16.8 times for synthetic workloads. For a real-world workload, it enhances transaction throughput by 25.5% and 29.2% in ordered and journal modes, respectively, with only 16 MB NVRAM. Also, DJ enhances the lifetime of NAND flash storage by eliminating almost all journal writes without any loss of reliability.

NAND flash memory is widely used as secondary storage in portable consumer electronics devices such as smartphones and digital cameras. These devices often employ a compressed file system to efficiently manage the limited storage space. However, retrieving data from a compressed file system incurs substantial delays in launching applications due to additional decompression procedures at run time. This paper presents an efficient compressed file system manager (CFSM) that reduces the application launch time in portable consumer electronics devices. CFSM uses two novel techniques. One is the selective decompression that reduces the user-perceived latency by decompressing only the actually requested data acquired by a bulk read. The other technique is cost-aware replacement that preferentially evicts data from uncompressed file systems when memory is full because they are quicker to access than compressed data. A prototype of CFSM has been implemented on the Linux operating system. Measurement studies show that CFSM reduces the application launch latency by 28% on average compared to the well-known CramFS compressed file system.

NAND flash memory has been widely used in consumer electronic devices. However, the write and erase operations consume too much time, creating a bottleneck in system performance, which is its main drawback. Thus, improving flash memory performance is critical in enhancing user experience of consumer electronic devices. Parallel flash memory was developed to support parallel operations of flash memories. However, no currently used flash translation layers (FTLs) can fully support this ideal feature of the flash memory. An efficient and simple parallel FTL (PFTL) is presented in the present paper to maximize the I/O parallelizability of flash memories. PFTL not only addresses the requests from the upper layer file system in parallel but also reclaims the invalid blocks in parallel. A trace-driven simulation using flash storage system simulator was conducted to evaluate PFTL. The experimental results show that the time used for the read and write operations was decreased by approximately 30% under both real-world and benchmark workloads. In addition, PFTL cut the erase time by around 50%. Thus, the I/O performance of consumer electronic devices can be largely improved by using PFTL.

Flash memory can be classified into NOR type and NAND type. The NOR type memories enables fast reading with byte level I/O is developed into memory for code storage such as ROM BIOS. The NAND type memories cheaper than NOR type and therefore more widely used to larger scale systems. This paper proposed the new file translation system by making a new file structure which can decrease write operations. This file structure reduced write operation frequency of flash memory in file system layer. We can reduced write operation rate because of a write operation rate can be improved the efficiency of file translation operations. Flash Translation Layer (FTL) is to mapping a logical data address to a physical data address in flash memory, its designed to realize erase policy of data in order to perform write operation. The FTL suggests fast erase algorithm reduced write operation through a new file system structure and FTL programming. In addition, we have made the oldest data clean algorithm and then, the most recent data maintained longest as a result of experiment that the recent applied program. In this result, Data tend to be implemented again through the concept of regional and time space which appears automatically when applied program is implemented. This work proves the efficiency of the file system of NAND type flash memories through experiments. Through experiment and realization of the Flash file system, this scheme proved the efficiency of NAND-type flash file system which is required in an embedded system.

NAND flash memory is utilized as code storage as well as for file system storage in consumer electronics. The demand paging technique for NAND flash code storage can reduce the required main memory space. However, in realtime systems, demand paging may invoke several problems, one such example is unpredictable timing behavior. Moreover, when NAND flash memory is used for both code storage and file system storage, the resource conflict issue needs to be resolved to allow for simultaneous accesses of demand paging and file system requests. This paper addresses several practical problems of NAND flash-based demand paging in real-time embedded systems and proposes a non-preemptive demand paging technique to resolve the resource conflict within non-preemptive critical sections. Experiments on a real mobile phone platform show that the proposed demand paging requires no significant overhead.

Deduplication is essential for efficient nonlinear editing (NLE), as large amounts of duplicated data are caused by NLE. In this paper, a new deduplication file system is designed for an embedded system based on NAND flash memory. In the suggested file system, to reduce computation overhead, duplication caused by NLE operations is predicted considering causality between I/O operations. Furthermore, an efficient management scheme for the shared data among files is proposed in NAND flash memory, including data indexing and garbage collection. The data indexing has distinctive characteristics in that it releases the page-alignment constraint and allows page sharing. The proposed garbage collection efficiently supports shared data in NAND flash memory. With this file system, it is possible to reduce write operations for redundant data and thus use NAND flash memory space efficiently. As a result, garbage collection overhead can be reduced greatly. Moreover, the file system can be widely applied to existing NLE applications, since it is compatible with existing POSIX system calls.

For efficient non-linear editing (NLE) operations, a flash file system should be designed considering three factors: data indexing, system calls and frame header updates. Based on the hybrid architecture of phase-change RAM (PRAM) and NAND flash, we introduce a non-linear editing flash file system (NLE-FFS) which is designed for mobile multimedia devices that support NLE. In the proposed file system, the following three features are proposed. First, new data indexing scheme is proposed that is not limited by page-alignment constraint. Not only does it deal effectively with large multimedia files, it also facilitates flexible data management. Second, new system calls are proposed that minimize re-write overhead due to NLE operations by updating a small amount of metadata. Finally, an H-data block is proposed to reduce the overhead caused by frame header updates. The H-data block is a PRAM region reserved for frame header data updates. It allows byte-level updates instead of page-level updates; hence, several bytes of frame headers can be effectively updated in this region. The experimental result of this study shows that only one second is enough for a cut operation on a five-minute video irrespective of the cutting position in NLE-FFS, whereas up to 118.7 seconds are required for the same video depending on the cutting position in YAFFS2.

In this work, we present a novel mobile multimedia file system, MNFS, which is specifically designed for NAND flash memory. Our design specifically addresses the needs of devices such as MP3 players, personal media players (PMPs), digital camcorders, etc. The file system has three novel features important in mobile multimedia applications: (1) predictable and uniform write latency, (2) quick file system mount, and (3) a small memory footprint. We implemented the proto-type file system on an embedded platform. In our experiments, MNFS exhibits uniform I/O latency for sequential write operation. It is mountable within 0.2 seconds and available with only 34 Kbytes of heap memory for a 128 Mbytes volume. The mounting time is 30 times faster compared to that of YAFFS, which is a well known file system for NAND flash memory, and the heap memory usage is only 5% of the YAFFS usage.

Cost-effectiveness is one of the most critical factors in the development of portable consumer devices. The use of compression techniques is a simple but effective solution for achieving such cost-effectiveness. This paper gives a comprehensive analysis of file system level compression techniques for portable consumer devices. Since conventional compressed file systems are optimized for disk like devices and relatively abundant computing resources, they are not suitable for portable devices with small amount of memory and weak processing power. This paper presents the design and implementation of LeCramFS, which is a new read-only compressed file system designed for small portable devices and flash memory. Experiments by implementation show that the proposed file system outperforms conventional ones in terms of memory-efficiency and I/O performance.

Scalable encoding scheme enables the player or streaming server to adaptively change the playback rate of multimedia content. However, in scalable streaming of layer encoded content, sequential playback of content does not necessarily coincide with the sequential scan of a file. This property introduces another dimension of complexity in the scheduling of data block retrieval. In this work, we develop a novel file organization strategy, harmonic interleaving, which can effectively handle the dynamically changing playback rate of multimedia data retrieval. The proposed scheme not only eliminates the retrieval of unnecessary blocks but also minimizes disk head movement. Via experiment, harmonic interleaving exhibits superior disk utilization on a moderately loaded network.

Flash memory has become the most important storage media in the mobile multimedia products such as MP3 players, mobile phones, and digital cameras. Most mobile multimedia devices, however, use one of the conventional FAT file systems slightly modified for flash memory environments. Our analysis shows that theses file systems have some restriction in recording a live multimedia stream stably because they have irregular write response times. In this paper, we have considered the problems of the existing FAT file system and propose two new techniques to solve the problems. The first technique called sector reservation method reduces internal overhead effectively. And the other method called ACPA avoids the periodic cluster allocation of the conventional FAT file system and removes the frequent modifications on the file allocation table in the FAT file system. To evaluate our new techniques, we implemented a prototype real-time FAT file system on ARM9 board with our two novel techniques. The experimental results show that our system achieves our goal successfully in that its write response times are very deterministic and more uniform.

This paper presents a solution for the broadcast file system based on digital storage media command and control (DSM-CC) data carousel protocol. Given the complexity of the object carousel protocol, we innovatively modify the data carousel protocol so that the hierarchical directory structure can be transmitted. The corresponding software has been implemented in set-top boxes. With the help of the virtual filesystem switch (VFS) mechanism, the broadcast file system can be accessed through unified interfaces. Considering the differences between the broadcast file system and the traditional file system, this paper also proposes the optimized strategies while receiving and caching data from the network in order to show better performance.

A digital TV system is necessary for not only video and audio, but also data processing. Especially in the case of bidirectional broadcasting, it should manage the return channel created by the Internet, PSTN, and so on. Because of many functionalities and multitasking jobs, it needs an operating system. Embedded Linux, as open source program can increase cost effectiveness in the market and has many advantages-reusable device drivers and application programs, more convenient development environment using shell and file system, and easy resolution of problem within the open source community. In this paper, we modified the embedded Linux kernel and the cross development environment for a big-endian system, redesigned device drivers for kernel execution, and configured system memory map in order to load the Linux kernel. Also we developed a device driver for the entire system control.

This paper presents a new design and implementation of HDD (hard disk drive) embedded DSR (digital satellite receiver). The digital broadcasting technology enables multimedia access via broadcasting systems. The amount of digital data to be processed is increased remarkably as compared to the previous broadcasting environments. In this paper, a method is proposed to provide storage ability for DSR to cope with these changes. Efficient digital data storage and management technology is also discussed. The real time data recording and playback are the most important functions of the proposed system. The trick modes such as fast forward and fast backward support are the other important factors of the proposed system as compared to the previous analog video recorder. The abovementioned functions are the main evaluation criteria for the system performance. The DSR uses a new file system that is designed by considering disk cluster size and limited memory in the system, which is more appropriate than that of the general personal computer. This system enables us to watch broadcasting and to manage multimedia data efficiently.

The design and implementation of a video conference recorder on an inexpensive PC is described. The recorder can simultaneously record several video and audio (A/V) streams in Unix file format. The objectives of the file system design are high throughput and low loss rate. A hard disk device driver and a file system are modified and tuned for A/V recording. The new file system can have up to 60% performance improvement over the traditional file system. Performance results from our experiments are presented and discussed.