File system aging—increasing the relevance of file system benchmarks

Smith, K. A.; Seltzer, Margo

doi:10.1145/258623.258689

Cited by 28 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, there are a number of issues left unexplored even by Chen, such as the slow fragmentation of data and free space in file systems over time and its effect on file system performance [21]. Other factors are usually ignored, such as the interplay of multiple I/O streams accessing a single device, which can result in two sequential streams with potentially excellent performance being converted at the device into a single 'random' stream with horrendous performance.…”

Section: I/o Benchmarkingmentioning

confidence: 99%

lmbench: an extensible micro-benchmark suite

Staelin

2005

Softw: Pract. Exper.

View full text Add to dashboard Cite

lmbench is a powerful and extensible suite of micro-benchmarks that measures a variety of important aspects of system performance. It has a powerful timing harness that manages most of the 'housekeeping' chores associated with benchmarking, making it easy to create new benchmarks that analyze systems or components of specific interest to the user. In many ways lmbench is a Swiss army knife for performance analysis. It includes an extensive suite of micro-benchmarks that give powerful insights into system performance. For those aspects of system or application performance not covered by the suite, it is generally a simple task to create new benchmarks using the timing harness. lmbench is written in ANSI-C and uses POSIX interfaces, so it is portable across a wide variety of systems and architectures. It also includes powerful new tools that measure performance under scalable loads to analyze SMP and clustered system performance. 1080C. STAELIN lmbench does not include benchmarks that measure all possible operations or combinations of operations, but it is extensible. This allows the user to create benchmarks that measure performance of particular subsystems, combinations of operations, or application components. For example, one of the lmbench developers was developing an image processing application where the bottleneck was a convolution operation between the input image and a fixed-size mask, so he developed a few different convolution implementations and measured their performance on different combinations of hardware and compilers and discovered that there was no single optimal implementation for all platforms.lmbench analyzes parallel and distributed system performance by measuring system performance under scalable load. This means that the user can specify the number of processes that will be executing the benchmarked feature in parallel during the measurements. It is possible to utilize this framework to develop benchmarks to measure distributed application performance, but it is primarily intended to measure the performance of multiple processes using the same system resource at the same time.In general the benchmarks report either the latency or bandwidth of an operation or data pathway. The exceptions are generally those benchmarks that report on a specific aspect of the hardware, such as the processor clock rate, which is reported in megahertz and nanoseconds.lmbench consists of three major components: a timing harness, the individual benchmarks built on top of the timing harness, and the various scripts and glue that build and run the benchmarks and process the results. The timing harness is the heart of the system. It manages the actual benchmarking process: starting the benchmarked activity, repeating the benchmarked activity as long as necessary to ensure accurate results, and finally managing the statistical analysis to report representative results. Great care is taken in the design and implementation of this timing harness to ensure that as many sources of experimental and measurement error are r...

show abstract

Section: I/o Benchmarkingmentioning

confidence: 99%

lmbench: an extensible micro-benchmark suite

Staelin

2005

Softw: Pract. Exper.

View full text Add to dashboard Cite

show abstract

“…With a block size of 4KB, one "extent" can map into a maximize continuous physical space of 128M[2,3]. Although ext4 has introduced many technologies that aim to prevent fragments, yet the system still vulnerable to large quantities of discontinuous fragments as the system is growing older [6,7].…”

Section: Related Workmentioning

confidence: 99%

“…Ext4 [1,2,3] can expand to 1024PB, compared with ext3's 16TB [4,5], thus supporting more big-files and bigger files. On the other hand, as the long-time usage of file system, increasing discontinuous segments are formed which we called "system aging" [6,7]. Too many quantities of segments deteriorate the performance of the system, especially those giant file systems.…”

Section: Introductionmentioning

confidence: 99%

Fragmentation Degree Research Based on File’s Layout

Zhu

Zhang

Wang

et al. 2011

AMM

View full text Add to dashboard Cite

Numerous resource allocating and releasing will cause fragmentation which will seriously affect the I/O performance of file systems. One method to solve this problem is file defragmentation. This paper focuses on fragmentation detection, the key part of the file defragmentation. We estimate file fragmentation situation through file’s layout, and then analyze the detailed effects of the situation on performance measurement. Then we quantize this by the file’s “fragmentation degree” through theoretical and experimental analyses. Finally we use it to estimate the file’s fragmentation and decide whether the file needs to be defragmented.

show abstract

“…1) Filesystems: Fragmented I/Os can be produced by a highly utilized filesystem, in which files are fragmented into multiple segments [14]. Sequential access to a fragmented file causes fragmented I/Os at the block level.…”

Section: E Prior Work For the Fragmented I/omentioning

confidence: 99%

Matrix-Stripe-Cache-Based Contiguity Transform for Fragmented Writes in RAID-5

Baek¹,

Park²

2007

IEEE Trans. Comput.

View full text Add to dashboard Cite

Given that contiguous reads and writes between a cache and a disk outperform fragmented reads and writes, fragmented reads and writes are forcefully transformed into contiguous reads and writes via a proposed matrix stripe cachebased contiguity transform (MSC-CT) method, which employs a rule of consistency for data integrity at the block level, and a rule of performance that ensures no performance degradation. MSC-CT performs for reads and writes, both of which are produced by write requests from a host, as a write request from a host employs reads for parity-update and writes to disks in a RAID-5 array. MSC-CT is compatible with existing disk technologies. The proposed implementation in a Linux kernel delivers a peak throughput that is 3.2 times higher than a case without MSC-CT on representative workloads. The results demonstrate that MSC-CT is extremely simple to implement, has low overhead, and is ideally suited for RAID controllers not only for random writes but also for sequential writes in various realistic scenarios.

show abstract

File system aging—increasing the relevance of file system benchmarks

Cited by 28 publications

References 20 publications

lmbench: an extensible micro-benchmark suite

lmbench: an extensible micro-benchmark suite

Fragmentation Degree Research Based on File’s Layout

Matrix-Stripe-Cache-Based Contiguity Transform for Fragmented Writes in RAID-5

Contact Info

Product

Resources

About