Pmbench: A Micro-Benchmark for Profiling Paging Performance on a System with Low-Latency SSDs

Yang, Jisoo; Seymour, Julian

doi:10.1007/978-3-319-54978-1_79

Cited by 5 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Storage tiering for price-to-performance has several implementations which can be classified into two groups: swap and cache. Swap [19] uses SSDs as part of virtual memory. Also, cache usage (e.g., disk caching [20][21][22]) caches disk data to SSDs mainly to make random access faster.…”

Section: Memory Extendermentioning

confidence: 99%

See 1 more Smart Citation

Toward Ultra-Low Latency SSDs: Analyzing the Impact on Data-Intensive Workloads

2023

Electronics

View full text Add to dashboard Cite

The recent trend in hyper-scale computing has shown that applications are getting hungrier for low, consistent latency for predictably fast service. In accordance with this change, storage vendors have innovated their SSDs to keep ultra-low latencies while delivering high IOPS. Even though these SSDs can provide significant value to a wide variety of workloads, their practical impact on performance has not been discussed much. In this context, our study aims to empirically examine the impact of emerging ultra-low latency SSDs on workload performance, particularly in comparison to the latest conventional SSDs. We conduct benchmarking using a diverse set of data-intensive workloads to comprehensively assess the performance of both ultra-low latency SSDs and conventional SSDs. Our research provides an in-depth performance analysis of the examined SSDs, shedding light on their comparative strengths and weaknesses. The results of our study contribute valuable insights into the practical implications of adopting ultra-low latency SSDs across various workloads, guiding future decisions in storage technology.

show abstract

Section: Memory Extendermentioning

confidence: 99%

“…ULL SSDs can be perfect candidates for swap partitions. In order to evaluate ULL SSDs as swap devices, we ran PMbench [19] and memcached [28] with a swap on them. The swap workload from PMbench was affected by typical latencies, and, thus, ULL SSDs required 4.1-5.6× lower latencies for file access (e.g., Figure 4m).…”

Section: Performance As Swap Devicementioning

confidence: 99%

Toward Ultra-Low Latency SSDs: Analyzing the Impact on Data-Intensive Workloads

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…2, and discussed in the following. They are taken from the processor documentation [12], and extended by measurements using lmbench [24] and pmbench [32]. The values denoted "best case" stem from the manufacturer documentation.…”

Section: Microarchitectural and Os Performance Modulatorsmentioning

confidence: 99%

“…Major page faults require disk access, which is orders of magnitude slower than the effects we are trying to observe here. For our SSD-equipped machine, we used the pmbench [32] tool and found the most frequent latency for major faults as between 262 thousand and 524 thousand cycles (coinciding with the median), same for both read and write accesses. Additionally, the distribution is tail-heavy, similar as in [32].…”

Section: Virtual Memory and Pagingmentioning

confidence: 99%

“…For our SSD-equipped machine, we used the pmbench [32] tool and found the most frequent latency for major faults as between 262 thousand and 524 thousand cycles (coinciding with the median), same for both read and write accesses. Additionally, the distribution is tail-heavy, similar as in [32]. That is, the estimated average is about one million cycles, due to some accesses exceeding several dozens of milliseconds.…”

Section: Virtual Memory and Pagingmentioning

confidence: 99%

See 1 more Smart Citation

Measuring Software Performance on Linux

Becker¹,

Chakraborty²

2018

Preprint

View full text Add to dashboard Cite

Measuring and analyzing the performance of software has reached a high complexity, caused by more advanced processor designs and the intricate interaction between user programs, the operating system, and the processor's microarchitecture. In this report, we summarize our experience on how performance characteristics of software should be measured when running on a Linux operating system and a modern processor. In particular, (1) we provide a general overview about hardware and operating system features that may have a significant impact on timing and explain their interaction, (2) we identify sources of errors that need to be controlled in order to obtain unbiased measurement results, and (3) we propose a measurement setup for Linux to minimize errors. Although not the focus of this report, we describe the measurement process using hardware performance counters, which can faithfully point to performance bottlenecks on a given processor. Our experiments confirm that our measurement setup has a large impact on the results. More surprisingly, however, they also suggest that the setup can be negligible for certain analysis methods. Furthermore, we found that our setup maintains significantly better performance under background load conditions, which means it can be used to improve high-performance applications.CCS Concepts • Software and its engineering → Software performance;

show abstract

FluidMem: Full, Flexible, and Fast Memory Disaggregation for the Cloud

Caldwell

Goodarzy

et al. 2020

2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)

View full text Add to dashboard Cite

Pmbench: A Micro-Benchmark for Profiling Paging Performance on a System with Low-Latency SSDs

Cited by 5 publications

References 10 publications

Toward Ultra-Low Latency SSDs: Analyzing the Impact on Data-Intensive Workloads

Toward Ultra-Low Latency SSDs: Analyzing the Impact on Data-Intensive Workloads

Measuring Software Performance on Linux

FluidMem: Full, Flexible, and Fast Memory Disaggregation for the Cloud

Contact Info

Product

Resources

About