Amber: Enabling Precise Full-System Simulation with Detailed Modeling of All SSD Resources

Gouk, Donghyun; Kwon, Miryeong; Zhang, Jie; Koh, Sungjoon; Choi, Won-Il; Kim, Nam Sung; Kandemir, Mahmut

doi:10.1109/micro.2018.00045

Cited by 47 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiment environment configuration. We leverage Amber [6], a full-system simulator, to perform precise simulation on the SSD hardware and the existing software from OS to SSD firmware. In our experiment, the storage is an NVMe SSD instance with TLC flash [14].…”

Section: Methodsmentioning

confidence: 99%

FastDrain: Removing Page Victimization Overheads in NVMe Storage Stack

Zhang¹,

Kwon²,

Han³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Host-side page victimizations can easily overflow the SSD internal buffer, which interferes I/O services of diverse user applications thereby degrading user-level experiences. To address this, we propose FastDrain, a co-design of OS kernel and flash firmware to avoid the buffer overflow, caused by page victimizations. Specifically, FastDrain can detect a triggering point where a near-future page victimization introduces an overflow of the SSD internal buffer. Our new flash firmware then speculatively scrubs the buffer space to accommodate the requests caused by the page victimization. In parallel, our new OS kernel design controls the traffic of page victimizations by considering the target device buffer status, which can further reduce the risk of buffer overflow. To secure more buffer spaces, we also design a latency-aware FTL, which dumps the dirty data only to the fast flash pages. Our evaluation results reveal that FastDrain reduces the 99 th response time of user applications by 84%, compared to a conventional system.

show abstract

Section: Methodsmentioning

confidence: 99%

FastDrain: Removing Page Victimization Overheads in NVMe Storage Stack

Zhang¹,

Kwon²,

Han³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compared with the existing Flash-based SSD simulators, it can be easily integrated into the publicly-available computer system simulators and evaluate the performance with a variety of storage technologies and microstructures. Amber is a new simulation framework based on SimpleSSD [ 12 ]. Through detailed modeling of the whole system, the system is simulated accurately.…”

Section: Related Workmentioning

confidence: 99%

A New NVM Device Driver for IoT Time Series Database

Cai

Liu

et al. 2022

Micromachines

View full text Add to dashboard Cite

Numerous IoT devices in IoT systems collect data concurrently, which brings great challenges to IoT time series databases to store and manage these data. NVM device has high read–write speed compared with HDD and Flash-based SSD, and it is a possible way to solve the storage bottleneck. However, there are some limitations that should be solved such as the overhead of the I/O software stack for NVM devices and the lack of optimization for IoT time series databases in a Linux environment. By analyzing the characteristics of IoT time series databases and NVM devices, we optimized the device driver of NVM in Linux and provide a new structure of a NVM device driver for IoT time series databases. A multi-queue management strategy and a lightweight load balance mechanism based on frequency were designed to improve the concurrency and efficiency of NVM device drivers. The prototype of an IoT-oriented NVM device driver named TS-PMEM was implemented based on an open-source NVM device driver. Six prototypes were used for evaluation with YCSB-TS, a test tool for time series databases. Results showed that TS-PMEM can improve write throughput of the time series databases by 18.6%, query throughput by 10.6%, and reduce the write latency by 8.3% and query latency by 6.4%.

show abstract

“…Full System Simulator. We implement IceClave with a computational SSD simulator developed based on the SimpleSSD [38], Gem5 [37], and USIMM [21] simulator. This allows us to conduct the study with different SSD configurations, which cannot be easily conducted with a real SSD board.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…Specifically, we implement IceClave with a full system simulator gem5 [37], and integrate an SSD simulator SimpleSSD [38] and memory simulator USIMM [21] into it for supporting secure instorage computing. We also develop a system prototype to verify the core functions of IceClave with a real-world OpenSSD Cosmos+ FPGA board [84].…”

Section: Introductionmentioning

confidence: 99%

IceClave: A Trusted Execution Environment for In-Storage Computing

Kang

Yang

Jia

et al. 2021

MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture

View full text Add to dashboard Cite

In-storage computing with modern solid-state drives (SSDs) enables developers to offload programs from the host to the SSD. It has been proven to be an effective approach to alleviate the I/O bottleneck. To facilitate in-storage computing, many frameworks have been proposed. However, few of them treat the in-storage security as the first citizen. Specifically, since modern SSD controllers do not have a trusted execution environment, an offloaded (malicious) program could steal, modify, and even destroy the data stored in the SSD.In this paper, we first investigate the attacks that could be conducted by offloaded in-storage programs. To defend against these attacks, we build a lightweight trusted execution environment, named IceClave for in-storage computing. IceClave enables security isolation between in-storage programs and flash management functions that include flash address translation, data access control, and garbage collection, with TrustZone extensions. IceClave also achieves security isolation between in-storage programs by enforcing memory integrity verification of in-storage DRAM with low overhead. To protect data loaded from flash chips, IceClave develops a lightweight data encryption/decryption mechanism in flash controllers. We develop IceClave with a full system simulator. We evaluate IceClave with a variety of data-intensive applications such as databases. Compared to state-of-the-art in-storage computing approaches, IceClave introduces only 7.6% performance overhead, while enforcing security isolation in the SSD controller with minimal hardware cost. IceClave still keeps the performance benefit of in-storage computing by delivering up to 2.31× better performance than the conventional host-based trusted computing approach. * Co-primary authors.† Work done while visiting the Systems Platform Research Group at UIUC. ‡ Now at NVIDIA.

show abstract

Amber: Enabling Precise Full-System Simulation with Detailed Modeling of All SSD Resources

Cited by 47 publications

References 29 publications

FastDrain: Removing Page Victimization Overheads in NVMe Storage Stack

FastDrain: Removing Page Victimization Overheads in NVMe Storage Stack

A New NVM Device Driver for IoT Time Series Database

IceClave: A Trusted Execution Environment for In-Storage Computing

Contact Info

Product

Resources

About