Longfei Luo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Longfei Luo has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Liang Shi
East China Normal University
8 shared publications - Yina Lv
School of Informatics, Xiamen University
4 shared publications - Dingcui Yu
MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application, East China Normal University
3 shared publications - Yunpeng Song
MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application and the School of Computer Science and Technology, East China Normal University, Shanghai, China
3 shared publications - Changlong Li
East China Normal University
2 shared publications - Chun Jason Xue
Mohamed bin Zayed University of Artificial Intelligence
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 56-63
MQSim 2.0: A Framework for Realistic Studies of AI-Era SSDs and Disaggregated Storage
Modern storage systems are being re-architected across several coupled layers: dense QLC media with pSLC caching and one-shot programming, host-directed placement (FDP, ZNS), disaggregated NVMe-oF data paths, and flash-management logic that can span SSDs, hosts, and DPUs, a regime driven by AI serving and dense multi-tenant cloud storage alike. Existing SSD simulators model storage through device-centric abstractions or support these mechanisms along separate axes, making their end-to-end interactions difficult to study in one framework. We present MQSim 2.0, a composable storage-system simulator that supports direct-attached and disaggregated deployments and uses SplitFTL to model flash-management decomposition across the device and an upstream controller. We validate MQSim 2.0 against a TLC NVMe Gen5 SSD and a real 24-SSD DPU-based storage enclosure, achieving throughput/latency MAPE of 7.9%/3.5% and 4.4%/4.8%, respectively. We then use MQSim 2.0 to study a disaggregated KV-cache design combining retention-aware placement, ZNS backends, and DPU-resident control, which reduces write amplification by 48% and P99 latency by 31% over the evaluated JBOF baseline.
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 56-63
Open AccessMQSim 2.0: A Framework for Realistic Studies of AI-Era SSDs and Disaggregated Storage
Modern storage systems are being re-architected across several coupled layers: dense QLC media with pSLC caching and one-shot programming, host-directed placement (FDP, ZNS), disaggregated NVMe-oF data paths, and flash-management logic that can span SSDs, hosts, and DPUs, a regime driven by AI serving and dense multi-tenant cloud storage alike. Existing SSD simulators model storage through device-centric abstractions or support these mechanisms along separate axes, making their end-to-end interactions difficult to study in one framework. We present MQSim 2.0, a composable storage-system simulator that supports direct-attached and disaggregated deployments and uses SplitFTL to model flash-management decomposition across the device and an upstream controller. We validate MQSim 2.0 against a TLC NVMe Gen5 SSD and a real 24-SSD DPU-based storage enclosure, achieving throughput/latency MAPE of 7.9%/3.5% and 4.4%/4.8%, respectively. We then use MQSim 2.0 to study a disaggregated KV-cache design combining retention-aware placement, ZNS backends, and DPU-resident control, which reduces write amplification by 48% and P99 latency by 31% over the evaluated JBOF baseline.
- Open Access
- 20 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 1153-1159
DISS: A Novel Data Invalidation Scheme for Swap-Data on Flash Storage Systems
Storage swapping has been a critical technique used to relieve memory pressure and improve user experience. However, it generates lots of data writes in flash storage, deteriorating the lifetime and performance. In this paper, inspired by empirical studies on swap data access characteristics, we propose a novel data invalidation scheme, namely DISS, which includes two methods. First, a cross-layer swap-data invalidation method is proposed to invalidate swapped-in data at a low cost. Second, a swap data separation method is proposed to schedule swap data and file-backed data into different places. Experimental results show that DISS achieves encouraging flash lifetime and performance optimization.
- 20 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 1153-1159
Open AccessDISS: A Novel Data Invalidation Scheme for Swap-Data on Flash Storage Systems
Storage swapping has been a critical technique used to relieve memory pressure and improve user experience. However, it generates lots of data writes in flash storage, deteriorating the lifetime and performance. In this paper, inspired by empirical studies on swap data access characteristics, we propose a novel data invalidation scheme, namely DISS, which includes two methods. First, a cross-layer swap-data invalidation method is proposed to invalidate swapped-in data at a low cost. Second, a swap data separation method is proposed to schedule swap data and file-backed data into different places. Experimental results show that DISS achieves encouraging flash lifetime and performance optimization.
- Open Access
- 20 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 21 (4) , 1-25
Access Characteristic-Guided Remote Swapping Across Mobile Devices
Memory swapping ensures smooth application switching for mobile systems by caching applications in the background. To further play the role of memory swapping, remote swapping across mobile devices has been widely studied, which caches applications to nearby remote devices by remote paging. However, due to the massive remote I/Os and unguaranteed swap throughput, the current remote swapping is limited with an unsatisfactory user experience, especially under variable network conditions. This paper first studies the access characteristics of applications and clarifies the impact of various network traffic on remote swapping. Motivated by these, an efficient access characteristic-guided remote swapping framework (ACR-Swap + ) is proposed to optimize remote swapping across mobile devices with resilient remote paging. ACR-Swap + first performs selective remote paging based on the swap-in frequency of different processes and then prefetches data across devices based on the process running states. Finally, it conducts hierarchical remote paging to avoid the impact of network traffic on remote swapping. Evaluations on Google Pixel 6 show that ACR-Swap + reduces the application switching latency by 21.6% and achieves a negligible performance fluctuation under various network traffic compared to the state of the art.
- 20 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 21 (4) , 1-25
Open AccessAccess Characteristic-Guided Remote Swapping Across Mobile Devices
Memory swapping ensures smooth application switching for mobile systems by caching applications in the background. To further play the role of memory swapping, remote swapping across mobile devices has been widely studied, which caches applications to nearby remote devices by remote paging. However, due to the massive remote I/Os and unguaranteed swap throughput, the current remote swapping is limited with an unsatisfactory user experience, especially under variable network conditions. This paper first studies the access characteristics of applications and clarifies the impact of various network traffic on remote swapping. Motivated by these, an efficient access characteristic-guided remote swapping framework (ACR-Swap + ) is proposed to optimize remote swapping across mobile devices with resilient remote paging. ACR-Swap + first performs selective remote paging based on the swap-in frequency of different processes and then prefetches data across devices based on the process running states. Finally, it conducts hierarchical remote paging to avoid the impact of network traffic on remote swapping. Evaluations on Google Pixel 6 show that ACR-Swap + reduces the application switching latency by 21.6% and achieves a negligible performance fluctuation under various network traffic compared to the state of the art.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
ElasticZRAM: Revisiting ZRAM for Swapping on Mobile Devices
Modern mobile devices adopt two-level memory swapping consisting of ZRAM and storage devices to relieve memory pressure. In the swap subsystem, ZRAM can improve application responsiveness and reduce write traffic to storage devices while consuming physical memory and additional CPU cycles. To better utilize ZRAM and improve system performance, we propose ElasticZRAM, an elastic ZRAM to redesign the traditional memory swapping with full awareness of the characteristics of applications and NAND flash-based storage devices on mobile devices. Experimental results on Google Pixel 6 demonstrate that ElasticZRAM improves application response time by up to 24.8% with negligible overhead compared with state-of-the-arts.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessElasticZRAM: Revisiting ZRAM for Swapping on Mobile Devices
Modern mobile devices adopt two-level memory swapping consisting of ZRAM and storage devices to relieve memory pressure. In the swap subsystem, ZRAM can improve application responsiveness and reduce write traffic to storage devices while consuming physical memory and additional CPU cycles. To better utilize ZRAM and improve system performance, we propose ElasticZRAM, an elastic ZRAM to redesign the traditional memory swapping with full awareness of the characteristics of applications and NAND flash-based storage devices on mobile devices. Experimental results on Google Pixel 6 demonstrate that ElasticZRAM improves application response time by up to 24.8% with negligible overhead compared with state-of-the-arts.
- Open Access
- 15 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 21 (1) , 1-23
Critical Data Backup with Hybrid Flash-Based Consumer Devices
Hybrid flash-based storage constructed with high-density and low-cost flash memory has become increasingly popular in consumer devices in the last decade due to its low cost. However, its poor reliability is one of the major concerns. To protect critical data for guaranteeing user experience, some methods are proposed to improve the reliability of consumer devices with non-hybrid flash storage. However, with the widespread use of hybrid storage, these methods will result in severe problems, including significant performance and endurance degradation. This is caused by the fact that the different characteristics of flash memory in hybrid storage are not considered, e.g., performance, endurance, and access granularity. To address these problems, a critical data backup (CDB) design is proposed to ensure critical data reliability at a low cost. The basic idea is to accumulate two copies of critical data in the fast memory first to make full use of its performance and endurance. Then, one copy will be migrated to the slow memory in the stripe to avoid the write amplification caused by different access granularity between them. By respecting the different characteristics of flash memory in hybrid storage, CDB can achieve encouraging performance and endurance improvement compared with the state-of-the-art. Furthermore, to avoid performance and lifetime degradation caused by the backup data occupying too much space of fast memory, CDB Pro is designed. Two advanced schemes are integrated. One is making use of the pseudo-single-level-cell (pSLC) technique to make a part of slow memory become high-performance. By supplying some high-performance space, data will be fully updated before being evicted to slow memory. More invalid data are generated which reduces eviction costs. Another is to categorize data into three types according to their different life cycles. By putting the same type of data in a block, the eviction efficiency is improved. Therefore, both can improve device performance and lifetime based on CDB. Experiments are conducted to prove the efficiency of CDB and CDB Pro. Experimental results show that compared with the state-of-the-arts, CDB can ensure critical data reliability with lower device performance and lifetime loss whereas CDB Pro can diminish the loss further.
- 15 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 21 (1) , 1-23
Open AccessCritical Data Backup with Hybrid Flash-Based Consumer Devices
Hybrid flash-based storage constructed with high-density and low-cost flash memory has become increasingly popular in consumer devices in the last decade due to its low cost. However, its poor reliability is one of the major concerns. To protect critical data for guaranteeing user experience, some methods are proposed to improve the reliability of consumer devices with non-hybrid flash storage. However, with the widespread use of hybrid storage, these methods will result in severe problems, including significant performance and endurance degradation. This is caused by the fact that the different characteristics of flash memory in hybrid storage are not considered, e.g., performance, endurance, and access granularity. To address these problems, a critical data backup (CDB) design is proposed to ensure critical data reliability at a low cost. The basic idea is to accumulate two copies of critical data in the fast memory first to make full use of its performance and endurance. Then, one copy will be migrated to the slow memory in the stripe to avoid the write amplification caused by different access granularity between them. By respecting the different characteristics of flash memory in hybrid storage, CDB can achieve encouraging performance and endurance improvement compared with the state-of-the-art. Furthermore, to avoid performance and lifetime degradation caused by the backup data occupying too much space of fast memory, CDB Pro is designed. Two advanced schemes are integrated. One is making use of the pseudo-single-level-cell (pSLC) technique to make a part of slow memory become high-performance. By supplying some high-performance space, data will be fully updated before being evicted to slow memory. More invalid data are generated which reduces eviction costs. Another is to categorize data into three types according to their different life cycles. By putting the same type of data in a block, the eviction efficiency is improved. Therefore, both can improve device performance and lifetime based on CDB. Experiments are conducted to prove the efficiency of CDB and CDB Pro. Experimental results show that compared with the state-of-the-arts, CDB can ensure critical data reliability with lower device performance and lifetime loss whereas CDB Pro can diminish the loss further.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (5) , 1618-1622
Revisiting TRIM on High-Density Flash-Based Hybrid Storage Systems
Hybrid solid state drives (SSDs) that integrate high-performance (HP) and large-capacity (LC) flash are widely used due to their cost-effectiveness. The TRIM command, which is a popular command in normal SSDs to improve performance and endurance, is also recommended in hybrid SSDs. However, employing TRIM on hybrid SSDs as on normal SSDs will induce performance loss and suboptimal endurance due to the different characteristics of flash in hybrid SSDs. To solve the problem, this article first explores the critical factors of issuing TRIM commands to different flash. Then, this article proposed a differential TRIM method (dTRIM), which suggests performing early TRIM on HP flash and lazy TRIM on high-capacity flash. Specifically, early TRIM will minimize garbage collection costs while lazy TRIM tries to avoid conflicting user requests. Experimental results demonstrate that dTRIM can significantly improve the performance and endurance of hybrid SSDs compared with the state-of-the-arts.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (5) , 1618-1622
Revisiting TRIM on High-Density Flash-Based Hybrid Storage Systems
Hybrid solid state drives (SSDs) that integrate high-performance (HP) and large-capacity (LC) flash are widely used due to their cost-effectiveness. The TRIM command, which is a popular command in normal SSDs to improve performance and endurance, is also recommended in hybrid SSDs. However, employing TRIM on hybrid SSDs as on normal SSDs will induce performance loss and suboptimal endurance due to the different characteristics of flash in hybrid SSDs. To solve the problem, this article first explores the critical factors of issuing TRIM commands to different flash. Then, this article proposed a differential TRIM method (dTRIM), which suggests performing early TRIM on HP flash and lazy TRIM on high-capacity flash. Specifically, early TRIM will minimize garbage collection costs while lazy TRIM tries to avoid conflicting user requests. Experimental results demonstrate that dTRIM can significantly improve the performance and endurance of hybrid SSDs compared with the state-of-the-arts.
- 1 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 33-38
Latency Aware Page Migration for Read Performance Optimization on Hybrid SSDs
The high-density flash memory makes it possible to store more information in a memory cell, while the drawbacks to it are degraded performance, less endurance, and wide variation of read latency. The prevalent hybrid solid state drives (SSDs) utilize a single-level cell (SLC) region as the write cache of high-density flash memory region and solve the problem of writes. However, this design did not take the read latency variation into consideration. Through evaluations on real storage device, we demonstrated the variation of read latency and presented the benefits and limitations on read performance optimization. Motivated by that, an efficient migration strategy, latency aware page migration (LAPM), is proposed. Its basic idea is to identify frequently read pages with high read latency and migrate them to the SLC region to improve the overall read performance. Experimental results show that LAPM can effectively reduce the read latency by 20% on average over the baseline while lowering the migration traffic to the device by up to 40%, compared with state-of-the-arts.
- 1 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 33-38
Latency Aware Page Migration for Read Performance Optimization on Hybrid SSDs
The high-density flash memory makes it possible to store more information in a memory cell, while the drawbacks to it are degraded performance, less endurance, and wide variation of read latency. The prevalent hybrid solid state drives (SSDs) utilize a single-level cell (SLC) region as the write cache of high-density flash memory region and solve the problem of writes. However, this design did not take the read latency variation into consideration. Through evaluations on real storage device, we demonstrated the variation of read latency and presented the benefits and limitations on read performance optimization. Motivated by that, an efficient migration strategy, latency aware page migration (LAPM), is proposed. Its basic idea is to identify frequently read pages with high read latency and migrate them to the SLC region to improve the overall read performance. Experimental results show that LAPM can effectively reduce the read latency by 20% on average over the baseline while lowering the migration traffic to the device by up to 40%, compared with state-of-the-arts.
- Open Access
- 22 June 2021
- Published by Association for Computing Machinery (ACM)
- p. 45-50
SFP
Currently, most of the Flash-based storage systems reduce the performance gap between the main memory and storage by data prefetching. However, conventional prefetching techniques perform well on hard disk drives but have limited effectiveness and efficiency on Flash. It is because the complicate data access patterns in modern systems have not been well considered. In this paper, we propose SFP, a smart file-aware prefetching scheme for Flash-based storage systems. SFP demonstrates that prefetching accuracy and efficiency can be improved comprehensively in a file-aware approach. Furthermore, three schemes are proposed: file access pattern learning, dynamic window-based file prefetching, and learning model size optimization. Experiments on the real server show that SFP reduces the access latency by up to 40% compared with the state-of-the-art with low memory and computation cost.
- 22 June 2021
- Published by Association for Computing Machinery (ACM)
- p. 45-50
Open AccessSFP
Currently, most of the Flash-based storage systems reduce the performance gap between the main memory and storage by data prefetching. However, conventional prefetching techniques perform well on hard disk drives but have limited effectiveness and efficiency on Flash. It is because the complicate data access patterns in modern systems have not been well considered. In this paper, we propose SFP, a smart file-aware prefetching scheme for Flash-based storage systems. SFP demonstrates that prefetching accuracy and efficiency can be improved comprehensively in a file-aware approach. Furthermore, three schemes are proposed: file access pattern learning, dynamic window-based file prefetching, and learning model size optimization. Experiments on the real server show that SFP reduces the access latency by up to 40% compared with the state-of-the-art with low memory and computation cost.
- 1 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 41 (3) , 544-557
Tail Latency Optimization for LDPC-Based High-Density and Low-Cost Flash Memory Devices
Flash memory has been developed with bit density improvement, technology scaling, and 3-D stacking. With this trend, its reliability has been significantly degraded. Error correction code (ECC), such as low-density parity code (LDPC), which has strong error correction capability, has been deployed to solve this problem. However, one of the critical issues of LDPC is that it would introduce a long decoding latency on devices with low reliability. In this case, tail latency would happen, which will significantly impact the quality of service. In this work, a set of smart refresh schemes is proposed to optimize the tail latency. The basic idea of the work is to refresh data when the accessed data have a long decoding latency. Two smart refresh schemes are proposed for this work. The first refresh scheme is designed to refresh data with a long access latency when they are accessed several times. The second refresh scheme is designed to periodically check data with an extremely long access latency and refresh them. To further optimize the refresh overhead caused by the above refresh schemes, a dual-ECC-based refresh scheme is proposed. Besides, a mathematical model for all proposed schemes is constructed to clarify the benefit of each scheme. The experimental results show that the proposed schemes can significantly improve the tail latency with acceptable overhead. What is more, the access performance is well maintained compared with the state-of-the-art work.
- 1 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 41 (3) , 544-557
Tail Latency Optimization for LDPC-Based High-Density and Low-Cost Flash Memory Devices
Flash memory has been developed with bit density improvement, technology scaling, and 3-D stacking. With this trend, its reliability has been significantly degraded. Error correction code (ECC), such as low-density parity code (LDPC), which has strong error correction capability, has been deployed to solve this problem. However, one of the critical issues of LDPC is that it would introduce a long decoding latency on devices with low reliability. In this case, tail latency would happen, which will significantly impact the quality of service. In this work, a set of smart refresh schemes is proposed to optimize the tail latency. The basic idea of the work is to refresh data when the accessed data have a long decoding latency. Two smart refresh schemes are proposed for this work. The first refresh scheme is designed to refresh data with a long access latency when they are accessed several times. The second refresh scheme is designed to periodically check data with an extremely long access latency and refresh them. To further optimize the refresh overhead caused by the above refresh schemes, a dual-ECC-based refresh scheme is proposed. Besides, a mathematical model for all proposed schemes is constructed to clarify the benefit of each scheme. The experimental results show that the proposed schemes can significantly improve the tail latency with acceptable overhead. What is more, the access performance is well maintained compared with the state-of-the-art work.