Yu Liang

Postdoc

Education

PhD in Computer Science

City University of Hong Kong
2016 - 2021

MSc in Computer Science

Shandong University
2010 - 2013

BSc in Computer Science

Shandong University
2006 - 2010

Languages

  • Chinese (Native)
  • Engilsh(Professional)

Research Interests

  • File systems and memory management of mobile devices
  • Design and optimization of mobile storage systems

Career Profile

I received my Ph.D. degree from the City University of Hong Kong and then continue to work as a postdoc in the team of Prof. Tei-Wei Kuo (Dean of College of Engineering, Fellow of ACM and IEEE). I focus on the design and optimization of mobile operating systems, aiming at the needs of rapid start-up and response of applications, and prolonging the service life of devices:

1) Put forward the cache file management technology to reduce unnecessary data writebacks to flash storage and prolong the service life of flash chips;

2) Proposed a memory replacement strategy in line with the characteristics of mobile applications to improve the startup and running performance of applications;

3) Proposed the joint optimization of file system and flash storage to improve the read and write performance and the service life of flash chips.

Publications

Conference Papers

[1] Yu Liang; Riwei Pan; Tianyu Ren; Yufei Cui; Rachata Ausavarungnirun; Xianzhang Chen; Changlong Li; Tei-Wei Kuo; Chun Jason Xue; CacheSifter: Sifting Cache Files for Boosted Mobile Performance and Lifetime, 20th USENIX Conference on File and Storage Technologies (FAST), Santa Clara, CA, USA, 2022-2-22 to 2022-2-24

[2] Yu Liang; Jinheng Li; Rachata Ausavarungnirun; Riwei Pan; Liang Shi; Tei-Wei Kuo; Chun Jason Xue; Acclaim: Adaptive Memory Reclaim to Improve User Experience in Android Systems, 2020 USENIX Annual Technical Conference (ATC), Boston, MA, USA, 2020-7-15 to 2020-7-17

[3] Yu Liang; Jinheng Li; Xianzhang Chen; Rachata Ausavarungnirun; Riwei Pan; Tei-Wei Kuo; Chun Jason Xue; Differentiating Cache Files for Fine-grain Management to Improve Mobile Performance and Lifetime, 12th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage), Boston, MA, USA, 2020-7-13 to 2020-7-14

[4] Yu Liang; Rachata Ausavarungnirun; Tei-Wei Kuo; Chun Jason Xue; Work-in-progress: Uncovering Critical Data in Launching Mobile Applications to Improve User Experience at Low Cost, 18th USENIX Conference on File and Storage Technologies (FAST '20) , Santa Clara, CA, USA, 2020-2-24 to 2019-2-27

[5] Yu Liang; Qiao Li; Chun Jason Xue; Mismatched Memory Management of Android Smartphones, 11th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage), RENTON, WA, USA, 2019-7-8 to 2019-7-9

[6] Qi Li; Aosong Deng; Congming Gao; Yu Liang; Liang Shi; Edwin H.-M. Sha; Optimizing Fragmentation and Segment Cleaning for CPS based Storage Devices, 2019 ACM/SIGAPP Symposium on Applied Computing (SAC), Limassol, Cyprus, 2019-4-8 to 2019-4-12

[7] Yu Liang; Chenchen Fu; Yajuan Du; Aosong Deng; Mengying Zhao; Liang Shi; Chun Jason Xue; An Empirical Study of F2FS on Mobile Devices, IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), Hsinchu, Taiwan, China, 2017-8-16 to 2017-8-18

Journal Papers

[1] Yu Liang; Riwei Pan; Yajuan Du; Chenchen Fu; Liang Shi; Tei-Wei Kuo; Chun Jason Xue; Read-Ahead Efficiency on Mobile Devices: Observation, Characterization, and Optimization, IEEE TRANSACTIONS ON COMPUTERS (TC), 2021, 70: 99-110

[2] Yu Liang; Cheng Ji; Chenchen Fu; Rachata Ausavarungnirun; Qiao Li; Riwei Pan; Siyu Chen;Liang Shi; Tei-Wei Kuo; Chun Jason Xue; iTRIM: I/O-Aware TRIM for Improving User Experience on Mobile Devices, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2021, 40: 1782-1795

[3] Changlong Li; Liang Shi; Yu Liang; Chun Jason Xue; SEAL: User Experience-Aware Two-Level Swap for Mobile Devices, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2020, 39: 4102-4114

[4] Qiao Li; Liang Shi; Yejia Di; Congming Gao; Cheng Ji; Yu Liang; Chun Jason Xue; Process Variation Aware Read Performance Improvement for LDPC-Based nand Flash Memory, IEEE Transactionson Reliability (TR), 2020, 69: 310-321

[5] Cheng Ji; Riwei Pan; Li-Pin Chang; Liang Shi; Zongwei Zhu; Yu Liang; Tei-Wei Kuo; Chun Jason Xue; Inspection and Characterization of App File Usage in Mobile Devices, ACM Transactions on Storage (TOS), 2020, 16: 1-25

[6] Yu Liang; Yajuan Du; Chenchen Fu; Riwei Pan; Liang Shi; Chun Jason Xue; Boosting read-ahead efficiency for improved user experience on mobile devices, SIGBED Review, 2019, 16: 75-80

Patents

[1] Jason Chun Xue, Riwei Pan, Yu Liang, Zhipeng Li, Ge Qiu, Jing Qian, Jian Yi, Jiaxin Li. Memory space management method and memory space management mechanism, 2021, China, 2021107427614

[2] Jason Chun Xue, Yu Liang, Riwei Pan, Zhipeng Li, Ge Qiu, Jing Qian, Jian Yi, Jiaxin Li. Cache file management method and mechanism, 2021, China, 2021107427864

[3] Jason Chun Xue, Yu Liang, Liang Shi. A method and electronic design for accelerating application startup, 2019, China, 2019110613620

[4] Jason Chun Xue, Liang Shi, Yu Liang. Method for separating hot and cold data, 2018, China, 2015110297112

Main Outputs for Projects

Research Institute Cooperation

[1] A TRIM optimization “f2fs: relax async discard commands more” motivated by my journal paper [2] has been submitted to the Linux kernel Archives by cooperators.

[2] Provide code interpretation and analysis of advantages and disadvantages of F2FS to help its deployment on their mobile devices.

Mobile Device Project

[1] Cache file optimization and deduplication work have been approved by manufacturer. They are most likely to be used in their mobile OS to save storage space.

[2] Provided five optimization prototypes for mobile devices (based on my five papers in 2020) and six patents. Some of them have been used in comerical smartphones.

eMMC Project

[1] Aiming at the data security of F2FS file system, a metadata and normal data separated storage scheme is proposed.

[2] To reduce data movement during GC, we propose to utilize hot/cold data of F2FS to implement data separation on eMMC.

ACADEMIC SERVICES

USENIX ATC '23 Heavy Program Committee

USENIX ATC '22 Artifact Evaluation Committee

USENIX OSDI '22 Artifact Evaluation Committee

Reviewer for International Journal of Intelligent Systems