목록논문/관심 논문 (23)

Happy to visit my research note ^^

(관심 논문) GL-Cache: Group-level learning forefficient and high-performance caching

Juncheng Yang, Carnegie Mellon University; Ziming Mao, Yale University; Yao Yue, Pelikan Foundation; K. V. Rashmi, Carnegie Mellon University February 21–23, 2023 • Santa Clara, CA, USA USENIX Association 21st USENIX Conference on File and Storage Technologies Abstract Web applications는 low-latency, high-throughput services를 위해 software cache에 매우 의존한다. 변화하는 workloads에 대응하기 위해, 최근 몇 년간 learned ca..
논문/관심 논문 2023. 3. 21. 14:30
(관심 논문) FUSEE: A Fully Memory-DisaggregatedKey-Value Store

Jiacheng Shen1 ∗ , Pengfei Zuo2 , Xuchuan Luo3 , Tianyi Yang1 , Yuxin Su4 , Yangfan Zhou3 , and Michael R. Lyu1 1The Chinese University of Hong Kong, 2Huawei Cloud, 3Fudan University, 4Sun Yat-sen University February 21–23, 2023 • Santa Clara, CA, USA USENIX Association 21st USENIX Conference on File and Storage Technologies Abstract Distributed in-memory key-value (KV) stores는 더 높은 resource uti..
논문/관심 논문 2023. 3. 20. 02:51
(관심 논문) ADOC: Automatically Harmonizing Dataflow Between Componentsin Log-Structured Key-Value Stores for Improved Performance

Jinghuan Yu, City University of Hong Kong; Sam H. Noh, UNIST & Virginia Tech; Young-ri Choi, UNIST; Chun Jason Xue, City University of Hong Kong February 21–23, 2023 • Santa Clara, CA, USA USENIX Association 21st USENIX Conference on File and Storage Technologies Abstract Log-Structure Merge-tree (LSM) based Key-Value (KV) system은 널리 사용되고 있다. 그러나 LSM-KV system에서는 write operation에 대한 압력이 커지면 perf..
논문/관심 논문 2023. 3. 20. 02:47
(관심 논문) PERSEUS: A Fail-Slow Detection Framework for Cloud Storage Systems

Ruiming Lu1*, Erci Xu3,1*, Yiming Zhang2†, Fengyi Zhu3 , Zhaosheng Zhu3 , Mengtian Wang3 , Zongpeng Zhu3 , Guangtao Xue1†, Jiwu Shu2 , Minglu Li1,4 , and Jiesheng Wu3 1Shanghai Jiao Tong University, 2Xiamen University, 3Alibaba Inc., and 4Zhejiang Normal University February 21–23, 2023 • Santa Clara, CA, USA USENIX Association 21st USENIX Conference on File and Storage Technologies Abstract 본 논문..
논문/관심 논문 2023. 3. 19. 22:15
(관심 논문) InftyDedup: Scalable and Cost-Effective CloudTiering with Deduplication

Iwona Kotlarska, Andrzej Jackowski, Krzysztof Lichota, Michal Welnicki, and Cezary Dubnicki, 9LivesData, LLC; Konrad Iwanicki, University of Warsaw February 21–23, 2023 • Santa Clara, CA, USA USENIX Association 21st USENIX Conference on File and Storage Technologies Abstract Cloud tiering은 최근 backup solution에서 중요해진 on-premise storage에서 선택한 data를 cloud로 이동시키는 과정을 말한다. 한번 backup이 일어나고 그다음에 일어나는 ba..
논문/관심 논문 2023. 3. 19. 13:53
(관심 논문) ParaRC: Embracing Sub-Packetization for RepairParallelization in MSR-Coded Storage

Xiaolu Li† , Keyun Cheng‡ , Kaicheng Tang‡ , Patrick P. C. Lee‡ , Yuchong Hu† , Dan Feng† , Jie Li∗ , and Ting-Yi Wu∗ †Huazhong University of Science and Technology ‡The Chinese University of Hong Kong ∗Huawei Technologies Co., Ltd., Hong Kong February 21–23, 2023 • Santa Clara, CA, USA USENIX Association 21st USENIX Conference on File and Storage Technologies Abstract Minimum-storage regenerati..
논문/관심 논문 2023. 3. 18. 22:03
(관심 논문) Practical Design Considerations for Wide Locally Recoverable Codes (LRCs)

Saurabh Kadekodi∗ , Shashwat Silas∗ , David Clausen, Arif Merchant Google February 21–23, 2023 • Santa Clara, CA, USA USENIX Association 21st USENIX Conference on File and Storage Technologies Abstract Large-scale storage clusters의 대부분 data는 # erasure coding이 사용된다. # Exascale에서는 # low storage overhead, efficient reconstruction, and easy deployment를 위해 erasure code를 최적화하는 것이 중요하다. (+참고 1) Locally..
논문/관심 논문 2023. 3. 17. 23:55
이전 Prev 1 2 3 Next 다음