Levin Li

Distributed System Engineer at TaoBao Inc.

Beijing, China
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Levin Li is a seasoned Distributed System Engineer with 16 years' experience, currently optimizing parallel and MPI-based machine learning workflows and maintaining large-scale MPI platforms at Taobao/Alibaba. He is a core developer of Sheepdog, a distributed storage system for QEMU, where his work on object list caching and recovery optimizations measurably improved list retrieval speed and reduced I/O during cluster recovery. Levin has also extended cluster resource managers (Torque) with job-level cgroup isolation and memory/cpu controls, and authored open-source IM projects including Hybrid and Openfetion. Comfortable in C/Linux/Vim/Git, he pairs deep systems engineering with a practical focus on performance and recoverability—often improving efficiency by rethinking data structures and cache behavior.
code16 years of coding experience
bookM.E., Communication and Information System, M.E., Communication and Information System at Beijing University of Post and Telecommunications
bookBS, Communication Engineering, BS, Communication Engineering at Ocean University of China
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (6)

c1710
data-storage10
distributed-systems10
distributed-file-system10
c1110
performance-optimization9

Programming languages (5)

JavaCGoCommon LispPython

Github contributions (5)

github-logo-circle
sheepdog/sheepdog

Mar 2012 - Dec 2012

Distributed Storage System for QEMU
Role in this project:
userBack-end Developer
Contributions:117 commits in 9 months
Contributions summary:Levin's contributions focused on implementing and optimizing the object list cache within the distributed storage system. They added a red-black tree-based object list cache and applied it to various modules, significantly improving the speed of retrieving object lists. Furthermore, the user optimized the cluster's recovery process to reduce I/O operations. The user also refactored the object cache to utilize a list for improved efficiency.
iscsiiscsi-targetdistributed-storageblockdeviceqemu-kvm
pai-eas/eas-python-sdk

May 2019 - Oct 2022

Contributions:28 commits, 15 PRs, 26 pushes in 3 years 5 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Levin Li - Distributed System Engineer at TaoBao Inc.