Devon O'dell
Software Engineer at Google
San Francisco Bay Area United States
Summary
🤩
RockstarDevon O'dell is a seasoned software engineer with 19 years of experience, currently at Google and based in the San Francisco Bay Area. He specializes in backend systems, performance engineering, and concurrency, with notable open-source contributions that include optimizing Ganglia’s monitoring core and hardening Facebook’s libphenom for concurrent use. Known as a “debugger and concurrency nut,” he blends low-level C systems expertise—hash algorithms, lock strategies, epoch-based memory reclamation—and practical network I/O improvements to squeeze latency and throughput gains. Colleagues rely on him to untangle tricky race conditions and refactor legacy code for production-scale reliability. An often-confused but highly effective engineer, he brings quiet rigor and a track record of measurable performance wins to distributed systems challenges.
19 years of coding experience
Dutch, English
Stackoverflow
2,340reputation
93kreached
36answers
0questions
posix
top-5%
Github Skills (19)
c1110
data-structure10
c1710
performance-optimization10
hashtable10
data-structures10
concurrency10
algorithms9
posix9
networking8
system-design8
embedded6
socket6
macos6
varnish6
Programming languages (12)
Github contributions (5)
ganglia/monitor-core
Jan 2014 - Feb 2015
Ganglia Monitoring core
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:16 commits, 2 PRs, 4 comments in 1 year 1 month
Contributions summary:Devon significantly contributed to improving the performance and functionality of the `ganglia/monitor-core` repository, primarily by refactoring and optimizing the hash table implementation. They introduced a new hash algorithm (FNV1a) and replaced the previous locking strategy with APR thread locks to enhance concurrency. Furthermore, the user implemented direct communication with `rrdcached` and addressed performance bottlenecks in data reading from the network, including buffer management improvements. These changes aimed to streamline data processing and improve overall system efficiency.
monitoringprometheus
facebookarchive/libphenom
Jun 2013 - Jun 2013
An eventing framework for building high performance and high scalability systems in C.
Role in this project:Back-end Developer
Back-end DeveloperContributions:9 commits in 1 day
Contributions summary:Devon focused on refactoring and improving the `libphenom` C library, particularly the counter and hash set functionalities. They converted data structures to utilize `ck_hs` (concurrent hash set), implemented epoch-based SMR (Safe Memory Reclamation) for thread safety and optimized performance. The user also addressed several stylistic issues and made various code improvements to improve code quality and thread safety.
eventingstream-processinginfinibandperformancehigh-scalability
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.