Linux Systems
Processes, memory, CPU, storage, scheduling and system calls.
Distributed & Large-Scale Systems
I engineer systems that scale.
I study, measure, build, operate, and improve distributed and large-scale computing systems — from the behavior of a single Linux machine to systems spanning machines, networks, data, and failure.
Engineering Responsibility
Measure first. Understand deeply. Improve continuously.
My work is centered on one responsibility: understand why systems behave the way they do, measure that behavior, and improve the system.
Systems
From one machine to large-scale systems.
I approach systems from the bottom up: hardware and operating systems, processes and networks, services and databases, distributed components, and eventually large-scale platforms.
Networking
Sockets, TCP/IP, latency, throughput, congestion and failure.
Concurrency
Threads, synchronization, contention and parallel execution.
Distributed Systems
Communication, replication, consistency, consensus and fault tolerance.
Data Systems
Storage, databases, partitioning, streaming and data movement.
Large-Scale Systems
Scalability, availability, reliability, observability and cost.
Cloud & Infrastructure
Containers, orchestration, deployment and resilient infrastructure.
Research Systems
Experimentation, measurement, modeling, implementation and analysis.
Method
The engineering loop.
Theory tells me what may happen. Code lets me create the conditions. Measurement tells me what actually happened.
OBSERVE
→
MEASURE
→
ASK WHY
→
MODEL
→
CODE
→
EXPERIMENT
→
EXPLAIN
→
IMPROVE
↺
Real-World Observations
Systems are understood through evidence.
I use real machines, real workloads, measurements, controlled experiments, and failure analysis to turn system behavior into understanding.
My Linux Laboratory
sys — an Ubuntu Linux machine used to investigate CPU, memory, processes, networking, storage, performance and system behavior.
CPUMemoryProcessesLatencyThroughput
My Android Laboratory
My Android smartphone is another Linux-based laboratory for studying real-world system behavior. I use it to observe hardware, operating system, networking, memory, processes, security, and runtime characteristics through direct measurement.
Engineering Stack
Tools for understanding and building systems.
CC++LinuxTCP/IPSocketsGitPythonSQLPostgreSQLMySQLDockerKubernetesKafkaSparkHadoopDistributed SystemsCloud Computing
Current Work
Building capability, one system at a time.
My current work combines systems experimentation, Linux and C, networking, distributed-systems fundamentals, implementation, measurement, and research-oriented learning.
Measure
Establish quantitative baselines for latency, throughput, utilization, concurrency, errors, resource consumption and reliability.
Build
Implement systems from the ground up, beginning with Linux and networking and progressing toward distributed components and data platforms.
Improve
Stress systems, expose bottlenecks and failure modes, explain observed behavior, redesign, and measure again.
Research
Move from implementation and measurement toward models, papers, experiments and new system designs.
Distributed & Large-Scale Systems
Understand the system.
Measure the system.
Improve the system.
This website documents that engineering practice — the systems I study, experiments I run, software I build, and what those systems teach me.