PgBouncer: From 45K to 210K Queries per Second
A benchmark-driven look at how one PgBouncer process became a CPU bottleneck, how multiple processes scaled it, and where the next limit appeared.
ls -lt ~/notes
field notes - the things I measured
Benchmark-driven notes on databases, Python, distributed systems, vector search, and performance.
4 published entries
Archive
TurboVec on 100M RAG Vectors
A benchmark-driven look at what happens when vector compression moves from 10M scale to 100M scale.
1M Rows Into Postgres in 1.29 Seconds
A benchmark-driven look at how much the PostgreSQL write path matters when loading large datasets.
Large JSON in Python: Parser Speed Is Not the Whole Problem
A benchmark-driven look at why large JSON ingestion in Python is often more about memory shape than raw parser speed.
Author
Written by Karan Jadhav, a backend engineer interested in databases, distributed processing, and finding the real bottleneck. Questions or corrections are welcome at karan@jadhav.dev.