From 245 Peak-Time Pods to Around 100: Halving Go Server CPU with DynamoDB SDK v2
Finding a reflection bottleneck with Pyroscope and moving to guregu/dynamo v2: 59% less CPU per request and roughly half as many HPA pods.
Performance, infrastructure and the decisions behind reliable services.
Finding a reflection bottleneck with Pyroscope and moving to guregu/dynamo v2: 59% less CPU per request and roughly half as many HPA pods.
An investigation that began with an 85% memory alert, traced 57 million unidentified objects, and ultimately found the real cause: ghost keys.
Hello, I’m Simon (Sangwon Lee), a server engineer on the allocation systems team. This is part two of “What Was Filling Up MemoryDB?” Part one followed our investigation into what…
Comparing mmap and direct embedding to remove the GeoIP database heap copy found with Pyroscope, reducing unnecessary memory use without changing deployment.
How we built BuzzForce, our in-house replacement for Salesforce: understanding workflows, redesigning the data model, dividing work with AI agents, and moving real business operations into the new system.
Tracing p99 spikes caused by synchronous go-feature-flag flushes holding a mutex during S3 uploads and jitter sleeps, then fixing them with AsyncExporter and an upstream PR.
Hello, I’m Jed from Buzzvil’s Supply Platform team. Low latency and high availability matter when handling large volumes of traffic. That is why we make extensive use of DynamoDB a…
Introduction Hello, I’m Elric from the Supply group’s Product Backend team. Honeyscreen frequently deploys new promotions, but its long CI pipeline—about thirteen minutes—had becom…
Hello, I'm Wynn, lead of the Product Backend team in Buzzvil's Supply group. We're currently looking for a new teammate to help us grow. A job posting can only tell you so much abo…
During 2023, Buzzvil reduced AWS costs by approximately KRW 120 million per month, equivalent to around KRW 1.4 billion annually. In this series, we share the experience and practi…