The Bug That Only Showed Up After a Week: Why We Still Needed to Add a Daily VACUUMPart 3 of 3 — A Quieter Story About Ongoing Ownership6 min read·tech.kompress.ai3Jul 8
Part 3: Building a Cluster That Manages ItselfThe partition index table, the monitoring system, and reading the sawtooth10 min read·tech.kompress.aiJun 20
Part 2: When 0% Tombstones Is Not the Finish Line"Four days after hitting 0.00000% droppable tombstones on all three nodes simultaneously — the cleanest state the cluster had ever been in — the Slack report showed 30% again8 min read·tech.kompress.ai3Jun 19
Part 1: When Your Time-Series Data Turns Against You...Migrating 3.9 Billion Rows to TWCS Without Downtime on a Constrained IoT Cluster The number that started everything was 7.99 ms. That was the average read latency on our Cassandra keyspace — a cluster11 min read·tech.kompress.aiJun 15
When Your Fix Creates a New Problem: Debugging the Production Partition MigrationPart 2 of 2 — Two Swap Cycles, One Rollback, and Why the Safety Net Made All the Difference9 min read·tech.kompress.ai1RJun 11