Introducing ScaleDB, the New Clustered, Distributed Storage Engine for MySQL (Part 1)
summary
ScaleDB is a clustered storage engine that plugs into MariaDB and runs as separate storage nodes (cas) + lock manager (slm) with volumes mirrored for redundancy. It targets streaming/time‑series tables with sequential storage, FIFO deletes and pushdown aggregations and filters to the storage tier. A Docker/EC2 deployment demonstrates sustained ~2 million rows/sec inserts, ~17–18 billion rows (~2 TB) across five storage nodes, counts in ~2s for recent minute windows and 10–15s for day‑range scans; some features (online ALTER, geo‑replication, rebalancing) are not yet implemented.
AI-written summary · about
chapters (10)
- 0:00ScaleDB introduction
- 1:06What is ScaleDB
- 3:54ScaleDB architecture
- 11:10ScaleDB capabilities and limitations
- 17:36ScaleDB admin
- 26:13Streaming tables
- 33:28Using streaming tables
- 41:10ScaleDB benchmarks
- 43:17Live demo
- 57:13Q&A
related talks
25mThe future of databases: Combining operational and analytical data at massive scale
17mState of MariaDB
18mBuilding Data Lake with MariaDB ColumnStore
26mSoar Higher With MariaDB SkySQL - The Ultimate MariaDB Cloud
37mThe MariaDB Evolution: Just a fork of MySQL?
45mThe MariaDB Evolution: Just a fork of MySQL?
32mData @Scale Seattle- Eric Hwang introduced by Ganapathy Krishnamoorthy
06mScaling your applications with Cloud SQL for MySQL