Rootconf Topical Edition on Databases 2026
2026-06-12..2026-06-13
Bengaluru, India
who it's for
storage engine developers, query engine developers, data engineers, backend engineers, site reliability engineers, platform engineers, engineering managers
topics
LSM Tree implementation; tiered and leveled compaction; learned execution optimizer; incremental view maintenance (Z-sets); ClickHouse migration and compression; ZSTD and Delta column codecs; bloom-filter skip indexes; high QPS scaling and circuit breaker patterns; HBase deadlock diagnosis and thread dumps; Badger-based distributed KV optimizations; property-based and deterministic simulation testing; Rust OLAP database deployment with V8
| title | author | length |
|---|---|---|
| Databases were not designed for this | Arpit Bhayani | 32m |
Databases face concrete changes when AI agents become primary users: enforce statement_timeouts per role and idle_in_transaction_timeout; record soft deletes… | ||
| From timeout to sub-second: solving scale dependent deadlocks in distributed systems | Varun Mishra | 20m |
A production-only deadlock in Apache HBase surfaces once clusters exceed about 50 region servers: a disaster-recovery log-roll pipeline repeatedly hits a… | ||
| No stats, no problem: building feedback-driven optimizers for lakehouses | Renu Pinky Sumam | 41m |
e6data builds a layered optimizer that learns from execution instead of trusting stale stats: an equivalence-set NDV seeding step, a magic‑number sensitivity… | ||
| Migrating Panacea.AI's 5TB/day log platform from Manticore to ClickHouse ... and the lessons learnt | Sohham Seal | 17m |
Panacea.AI moves 5 TB of logs per day (154 billion rows, 870k+ inserts/s) from Manticore Search to ClickHouse and cuts projected storage from hundreds of TB to… | ||
| How three engineers at Antithesis shipped a production database in 14 months - safely! | Shomik Ghose | 37m |
Antithesis builds and ships Pangolin, a tree‑based OLAP database written in Rust and deployed to S3 with V8 for query lambdas, in 14 months with three… | ||
| What breaks when Aerospike hits 6 million QPS | Shivam Gupta | 29m |
Runs Aerospike at multi‑million QPS for real‑time bidding, managing 13B user records on ~8 TB RAM across ~50 64‑core VMs with RF=2. At ~3M QPS 1–2% key busy… | ||
| Fast on paper, slow in reality: what we got wrong about performance | Sarthak Makhija | 35m |
Built a strongly-consistent distributed key‑value store in Go on Badger LSM with hash partitioning and persistent TCP connections, then discover real… | ||
| Database systems: a decade of disruption and innovation | Karthik Ramachandra | 51m |
Argues that the cloud breaks two core assumptions — a stable outside world and a monolithic engine — and shows concrete fixes: cloud‑native architectures such… | ||
| Incremental Computation | Mihai Budiu | 49m |
Claims a practical, general solution to incremental view maintenance for arbitrary SQL (including recursive queries) by representing updates as Z-sets… | ||
| Hands-on workshop going from zero to a working LSM Tree | Anirudh Rowjee | 04h 05m |
Hands-on workshop that has attendees write your own LSM Tree in Go, including memtable writes, reads, deletes, and a flush that persists data to SSTable format… | ||
| Topical Edition on Databases - Track 2 | Sandeep Joshi, Ranganadh Thata | 04h 15m |
Firebolt admits it started as a ClickHouse fork but now ships a rebuilt planner, full distributed query execution, Iceberg and DuckLake read support, Postgres… | ||
| Topical Edition on Databases - Track 1 | Sandeep Joshi, Ranganadh Thata | 06h 54m |
A concrete method for full-query incremental maintenance turns billion‑row SQL workflows into fast streaming updates: represent changes as Z‑sets (signed row… | ||
| nothing matches | ||