Miguel Ángel Pastor Olivar

bbtree: fastest ordered map

Maxing Out a $12 Server www.youtube.com/watch?v=-BFt...

Inside the Guts of FloeScan and other Interesting Design Magic

FDP: The Data Placement Promise of Modern NVMe SSDs arxiv.org/abs/2610.02676

Resumable Remote Compaction rocksdb.org/blog/2026/05...

How to effectively debug when you no longer understand the code

Rebalancer: A Generic, High-Performance Library for Solving Assignment Problems

Survey of Filtered Approximate Nearest Neighbor Search over the Vector-Scalar Hybrid Data arxiv.org/abs/2505.06501

Redesigning infrastructure: Why architecture determines performance

Everything Has Bugs. Here’s How Antithesis Catches Them. db.cs.cmu.edu/events/andy-...

Apache Doris: Real-Time Analytics and Search Database for AI Agents db.cs.cmu.edu/events/andy-...

The Physical Stack Behind AI

Why are AI agents lying, cheating and coordinating?

Breaking the Server: Systems for Disaggregated Datacenters www.youtube.com/watch?v=LR8e...

Jetpack: Consensus Made Generally Fast

A faster way to calculate the day-of-the-week

The Decompilation Book

118,538,803 queries per second. 1.22 PiB of data. 512 shards. Powered by Neki. planetscale.com/blog/118-mil...

A Design Space Exploration of Async/Await

Lessons in systems thinking

Lessons from Operating a Large-Scale Distributed Database with a Replicated Key-Value Engine www.usenix.org/conference/f...

Mission-Critical www.youtube.com/watch?v=1Wcz...

How to write to SSD

Garnet: A Next-Generation Cache-Store for Accelerating Applications and Services

High-Performance DBMSs with io_uring: When and How to Use

BtrLog: Low-Latency Logging for Cloud Database Systems

The Power of Ten: Rules for Safety Critical Coding by Gerard Holzmann

Making the Impossible Possible (Again): Ten Years of Flexible Paxos youtu.be/P0cAG-RM1_c

What is a data topology? planetscale.com/blog/what-is...

Git at any scale cursor.com/blog/git-at-...

Systems Distributed '26 will be available really soon www.youtube.com/playlist?lis... Eager to watch some of the talks!

Move Fast And Don’t Break Things: Automatic Apache Kafka® Migrations With Orbit www.warpstream.com/blog/orbit-k...

How to ship a database every day

I’m really happy to announce that this coming Monday, I’ll be joining the amazing folks at @planetscale.com 🚀 I’m excited to be back working at the intersection of distributed systems and databases. Thanks everyone at PlanetScale for the opportunity. Can’t wait to get started! 🎉

On building scalable control planes

We replaced Redis with MySQL for inventory reservations—and it scaled (2026)

"Code was never the hard part" is an insult to all programmers

What's the best programming language for coding agents?

DuckDB Internals: Why is DuckDB Fast? (Part 2 Vectorized Execution)

DuckDB Internals: Why is DuckDB Fast?

PostgreSQL's MVCC is bad. So is everyone else's.

The Bottlenecks for AI-Driven System Design: why Principal Engineers are not (yet) obsolete. maheshba.bitbucket.io/blog/2026/07...

How MVCC and Transactions Work in RocksDB artem.krylysov.com/blog/2026/07...

The LogDrive: Composable Durability for Cloud-Based Shared Logs www.usenix.org/conference/o...

Aurora DSQL: Scalable, Multi-Region OLTP arxiv.org/abs/2607.13276

Shard your locks: benchmarking 6 Go cache designs

Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database Bypass arxiv.org/abs/2607.07696

Introducing Meerkat: an experiment in global consensus

The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems arxiv.org/abs/2605.21997

Client-Side Load Balancing at a Million Requests Per Second engineering.zalando.com/posts/2026/0...