AI如何改变JIT编译器的经济学
… 阅读全文 该帖子“人工智能如何改变JIT编译器的经济性 ”最早发布于“ ”。 
评论
点赞
收藏让 Postgres 分析查询提速 300 倍：批处理、算子融合与 SIMD
pgrust 0.2 发布，分析查询性能比 Postgres 快 300 倍，在 ClickBench 上甚至超过 ClickHouse。核心优化来自查询引擎重构：批处理、算子融合和 SIMD。Volcano 模型每次处理一行带来巨大开销，批处理将 5 亿数求和从 1.3 秒降至 480 毫秒，算子融合进一步降至 358 毫秒，SIMD 优化后仅需 135 毫秒。Postgres 诞生于磁盘 I/O 瓶颈时代，如今数据常驻内存、NVMe 普及，CPU 和内存带宽成为新瓶颈，传统查询引擎架构已不适应。 
PostgreSQL 转写 Rust：在通过全部回归测试前的三个死胡同
Mali 团队耗时重写 PostgreSQL 核心代码至 Rust，经历三次失败并花费十万美元后，最终通过全部回归测试。文章详细记录了从 C 到 Rust 迁移过程中的技术陷阱、性能权衡及具体实现细节，包括内存管理、并发模型适配及编译期检查策略，为大型 C 项目现代化改造提供了极具参考价值的一手工程经验。
pgrust 构建实录：四次尝试与十万美金投入，用 AI 重写 Postgres
简而言之：经过四次尝试，并投入了10万美元，我们成功利用Opus将Postgres改写成了Rust。 我们明确了若干关键技能，并能够建立一套可重复的流程，将Postgres的文件改写为Rust代码。 在运行过程中…… 阅读其余部分 文章“prust 是如何构建的：用 AI 用 Rust 重写 Postgres 的四次尝试 ”最初发表于。
pgrust 通过 100% PostgreSQL 回归测试
pgrust 项目宣布通过全部 PostgreSQL 回归测试及隔离测试，兼容 PG 18.3。作为用 Rust 重写 Postgres 的尝试，这一进展验证了其在核心兼容性上的可行性。对于关注数据库底层重构、Rust 在基础设施领域落地以及 Postgres 替代方案的技术读者而言，这是评估该项目成熟度的关键里程碑。
导致PostgreSQL宕机的四大杀手
作者基于大量初创公司生产事故经验，总结导致PostgreSQL宕机的四大核心原因：VACUUM与事务ID回卷、进程模型导致的连接瓶颈、查询计划器缺乏控制且易出错、JSON字段统计缺失引发的性能灾难。针对这些问题，作者介绍了其重构项目pgrust的技术方案，包括引入64位事务ID、改用线程模型、构建自适应查询计划器以及改进JSON统计与压缩。
pgrust update: at 67% Postgres compatibility, and accelerating
It’s been a week since I published the original pgrust post. pgrust is my attempt to rewrite Postgres in Rust. My ultimate goal is to build a database that is safer to work with so that I can work … ...
Pgrust: Rebuilding Postgres in Rust with AI
I’ve written dozens of blog posts about Postgres internals. Postgres is one of the greatest databases out there. But from chatting with a lot of my friends at startups, I’ve seen consistent challenges...
Simple Rules for Building Simple Systems
Once a design of a system meets all the business constraints necessary, my next priority is to make the system as simple as possible. By simple, I mean a system that is both easy to understand and eas...
An Algorithm for Passing Programming Interviews
Over the past few years, I’ve interviewed with a dozen or so companies and have completed ~50 or so individual algorithm problems. I’m frequently given feedback that I did a great job at the algorithm...
Tools in My Toolbox
One of the most important skills I believe programmers need is to understand when to use certain tools. My typical process for solving a problem is to go through each tool in my toolbox and see which ...
Advent of Code: Day 3
Day 3’s problem was an interesting one. We are given two wires and have to find the point where the two wires intersect that’s closest to the origin. As usual, we’ll approach this problem in two steps...
Advent of Code: Day 2
Day 2 of the Advent of Code is a classic – implement a virtual machine for a simple assembly like. Eric Wastl, the creator of the AoC, has been writing challenges like this for years before the AoC ev...
Advent of Code: Day 1
The Advent of Code is back! In past iterations of the Advent of Code, a bunch of my friends and I would share all our solutions. This year, I thought why not go the extra step and publicly write up … ...
Generating Fractals with Postgres: Self-Similar Fractals
In my last post, I showed you how you could use a number of SQL tricks to generate a class of fractals known as the “escape-time fractals”. In this post I’ll show you how you can use the same … Read t...
Generating Fractals with Postgres: Escape-Time Fractals
This post is based on half of a talk I gave at!!con. If you want to watch the talk, you can find it here. One not too well known aspect of SQL is that it’s Turing complete. This … Read the rest The...
Generating Fractals with SQL Queries
I recently gave a talk at!!Con West about how you can use some of the dark corners of SQL to generate fractals. You can watch the recording here: To summarize the video, I write SQL queries that gene...
Perfalytics is now Generally Available
After being in beta for several months, Perfalytics is now generally available. Perfalytics is my attempt to bring a new approach to database performance. Perfalytics integrates directly with your da...
Announcing Perfalytics: Never Run EXPLAIN ANALYZE Again
Today I’m announcing the beta for Perfalytics. Perfalytics is a tool I’ve been working on designed to make it easy to analyze query performance for Postgres. As the lead of the Database team at Heap, ...
Postgres Backups with Continuous Archiving
It’s extremely important that you have backups. Without backups, you are at serious risk of losing data. If you don’t have backups, all it takes is one machine failure or fat fingered command to lose ...
Postgres JSONB
JSONB is a nifty Postgres type that allows you to store unstructured data inside of Postgres. A common use case of JSONB is to represent a mapping from a set of keys to arbitrary values. JSONB is nice...
track_io_timing
The parameter track_io_timing is a relatively unknown, but super helpful parameter when optimizing queries. As the name suggests, when the parameter is turned on, Postgres will track how long I/O take...