The Great CPU Stagnation(databasearchitects.blogspot.com)

237 points by greghn 3 years ago | 197 comments

C++ exception performance three years later(databasearchitects.blogspot.com)

73 points by gpderetta 1 year ago | 51 comments

Fun with Char in SQL(databasearchitects.blogspot.com)

38 points by greghn 3 years ago | 13 comments

B-Trees Require Fewer Comparisons Than Balanced Binary Search Trees(databasearchitects.blogspot.com)

155 points by greghn 2 years ago | 67 comments

Advent of Code 2024 in pure SQL(databasearchitects.blogspot.com)

461 points by greghn 1 year ago | 103 comments

Blog post describing solving every Advent of Code 2024 puzzle in pure SQL, with a full recursive-query solution for one day shown as an example.

Safe Optimistic Lock Coupling(databasearchitects.blogspot.com)

38 points by greghn 25 days ago | 6 comments

A Database Architects blog post on making optimistic lock coupling safe for scalable concurrent data structures like trees on many-core CPUs.

Saving 100 terabytes of memory by optimizing 1.1.1.1's DNS cache(blog.cloudflare.com)

857 points by TangerineDream 2 months ago | 250 comments

Cloudflare blog deep dive on how optimizing the 1.1.1.1 DNS resolver's cache data structures saved 100 terabytes of memory.

Unpowered SSDs slowly lose data(xda-developers.com)

710 points by amichail 11 months ago | 285 comments

XDA Developers article explaining that SSDs left unpowered for long periods gradually lose stored data due to charge leakage in NAND flash.

S3 Is the Future, S3 Is the Past(btrblocks.com)

56 points by tkhattra 1 month ago | 61 comments

Blog post by Viktor Leis arguing that S3-centric cloud data architectures rest on hardware assumptions that are becoming obsolete.

DuckDB Doesn't Need Data to Be a Database(nikolasgoebel.com)

353 points by tosh 2 years ago | 115 comments

A blog post by Nikolas Göbel discussing how DuckDB can act as a database without storing data itself, querying external data sources directly.

How AWS S3 serves 1 petabyte per second on top of slow HDDs(bigdata.2minutestreaming.com)

338 points by todsacerdoti 1 year ago | 147 comments

A Big Data Stream newsletter article explaining how AWS S3 achieves 1 PB/s throughput and 150M QPS using commodity hard drives.

Local AI needs to be the norm(unix.foo)

1767 points by cylo 5 months ago | 699 comments

Blog post on unix.foo arguing that apps should run AI models locally rather than relying on API calls to OpenAI or Anthropic.