I've just published my duplicate file finder #fclones in the snap store. Now you can `sudo snap install fclones`.

This is the best explanation I’ve ever seen on why designing good abstractions is both important and difficult. From ⁦John Ousterhout⁩’s A Philosophy of Software Design.

Returning Optional in Java is slow: pkolaczk.github.io/overhead-of-op…

#fclones has just received support for copy-on-write deduplication on BTRFS, XFS, macOS, and other file systems with reflink support (github.com/pkolaczk/fclon…)

#fclones reported 2.5x faster than jdupes on 2TB of data on HDD... despite some optimisations not kicking in github.com/pkolaczk/fclon…

Your intelligence cannot be measured by a number. It is defined by your willingness to learn, solve problems and try new things. You are more than just a number. Develop your skills. Share your brilliant ideas. Your skills are more valuable than your grades. 🧠

My #Cassandra benchmarking program Latte (github.com/pkolaczk/latte) has just gotten an ability to run user-defined workloads! Now you can script it with #Rune. (rune-rs.github.io)

Forget performance, Latte is now the most colorful benchmarking tool for Cassandra: github.com/pkolaczk/latte

I'm using async Rust to fetch HTTP content at >700 mbps and my system total CPU utilization hovers at 1%. This is on a Ryzen 5950X with 32 reported CPUs. So ~1/3 a CPU core to ~fully saturate my home Internet link. I didn't even have to think about optimizing the code!

Hey #cassandra fam. Our very own Artem Chebotko is stuck behind the lines in #Ukraine right now. He could use your love and support right now. If you know of ways to get people out DM and we can connect the right people.

The fastest duplicate file finder #fclones got even faster! Now file hashes can be cached: github.com/pkolaczk/fclon…

#fclones duplicate file finder now officially available on #macOS and #Linux with `brew install fclones`. Thanks to #homebrew team for a quick merge into the core repo!

Apache Cassandra 4.1 configuration has been standardized to reduce potential mistakes.😃 Interested to know more? Read Ekaterina Dimitrova's blog post about it: cassandra.apache.org/_/blog/Apache-… #ApacheCassandra #devops #OpenSource

Version 0.28.0 of #fclones file deduplicator adds support for many modern hash functions: xxHash, blake3, sha256, sha512, sha3-256, sha3-512: github.com/pkolaczk/fclon…

Escaping strings faster with AVX-512 lemire.me/blog/2022/09/1…

Our paper was accepted for ICPE23 and is now available on arxiv! Hunter: Using Change Point Detection to Hunt for Performance Regressions arxiv.org/abs/2301.03034

All build tools suck, but I have to admit that so far I hate Cargo way, way less than I hate Gradle or Maven.

This is why you cannot just optimize software at the end. Performance should be considered in all phases of software development: lemire.me/blog/2023/04/2…

Vector search in Astra DB delivers 8X - 15X higher throughput than Pinecone. Learn about the top 5 challenges with vector search, and how DataStax's vector DB solves them ⤵️ dtsx.io/3LwEAbk #VectorDatabase

I don't do Windows but here are some (initial) details about why the CrowdStrike's CSAgent.sys crashed Faulting inst: mov r9d, [r8] R8: unmapped address ...taken from an array of pointers (held in RAX), index RDX (0x14 * 0x8) holds the invalid memory address John Hammond