New blog. From Rust to Reality: The Hidden Journey of fetch_max. Enjoy! questdb.com/blog/rust-fetch-… "Nearly everything is really interesting if you go into it deeply enough."

Kernel 6.17 has a bug causing async-profiler to freeze an entire system. I noticed this yesterday evening. I thought I was just too tired, but it happened even today. Independently, @forked_franz observed it too: github.com/async-profiler/as… Kernel fix: git.kernel.org/pub/scm/linux…

Christmas is early this year 😍 This is a book I might actually read. For a change 🤦‍♂️

Me: "Let's call it a day" -> sudo poweroff One second later: "Oh, this was a remote shell. My office PC!" I guess I am not working from home tomorrow 🤦‍♂️🤦‍♂️🤦‍♂️

"I have an epoll bug, it's an Edge-case."

My new bug: Race between stdout and stderr causing CI builds to fail. questdb.com/blog/azure-pipel…

It’s the world’s first #CPU! Almost 54 years ago, on November 15th 1971, #Intel launched the first commercial single-chip microprocessor. With the following tweets, let’s jointly explore the greatest milestone in #computing #history after the invention of the #transistor!

It's funny how last week everyone was dunking on Supabase for their not-an-outage, and replying angrily to a post of mine where I defended them, saying that no, no, they had to have a multi-cloud strategy, deploy to the moon, shard to mars, completely unacceptable... Turns out that now that AWS is really down, nobody is doing any of that, and even some of the people grandstanding last week are affected. The reality is that as with everything in life, everything is a trade off. Most companies - including mine, btw, will base their services on the very good assumption that AWS is very stable and will generally work (them going down now doesn't make it false). Yes, we all could design heavily distributed systems with failover to 35 regions, but they would be a lot more expensive, a lot more complex to operate, a lot longer time-to-market. AWS (the single affected region) will be back soon, and we'll all go back to business.

My book is today’s @ManningBooks deal of the day!

Thought I’d seen every kind of race condition. But a bug caused by a race between stdout and stderr? That’s new. Yes, it bit me. Yes, figuring it out was painful. Details: github.com/microsoft/azure-p…

What S3 API server implementation do people use in *tests* these days? Minio/LocalStack used to be popular, but that's probably overkill for tests? Is there anything simpler and compliant-enough?

QuestDB 9.1 is out. While the release includes tons of features like nanosecond timestamp precision, my favorite DX addition is that thanks to @jerrinot it now ships with built-in async-profiler. github.com/questdb/questdb/r…

#PostgreSQL Are you a maintainer of a driver for Postgres? We would like to get as many as possible together in Vancouver next year at pgconf.dev. Please reach out to me and or spread the word to developers

Last week, I described a gloomy situation: all public TLS certificate providers log your requests. By browsing through the subdomains, one can get their respective IP addresses. My solution caters to my Synology NAS, as it’s the one I’m using. blog.frankel.ch/privacy-subd…

Mind. . . blown!🤯 lwn.net/SubscriberLink/10388…

Tip: If you are on Ubuntu `sudo apt install bcc` and then `sudo biolatency-bpfcc -e 1` gives you nice histograms of I/O device latencies. Powered by eBPF.

TIL: async-profiler can create heatmaps showing events over time. You can drill down into arbitrary time intervals with 20ms granularity.

C++ geeks can be funny too! 😅 "Note: this is an early draft. It’s known to be incomplet and incorrekt, and it has lots of bad formatting."

ARM is hiring compiler engineers to work on GCC/ LLVM linkedin.com/jobs/view/42894…

I had been meaning to comment on @Jonathan_Blow’s “Why can’t we even conceive of writing a new OS today” post. Coincidentally, I just got an email that opened with: ——————————————— Hey John, 2 years ago I pitched you LIBBA - a dedicated OS for smart glasses. You were sceptical, your main concern was that a custom OS rarely justifies itself: cost, shelf life, and developer burden outweigh the benefits. You were right. ——————————————— I deeply love the ideals of clear, efficient programs that do their job without baggage, and I have always been very sympathetic to efforts like Oberon, Plan 9, and even TempleOS. But building a new operating system today doesn’t make any product sense. Meta spent a lot of resources working on a fully custom XROS, over my rather strenuous objections. They had top tier engineering talent, tons of support, and they were producing high quality code and docs. It was a best case scenario from a “new OS” perspective, and, as one of the engineers put it, “If we can’t do it, who could?” I wish I could drop (so many of) my old internal posts publicly, since I don’t really have the incentive to relitigate the arguments today – they were carefully considered and prescient. They also got me reported to HR by the manager of the XROS effort for supposedly making his team members feel bad, but I expect many of them would acknowledge in hindsight that the Meta products would not be in a better place today if the new OS effort had been rammed into them. I can only really see a new general purpose OS arriving due to essentially sacrificing a highly successful product’s optimality to the goal of birthing the new OS, and I wouldn’t do that myself as a stakeholder. To make something really different, and not get drawn into the gravity well of existing solutions, you practically need an isolated monastic order of computer engineers. Which was sort of Plan 9…