Hacker News: mrngm

New comment by mrngm in "Ask HN: Who's still keeping a DOS machine up because the business depends on it?"

mrngm — Mon, 28 Sep 2026 20:59:04 +0000

Don't underestimate the work speed a person can maintain with a reliable, fast keyboard interface. Finding the right spot on a web interface and navigating with a mou---too late, the keyboard user already entered the invoice for that account using some odd VAT rate on 3 of the 5 products.

New comment by mrngm in "I've operated petabyte-scale ClickHouse clusters for 5 years"

mrngm — Fri, 11 Sep 2026 16:37:11 +0000

For those interested, there's also a second part [2025]: https://www.tinybird.co/blog/what-i-learned-operating-clickh...

(note: the first part was originally published April 2025 according to the date tooltip)

New comment by mrngm in "Don't enthusiastically agree to rewrite the system at work"

mrngm — Sun, 30 Aug 2026 10:53:35 +0000

Dear OP,

> "I'm hoping to close them out soon, ideally before I run out of goodwill."

Your goodwill is already depleted, time to move on.

New comment by mrngm in "Secrets of the Atomic City"

mrngm — Fri, 28 Aug 2026 18:30:41 +0000

Full version of the longread over at The Atavist Magazine, titled "Toxic Lies": https://magazine.atavist.com/2026/toxic-lies-radiation-paduc...

Earlier submission (4 points, 0 comments): https://news.ycombinator.com/item?id=49149056

New comment by mrngm in "Tell HN: I hate your fuzzy search"

mrngm — Sat, 01 Aug 2026 18:58:23 +0000

Asana has the same problem. Really frustrating.

The Busy Person's Guide to Thinking (2015)

mrngm — Sat, 01 Aug 2026 18:32:54 +0000

Article URL: https://fs.blog/how-to-think/

Comments URL: https://news.ycombinator.com/item?id=49137067

Points: 2

# Comments: 0

Multicast TV Distribution on My Home Network

mrngm — Sat, 25 Jul 2026 20:55:12 +0000

Article URL: https://www.apalrd.net/posts/2026/isp_mcast/

Comments URL: https://news.ycombinator.com/item?id=49051463

Points: 65

# Comments: 19

BYO NOS: Building a maintainable, SRE-friendly switch

mrngm — Thu, 16 Jul 2026 21:11:25 +0000

Article URL: https://blog.rezero.org/byo-nos

Comments URL: https://news.ycombinator.com/item?id=48940312

Points: 11

# Comments: 0

Dependencies should be fetched directly from VCS

mrngm — Sun, 05 Jul 2026 20:44:01 +0000

Article URL: https://www.arp242.net/deps-vcs.html

Comments URL: https://news.ycombinator.com/item?id=48797771

Points: 54

# Comments: 44

Zero-copy in Go: sendfile, splice, and the cost of io.Copy

mrngm — Sun, 05 Jul 2026 20:24:31 +0000

Article URL: https://segflow.github.io/post/zero-copy-sendfile-splice/

Comments URL: https://news.ycombinator.com/item?id=48797655

Points: 75

# Comments: 22

TCP Throughput Calculator

mrngm — Mon, 29 Jun 2026 14:40:29 +0000

Article URL: https://network.switch.ch/pub/tools/tcp-throughput/

Comments URL: https://news.ycombinator.com/item?id=48719893

Points: 2

# Comments: 0

Performance Tuning on Linux

mrngm — Mon, 29 Jun 2026 14:32:05 +0000

Article URL: https://cromwell-intl.com/open-source/performance-tuning/

Comments URL: https://news.ycombinator.com/item?id=48719769

Points: 3

# Comments: 0

New comment by mrngm in "Ten years of ClickHouse in open source"

mrngm — Sun, 21 Jun 2026 11:52:34 +0000

Probably trace_log (we had a similar experience), but you'll only notice with limited storage space, and a regular keen eye on how your database fills up.

New comment by mrngm in ".de TLD offline due to DNSSEC?"

mrngm — Tue, 05 May 2026 21:23:29 +0000

Unfortunately, even domains that did not have DNSSEC enabled earlier today are affected.

We observed issues on a non-DNSSEC .de domain at 19:45Z and confirmed around 20:12Z it wasn't just us, but also more high profile domain names.

Implicit SLOs and their dangers (2024)

mrngm — Tue, 28 Apr 2026 18:56:27 +0000

Article URL: https://blog.relyabilit.ie/implicit-slos-and-their-dangers/

Comments URL: https://news.ycombinator.com/item?id=47938892

Points: 1

# Comments: 0

New comment by mrngm in "Queueing Requests Queues Your Capacity Problems, Too"

mrngm — Fri, 03 Apr 2026 20:01:39 +0000

If you have individual request logs with timing infomation, you could construct that afterwards. It does take some effort to have an effective way of displaying these metrics. Where would you put an individual request that took 532ms and started at t=34.682s? Would you align all requests that started in the 34th second at t=34s, or look at completion time (ie within t=35s)?

Would you rather see "number of requests started at this ms" (you seem to suggest this), or is something else more interesting?

I think a sort of Gantt chart that plots duration of requests as well as starting time within the time span (e.g. a second or more) might be very informative. Each individual request on a different position on the Y axis, time on the X axis. Perhaps you have some bound on requests in flight, that could be the height of the Y axis, so you can easily see calm or busy periods.

At least our observability stack doesn't show this level of detail, but it would be very interesting to have it. (We do have calculated heatmaps based on maximum request time in Grafana, which is at least better than plots of average request times)

New comment by mrngm in "Queueing Requests Queues Your Capacity Problems, Too"

mrngm — Mon, 30 Mar 2026 18:09:46 +0000

That reminds me of this talk[0] by Gil Tene called "How NOT to Measure Latency" at the Strangeloop conference in 2015 (or read this blog post[1] that contains the most important points).

[0] https://www.youtube.com/watch?v=lJ8ydIuPFeU

[1] https://bravenewgeek.com/everything-you-know-about-latency-i...

New comment by mrngm in "Printf-Tac-Toe"

mrngm — Thu, 12 Mar 2026 18:16:35 +0000

[2020], and written for IOCCC: The International Obfuscated C Code Contest.

This was awarded "Best of Show - abuse of libc" at the time[0]. See also the judges' remarks[1]:

This program consists of a single printf(3) statement wrapped in a while loop. You would not think that this would amount to much, but you would be very, very wrong. A clue to what is happening and how this works is encoded in the ASCII art of the program source.

[0] https://www.ioccc.org/2020/index.html

[1] https://www.ioccc.org/2020/carlini/index.html

New comment by mrngm in "Process-Based Concurrency: Why Beam and OTP Keep Being Right"

mrngm — Mon, 02 Mar 2026 09:19:35 +0000

Related thread from 11 days ago: https://news.ycombinator.com/item?id=47067395 "What years of production-grade concurrency teaches us about building AI agents", 144 points, 51 comments.

H-Bomb: A Frank Lloyd Wright typographic mystery

mrngm — Thu, 26 Feb 2026 09:18:57 +0000

Article URL: https://www.inconspicuous.info/p/h-bomb-a-frank-lloyd-wright-typographic

Comments URL: https://news.ycombinator.com/item?id=47163779

Points: 153

# Comments: 38