Top all-time · #7541
Scalability.org
Personal blog · scalability.orgsystemsai
Scalability.org is a personal blog at scalability.org about systems and ai. Since 2009, 10 different Hacker News readers have linked it 40 times, most often “Requiem”. It is still writing: the last post was on 2026-10-18, and you can follow it by feed.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
HN readers link Joe Landman's scalability.org for posts on high-performance storage and I/O benchmarking, such as a follow-up to a Bonnie benchmarking critique and a 2017 post about Scalable Informatics closing.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Musings on HPC/AI, technology, science, economics, politics and other things of interest
Most-linked posts?
- Requiem2 people · 2 mentions · first linked 2017-03-22
What Hacker News says?
Quick plug for a company I've used: SSLmate ( http://sslmate.com ) makes cert purchase (for those whom need this) painless and fast. They use Comodo and Geotrust FWIW. I've had my own pain with Comodo through other resellers, and moved on to sslmate and godaddy. Recently moved my home blog ( http://scalability.org ) to LE. Work ( http://scalableinformatics.com ) is using godaddy for now, though thinking hard on usin…
Comment linking /
on “Defending Our Brand”Submitted The looming (storage) bandwidth wall as a story · 11 points
HN discussionAirbnb has had issue for a while. This[1] is a post I wrote about them in 2014. Basically, it is not in Airbnb's interests to provide quality control, or stop these scams, as either action will negatively impact their revenue. [1] https://scalability.org/2014/03/ot-airbnb-and-their-issues/
Comment linking /2014/03/ot-airbnb-and-their-issues/
on “I Accidentally Uncovered a Nationwide Scam on Airbnb”Submitted Bonnie isn't that good at characterizing system IO rates as a story · 6 points
HN discussionNo, the numbers are pretty accurate. In most of the cases I've run into, Perl is faster than Python for its operations. Some trivial examples[1] showed up on HN a few weeks ago, about how this person "optimized" python, by eventually replacing python with C. As for the nested complex data structures, Perl's been doing that forever (e.g. since 5.x started). And its trivial to use. That's one of the nicer aspects of P…
Comment linking /2020/05/on-optimizing-scripting-languages-and-where-they-are-useful-and-where-they-are-not/
on “Perl 7 is going to be Perl 5.32, mostly”Submitted Perl on the rise for DevOps as a story · 5 points
HN discussionIn my 30 years (yes) working with Perl (4->5.32), I have never, once, used wantarray. Perl does not lend itself to bad code. Bad coders, people whom cannot use or articulate good practice in coding or documentation, lend themselves to write bad code, in any language. I used it for automation of my calculations in grad school. For data analysis. For monitoring. In my subsequent day jobs, I used it to develop shipping…
Comment linking /2020/04/fun-and-topical-hpc-project-at-the-dayjob/
on “Perl 7 is going to be Perl 5.32, mostly”Submitted Serial languages in HPC, why? as a story · 3 points
HN discussionNot all of it. I blog here[1]. The post where I talked about the end is here[2]. Note the 'laws' I quote at the end of the post. My first post is here[3]. There I talk about the HPC market, accelerators, and some of our plans. We were working on board level inexpensive accelerators before these were a thing. We gave up trying to get funding for this in 2006. I did say, you have to be at the right place, at the right…
Comment linking /2005/10/venture-capital-and-high-performance-computing/
on “Y Combinator has lost its soul: A YC founder's perspective”Submitted Just No as a story · 2 points
HN discussionMe[1]: Ph.D. Theoretical/Computational Physics in mid 90s[2], working on simulation of semiconductor defect states, formation and migration energies. Went commercial rather than academic, as the job market was insanely crowded, and I didn't have "enough" differentiation in my opinion, to land a tenure track, at a lower tier school given the huge influx of high quality talent from the former soviet union (FSU). I was…
Comment linking /about-me/
on “Ask HN: Physicists of HN, what are you working on these days?”Submitted Real measurement is hard as a story · 2 points
HN discussionI find it somewhat humorous that more than 25 years on, we are effectively reverting to static linking and bundling [1]. Way ... way back in the day, the argument was it would save memory, encourage reuse, etc. While some of this may have been true, it also gave rise to dynamic library hell. Reuse was overshadowed by incompatible versions, or API changes between versions that became the stuff of legends. This would…
Comment linking /2017/03/what-is-old-is-new-again/
on “Why I’m Learning Perl 6”Submitted Negative latencies as a story · 2 points
HN discussionThanks for the shout out! Without being a commercial, this high performance storage/analytics realm is what we focus on. We were demoing units like this: https://scalability.org/images/30GBps.png for years now. Insanely fast, tastes great, less filling. Our NVM versions are pretty awesome as well. [edit] I should point out that we build systems that the OP wants ... they likely don't know about us as we are a small…
Comment linking /images/30GBps.png
on “How We Knew It Was Time to Leave the Cloud”Submitted Rethinking how we build and invest in partnerships as a story · 2 points
HN discussionHang in there ... I've ridden that particular train[1][2]. You have to be strong, positive for the family member. Know you are not alone, there have been many people who've gone through this, and as I discovered, it helps to talk to them. I am happy to report that as of 29-Dec, we are at 7 years post op. On the 1 year anniversary of when we got the diagnosis, I saw an xkcd strip[3]. That gave me some hope of an even…
Comment linking /2012/01/ot-what-is-and-what-should-never-be/
on “Cancer Progress: Much More Than You Wanted To Know (2018)”Submitted Requiem as a story · 1 points
HN discussionOne of the major concerns I have with this code, and codes derived from this, has to do with specific numerical underflow that can be seen to be happening before the series is summed. 1st: let pi_major = 3.1415927f32; let pi_minor = -0.00000008742278f32; [...] (x - pi_major - pi_minor) * (x + pi_major + pi_minor) * p1 * x Focus on the x, pi_minor and pi_major. This is fine, pi_major is basically pi. pi_minor is a sm…
Comment linking /2007/11/why-am-i-surprised-that-people-found-this-surprising/
on “Approximating sin(x) to 5 ULP with Chebyshev polynomials”Submitted Real scalability is hard, aka there are no silver bullets as a story · 1 points
HN discussionA little tooting of my own horn here, but nyble[1] allows you to build a ramdisk bootable image and kernel, that you can serve trivially with any http server and iPXE. A related project, tiburon[2] allows you to make this JSON db controlled. Still working on documenting them in greater depth, but you can see an example of what nyble can do[3]. [1] https://github.com/joelandman/nyble [2] https://github.com/joelandman…
Comment linking /2019/05/nyble-ftw-installing-my-rambooted-environment-on-linux-laptop-for-rescue-with-grub/
on “Ramroot – Run Arch Linux Entirely from RAM (2017)”Submitted Entrepreneurs are optimists as a story · 1 points
HN discussionCool result! I've done similar things in the past with previous company's units[1] using Mellanox cards. We worked quite a bit with Chelsio as well, and have shown nice results there. I am surprised on the spinning disk front though, as I was showing off about 5.5-6GB/s for previous company's 60 drive bay units 3 years ago[2]. This was a single PCIe gen3 x8 NIC, we were bounded by the IB network (56Gb) performance,…
Comment linking /2014/10/massive-unapologetic-firepower-part-2-the-dashboard/
on “Serving 100 Gbps from an Open Connect Appliance”Submitted Pbzip2, how do I love thee? as a story · 1 points
HN discussionDependency radii of packages in CentOS are horrible. Your minimal installs are hovering above 1GB. Debian are better at 400MB or so. Alpine is great, in that you can get this down to well under 100MB. This has been a long standing complaint of mine[1], and an argument I've had with many proponents of "software must come packaged only from the provider of the distro" people. Physical and logical footprint is a real t…
Comment linking /2018/04/distribution-package-dependency-radii-or-why-distros-may-be-doomed/
on “FreeBSD has lower latency, and Linux has faster application speeds”This ^^. I got a masters at one U, and was ensconced at another U for the Ph.D. by then. Actually that was the year that I started at the new U, and they told me, 2 weeks before I started, that they expected me to take and pass the Ph.D. qual exam. Which was in 2 weeks. I did, but it was not a fun 2 weeks. That was ... er ... ah ... 28 years ago. I've used the Ph.D., outside of press releases and presentations, mebb…
Comment linking /2018/07/typecasting-and-the-trust-us-factor/
on “Ask HN: What were/are you doing at age 25? What would you change?”ARM isn't going to displace Intel, or more correctly, x86, any time soon. My rationale is simple, in that there are many different ARM vendors, with many different (yes) ABIs and toolchains, no real industry/market push behind any of them specifically in this space. There is no consensus ARM ABI/chip/arch to replace x86. There are a few vendors fighting, hoping to do something. But no one whom is winning this war. S…
Comment linking /2013/12/the-evolving-market-for-hpc-part-1-recent-past/
on “Reasonably Secure Computing in the Decentralized World”I'm not sure why you're throwing Gentoo under the bus when its upgrade system is completely different. There is no "time to upgrade" because there are no releases to upgrade to -- you just install new versions of the software you happen to use when they come out and you feel like it. My own experiences with keeping my Gentoo systems up-to-date have been considerably more enjoyable than keeping my Ubuntu systems up-t…
Comment linking /?p=6270
on “XMir postponed in Ubuntu”I've too been in the position of trying everything I could think of to avoid being shot in the head (my company that is), and then watching it get destroyed by the bank ... I can and do empathize with those in this position now. Obviously I don't and won't condone the lying to investors, the apparent falsifying of test modalities, and so on. But I know what watching your baby, that you poured your life blood, your e…
Comment linking /2017/03/requiem/
on “Theranos’ Letter to Shareholders Shows the Company Is on Its Deathbed”Alternative theory. Perl aficionados have a long history of being on the receiving end of passive aggressive language zealots. Usually they are Pythonistas, but others have joined in as well. You see this in messages that say "perl is a write once language" or "its too complex" or "line noise" or "why is it still alive when X is better" ... Really, its tiring after 25+ years using it. So, in an effort to express a v…
Comment linking /2020/05/on-optimizing-scripting-languages-and-where-they-are-useful-and-where-they-are-not/
on “Why does OpenBSD still include Perl in its base installation?”
