Live data from Hacker News

Cloud VM benchmarks 2026

devblog.ecuadors.net

131–140 of 165 posts

Re: Cloud VM benchmarks 2026

#131

Earlier quoted context omitted.

> I just don’t understand it Maintaining and updating your own hardware comes with so much operational overhead compared to magically spinning up and down resources as needed. I don’t think this really needs to be said.

I dunno… for setup, yes absolutely. One time cost in time. After that, not really.

It’s absolutely not a one time cost. Once you have it you need to hire people full time to maintain it and eventually upgrade it. Hardware fails constantly

Re: Cloud VM benchmarks 2026

#132

Earlier quoted context omitted.

It’s wild that no one knows just how cheap bandwidth really is. AWS pulled one over on people and it’s like the movie studios still demanding 10% of the top for VHS distribution. Today.

That’s with every industry Make things look like a complicated black box. Make sure it feels scary to roll your own. Hide the core technical skills behind abstracted skills

Cloud has done a truly epically awesome job at this. People are now afraid to set stuff up.

Re: Cloud VM benchmarks 2026

#134

> The Azure pricing is at least as complex as AWS/GCP, plus the pricing tool seems worse. They also lag behind the other two major providers in CPU releases - Turin and Granite Rapids are still in closed preview at the time of writing this. Small nitpick, but Turin-based VM's have been available for more than a month now [1], and they are a beast. [1] - https://techcommunity.microsoft.com/blog/azurecompute/announ...

The testing was from mid-September to mid-January, Turin was released on Azure end of January. They simply did not make the cut, unfortunately I could not wait forever for them, they always seem to lag behind at least half a year :(

I might do an addendum just for Azure...

Re: Cloud VM benchmarks 2026

#135
post #18

Earlier quoted context omitted.

I wrote the article. I would NEVER tell anyone to use Oracle, as the vendor lock in and strong-arming and pricing is ridiculous. That said, I am hosting small projects on Oracle Cloud, due to the super low cost. I can just move them whenever they decide to be naughty, I am not using an oracle DB or anything proprietary, just linux VMs with my own mysql setup.

I was confused by your comment. I assume you meant to say "I would NEVER tell anyone to use Oracle DB" (as opposed to Oracle Cloud)?

I meant pretty much anything Oracle... except their free/cheap VMs :)

Re: Cloud VM benchmarks 2026

#136

Anyone have experience with Oracle Cloud and ease of moving away? This benchmark seems to recommend Oracle Cloud, but I’ve heard that Oracle has historically used aggressive licenses and legal terms to keep customers locked-in.

I signed up for an Oracle Cloud trial. They closed my trial a few days later and shut down my one trial VM without warning. Weirdly they didn’t allow me to add payment info to continue. Even weirder their sales people kept contacting me asking me to come back. When I explained the situation they all tried to fix it and then went radio silent until the next sales rep came along to try to convince me to stay. I searche…

I had a bit of a hard time when I first signed up. It turns out the problem was I had included "oracle" in my email (I give a different email on my domain to every provider), so some part of the system considered it an internal email and others part did not, so I had a weird account that could not do anything. Took them a month of two to figure out what was wrong...

Re: Cloud VM benchmarks 2026

#137
post #27

Earlier quoted context omitted.

I used their free tier. The account creation process was really confusing, and they kept turning off my instance because usage was not high enough. It seemed quited oudated/confusing to use last time I tried it a few years ago.

This has made me leery of Oracle Cloud in the past. https://docs.oracle.com/en-us/iaas/Content/FreeTier/freetier... : > Idle Always Free compute instances may be reclaimed by Oracle. Oracle will deem virtual machine and bare metal compute instances as idle if, during a 7-day period, the following are true: > • CPU utilization for the 95th percentile is less than 20% > • Network utilization is less than 20% > • Memory…

They warn they will reclaim. I had two accounts, one processing data for a free weather service I volunteer for, so it's not idle and has had no issues for a couple of years now. The other for personal projects, so at times it stays idle for a while and I would get these email warnings which made me switched it to paid. I have not paid a cent, again for a couple of years now.

Re: Cloud VM benchmarks 2026

#138
post #20

I just ran some massive tests on our own CI. I use AMD Turin for this on gcp, which was noted as one of the fastest ones in the article. The most insane part here is that the AMD EPYC 4565p can beat the turin's used on the cloud providers, by as much as 2x in the single core. Our tests took 2 minutes on GCP, 1 minute flat on the 4565p with its boost to 5.1ghz holding steady vs only 4.1ghz on the gcp ones. GCP charges…

Hetzner charge between €10 and €48 for an 8vcpu setup, depending on how many other users you're happy to share with. For €104/mo you can get a 16-core Ryzen 9 7950X3D (basically identical to your 4565p) w/ 128GB DDR5, 2x2TB PCIE Gen4 SSD. That's not to say you're wrong about dedicated being much better value than VPS on a performance per dollar basis, but the markup that the European companies charge is much, much lo…

I'd be terrified to run anything other than a classic web server on Hetzner, have heard too many stories of them arbitrarily terminating workloads they didn't understand.

Re: Cloud VM benchmarks 2026

#139

Earlier quoted context omitted.

Hetzner charge between €10 and €48 for an 8vcpu setup, depending on how many other users you're happy to share with. For €104/mo you can get a 16-core Ryzen 9 7950X3D (basically identical to your 4565p) w/ 128GB DDR5, 2x2TB PCIE Gen4 SSD. That's not to say you're wrong about dedicated being much better value than VPS on a performance per dollar basis, but the markup that the European companies charge is much, much lo…

Great points. If we’re going to talk about dedicated servers and long lock-in contracts, you have to look at the equivalent prices for hosted alternatives. It’s fun to start thinking about building your own server and putting in a rack, but there’s always a lot of tortured math to compare it to completely different cloud hosted solutions. One of the great things about cloud instances is that I can scale them up or do…

If you can reasonably estimate your usage and the peak total usage is less than ~5x the minimum, it still makes sense to just rent hardware at Hetzner.

You even have the possibility of managed racks, whereby you rent one or more racks, but the servers are still provided by Hetzner so you don't have to handle procurement, logistics or replacements.

Re: Cloud VM benchmarks 2026

#140

Earlier quoted context omitted.

Yeah I expected this benchmark to include hosted "metal" hardware with the "per instruction cost" benchmark to see how provider like Hetnzer fare against classic AWS VMs. It's a bit apple to oranges I know, but I think nowadays is what most people compared pure performance cost are interested in. I'm not going to migrate from AWS VMs to GCP or Hetzner VMs, but I might be open to Hetzner hosted servers instead for a m…

> ... but I might be open to Hetzner hosted servers instead for a massive enough cost reduction. Don't use Hetzner for anything actually important to you. :( As to why: https://news.ycombinator.com/item?id=45481328

A good business would send you a warning a month before your credit card expires, not after the fact.
Post reply on HN