Frederic Branczyk
@brancz.com
Founder polarsignals.com 🧊 ❄️ Building parca.dev, Prometheus maintainer. Distributed systems, databases, and performance engineering. Actually born in Berlin. (he/him)
Right, I was saying I agree with that perspective from the user (at least currently).
That said, time will tell I think, it’s possible that databases will blur this as they get even better at storing and querying it, but I’m less sure about that aspect.
That said, time will tell I think, it’s possible that databases will blur this as they get even better at storing and querying it, but I’m less sure about that aspect.
January 5, 2026 at 6:40 PM
Right, I was saying I agree with that perspective from the user (at least currently).
That said, time will tell I think, it’s possible that databases will blur this as they get even better at storing and querying it, but I’m less sure about that aspect.
That said, time will tell I think, it’s possible that databases will blur this as they get even better at storing and querying it, but I’m less sure about that aspect.
I think we’re less than a year away from both being the same for databases. TSDBs like Prometheus had 10 years of optimizing, but all of the optimizations are slowly but surely landing in “general purpose” column stores. I agree with the sampled vs unsampled from a user perspective notion though!
January 5, 2026 at 6:10 PM
I think we’re less than a year away from both being the same for databases. TSDBs like Prometheus had 10 years of optimizing, but all of the optimizations are slowly but surely landing in “general purpose” column stores. I agree with the sampled vs unsampled from a user perspective notion though!
Yes, it looks like that. When I started noticing issues, the status page hadn't been updated yet. Uff, they've been having a rough time.
December 5, 2025 at 9:10 AM
Yes, it looks like that. When I started noticing issues, the status page hadn't been updated yet. Uff, they've been having a rough time.
I hear cpu and motherboard prices are expected to increase soon as well fyi
November 29, 2025 at 4:51 PM
I hear cpu and motherboard prices are expected to increase soon as well fyi
Someone on our team bought 192gb for just under $600 a few months ago 😭
November 29, 2025 at 4:24 PM
Someone on our team bought 192gb for just under $600 a few months ago 😭
Omg same, so frustrated with memory processing that I gave up after all.
November 29, 2025 at 4:08 PM
Omg same, so frustrated with memory processing that I gave up after all.
Not exactly the same thing but we’ve been creating jobs from sql databases for some time with this github.com/brancz/locutus
GitHub - brancz/locutus
Contribute to brancz/locutus development by creating an account on GitHub.
github.com
November 10, 2025 at 2:15 AM
Not exactly the same thing but we’ve been creating jobs from sql databases for some time with this github.com/brancz/locutus
It only works out to be beneficial if each request is relatively large, which happens to be the case for our product.
November 7, 2025 at 4:30 PM
It only works out to be beneficial if each request is relatively large, which happens to be the case for our product.
It’s somewhat specific to what I want to do. I want to route the same customer’s traffic to the same zone in GCP. Within that zone I run a load balancer infra structure myself with eg. nginx. Ingress traffic itself is free on cloud providers. So I use workers as my global load balancer.
November 7, 2025 at 4:28 PM
It’s somewhat specific to what I want to do. I want to route the same customer’s traffic to the same zone in GCP. Within that zone I run a load balancer infra structure myself with eg. nginx. Ingress traffic itself is free on cloud providers. So I use workers as my global load balancer.