Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM

blog.vectorchord.ai

Post reply on HN
Print view View original

21–27 of 27 posts

Re: Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM

#21

Post by q3k »

anko wrote: post #20
q3k wrote: post #19

> $272 monthly + GPU cost Imagine paying $250+/mo for 32GB of RAM and 4 VCPUs. No wonder Amazon is swimming in cash, the markup on this is bonkers.

100% this, i've been finding metal is getting very compelling against aws. For example latitude has 4 real cores and 32 GB of ram for $92/month. https://www.latitude.sh/pricing/c2-small-x86?gen=gen-2 hetzner doesn't even have specs this low from what i can tell! https://www.hetzner.com/dedicated-rootserver/#cores_threads_...

It has a VM with 32GB RAM and 4x the cores for 1/10th of the price: 25eur/mo. Effectively even lower because it has 20TB of included traffic, and the overage cost for it is ~1/10th of the AWS egress cost.

Or, for 184eur/mo you can get one of their bare metal GPU offerings with 64GB of RAM, a i5-13500 and an RTX4000.

Re: Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM

#22

Post by positron26 »

riku_iki wrote: post #9
positron26 wrote: post #7

Earlier quoted context omitted.

Do we mean managed or PG on K8s like CNPG? In all cases, I use the infra to simplify things like having disk redundancy and failover nodes, not because 12GB is interesting.

Primary managed PG, since you still need setup/maintenance/monitoring on your K8S own solution.

You guys are doing monitoring? ;-)

Re: Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM

#23

Post by lelanthran »

Imustaskforhelp wrote: post #14
lelanthran wrote: post #8

Earlier quoted context omitted.

That's not the only alternative. Rent your VPS and add in extra volumes for like $10 per 100GB.

Funny thing but netcup has $10 per 1 TB Netcup is under-rated but there are also other providers too at lowendbox/lowendtalk and I am interested to try out hetzner too sometime.

> Funny thing but netcup has $10 per 1 TB

Nice to know, but I was just guessing at what a reasonable price would be :-)

Re: Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM

#24

Post by paulddraper »

q3k wrote: post #19

> $272 monthly + GPU cost Imagine paying $250+/mo for 32GB of RAM and 4 VCPUs. No wonder Amazon is swimming in cash, the markup on this is bonkers.

+ 3.75 TB NVMe

And that’s the per second pricing applied 24/7 for a month. A year commitment takes 30% off.

Still a big markup, but a lot of these comparisons are the the on demand instant on/off price.

Re: Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM

#25

Post by Nextgrid »

riku_iki wrote: post #18
tjwebbnorfolk wrote: post #13

Earlier quoted context omitted.

What are you willing to pay for cloud-native failover? Not every use case requires 100% uptime

Sure, but those who require (99% of major businesses) are ready to pay.

Is that why most of them go down every time a single provider or even region goes down?

Actual active-active HA of your datastores is really hard to do (CAP theorem and all that). The majority of companies don't do it.

Re: Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM

#26

Post by Nextgrid »

duckbot3000 wrote: post #2

Kinda makes you wonder why you need cloud for anything besides remote encrypted backups if you can run all that on 12GB

You don't, but business executives aren't the kind to easily admit they got conned - and if they're getting close to that stage, a nice dinner or golfing session paid by the vendor's representative generally alleviates those feelings very well.

Engineers who started their career during the cloud craze and don't know anything else are also not the kind to rock the boat, lest the cash cow dies and their whole "investment" in their career becomes useless.

Re: Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM

#27

Post by riku_iki »

Nextgrid wrote: post #25
riku_iki wrote: post #18

Earlier quoted context omitted.

Sure, but those who require (99% of major businesses) are ready to pay.

Is that why most of them go down every time a single provider or even region goes down? Actual active-active HA of your datastores is really hard to do (CAP theorem and all that). The majority of companies don't do it.

PG doesn't have active-active. Solution is to have multizone failover with replication.
Post reply on HN