Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM
Posted by gaocegege 7 days ago
Comments
Comment by q3k 1 day ago
Imagine paying $250+/mo for 32GB of RAM and 4 VCPUs. No wonder Amazon is swimming in cash, the markup on this is bonkers.
Comment by anko 1 day ago
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_...
Comment by q3k 1 day ago
Or, for 184eur/mo you can get one of their bare metal GPU offerings with 64GB of RAM, a i5-13500 and an RTX4000.
Comment by paulddraper 1 day ago
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.
Comment by nwellinghoff 6 days ago
Comment by ayende 2 days ago
You must have the data upfront, you cannot build this in an incremental fashion
There is also bo mention on how this would handle updates, and from the description, even if updates are possible, this will degrade over time, requiring new indexing batch
Comment by esafak 1 day ago
Comment by duckbot3000 6 days ago
Comment by Nextgrid 1 day ago
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.
Comment by riku_iki 5 days ago
Comment by logifail 1 day ago
Comment by riku_iki 1 day ago
But realistically, I believe major clouds (google, aws) likely has more robust org and infra for recovery than I can built and maintain.
Comment by positron26 2 days ago
Comment by riku_iki 2 days ago
Comment by positron26 1 day ago
Comment by tjwebbnorfolk 1 day ago
Not every use case requires 100% uptime
Comment by riku_iki 1 day ago
Comment by Nextgrid 1 day ago
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.
Comment by riku_iki 1 day ago
Comment by benjiro 1 day ago
And yes, i agree, the PG failover setup (and especially dealing with a failure afterwards, to restore the ex-master is beyond infuriating).
But its not pay 10x the amount, while eating easily 10x performance infuriating :)
Comment by setr 6 days ago
Comment by lelanthran 2 days ago
Rent your VPS and add in extra volumes for like $10 per 100GB.
Comment by Imustaskforhelp 1 day ago
Netcup is under-rated but there are also other providers too at lowendbox/lowendtalk and I am interested to try out hetzner too sometime.
Comment by benjiro 1 day ago
Not counting the fact that Netcup is raided (also Netcup is limited to 8TB on a VPS).
That is like 4.7 Euro /TB. That is like 4$/TB. 6 Euro / TB in a raid 5 setup.
I do not understand why they are not using this new pricing model on their older servers. There the best you can get is like 10 Euro /TB (for the single 15TB U.2).
Comment by lelanthran 1 day ago
Nice to know, but I was just guessing at what a reasonable price would be :-)