GN. I'm off to sleep, but Merry Christmas to those just waking up :)
ChipTuner
ChipTuner@gitcitadel.com
npub1qdjn...fqm7
Building software they don't like. Free, as in freedom.
Low-level and server engineer: libnoscrypt, NVault, vnlib.
Staff @GitCitadel
https://geyser.fund/project/gitcitadel
Just a little PSA that any consumer SSD you purchase off the shelf will not last for server use cases.
I've had pretty equal amounts of
- Samsung Pro
- Samsung Evo
- OCZ (yeah long time ago)
- Crucial (micron silicon)
- Sandisk
- Sandisk Ultra
- Intel consumer
The sad part is 1-2 years after purchase it's known that so many these off the shelf drives are garbage, but you'll still see people argue for new drives like it's not a continuous cycle. While the quality of consumer nand has only declined.
The Intel 545s were amazing engineering - became known for one of the worst consumer drives shipped like 6 months after release, and were discontinued like immediately iirc.
Sandisk and OCZ were known for crappy controllers but good nand for a long time.
The only exception is Samsung Pros, and to be fair, I've had higher hours on them, but not in more reliable "test" conditions. The price on the Pro drives kind of out weighs the benefits imo. Because if you still need a big array to be fault tolerant you're just adding cost. The only benefit is IOPs.
If you're going to purchase consumer drives, the move has been,
- Buy the cheapest option you trust
- buy in BULK,
- spread the IOPs across a much larger array
- Make your array tolerant enough to handle multiple failures in quick succession
- have plenty of spares and 2-3 HOT
This heavily depends on your workload though. It depends how heavily you depend on consistent random IO. A ZFS system with lots of memory 64GB+, can handle random bust writes well. This is because cheaper consumer drives are usually horrible at random IO and rarely have any dram cache. The usually have terrible realized IOPs.
The last issue with super cheap consumer drives is monitoring. They usually just die completely without reporting anything. It's not until a check runs that data corruption will be detected (zfs scrub). They often fake or underreport SMART useful data.
For the price, I might just be going back to a big ass pool of spinning hard drives.
Wait. Isn't one of the advertised features of modern LLMs interpolation? Just let LLMs fill in the redactions XD
View quoted note →
Archiving tip if you're a data hoarder like me
If you have files you don't touch often (or ever). Archive them with tar or zip or 7zip. I'd suggest 7zip when you have more than a few gigabytes to store, and break them into smaller archive files, its easier on machines, youll thank me later.
- Add your file to the archive
- name your archives well, but not too verbose.
- compute a checksum of the archive(s) (sha1, sha256, etc)
- Take the first 8-12 hex character and append it to the end of the filename
What you get
- Likely less disk space
- A chance for better organization
- A smooth brain way to verify the integrity of the file incase you experience a disk error, bitrot etc
- Less likely to lose single files when you copy files between disks. Losing a 5gb archive is far more obvious than a 50k pdf.
I migrate storage, for hardware reasons, software reasons, disk failures, disk upgrades etc. Every time I move files I have a chance of losing one somewhere in the migration log. Most archive tools do a checksum, but having a smooth brain, universal check in the file name makes it super simple to check if the archive is corrupted if your tool set is limited.
You love to see it
View quoted note →
Vector remap language :)
I love this time of year.
Taxes and Fines, Fines and Taxes. Enjoy your corporate 9-5 if you got one.
No government offices will answer a phone or call you back. You get less than a week to respond to notices or fines double. Biggest holidays of the year so offices are closed twice as often.
Ready for this. One of the local offices is only open in person from 11am-4pm on Thursdays. They only have an answering machine and despite calling multiple times a day leaving voicemails, no return call back after a week.
"noise protocol" for DNS? Thoughts?
View quoted note →
*Opens up nostr client for 0.0001 seconds*
211 dns queries
You think 26 hard drives bays is enough. Then you find your pile of accumulated high hour drives.