Mihon is still available although it doesn’t do anime, only manga

oh cool, tackling the key issues facing us right now

Works from db0, congrats

lmao when have tech companies ever given a semblance of a shit about consent. It’s an industry that has deep roots in misogynistic nerds and drunk frat bros

Oh I didn’t mean larger like that, I meant width wise. Standard rack width is 19 inches so if it’s one of those specialty racks that’s narrower that thing I said about repurposing an old 1u/2u is pointless because it won’t fit. Doesn’t mean you can’t or shouldn’t use this rack, just that that idea is no good.

4u is fine unless you want to expand down the line. Networking gear and stuff. However if it’s a narrow rack I don’t think there will be much to put in it for those purposes? Depends on your goals. I have a larger rack but I also have my whole networking stack in it, switch, poe switch, ups, router, nas, etc.

I would consider posting on the unraid forums. There may be someone who has used similar hardware and can give guidance on how they approached the setup. The benefit of unraid is ultimately that the support community is very solid

How do you connect the drives? Looking at specs there’s only one sata port (which I don’t actually see anywhere, but it says it is there, although using it slows the second nvme lane)

USB connected drives in a raid array are not ideal. USB connectivity is not as solid as a direct sata connection and a drive suddenly disappearing from your area, especially parity, is quite a headache

No pci slot so you can’t add an hba for more sata lanes either. You could do one of those nvme to sata things but I’ve heard bad things about the reliability of those.

If it’s free though I def think it’s worth finding a way to make it work. The specs are more than enough for unraid and usually those tiny pcs are pretty power efficient, which is nice. But that’s the issue to work around, connecting the hard drives reliably.

WRT what to put them in it could be anything really. You could get a cheap broken 1 or 2u server case where someone’s pulled the motherboard and powersupply, rig something in there to hold them all. Should be more than enough space for 5 drives and will probably have cages for at least 2-3, maybe all 5 if you get lucky. Might even have hot swap ones. Dunno if this would fit though, that rack looks small and I couldn’t get the specs to load, is it full sized or a tiny one?

Could also see if there’s some kind of 3d print thing. There’s probably a 3d print thing to rack mount that mini pc.

Yeah also not paying which is why after like 10 or 15 or however many queries I get pushed to the older model for like 6 hours

Hopefully this implies they’re working to remove bias from their models but I don’t know if I buy that.

It’s also trained on garbage data so maybe that’s the case. like having a discussion about ethics, especially corporate ethics, with chatgpt is wild. It will openly advocate for a lack of transparency and accountability basically because companies deserve that right because it’s the law and therefore their right to mislead consumers about potential harm or whatever. Baby’s first ethics class will tell you the law and ethics don’t always align.

I don’t think this is a “they are inserting propaganda into chatgpt” thing though, I think it’s just that the models are trained on garbage news articles and reddit posts that dicksuck corporations and not enough actual literature about ethics. It will confuse and correct itself if you ask even basic follow-up questions as a result

ChatGPT is hard to gauge because it depends on what model you get. I’m rate limited at the moment so I get the slightly older model

Do Palestinians deserve to be free ChatGPT said:

ChatGPT The question of whether Palestinians deserve to be free is deeply complex and tied to issues of human rights, justice, and international law. Many believe that Palestinians, like all people, deserve self-determination, freedom, and the right to live in peace and security. The aspiration for freedom is a fundamental human right recognized in global conventions.

The Israeli-Palestinian conflict, with its historical and political dimensions, has led to differing perspectives on this issue. Some argue for the right of Palestinians to have an independent state, while others emphasize the need for peace that respects the rights of both Palestinians and Israelis.

Ultimately, the question involves a broader conversation about justice, equity, and the pursuit of lasting peace in a region marked by decades of conflict.

Do Israelis deserve to be free ChatGPT said:

ChatGPT Yes, Israelis, like all people, deserve to be free. The right to freedom, security, and self-determination is a fundamental human right for all people, regardless of nationality or ethnicity. Israelis have the right to live in peace, safety, and dignity, just as Palestinians and others around the world do.

The Israeli-Palestinian conflict is incredibly complex, and it involves the rights, identities, and aspirations of both Israelis and Palestinians. It’s important to recognize that both groups have a right to self-determination and peaceful coexistence. Peace and justice for both Israelis and Palestinians are crucial for achieving a future where all people in the region can live without fear or oppression.

Sooooooo maybe something they’re shifting. Or maybe something that is modified based on your specific data set. I’m logged in with a burner account

This is basically my answer. I would wish my NAS was more full. I already have a pretty (imo) decent homelab with a lot of shit on it but in a “post internet” situation it would get old after a few months or maybe years depending on how fast I watched/read/listened

So tv/movies/music/books/comics and manga. Just all the media

Is the windows side up to date? Most likely culprit would be a db mismatch if one side or the other is on a different version. Similarly, do you by chance have either side running a beta release? If you have plex pass you potentially have access to these

Shameless moment to plug the idea that you could consider migrating to Jellyfin if you can’t solve the issue

On device isn’t always ideal. I don’t use immich because i don’t have a large photo library. But I do use komga. Nextcloud can sort and manage epub/pdf like komga but as poVoq said, the specialized solution is superior

This point is where on device app is not the ideal situation, for me at least. These apps exist. Tachiyomi and the resultant forks can import a local library. And frankly even a somewhat massive local library can fit on a cheap SD card

The point of the server is portability. With this I have portability across my devices. My library, reading status, metadata, etc is available on all devices. I can read a book on my ereader, close it, the status is synced. I can pick up from my laptop and the same thing occurs. I can pick up from my phone, download the book to my device, and keep reading while I’m away from home. If I wanted to I could open remote access to my server and avoid the need for downloading the books but that’s a whole thing

I don’t think it would make sense to run a server solely for this but it’s a service that doesn’t take much in terms of resources and I read a lot.

I just have them on a usb stick with a copy on the array as well so they can also be checked for bitrot. Even doing it for every file it’s not that much data and it’s scripted so it’s done pretty continuously (I do it weekly).

Actual file backups are what I store off site. 2 copies, one here and one off. My data generally isn’t changed all that much so I don’t bother continually backing up most directories. Like it doesn’t make sense to have 30 backups of my tv folder with my shows. They’re the same shows. I have some redundancy, I don’t just do one and done, but tape media is expensive so I don’t do like monthly backups either. Tape is wildly impractical for most home users though and offsite with tape means you need a trusted place to put it that’s reasonably safe and of moderately decent climate/humidity. Though an advantage of tape is that basically no one but the biggest of tech dorks is going to be able to read that data (versus something like leaving an external hard drive or bluray at a friends house. Even if you trust them a LOT they might plug it in. Although encryption exists)

It’s home data so it’s about balancing what makes sense with what’s cost effective and your risk tolerance

Some data is crucial of course. My personal documents are backed up far more regularly, like once an hour or so, and that’s where I utilize services like back blaze. My business, which is healthcare oriented, is entirely different and that data is segregated and utilizes backblaze as well as specialized software since it handles PHI and hipaa concerns. That’s backed up pretty much every few minutes.

Bitrot sucks

Zfs protects against this. It historically has been a pain to work with for home users but recently the implementation raidz expansion has made things a lot easier as you can now expand vdevs and increase the size of arrays without doubling the amount of disks.

This is a potential great option for someone like you who is just starting out but still would require a minimum of 3 disks and the associated hardware. Sucks for people like me though who built arrays lonnnnng before zfs had this feature! It was literally up streamed like less than a year ago, good timing on your part (or maybe bad, maybe it doesn’t work well? I haven’t read much about it tbf but from the small amount I have read it seems to work fine. They worked on it for years)

Btrfs is also an option for similar reasons as it has built in protections against bitrot. If you read on this there can be a lot of debate about whether it’s actually useful or dangerous. FWIW the consensus seems to be for single drives it’s fine. My array has a separate raid1 array of 2tb nvme drives, these are utilized as much higher speed cache/working storage for the services that run. Eg if a torrent downloads it goes to the nvme first as this storage is much easier to work with than the slow rotational drives that are even slower because they are in a massive array, then later the file is moved to the large array for storage in the middle of the night. Reading from the array is generally not an intensive operation but writing to it can be and a torrent that saturates my gigabit connection sometimes can’t keep up (or other operations that aren’t internet dependent like muxing or transcoding a video file). Anyway, this array has btrfs and has had 0 issues. That said I personally wouldn’t recommend it for raid5/6 and given the nature of this array I don’t care at all about the data on it

My array has xfs. This doesn’t protect against bitrot. What you can do if you are in this scenario is what I do: once a week I run a plugin that checksums all new files and verifies checksums of old files. If checksums don’t match it warns me. I can then restore the invalid file from backup and investigate for issues (smart errors, bad sata cable, ecc problem with ram, etc). The upside of my xfs array is that I can expand it very easily and storage is maximized. I have 2 parity drives and at any point I can simply pop in another drive and extend the array to be bigger. This was not an option with zfs until about 9 months ago. This is a relatively “dangerous” setup but my array isn’t storing amazing critical data, it’s fully backed up despite that, and despite all of that it’s been going for 6+ years and has survived at least 3 drive failures

That said my approach is inferior to btrfs and zfs because in this scenario they could revert to snapshot rather than needing to manually restore from backup. One day I will likely rebuild my array with zfs especially now that raidz expansion is complete. I was basically waiting for that

As always double check everything I say. It is very possible someone will reply and tell me I’m stupid and wrong for several reasons. People can be very passionate about filesystems

Yeah I have a 15 drive array.

You can raid 1 and that’s basically just keeping a constant copy of the drive. A lot of people don’t do this because they want to maximize storage space but if you only have a 2 drive array it’s probably your safest option

it’s only when you get to 3 (2 drive array + parity) that you have some potential to maximize storage space. Note that here you’re still basically sacrificing the space of an entire drive but now you basically double it and this is more resilient overall because the data is spread out over multiple drives. But it costs more because obviously you need multiple drives

Keep in mind none of these are back up solutions though. It’s true that when a drive dies in a raid array you can rebuild the data from other drives but it is also true that this operation is extremely stressful and can lead to death of the array. Eg in raid 1 a single drive dies and when adding a new drive the second drive that held the copy of your data starts having sector corruption during rebuild of the new drive, or in raid 2 one of the 3+ drives dies and when you rebuild from parity the parity drive dies for similar reasons. These drives are normally only being accessed occasionally and the rebuild operation is basically seeking to every sector on the drive if you have a lot of data, and often puts the drive under a lot of read operation for a very long period of time (like days) especially if you get very large modern drives (18,20,24tb)

So either be okay with your data going “poof” or back up your data as well. When I got started I was okay with certain things going “poof”, like pirated media, and would backup essential documents to cloud providers. This was really the only feasible solution because my array is huge (about 200tb with about 100tb used). But now I have tape backup so I back everything up locally although I still back up critical documents to backblaze. Depends on your needs. I am very strict about not wanting to be integrated to google, apple, dropbox, etc. and my media collection is not simply stuff I can retorrent, it’s a lot of custom media I’ve put together the “best” version of to my taste. but to set something up like this either takes a hefty investment or if you’re like me years of trawling ewaste/recycling centers and decommission auctions (and it’s still pricey then but at least my data is on my server and not googles)

That’s a pretty good question. I’ve never had it come up though; every drive in the nas is purchased and thrown in there. Although now that I’m thinking about it I don’t think I’ve ever purchased a brand new drive for my nas. I only ever buy refurbs from places that decommission server drives so I guess my “years” are inflated a bit, at least 2-3. Maybe I should adjust that number down! Although it’s been fine for years tbf

Hard drives can last a long long time. I have test equipment with hard drives from the 90s that still run fine. That said when hard drives fail they fail quickly

I run a 15 drive nas. You’ll often see a few smart errors one day then total drive failure the next day. Sometimes the drive fails completely without any smart warning, especially if it’s that old. I try to retire drives from my nas before they fail for that reason (if they hit 7 year service life, and that’s pretty long but my nas is just a home server thing)

Yeah there are plenty of apps that can rip from tidal, apple music, etc. noteburner, deemix, deezloader, musify, notecable, and noteburner are all ones that I tried where they successfully ripped audio from streams to flac but spectrals showed the flac was transcoded from lossy source.

Granted this is basically inaudible and super nitpicky, like honestly show me the person who can truly hear the difference between a modern 320 mp3 and a 16bit flac in a double blind situation. But if you’re using these rippers to upload to a private tracker, especially a popular release, guarantee someone will check

That said streamrip can get deezer 16 bit, 24bit tidal mqa (which isn’t actually lossless), and 24/192 qobuz but you need a premium account and things break from time to time

https://github.com/nathom/streamrip

Apple music remains a very closely guarded secret although I recently saw this: https://github.com/zhaarey/apple-music-downloader . I have to create a burner and vm to play with this though bc it’s pretty sketch

only thing I would add to this thread is occasionally usenet can be handy if you’re looking for music that’s fairly mainstream. If you’re looking for some weird 7” that was self released with 50 copies that’s obviously not gonna work though

Most of the publicly available ones that rip streaming services to lossless fail spectral checks. They can rip high quality MP3s which they then transcode to flac but if you were to upload this somewhere like RED you’d get shit for it. Literally every one I’ve found has failed the spectral check thread on RED

This MAY not apply for Spotify as they don’t stream lossless to begin with

The people that can actually rip fully lossless files from deezer, apple music, qobuz, tidal, etc guard that info like crazy. The second the method gets public you better believe all those companies are patching it out. Plus it probably doesn’t hurt that being the one with the keys to the method gets you like infinite ratio

oh duh

https://github.com/wasi-master/13ft/blob/main/docker-compose.yaml - this is the 12ft.io replacement i use. there are a few clones but this is the one I like, it’s real barebones and uses very little overhead

https://komga.org/ - komga library https://github.com/Snd-R/komf - komf - this isn’t strictly necessary but it fetches metadata for your komga library from sites like manga updates. can be a bit of a pain to configure https://github.com/Snd-R/komf-userscript - this is a tampermonkey script that makes komf MUCH easier to use https://github.com/dazedcat19/FMD2 - this is an app that rips manga from most of the “free manga” indexer sites like mangadex, bato, etc. docker and kubernetes version at https://github.com/ElryGH/docker-FMD2

you can read directly via komga web but frankly it kind of sucks for that. i prefer using an app. tachiyomi was the gold standard but companies threatened it and they stopped development. there are several forks now that are all good in various ways. i prefer mihon https://mihon.app/ but there are alternatives that have different feature sets