• 3 Posts
  • 52 Comments
Joined 1Y ago
cake
Cake day: Sep 08, 2023

help-circle
rss

I think dd is the right tool for the job. Consider using pv though. It can be much much faster.


Take a look at tubearchivisit. Works great and is in development.


Sonarr prowlarr radarr and many more. These are very powerful media download managers. I recommend using usenet.


One router (opnsense) a big Poe switch and unifi aps made a huge difference. Also wiring Ethernet everywhere helped a lot.

Previously we had devolo mesh plugs.


Ahh nice good to know. For my use case I’d rather not distribute the certificates to all my services.


True multiple drives speed up reads significantly. As long as the videos are sequential read speeds can be very fast (600MB/s) even on one drive though. Results may vary.


I have a ~40TB HDD array and jellyfin is super fast. Just put the database and cache files on a SSD.

For bulk storage of 4k videos with high bitrates HDDs are way cheaper.


Full pass through has no advantage when my reverse proxy terminates ssl and internal services are http only right?

Regardless of fqdn nginx has to decrypt and restream anyways.


I think mixing RAM sticks is mostly fine today. Maybe you won’t get 100% performance but I don’t think it will be very noticeable. You may still run into issues with some capacity combinations depending on the mainboard/cpu. Regarding clock speeds usually all run on the clock of the slowest one.

Matching RAM latency also matters for performance.

When using different capacity RAM channels matter so take care on the order of population.


Reminds me of: https://www.wired.com/story/null-license-plate-landed-one-hacker-ticket-hell/

A guy thought it would be funny to change his license plate to NULL.


SATA minimum rated connection cycles is 50. 😂


I use it in readonly mode. Works great nice app and great search capabilities.


I use nextcloud and immich in read only mode on top. Works like a charm. I sync my phone over weebdav every night.


My first server was called xenon because I misread Xeon for Xenon but I decided to stick with it. My new server is called argon. For beefy servers I will now go with noble gases. Now that I think about it maybe I will use other elements in the future. Bismut sounds cool.

I have only one cloud VM and called it firstborn. 🤷

All my PCs get names I like Aveline, Elisabeth, Amanda, Eve…

I have yet to decide on a naming scheme for mobile phones.

Networking hardware gets descriptive names for their location and purpose.



Pid 3386 behave or I am gonna SIGKILL all your children. That’s not an EMPTY THREAT. In fact I will start with the first one RIGHT NOW.


What do I take if I need more example domains on the second level? Do I use otherexample.com?


Thanks for a all the details. Makes perfect sense. I got it to work!


I just switched to porkbun. Saves me about 20EUR per year. Thanks for the tip.

I missed the keyword “glue records”. Ultimately I managed to get my dns server to work but decided against using it for now as the acme plugin is not able to do what I want. https://github.com/mariuskimmina/coredns-tlsplus/issues/2


Which provider do you use? Can you enter an ip there?


Do I need a second domain to run my own authoritative dns server?
I have a static ip (lets say 142.251.208.110). I own the domain: website.tld My registrar is godaddy. If I want to change my nameserver godaddy won't allow me to enter a static ip. It wants a hostname. I observed that many use ns1.website.tld and ns2.website.tld. I don't understand how this can work because ns1.website.tld would be served by my dns server which is not yet known by others. Do I need a second domain like domains.tld where I use the registrars dns server for serving ns1.domains.tld which I can then use as the nameserver for website.tld? I would like to avoid the registrars nameserver and avoid getting a second domain just for dns. Thank you for your input.
fedilink

Note: Adding a user to the docker is effectively root.


I got a dahua put it on its own vlan. It is powered and connected via Poe. I stream an rtsp stream to frigate for detection and frigate restreams to home assistant.

If you want a WiFi solution and a constant life stream you may experience degraded performance on your other devices but you have to check youself.


Just want to note here:

Snapshots are NOT a backup.

While btrfs is quite stable corruption/disk failure can always happen. Bcachefs had a little opsie daisy that caused some FS level corruption. Snapshots won’t help in this case.

Snapshots are great for quick restoration on user error.


Tasmota nous sametplugs work great and have a tiny footprint. They integrate nicely in home assistant. They must be calibrated once with a resistive load eg old light bulb.


Disk IO can cause rediculous load averages. The highest one I have seen:

high load

My HDDs were sweating that day. Turns out running btrfs defrag once a blue moon is a good idea…


Can you link me to an example or show me an example docker compose yml that adds an addon? I currently run a script that manually installs all my addons to the docker container by copying. Maybe you can show me with this: https://github.com/danielperna84/custom_homematic or any other really.


This is the way usually but some people just don’t learn from their mistakes…


Thanks sounds like a fun weekend project. My 72 cores are bored most of the time anyways. 😃



Vaultwarden really is great. The offline edits are my only grime with it. Also I dislike how happily the browser extension discards your inputs when you click outside.



Which vpn provider do you use for torrents?


Bonus points for creating lots and lots of networks grouping the databases together with only their respective containers.

ip a is a huge mess.


Thank you very much. I knew I needed a few nat rules but was unsure which exactly. I think I will be able to figure it out now. 😃


Jes exactly but without being http/https only and without decrypting the traffic on the vps.

That’s why the forwarded for header won’t work. It’s one layer below.



That’s not what I want accomplish. The clients connecting to machine B should not know that their traffic was handled by machine A. I will use DNATs to accomplish my goal. It is possible because tailscale can do exactly that. Thank you for your input though.

Maybe I am wrong we will see soon. 🙃


Wow this may have been the missing piece to get my setup working. If I manage to do it will send you an URL to a git repo.


Looks nice. I think I will build two docker containers with wireguard and iptables. This blog will be a great help.


I have heard of it seems like a good option. If you use it please tell me if it can fullfil my requirements.

Mhh I didn’t know headscale exists. Tailscale being proprietary was the main thing keeping me from using it.


Setting Up a Secure Tunnel Between Two Machines
I have two machines running docker. A (powerful) and B (tiny vps). All my services are hosted at home on machine A. All dns records point to A. I want to point them to B and implement split horizon dns in my local network to still directly access A. Ideally A is no longer reachable from outside without going over B. How can I forward requests on machine B to A over a tunnel like wireguard without loosing the source ip addresses? I tried to get this working by creating two wireguard containers. I think I only need iptable rules on the WG container A but I am not sure. I am a bit confused about the iptable rules needed to get wireguard to properly forward the request through the tunnel. What are your solutions for such a setup? Is there a better way to do this? I would also be glad for some keywords/existing solutions. Additional info: * Ideally I would like to not leave docker. * Split horizon dns is no problem. * I have a static ipv6 and ipv4 on both machines. * I also have spare ipv6 subnets that I can use for intermediate routing. * I would like to avoid cloudflare.
fedilink

A Containerized Night Out: Docker, Podman, and LXC Walk into a Bar
### A Containerized Night Out: Docker, Podman, and LXC Walk into a Bar --- 🌆 **Setting: The Busy Byte Bar, a local hangout spot for tech processes, daemons, and containerization tools.** --- 🍺 **Docker**: *walks in and takes a seat at the bar* Bartender, give me something light and easy-to-use—just like my platform. 🍸 **Bartender**: Sure thing, Docker. One "Microservice Mojito" coming up. --- 🥃 **Podman**: *strides in, surveying the scene* Ah, Docker, there you are. I heard you've been spinning up a lot of containers today. 🍺 **Docker**: Ah, Podman, the one who claims to be just like me but rootless. What'll it be? 🥃 **Podman**: I'll have what he's having but make it daemonless. --- 🍹 **LXC**: *joins the party, looking slightly overworked* You two and your high-level functionalities! I've been busy setting up entire systems, right down to the init processes. 🍺 **Docker**: Oh, look who decided to join us. Mr. Low-Level himself! 🥃 **Podman**: You may call it low-level, but I call it flexibility, my friends. 🍸 **Bartender**: So, LXC, what can I get you? 🍹 **LXC**: Give me the strongest thing you've got. I need all the CPU shares I can get. --- 🍺 **Docker**: *sips his mojito* So, Podman, still trying to "replace" me? 🥃 **Podman**: Replace is such a strong word. I prefer to think of it as giving users more options, that's all. *winks* 🍹 **LXC**: *laughs* While you two bicker, I've got entire Linux distributions depending on me. No time for small talk. --- 🍺 **Docker**: Ah, but that's the beauty of abstraction, my dear LXC. We get to focus on the fun parts. 🥃 **Podman**: Plus, I can run Docker containers now, so really, we're like siblings. Siblings where one doesn't need superuser permissions all the time. 🍹 **LXC**: *downs his strong drink* Well, enjoy your easy lives. Some of us have more... weight to carry. --- 🍸 **Bartender**: Last call, folks! Anyone need a quick save and exit? 🍺 **Docker**: I'm good. Just gonna commit this state. 🥃 **Podman**: I'll podman checkpoint this moment; it's been fun. 🍹 **LXC**: Save and snapshot for me. Who knows what tomorrow's workloads will be? --- And so, Docker, Podman, and LXC closed their tabs, leaving the Busy Byte Bar to its quiet hum of background processes. They may have different architectures, capabilities, and constraints, but at the end of the day, they all exist to make life easier in the ever-expanding universe of software development. And they all knew they’d be back at it, spinning up containers, after a well-deserved system reboot. 🌙 **The End.** I was bored a bit after working with podman, docker and lxc. So I asked [chat gpt](https://chat.openai.com/share/bace90e6-2810-4cc5-8098-12083d2eff97) to generate a fun story about these technologies. I think its really funny and way better than these things usually turn out. I did a quick search to see if I can find something similar but I couldn't find anything. I really suspect it being *repurposed* from somewhere. I hope you can enjoy it despite being ai generated.
fedilink