I just asked Llama3 Instruct (7B Q8): "Tell me all you know about ZFS on OpenBSD"
Llama3 replied: "A great topic!
ZFS is a combined file system and logical volume manager designed by Sun Microsystems, now owned by Oracle. It's known for its advanced features, high performance, and reliability. On OpenBSD, ZFS is available as part of the base system since version 5.4 (released in 2011). Here are some key aspects of using ZFS on OpenBSD:
Installation
To install ZFS on OpenBSD, you'll need to specify zfs as your file system during installation. This will create a ZFS pool with a single vdev (virtual device) containing the root file system.
ZFS Pool
A ZFS pool is the top-level container for all ZFS storage. It can contain one or more virtual devices (vdevs), which are used to store data and metadata. On OpenBSD, you'll typically create a single pool with a single vdev containing the root file system.
VDEVs
Vdevs are the building blocks of a ZFS pool. They're composed of one or more disk devices, and can be configured in various ways (e.g., RAID-Z, mirror, single-disk). OpenBSD supports the following vdev types:
raidz: A type of RAID-5, providing redundancy with data striping.
mirror: A simple mirroring configuration for each block.
single: A single disk vdev, used for a standalone pool or for testing.
ZFS Features
Some notable ZFS features available on OpenBSD:
Snapshots: Instantaneous copies of your file system at a specific point in time. You can take snapshots, clone them, and even revert to previous states if needed.
Send/Receive: Allows you to send and receive entire ZFS pools or datasets between systems.
Checksums: Data integrity checks are performed on all data written to disk.
Compressed: Compression is supported for both data and metadata, reducing storage requirements.
Quotas: Limits can be set for individual datasets to prevent excessive usage.
OpenBSD-specific ZFS settings
Some OpenBSD-specific configuration options:
zfs_load: Controls whether the ZFS module is loaded at boot time. Set it to YES in /etc/sysctl.conf to enable ZFS support.
zfs_root: Specifies the root file system dataset name. Typically set to tank/root.
zfs_pool: Sets the default pool name (e.g., tank).
ZFS CLI
The OpenBSD ZFS command-line interface (CLI) is similar to other Unix-like systems:
# zpool list # List all pools and their status
# zfs list # List all datasets in a pool
# zfs snapshot # Create a new snapshot of a dataset
# zfs clone # Clone a snapshot or dataset
# zfs send # Send a dataset or snapshot to another system
Tips and Considerations
Be cautious when using ZFS, as some operations (e.g., zpool destroy) can be destructive.
Regularly check your pool's health with zpool status and ensure you have enough disk space.
Use zfs snapshots to create regular backups of your file systems.
This is just a brief overview of using ZFS on OpenBSD. If you have specific questions or concerns, feel free to ask!"
We're safe. And I should ask Theo why he's always lied and never announced ZFS support on OpenBSD. 😆
Another text for today - " Why you shouldn't run a BSD on a PC"
"Changing GNU/Linux distribution can be done on a whim, as underneath all of that you’ve got the same basic operating systems. With BSDs it’s not the same. One should try to understand the downsides, as not to waste the next 20 years exploring an OS that simply is not a good fit."
I still remember my first #BSD steps.
I was absolutely fascinated by #OpenBSD when I first found it back on 2009...
Well, it's been a long time... and I still run #BSD :openbsd:
The feeling of running #OpenBSD never left. I can't quite explaint it.. it felt alien and familiar at the same time - peradox.
Here at Emacs.ch we run an experimental side instance [1] based on Snac2 [2], which is a Mastodon-compatible Fediverse server written in C, runs completly file-based and features a zero-JS UI.
It doesn't have many of the fancy features of Mastodon, but is a bright example of how a super-minimal system can do the job very well. It'll also work with your mobile Mastodon apps and small browsers like Dillo[3].
It runs on OpenBSD and we accept a few more testers. There is no automatic sign-up, so if you are interested, DM me with the desired account name and I'll send you the credentials.
if I were to start learning more about one of the listed BSD operating systems, which would you recommend? Guessing the answer could be different if we're talking about daily desktop usage vs server, so maybe clarify your answer via a reply if you can (fwiw, probably more interested in daily desktop usage, but open to whatever too).
Given that you said "learn about" and not "use", and given that you said that you had MacOS, I'd say learn FreeBSD first, then NetBSD, then OpenBSD.
It's worth learning them all.
But #FreeBSD is the closest to what you have in MacOS, with there being somewhat of a common heritage from many years ago; #NetBSD will expand your horizons from that, and then #OpenBSD is the furthest away from MacOS with very different ideas about almost everything and different abstractions.
I use Ctrl+Super+L for screen locking in #KDE#Plasma.
It works fine, but Plasma doesn't automatically pause media playback when locking the screen.
So, I removed the lockscreen shortcut, and added a custom Ctrl+Super+L shortcut to execute:
bash -c 'playerctl pause & qdbus org.freedesktop.ScreenSaver /ScreenSaver Lock'
Nice, nice! I have ctrl + super + [-=] for brightness, ctrl + shift + super + [-=] for volume, and ctrl + shift + super for play/pause (used to be mute toggle)
I tend to write single-purpose scripts that work on as many platforms as I use, so my volume and brightness scripts work on multiple linux distros and #OpenBSD. ;)
#BoxyBSD is a non-profit VM & service provider for the open-source community with a focus on BSD based Systems like #FreeBSD, #OpenBSD and #NetBSD. BoxyBSD also provides additional services like webhosting, git, email and DNS solutions for #opensource projects to give valuable things back to the community.