nix-config/nixos/viridian/services/borgbackup/offsite.nix
jasmine d21b36a1b0
fix(borgbackup): remove persistent timers to prevent post-resume failures
Removes persistentTimer from all borgbackup services and unnecessary
network-online.target dependencies. Changes fuchsia offsite to 14:00
fixed schedule when system is reliably awake.

Persistent timer catch-ups immediately after system resume caused
failures due to services starting before network/system fully stabilized:
- Onsite: DNS resolution failures (viridian.home.arpa)
- Offsite: BorgBase connection refusals during SSH/borg handshake

Fixed schedules provide reliable backups without catch-up complexity:
- fuchsia offsite: 14:00 daily (typical awake time for desktop)
- viridian offsite: midnight daily (always-on server)
- All onsite: hourly (no catch-up needed)

Offsite services retain wants/after dependencies on onsite completion
to prevent race conditions on shared /btrfs-subvolumes snapshot paths.

Network dependencies removed as fixed schedules run when system is
already stable, eliminating timing issues with network-online.target.
2025-10-14 09:59:27 +08:00

114 lines
3.2 KiB
Nix

{
config,
pkgs,
...
}: {
# Encrypted passphrase for offsite borgbackup repository
age.secrets.borgbackup = {
rekeyFile = ./passphrase.age;
};
# Create staging directory before borg service starts
systemd.tmpfiles.rules = [
"d /btrfs-subvolumes 0755 root root -"
];
# Wait for onsite backup to complete before starting offsite
systemd.services."borgbackup-job-offsite" = {
wants = ["borgbackup-job-onsite.service"];
after = ["borgbackup-job-onsite.service"];
serviceConfig = {
Type = "oneshot";
};
};
services.borgbackup.jobs."offsite" = {
# Allow writing to staging directory
readWritePaths = [ "/btrfs-subvolumes" ];
preHook = let
subvolumes = [
"srv-containers"
"srv-forgejo"
"srv-lighttpd"
"srv-minecraft"
"srv-opengist"
];
in /* sh */ ''
# Clean up orphaned snapshots from failed runs (crash/power loss)
for subvol in ${toString subvolumes}; do
[ -d "/btrfs-subvolumes/$subvol" ] && \
${pkgs.btrfs-progs}/bin/btrfs subvolume delete \
"/btrfs-subvolumes/$subvol" 2>/dev/null || true
done
# Create read-only BTRFS snapshots for backup
for subvol in ${toString subvolumes}; do
case "$subvol" in
srv-containers) src="/srv/multimedia/containers" ;;
srv-*) src="/srv/''${subvol#srv-}" ;;
esac
${pkgs.btrfs-progs}/bin/btrfs subvolume snapshot -r \
"$src" "/btrfs-subvolumes/$subvol"
done
'';
# Backup staging snapshots and explicit persistent files
paths = [
"/btrfs-subvolumes/srv-containers"
"/btrfs-subvolumes/srv-forgejo"
"/btrfs-subvolumes/srv-lighttpd"
"/btrfs-subvolumes/srv-minecraft"
"/btrfs-subvolumes/srv-opengist"
# Persistent files (actual storage location)
"/persist/etc/machine-id"
"/persist/etc/ssh/ssh_host_rsa_key"
"/persist/etc/ssh/ssh_host_rsa_key.pub"
"/persist/etc/ssh/ssh_host_ed25519_key"
"/persist/etc/ssh/ssh_host_ed25519_key.pub"
# Persistent directories (actual storage location)
"/persist/var/lib/bluetooth"
"/persist/var/lib/nixos"
"/persist/var/lib/private"
"/persist/etc/NetworkManager/system-connections"
];
postHook = let
subvolumes = [
"srv-containers"
"srv-forgejo"
"srv-lighttpd"
"srv-minecraft"
"srv-opengist"
];
in /* sh */ ''
# Clean up snapshots after successful backup
for subvol in ${toString subvolumes}; do
${pkgs.btrfs-progs}/bin/btrfs subvolume delete \
"/btrfs-subvolumes/$subvol"
done
'';
# Remote repository configuration
repo = "r7ag7x1w@r7ag7x1w.repo.borgbase.com:repo";
encryption = {
mode = "repokey-blake2";
passCommand = "cat ${config.age.secrets.borgbackup.path}";
};
environment.BORG_RSH = "ssh -i /etc/ssh/ssh_host_ed25519_key";
compression = "zstd,9";
startAt = "daily"; # Daily at midnight
# Retention policy for daily remote backups
prune.keep = {
daily = 7; # Keep 7 daily backups (1 week)
weekly = 4; # Keep 4 weekly backups (1 month)
monthly = 12; # Keep 12 monthly backups (1 year)
};
};
}