mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-20 03:11:46 +00:00
Josh Siviour
6f4aa495e6
* feat: reconcile systemd unit files on upgrade Unit files were written once at install time by install_systemd() in scripts/setup.sh and never re-asserted. A node upgraded by swapping the spx binary kept whatever units it was installed with, so any fix that lives in a unit rather than in code never reached it. This is not theoretical. A node whose spinifex-viperblock.service predates KillMode=process defaults to KillMode=control-group, so on a target stop TimeoutStopSec expires mid-flush and systemd cgroup-SIGKILLs every nbdkit while guest QEMU survives in the daemon's own cgroup: the guest keeps running with no storage path. Units are now stamped with a spinifex-unit-version marker, embedded in the binary via a generated file, and reconciled by spx admin upgrade. Missing or version-stale units are replaced after a timestamped backup; a unit at the current version whose content differs is reported as operator-modified and never overwritten. Drop-ins under <unit>.d are untouched, so systemctl edit overrides survive. Nothing is restarted. A daemon-reload is enough for KillMode and TimeoutStopSec to apply to the next stop, so drift is corrected without disturbing a running guest. Adds --dry-run, --units-only and --skip-units to spx admin upgrade. * test: cover systemd reconcile error paths and the admin upgrade CLI flow Diff coverage on the unit-migration PR sat at 45.8%, below the 60% gate. Adds tests for reconcile.go's error/edge paths (unreadable unit, backup and write failures, daemon-reload failure, malformed version markers, downgrade-is-conflict) and drives admin_upgrade.go's CLI flow directly via an injectable exit and a decision matrix extracted into validateUpgradeFlags/upgradeSummary for testability.
24 lines
1.0 KiB
Desktop File
24 lines
1.0 KiB
Desktop File
# spinifex-unit-version: 1
|
|
[Unit]
|
|
Description=Spinifex graceful guest drain
|
|
PartOf=spinifex.target
|
|
# After= all services so it stops FIRST on target/host shutdown: the drain runs
|
|
# while nats/predastore/viperblock/daemon are still up (QMP, unmount, WAL flush).
|
|
After=spinifex-nats.service spinifex-predastore.service spinifex-viperblock.service spinifex-daemon.service
|
|
|
|
[Service]
|
|
Type=oneshot
|
|
RemainAfterExit=yes
|
|
ExecStart=/bin/true
|
|
# ExecStop fires on ANY target stop, including the stop half of `systemctl
|
|
# restart spinifex.target` (a rolling deploy) -- PartOf propagates regardless
|
|
# of whether the host is actually going down. --unless-restarting drains on a
|
|
# real shutdown/reboot and on a plain `systemctl stop spinifex.target`; it
|
|
# skips only when a restart of the stack is already queued, so QEMU/nbdkit
|
|
# survive (KillMode=process) and the daemon reconnects on the way back up.
|
|
ExecStop=/usr/local/bin/spx admin node drain --local --timeout=120s --unless-restarting
|
|
TimeoutStopSec=180
|
|
|
|
[Install]
|
|
WantedBy=spinifex.target
|