Files
kubesolo-os/update/cmd/apply.go
Adolfo Delorenzo dfed6ddba8
Some checks failed
ARM64 Build / Build generic ARM64 disk image (push) Failing after 3s
CI / Go Tests (push) Successful in 1m23s
CI / Shellcheck (push) Successful in 46s
CI / Build Go Binaries (amd64, linux, linux-amd64) (push) Successful in 1m32s
CI / Build Go Binaries (arm64, linux, linux-arm64) (push) Successful in 1m15s
feat(update): channels, maintenance windows, min-version gate
Phase 6 of v0.3. The update agent now refuses to apply artifacts whose
channel doesn't match local policy, whose architecture differs from the
running host, or whose min_compatible_version is above the current
version. It also refuses to apply outside a configured maintenance window
unless --force is given.

New package update/pkg/config:
- config.Load parses /etc/kubesolo/update.conf (key=value, # comments,
  unknown keys ignored). Missing file is fine — fresh systems before
  cloud-init has run.
- ParseWindow handles "HH:MM-HH:MM" plus the wrapping midnight case
  (e.g. "23:00-01:00"). Empty input -> AlwaysOpen (no constraint).
  Degenerate zero-length windows never match.
- CompareVersions does a simple 3-component semver compare with the 'v'
  prefix optional and pre-release suffix ignored.
- 14 unit tests total.

update/pkg/image/image.UpdateMetadata gains three optional fields:
- channel ("stable", "beta", ...)
- min_compatible_version (refuse upgrade if current < this)
- architecture ("amd64", "arm64", ...)

update/cmd/opts.go reads update.conf and merges it into opts; explicit
--server / --channel / --pubkey / --maintenance-window CLI flags override
the file. New --force, --conf, --channel, --maintenance-window flags.
Precedence: CLI > config file > package defaults.

update/cmd/apply.go gains four gates in order:
1. Maintenance window — checked locally before any HTTP work; skipped
   with --force.
2. Channel — refused if metadata.channel doesn't match opts.Channel.
3. Architecture — refused if metadata.architecture != runtime.GOARCH.
4. Min compatible version — refused if FromVersion < min_compatible.
All gate failures transition state to Failed with a clear LastError.

cloud-init gains a top-level updates: block (Server, Channel,
MaintenanceWindow, PubKey). cloud-init.ApplyUpdates writes
/etc/kubesolo/update.conf from those fields on first boot. Empty block
leaves any existing file alone (so hand-edited update.conf survives a
reboot without cloud-init re-applying). 4 new tests cover empty / all /
partial / parent-dir-creation cases. full-config.yaml example updated.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 18:21:46 -06:00

169 lines
6.0 KiB
Go

package cmd
import (
"fmt"
"log/slog"
"runtime"
"time"
"github.com/portainer/kubesolo-os/update/pkg/config"
"github.com/portainer/kubesolo-os/update/pkg/image"
"github.com/portainer/kubesolo-os/update/pkg/partition"
"github.com/portainer/kubesolo-os/update/pkg/state"
)
// Apply downloads a new OS image and writes it to the passive partition.
// It does NOT activate the new partition — use 'activate' for that.
//
// State transitions: Idle/Success/Failed → Checking → Downloading → Staged.
// On any error the state moves to Failed with LastError set.
func Apply(args []string) error {
opts := parseOpts(args)
if opts.ServerURL == "" {
return fmt.Errorf("--server is required (or set in /etc/kubesolo/update.conf)")
}
// Maintenance window gate — earliest cheap check, before any HTTP work.
// Skipped with --force.
window, werr := config.ParseWindow(opts.MaintenanceWindow)
if werr != nil {
return fmt.Errorf("parse maintenance_window: %w", werr)
}
if !opts.Force && !window.Contains(time.Now()) {
return fmt.Errorf("outside maintenance window (%s); pass --force to override",
window.String())
}
st, err := state.Load(opts.StatePath)
if err != nil {
// Don't block the operation on a corrupt state file. Log + recover.
slog.Warn("state file unreadable, starting fresh", "error", err)
st = state.New()
}
env := opts.NewBootEnv()
// Record the current running version as the "from" reference. The active
// slot's version file is the most reliable source.
activeSlot, slotErr := env.ActiveSlot()
if slotErr == nil {
if partInfo, perr := partition.GetSlotPartition(activeSlot); perr == nil {
mp := "/tmp/kubesolo-active-" + activeSlot
if merr := partition.MountReadOnly(partInfo.Device, mp); merr == nil {
if v, rerr := partition.ReadVersion(mp); rerr == nil {
st.SetFromVersion(v)
}
partition.Unmount(mp)
}
}
}
// Determine passive slot
passiveSlot, err := env.PassiveSlot()
if err != nil {
_ = st.RecordError(opts.StatePath, fmt.Errorf("reading passive slot: %w", err))
return fmt.Errorf("reading passive slot: %w", err)
}
slog.Info("applying update", "target_slot", passiveSlot)
// Check for update
stageDir := "/tmp/kubesolo-update-stage"
client := image.NewClient(opts.ServerURL, stageDir)
defer client.Cleanup()
// Enable signature verification if public key is configured
if opts.PubKeyPath != "" {
client.SetPublicKeyPath(opts.PubKeyPath)
slog.Info("signature verification enabled", "pubkey", opts.PubKeyPath)
}
if err := st.Transition(opts.StatePath, state.PhaseChecking, "", ""); err != nil {
slog.Warn("state transition failed", "phase", state.PhaseChecking, "error", err)
}
meta, err := client.CheckForUpdate()
if err != nil {
_ = st.RecordError(opts.StatePath, fmt.Errorf("checking for update: %w", err))
return fmt.Errorf("checking for update: %w", err)
}
slog.Info("update available", "version", meta.Version, "channel", meta.Channel, "arch", meta.Architecture)
// Channel gate — refuse mismatched channels.
if meta.Channel != "" && meta.Channel != opts.Channel {
err := fmt.Errorf("metadata channel %q does not match local channel %q",
meta.Channel, opts.Channel)
_ = st.RecordError(opts.StatePath, err)
return err
}
// Architecture gate — refuse cross-arch artifacts. runtime.GOARCH is our
// canonical identifier ("amd64", "arm64", "arm").
if meta.Architecture != "" && meta.Architecture != runtime.GOARCH {
err := fmt.Errorf("metadata architecture %q does not match runtime %q",
meta.Architecture, runtime.GOARCH)
_ = st.RecordError(opts.StatePath, err)
return err
}
// Min-compatible-version gate — refuse if a stepping-stone is required.
// We need the active slot's version (already populated into st.FromVersion
// earlier in this command).
if meta.MinCompatibleVersion != "" && st.FromVersion != "" {
cmp, cerr := config.CompareVersions(st.FromVersion, meta.MinCompatibleVersion)
if cerr != nil {
slog.Warn("min-version comparison failed", "error", cerr,
"from", st.FromVersion, "min", meta.MinCompatibleVersion)
} else if cmp < 0 {
err := fmt.Errorf("current version %s is below min_compatible_version %s; install %s first",
st.FromVersion, meta.MinCompatibleVersion, meta.MinCompatibleVersion)
_ = st.RecordError(opts.StatePath, err)
return err
}
}
// Now we know the target version — record it (resets attempt count if it
// differs from the previous attempt's ToVersion).
if err := st.Transition(opts.StatePath, state.PhaseDownloading, meta.Version, ""); err != nil {
slog.Warn("state transition failed", "phase", state.PhaseDownloading, "error", err)
}
// Download and verify
staged, err := client.Download(meta)
if err != nil {
_ = st.RecordError(opts.StatePath, fmt.Errorf("downloading update: %w", err))
return fmt.Errorf("downloading update: %w", err)
}
// Mount passive partition
partInfo, err := partition.GetSlotPartition(passiveSlot)
if err != nil {
_ = st.RecordError(opts.StatePath, fmt.Errorf("finding passive partition: %w", err))
return fmt.Errorf("finding passive partition: %w", err)
}
mountPoint := "/tmp/kubesolo-passive-" + passiveSlot
if err := partition.MountReadWrite(partInfo.Device, mountPoint); err != nil {
_ = st.RecordError(opts.StatePath, fmt.Errorf("mounting passive partition: %w", err))
return fmt.Errorf("mounting passive partition: %w", err)
}
defer partition.Unmount(mountPoint)
// Write image to passive partition
if err := partition.WriteSystemImage(mountPoint, staged.VmlinuzPath, staged.InitramfsPath, staged.Version); err != nil {
_ = st.RecordError(opts.StatePath, fmt.Errorf("writing system image: %w", err))
return fmt.Errorf("writing system image: %w", err)
}
if err := st.Transition(opts.StatePath, state.PhaseStaged, staged.Version, ""); err != nil {
slog.Warn("state transition failed", "phase", state.PhaseStaged, "error", err)
}
fmt.Printf("Update v%s written to slot %s (%s)\n", staged.Version, passiveSlot, partInfo.Device)
fmt.Println("Run 'kubesolo-update activate' to boot into the new version")
return nil
}