Files
restic-manager/internal/store/hosts.go
T
steve 8fb1c100fd P2-04.5: kill host.default_paths in favour of manual schedules
Two independent path lists for "what does this host back up?" was
a real divergence footgun — operator types one set at Add-host time
and a different set into a schedule, both end up in the same repo,
the snapshot history looks fine until restore. Resolution: drop
host.default_paths entirely; add a `manual` flag on schedules.
A manual schedule has paths/excludes/tags/retention like any other
but no cron — it fires only via per-schedule Run-now. Single source
of truth for what gets backed up.

Schema (migration 0007):
* schedules.manual INTEGER NOT NULL DEFAULT 0.
* For every host with non-empty default_paths, seed a manual
  schedule with those paths and bump host_schedule_version.
* ALTER TABLE hosts DROP COLUMN default_paths.
* ALTER TABLE enrollment_tokens RENAME COLUMN default_paths
  TO initial_paths.

Original draft of this migration rebuilt hosts via the
create-new + drop-old + rename-new pattern. With foreign_keys=ON
(set in the connection DSN), DROP TABLE on the parent fired
ON DELETE CASCADE on every child of hosts(id) — schedules /
jobs / snapshots / host_credentials all wiped on the smoke env
when I tried it. SQLite 3.35+ supports column-level ALTERs
directly, so we skip the rebuild dance and avoid the cascade
trap. Six lines of SQL instead of sixty, no FK risk.

Run-now rewiring:
* New `dispatchScheduleNow(hostID, scheduleID, conn?)` helper
  unifies the agent-driven path (cron fire → schedule.fire →
  OnScheduleFire callback) and the UI-driven path (operator
  clicks Run-now on a schedule row). Conn arg is optional; nil
  falls back to Hub.Send.
* New POST /hosts/{id}/schedules/{sid}/run endpoint — per-row
  Run-now button on the schedules list.
* Dashboard's per-host Run-now (handleUIRunBackup) now picks the
  host's only enabled manual schedule, falls back to the only
  enabled schedule, else returns "pick one in Schedules tab".
  Keeps one-click for the common case.

Agent:
* Scheduler skips manual schedules in cron build (silent — they're
  a normal data shape, not an error).
* Wire Schedule struct gains Manual flag.
* Schedule.fire flow unchanged — the agent only ever fires
  non-manual schedules anyway.

UI:
* Add-host form retitled "Initial schedule · manual" so the
  operator knows the paths become an editable schedule under
  the Schedules tab. Result page calls out the manual schedule
  + points at Host > Schedules.
* Schedule edit form: "Manual schedule" checkbox at the top of
  the When section; toggling it hides/shows the cron field via
  inline JS. Server-side validator skips the cron requirement
  when manual=true.
* Schedule list shows a "manual" tag under the status pill and
  renders the When column as "— run-now only —" for manual rows.
  Each row gets a Run-now button when the schedule is enabled
  and the host is online.

Tests + go test ./... green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 12:26:06 +01:00

230 lines
7.2 KiB
Go

package store
import (
"context"
"database/sql"
"encoding/json"
"errors"
"fmt"
"time"
)
// CreateHost inserts a new host row. Used by the enrollment flow.
// The caller has already minted the host id and hashed the agent
// bearer token.
func (s *Store) CreateHost(ctx context.Context, h Host, agentTokenHash, certPinSHA256 string) error {
tags, err := json.Marshal(h.Tags)
if err != nil {
return fmt.Errorf("store: marshal tags: %w", err)
}
_, err = s.db.ExecContext(ctx,
`INSERT INTO hosts (
id, name, os, arch, agent_version, restic_version, protocol_version,
enrolled_at, status, tags,
agent_token_hash, cert_pin_sha256
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 'offline', ?, ?, ?)`,
h.ID, h.Name, h.OS, h.Arch,
h.AgentVersion, h.ResticVersion, h.ProtocolVersion,
h.EnrolledAt.UTC().Format(time.RFC3339Nano),
string(tags),
agentTokenHash, certPinSHA256)
if err != nil {
return fmt.Errorf("store: create host: %w", err)
}
return nil
}
// LookupHostByAgentToken resolves a hashed agent bearer token to the
// host it belongs to. Returns ErrNotFound on miss.
func (s *Store) LookupHostByAgentToken(ctx context.Context, tokenHash string) (*Host, error) {
row := s.db.QueryRowContext(ctx,
`SELECT id, name, os, arch, agent_version, restic_version, protocol_version,
enrolled_at, last_seen_at, status, repo_id, tags,
current_job_id, last_backup_at, last_backup_status,
repo_size_bytes, snapshot_count, open_alert_count,
applied_schedule_version, repo_initialised_at
FROM hosts WHERE agent_token_hash = ?`,
tokenHash)
return scanHost(row)
}
// GetHost returns a host by ID. Returns ErrNotFound on miss.
func (s *Store) GetHost(ctx context.Context, id string) (*Host, error) {
row := s.db.QueryRowContext(ctx,
`SELECT id, name, os, arch, agent_version, restic_version, protocol_version,
enrolled_at, last_seen_at, status, repo_id, tags,
current_job_id, last_backup_at, last_backup_status,
repo_size_bytes, snapshot_count, open_alert_count,
applied_schedule_version, repo_initialised_at
FROM hosts WHERE id = ?`, id)
return scanHost(row)
}
// MarkHostHello updates the host row with metadata received in the
// agent's hello message and flips status to 'online'.
func (s *Store) MarkHostHello(ctx context.Context, id string, agentVersion, resticVersion string, protoVersion int, when time.Time) error {
_, err := s.db.ExecContext(ctx,
`UPDATE hosts
SET agent_version = ?, restic_version = ?, protocol_version = ?,
last_seen_at = ?, status = 'online'
WHERE id = ?`,
agentVersion, resticVersion, protoVersion,
when.UTC().Format(time.RFC3339Nano), id)
if err != nil {
return fmt.Errorf("store: mark hello: %w", err)
}
return nil
}
// TouchHost updates last_seen_at on heartbeat, leaving status alone if
// already online (the offline-marker is a separate sweep).
func (s *Store) TouchHost(ctx context.Context, id string, when time.Time) error {
_, err := s.db.ExecContext(ctx,
`UPDATE hosts
SET last_seen_at = ?,
status = CASE WHEN status = 'offline' THEN 'online' ELSE status END
WHERE id = ?`,
when.UTC().Format(time.RFC3339Nano), id)
if err != nil {
return fmt.Errorf("store: touch host: %w", err)
}
return nil
}
// MarkHostsOfflineStale flips any host that hasn't been seen since
// before `cutoff` from 'online' to 'offline'. Returns the number of
// rows affected so the caller can log non-zero events.
func (s *Store) MarkHostsOfflineStale(ctx context.Context, cutoff time.Time) (int64, error) {
res, err := s.db.ExecContext(ctx,
`UPDATE hosts
SET status = 'offline'
WHERE status = 'online'
AND (last_seen_at IS NULL OR last_seen_at < ?)`,
cutoff.UTC().Format(time.RFC3339Nano))
if err != nil {
return 0, fmt.Errorf("store: mark offline: %w", err)
}
n, _ := res.RowsAffected()
return n, nil
}
// ListHosts returns every host. Phase 1 callers fit a small fleet in
// memory; pagination lands when it matters.
func (s *Store) ListHosts(ctx context.Context) ([]Host, error) {
rows, err := s.db.QueryContext(ctx,
`SELECT id, name, os, arch, agent_version, restic_version, protocol_version,
enrolled_at, last_seen_at, status, repo_id, tags,
current_job_id, last_backup_at, last_backup_status,
repo_size_bytes, snapshot_count, open_alert_count,
applied_schedule_version, repo_initialised_at
FROM hosts ORDER BY name`)
if err != nil {
return nil, fmt.Errorf("store: list hosts: %w", err)
}
defer rows.Close()
var out []Host
for rows.Next() {
h, err := scanHostRow(rows)
if err != nil {
return nil, err
}
out = append(out, *h)
}
return out, rows.Err()
}
// ----- scan helpers --------------------------------------------------
type hostScanner interface {
Scan(dest ...any) error
}
func scanHost(row *sql.Row) (*Host, error) {
h, err := scanHostRow(row)
if errors.Is(err, sql.ErrNoRows) {
return nil, ErrNotFound
}
return h, err
}
func scanHostRow(s hostScanner) (*Host, error) {
var h Host
var (
lastSeen, lastBackupAt sql.NullString
repoID, currentJob, lastBkSt sql.NullString
enrolled string
tags string
repoInitAt sql.NullString
)
err := s.Scan(&h.ID, &h.Name, &h.OS, &h.Arch,
&h.AgentVersion, &h.ResticVersion, &h.ProtocolVersion,
&enrolled, &lastSeen, &h.Status, &repoID, &tags,
&currentJob, &lastBackupAt, &lastBkSt,
&h.RepoSizeBytes, &h.SnapshotCount, &h.OpenAlertCount,
&h.AppliedScheduleVersion, &repoInitAt)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
return nil, ErrNotFound
}
return nil, fmt.Errorf("store: scan host: %w", err)
}
t, err := time.Parse(time.RFC3339Nano, enrolled)
if err != nil {
return nil, fmt.Errorf("store: parse enrolled_at: %w", err)
}
h.EnrolledAt = t
if lastSeen.Valid {
t, err := time.Parse(time.RFC3339Nano, lastSeen.String)
if err != nil {
return nil, fmt.Errorf("store: parse last_seen_at: %w", err)
}
h.LastSeenAt = &t
}
if lastBackupAt.Valid {
t, err := time.Parse(time.RFC3339Nano, lastBackupAt.String)
if err != nil {
return nil, fmt.Errorf("store: parse last_backup_at: %w", err)
}
h.LastBackupAt = &t
}
if repoID.Valid {
s := repoID.String
h.RepoID = &s
}
if currentJob.Valid {
s := currentJob.String
h.CurrentJobID = &s
}
if lastBkSt.Valid {
s := lastBkSt.String
h.LastBackupStatus = &s
}
if tags != "" {
_ = json.Unmarshal([]byte(tags), &h.Tags)
}
if repoInitAt.Valid {
t, err := time.Parse(time.RFC3339Nano, repoInitAt.String)
if err != nil {
return nil, fmt.Errorf("store: parse repo_initialised_at: %w", err)
}
h.RepoInitialisedAt = &t
}
return &h, nil
}
// MarkHostRepoInitialised sets repo_initialised_at to `when` if it is
// currently NULL. Idempotent: re-firing for an already-initialised
// host is a no-op (we never want to clobber the original timestamp).
// Returns true if the row was updated, false if it was already set.
func (s *Store) MarkHostRepoInitialised(ctx context.Context, hostID string, when time.Time) (bool, error) {
res, err := s.db.ExecContext(ctx,
`UPDATE hosts SET repo_initialised_at = ?
WHERE id = ? AND repo_initialised_at IS NULL`,
when.UTC().Format(time.RFC3339Nano), hostID)
if err != nil {
return false, fmt.Errorf("store: mark repo initialised: %w", err)
}
n, _ := res.RowsAffected()
return n > 0, nil
}