Files
felhom-agent/internal/proxmox/query.go
T
admin 6e38e2f921 agent v0.49.0: reboot-during-backup stale-lock recovery (F2-b) + shared-parent script redeploy fix (F2-a)
F2-b: at startup, recover a guest left with a stale vzdump lock by a
reboot-during-backup — pct unlock -> delete dangling vzdump snapshot ->
start iff onboot, guarded by a no-vzdump-running invariant (fail-safe).
New internal/localapi/stalelock.go; proxmox GuestConfig.Lock()/OnBoot(),
ListSnapshots, ListRunningTasks, Snapshot type. New narrow sudoers grant
FELHOM_STALELOCK (pct unlock) + Critical capability stalelock-unlock.

F2-a: EnsureSharedParent only redeployed the boot script when the UNIT
differed, so the v0.36.6 make-private fix never reached hosts whose unit
was current -> /mnt/felhom-drives stayed in root's shared:1 and doubled
every drive bind. New sharedParentInstallStale compares BOTH script and
unit. Boot-time-only; never churns the live mount.

Both root causes confirmed live on felhom-pve before fixing. Green gate
(build/vet/test) all pass.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0162BnMpUXscPsUB1cU8Tr6K
2026-06-30 09:00:32 +02:00

120 lines
4.4 KiB
Go

package proxmox
import (
"context"
"fmt"
"net/url"
)
// Read-only query operations. All API-backed (Datastore.Audit / VM.Audit /
// Sys.Audit). These are what `felhom-agent --selftest` exercises against a live
// host — they mutate nothing.
// Version returns GET /version.
func (c *Client) Version(ctx context.Context) (Version, error) {
var v Version
return v, c.get(ctx, "/version", &v)
}
// Nodes returns GET /nodes. Use this to confirm the node name and read each
// node's ssl_fingerprint (which is what to pin in TLSConfig).
func (c *Client) Nodes(ctx context.Context) ([]Node, error) {
var ns []Node
return ns, c.get(ctx, "/nodes", &ns)
}
// NodeStatus returns GET /nodes/{node}/status (host metrics; needs Sys.Audit).
func (c *Client) NodeStatus(ctx context.Context) (NodeStatus, error) {
var s NodeStatus
return s, c.get(ctx, "/nodes/"+c.node+"/status", &s)
}
// ListLXC returns GET /nodes/{node}/lxc (the guests on this node).
func (c *Client) ListLXC(ctx context.Context) ([]Guest, error) {
var gs []Guest
return gs, c.get(ctx, "/nodes/"+c.node+"/lxc", &gs)
}
// GuestStatus returns GET /nodes/{node}/lxc/{vmid}/status/current. The API body
// has no vmid field (it is in the path), so it is set from the argument.
func (c *Client) GuestStatus(ctx context.Context, vmid int) (Guest, error) {
var g Guest
path := fmt.Sprintf("/nodes/%s/lxc/%d/status/current", c.node, vmid)
if err := c.get(ctx, path, &g); err != nil {
return Guest{}, err
}
g.VMID = vmid
return g, nil
}
// GuestConfig returns GET /nodes/{node}/lxc/{vmid}/config.
func (c *Client) GuestConfig(ctx context.Context, vmid int) (GuestConfig, error) {
var cfg GuestConfig
path := fmt.Sprintf("/nodes/%s/lxc/%d/config", c.node, vmid)
return cfg, c.get(ctx, path, &cfg)
}
// ListSnapshots returns GET /nodes/{node}/lxc/{vmid}/snapshot (the guest's snapshots, including the
// synthetic "current"). The startup stale-lock recovery uses it to find a dangling "vzdump" snapshot
// left by an interrupted snapshot-mode backup.
func (c *Client) ListSnapshots(ctx context.Context, vmid int) ([]Snapshot, error) {
var ss []Snapshot
path := fmt.Sprintf("/nodes/%s/lxc/%d/snapshot", c.node, vmid)
return ss, c.get(ctx, path, &ss)
}
// ListRunningTasks returns the node's currently-running tasks (GET /nodes/{node}/tasks?running=1).
// The startup stale-lock recovery uses it as the load-bearing safety guard: a backup lock is cleared
// ONLY when no vzdump task is genuinely in-flight for the guest (an agent restart while a real backup
// runs must never clear the live lock).
func (c *Client) ListRunningTasks(ctx context.Context) ([]TaskStatus, error) {
var ts []TaskStatus
return ts, c.get(ctx, "/nodes/"+c.node+"/tasks?running=1", &ts)
}
// ListStorage returns GET /storage (cluster-wide storage definitions).
func (c *Client) ListStorage(ctx context.Context) ([]Storage, error) {
var ss []Storage
return ss, c.get(ctx, "/storage", &ss)
}
// NodeStorage returns GET /nodes/{node}/storage (storage with live usage).
func (c *Client) NodeStorage(ctx context.Context) ([]Storage, error) {
var ss []Storage
return ss, c.get(ctx, "/nodes/"+c.node+"/storage", &ss)
}
// StorageContent returns GET /nodes/{node}/storage/{store}/content (e.g. vzdump
// archives + CT templates available for a restore).
func (c *Client) StorageContent(ctx context.Context, store string) ([]StorageContent, error) {
var cs []StorageContent
path := fmt.Sprintf("/nodes/%s/storage/%s/content", c.node, url.PathEscape(store))
return cs, c.get(ctx, path, &cs)
}
// LatestBackupVolID resolves the most recent vzdump archive for vmid on a backup storage.
// It lists the store's content, keeps only backup archives for that vmid, and returns the
// one with the greatest CTime. This is how a backup's produced archive is resolved after
// Vzdump+WaitTask (the task status carries no result volid), and how the restore-test picks
// a backup to restore. Returns ("", nil) when the guest has no archive on that store.
func (c *Client) LatestBackupVolID(ctx context.Context, store string, vmid int) (string, error) {
contents, err := c.StorageContent(ctx, store)
if err != nil {
return "", err
}
var bestVol string
var bestCTime int64 = -1
for _, e := range contents {
if e.Content != "backup" || e.VMID != vmid {
continue
}
if e.CTime > bestCTime {
bestCTime, bestVol = e.CTime, e.VolID
}
}
return bestVol, nil
}
// urlEscape escapes a path segment (a UPID contains ':' and '@').
func urlEscape(s string) string { return url.PathEscape(s) }