Files
felhom-agent/internal/proxmox/types.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

220 lines
7.8 KiB
Go

package proxmox
import "encoding/json"
// Types mirror the exact JSON shapes captured from the live demo host
// (demo-felhom, PVE 9.2.2, 2026-06-08) via `pvesh get ... --output-format json`.
// Decoding ignores unknown fields, so we depend only on the fields we use.
// Version is GET /version.
type Version struct {
Release string `json:"release"` // "9.2"
RepoID string `json:"repoid"`
Version string `json:"version"` // "9.2.2"
}
// Node is one entry of GET /nodes.
type Node struct {
Node string `json:"node"` // node name, e.g. "demo-felhom"
Status string `json:"status"` // "online"
CPU float64 `json:"cpu"` // load fraction 0..1
MaxCPU int `json:"maxcpu"`
Mem int64 `json:"mem"`
MaxMem int64 `json:"maxmem"`
Disk int64 `json:"disk"`
MaxDisk int64 `json:"maxdisk"`
Uptime int64 `json:"uptime"`
SSLFingerprint string `json:"ssl_fingerprint"`
}
// NodeStatus is GET /nodes/{node}/status (host metrics; needs Sys.Audit).
type NodeStatus struct {
CPU float64 `json:"cpu"` // load fraction 0..1
Uptime int64 `json:"uptime"`
LoadAvg []string `json:"loadavg"` // 1/5/15-min, as strings in the API
PVEVersion string `json:"pveversion"`
KVersion string `json:"kversion"`
Memory struct {
Total int64 `json:"total"`
Used int64 `json:"used"`
Free int64 `json:"free"`
Available int64 `json:"available"`
} `json:"memory"`
RootFS struct {
Total int64 `json:"total"`
Used int64 `json:"used"`
Free int64 `json:"free"`
Avail int64 `json:"avail"`
} `json:"rootfs"`
Swap struct {
Total int64 `json:"total"`
Used int64 `json:"used"`
Free int64 `json:"free"`
} `json:"swap"`
CPUInfo struct {
Cores int `json:"cores"`
CPUs int `json:"cpus"`
Sockets int `json:"sockets"`
Model string `json:"model"`
} `json:"cpuinfo"`
}
// Guest is one entry of GET /nodes/{node}/lxc and the body of
// GET /nodes/{node}/lxc/{vmid}/status/current. The status/current response has no
// vmid field (it is in the path), so callers set VMID from the request argument.
type Guest struct {
VMID int `json:"vmid"`
Name string `json:"name"`
Status string `json:"status"` // "running" | "stopped"
Type string `json:"type"` // "lxc"
CPUs int `json:"cpus"`
CPU float64 `json:"cpu"`
Mem int64 `json:"mem"`
MaxMem int64 `json:"maxmem"`
Disk int64 `json:"disk"`
MaxDisk int64 `json:"maxdisk"`
Uptime int64 `json:"uptime"`
}
// GuestConfig is GET /nodes/{node}/lxc/{vmid}/config. The config surface is
// dynamic (net0..netN, mp0..mpN, unusedN), so known fields are typed and the full
// raw map is preserved in Extra for the dynamic ones.
type GuestConfig struct {
Hostname string `json:"hostname"`
Arch string `json:"arch"`
Cores int `json:"cores"`
Memory int64 `json:"memory"`
Swap int64 `json:"swap"`
OSType string `json:"ostype"`
RootFS string `json:"rootfs"`
Features string `json:"features"` // e.g. "nesting=1,keyctl=1"
Unprivileged int `json:"unprivileged"` // 1 if unprivileged
Digest string `json:"digest"`
// Extra holds every field as raw JSON, including the dynamic netN/mpN/unusedN
// keys not promoted above.
Extra map[string]json.RawMessage `json:"-"`
}
// UnmarshalJSON fills both the typed known fields and the raw Extra map.
func (g *GuestConfig) UnmarshalJSON(b []byte) error {
type alias GuestConfig // avoid recursion
var a alias
if err := json.Unmarshal(b, &a); err != nil {
return err
}
*g = GuestConfig(a)
return json.Unmarshal(b, &g.Extra)
}
// MountPoints returns the mpN entries (e.g. "mp0" -> "local-lvm:1,mp=/mnt/mp1,backup=0")
// pulled from Extra. Relevant for later slices' bulk-volume placement.
func (g *GuestConfig) MountPoints() map[string]string {
return g.prefixed("mp")
}
// Nets returns the netN entries from Extra.
func (g *GuestConfig) Nets() map[string]string {
return g.prefixed("net")
}
// Lock returns the guest's current lock ("backup", "snapshot-delete", "migrate", …) from the config,
// or "" when unlocked. An interrupted vzdump leaves a "backup" or "snapshot-delete" lock — the signal
// the startup stale-lock recovery (F2-b) keys on.
func (g *GuestConfig) Lock() string {
raw, ok := g.Extra["lock"]
if !ok {
return ""
}
var s string
if json.Unmarshal(raw, &s) != nil {
return ""
}
return s
}
// OnBoot reports whether the guest is configured to auto-start at host boot (onboot:1). PVE omits the
// key when 0, so an absent key reads as false.
func (g *GuestConfig) OnBoot() bool {
raw, ok := g.Extra["onboot"]
if !ok {
return false
}
var n int
if json.Unmarshal(raw, &n) != nil {
return false
}
return n == 1
}
func (g *GuestConfig) prefixed(prefix string) map[string]string {
out := map[string]string{}
for k, raw := range g.Extra {
if len(k) <= len(prefix) || k[:len(prefix)] != prefix {
continue
}
// require the suffix to be a digit (mp0, net0 — not "memory")
if c := k[len(prefix)]; c < '0' || c > '9' {
continue
}
var s string
if json.Unmarshal(raw, &s) == nil {
out[k] = s
}
}
return out
}
// Snapshot is one entry of GET /nodes/{node}/lxc/{vmid}/snapshot. The list always includes the
// synthetic "current" pseudo-snapshot; named entries are real snapshots. An interrupted vzdump
// snapshot-mode backup leaves a dangling snapshot named exactly "vzdump".
type Snapshot struct {
Name string `json:"name"`
Description string `json:"description,omitempty"`
SnapTime int64 `json:"snaptime,omitempty"`
Parent string `json:"parent,omitempty"`
}
// Storage is one entry of GET /storage (cluster) and GET /nodes/{node}/storage
// (the latter adds usage fields). Unused fields stay zero.
//
// The lower block (Server/Export/Share/Datastore/Fingerprint/VGName/ThinPool) are the
// type-specific config fields the cluster /storage definition carries; they are the
// source for slice-5's deterministic durable_id derivation (server:export for NFS/CIFS,
// repo+fingerprint for PBS, vg/pool for lvmthin). Additive parse-only fields — decoding
// ignores unknown keys, so a storage type that lacks one simply leaves it zero.
type Storage struct {
Storage string `json:"storage"`
Type string `json:"type"` // "dir" | "lvmthin" | "nfs" | "cifs" | "pbs"
Content string `json:"content"` // comma list, e.g. "vztmpl,backup,iso,import"
Path string `json:"path,omitempty"`
Total int64 `json:"total,omitempty"`
Used int64 `json:"used,omitempty"`
Avail int64 `json:"avail,omitempty"`
Active int `json:"active,omitempty"`
Enabled int `json:"enabled,omitempty"`
Shared int `json:"shared,omitempty"`
UsedFraction float64 `json:"used_fraction,omitempty"`
// Type-specific config (durable_id sources).
Server string `json:"server,omitempty"` // nfs/cifs/pbs server host
Export string `json:"export,omitempty"` // nfs export path
Share string `json:"share,omitempty"` // cifs share name
Datastore string `json:"datastore,omitempty"` // pbs datastore name
Fingerprint string `json:"fingerprint,omitempty"` // pbs server cert fingerprint
Username string `json:"username,omitempty"` // pbs auth id, e.g. "felhom@pbs!n100"
VGName string `json:"vgname,omitempty"` // lvm/lvmthin volume group
ThinPool string `json:"thinpool,omitempty"` // lvmthin pool LV name
}
// StorageContent is one entry of GET /nodes/{node}/storage/{store}/content
// (e.g. vzdump archives, CT templates, guest volumes).
type StorageContent struct {
VolID string `json:"volid"` // e.g. "local:backup/vzdump-lxc-9001-...tar.zst"
Content string `json:"content"`
Format string `json:"format"`
Size int64 `json:"size"`
CTime int64 `json:"ctime"`
VMID int `json:"vmid,omitempty"`
}