Files
restic-manager/internal/server/http/tree_cache.go
T
steve 6d295bc9f6 P3-X2: tree.list synchronous WS RPC + per-session cache
Foundational for the restore wizard's tree browser. The wizard needs to
lazy-load directory contents from a snapshot as the operator drills
down; this lands the transport.

- internal/api adds MsgTreeList (server → agent) + MsgTreeListResult
  (agent → server) with TreeListRequestPayload / TreeListEntry /
  TreeListResultPayload types. Reply correlates by Envelope.ID.
- internal/restic.ListTreeChildren wraps 'restic ls --json' and
  filters its recursive output to direct children of the requested
  path. Parser + path-normalisation + isDirectChild are unit-tested.
- internal/server/ws/rpc.go introduces a generic SendRPC helper on
  Hub: register a buffered channel keyed by ULID, send the request,
  block on ctx.Done()/timeout/reply. Reply routing piggybacks on the
  existing dispatchAgentMessage by adding a MsgTreeListResult case
  that forwards to the registered waiter; if no waiter is registered
  (caller already gave up) the stray reply is dropped quietly.
- cmd/agent gains a tree.list handler that runs ListTreeChildren on a
  fresh per-call context (60s ceiling) and ships the matching
  tree.list.result envelope. Errors surface in result.Error rather
  than as transport failures so the server-side waiter can render a
  sensible UI message.
- internal/server/http/tree_cache.go is the per-wizard-session cache
  layer (~30min TTL, sweep-on-access) that fetchTreeWithCache uses
  before falling through to SendRPC. Cached on success only; agent
  errors aren't cached so a transient failure doesn't poison the
  session.

Tests:
- internal/restic/ls_test.go covers parseLsChildren at root / mid-tree
  / leaf, plus normalizeTreePath and isDirectChild edge cases.
- internal/server/ws/rpc_test.go unit-tests the registry: round-trip,
  release semantics, concurrent waiters, ctx-cancel.
- internal/server/http/tree_rpc_test.go is the full round-trip: server
  SendRPC → fake-agent over a real WS → reply → server gets the
  payload. Plus a timeout test that confirms ~300ms timeouts terminate
  in ~300ms rather than waiting forever.

The cache is plumbed but no UI handler hits fetchTreeWithCache yet —
that lands with P3-01 (wizard backend). The unused-linter is suppressed
via nolint until the wizard wires it in.
2026-05-04 15:19:22 +01:00

113 lines
3.3 KiB
Go

package http
import (
"context"
"sync"
"time"
"gitea.dcglab.co.uk/steve/restic-manager/internal/api"
)
// treeCacheTTL is how long a per-session cached directory listing
// stays valid. The whole point of the cache is to make re-expanding
// nodes within the same wizard session snappy; 30 minutes covers a
// generous wizard interaction window without holding stale data
// indefinitely.
const treeCacheTTL = 30 * time.Minute
// treeCacheKey identifies one cached listing. session_id scopes
// entries to a single browser session so two operators don't share
// view state; snapshot_id + path identify the directory inside the
// snapshot.
type treeCacheKey struct {
SessionID string
HostID string
SnapshotID string
Path string
}
type treeCacheEntry struct {
Result api.TreeListResultPayload
ExpiresAt time.Time
}
// treeCache is a per-process map of synchronously fetched directory
// listings. Concurrency is light (a few entries per active wizard
// session) so a single mutex is fine.
type treeCache struct {
mu sync.Mutex
entries map[treeCacheKey]treeCacheEntry
}
func newTreeCache() *treeCache {
return &treeCache{entries: make(map[treeCacheKey]treeCacheEntry)}
}
// Get returns a cached entry if one exists and hasn't expired.
func (c *treeCache) Get(k treeCacheKey, now time.Time) (api.TreeListResultPayload, bool) {
c.mu.Lock()
defer c.mu.Unlock()
e, ok := c.entries[k]
if !ok {
return api.TreeListResultPayload{}, false
}
if now.After(e.ExpiresAt) {
delete(c.entries, k)
return api.TreeListResultPayload{}, false
}
return e.Result, true
}
// Put records a fresh listing under k. Caller is responsible for
// having validated the result first (Error == "").
func (c *treeCache) Put(k treeCacheKey, result api.TreeListResultPayload, now time.Time) {
c.mu.Lock()
c.entries[k] = treeCacheEntry{
Result: result,
ExpiresAt: now.Add(treeCacheTTL),
}
c.mu.Unlock()
}
// Sweep deletes expired entries. Called opportunistically from the
// wizard handler — no separate goroutine needed; cache size is small.
func (c *treeCache) Sweep(now time.Time) {
c.mu.Lock()
for k, e := range c.entries {
if now.After(e.ExpiresAt) {
delete(c.entries, k)
}
}
c.mu.Unlock()
}
// fetchTreeWithCache returns a directory listing — cache hit, or a
// synchronous tree.list RPC against the agent on miss. On agent error
// (not transport error), the result is returned as-is with Error set
// rather than cached, so a transient failure doesn't poison subsequent
// requests for the same path.
//
//nolint:unused // wired in by the wizard handler in the next slice
func (s *Server) fetchTreeWithCache(ctx context.Context, sessionID, hostID, snapshotID, path string) (api.TreeListResultPayload, error) {
now := time.Now()
k := treeCacheKey{SessionID: sessionID, HostID: hostID, SnapshotID: snapshotID, Path: path}
if cached, ok := s.treeCache.Get(k, now); ok {
return cached, nil
}
reply, err := s.deps.Hub.SendRPC(ctx, hostID, api.MsgTreeList,
api.TreeListRequestPayload{SnapshotID: snapshotID, Path: path},
30*time.Second)
if err != nil {
return api.TreeListResultPayload{}, err
}
var result api.TreeListResultPayload
if perr := reply.UnmarshalPayload(&result); perr != nil {
return api.TreeListResultPayload{}, perr
}
if result.Error == "" {
s.treeCache.Put(k, result, now)
}
return result, nil
}