feat: cache merged /facts and /nodes in memory, stale on backend failure

A busy Puppetboard re-fans-out the same /facts query every few seconds, and a
502 is worse than 30-second-old facts when every PuppetDB is unreachable.

- Add a `Cache` interface (get reports fresh/stale/miss, put, stats) keyed on
  `<path>?<params>` with keys and repeated values sorted, plus a no-op default
  so uncached paths behave exactly as before.
- Route serveMerged/serveUnion/serveSummed through `serveCached`, so the
  reports cache drops in at `cacheFor` without touching a handler.
- Back /facts and /nodes with a byte-bounded LRU: `facts_ttl` (default 30s,
  clamped to a 30s cap) and `facts_cache_bytes` (default 64 MiB); expired
  entries are kept and served only when every backend fails.
- Single-flight identical keys so N concurrent requests cause one fan-out.
- Surface `cache` state and `serving_stale` in /healthz and the cache settings
  in `config show`.
This commit is contained in:
2026-09-05 20:41:59 +10:00
parent 083fb6ba53
commit cab1d7ade0
7 changed files with 1230 additions and 46 deletions
+248
View File
@@ -0,0 +1,248 @@
package main
import (
"container/list"
"context"
"net/url"
"sort"
"sync"
"time"
)
// CacheStatus distinguishes the three outcomes of a lookup: nothing stored, a
// stored entry within its TTL, and a stored entry past it.
type CacheStatus int
const (
CacheMiss CacheStatus = iota
CacheFresh
CacheStale
)
func (s CacheStatus) String() string {
switch s {
case CacheFresh:
return "fresh"
case CacheStale:
return "stale"
default:
return "miss"
}
}
// CacheEntry is a stored response body and the time it was stored.
type CacheEntry struct {
Body []byte
StoredAt time.Time
}
// CacheStats is the cache state reported by /healthz.
type CacheStats struct {
Backend string `json:"backend"`
Entries int `json:"entries"`
StaleEntries int `json:"stale_entries"`
Bytes int64 `json:"bytes"`
}
// Cache stores merged responses keyed by cacheKey. Get reports freshness rather
// than hiding expired entries so a caller can fall back to a stale body when the
// upstream fetch fails. The context and error exist for out-of-process backends
// (the reports cache lands on S3); an in-process backend ignores both.
//
// A Body handed back by Get aliases the cache's copy and must not be mutated.
type Cache interface {
Get(ctx context.Context, key string) (CacheEntry, CacheStatus, error)
Put(ctx context.Context, key string, body []byte) error
Stats() CacheStats
}
// cacheKey is the request path when there are no params, else "<path>?<params>"
// where params is url.Values.Encode() over a copy whose repeated values have
// been sorted. Encode() already sorts keys ascending, so both the order params
// arrive in and the order of a repeated param's values are irrelevant to the
// key: one canonical string per distinct request.
func cacheKey(path string, params url.Values) string {
if len(params) == 0 {
return path
}
norm := make(url.Values, len(params))
for k, vs := range params {
sorted := append([]string(nil), vs...)
sort.Strings(sorted)
norm[k] = sorted
}
encoded := norm.Encode()
if encoded == "" {
return path
}
return path + "?" + encoded
}
// noopCache is the default for every path with no cache configured, so wiring a
// handler through the cache leaves its behaviour unchanged.
type noopCache struct{}
func (noopCache) Get(context.Context, string) (CacheEntry, CacheStatus, error) {
return CacheEntry{}, CacheMiss, nil
}
func (noopCache) Put(context.Context, string, []byte) error { return nil }
func (noopCache) Stats() CacheStats { return CacheStats{Backend: "none"} }
type memoryEntry struct {
key string
body []byte
storedAt time.Time
}
// memoryCache is a byte-bounded LRU. Expired entries are kept, not dropped, so
// they remain available as a stale fallback; only the byte budget evicts.
type memoryCache struct {
ttl time.Duration
maxBytes int64
now func() time.Time
mu sync.Mutex
ll *list.List // front = most recently used
items map[string]*list.Element
bytes int64
}
func newMemoryCache(ttl time.Duration, maxBytes int64) *memoryCache {
return &memoryCache{
ttl: ttl,
maxBytes: maxBytes,
now: time.Now,
ll: list.New(),
items: make(map[string]*list.Element),
}
}
func (c *memoryCache) Get(_ context.Context, key string) (CacheEntry, CacheStatus, error) {
c.mu.Lock()
defer c.mu.Unlock()
el, ok := c.items[key]
if !ok {
return CacheEntry{}, CacheMiss, nil
}
c.ll.MoveToFront(el)
e := el.Value.(*memoryEntry)
status := CacheFresh
if c.now().Sub(e.storedAt) >= c.ttl {
status = CacheStale
}
return CacheEntry{Body: e.body, StoredAt: e.storedAt}, status, nil
}
func (c *memoryCache) Put(_ context.Context, key string, body []byte) error {
// A response larger than the whole budget would evict everything else.
if int64(len(body)) > c.maxBytes {
return nil
}
stored := append([]byte(nil), body...)
c.mu.Lock()
defer c.mu.Unlock()
if el, ok := c.items[key]; ok {
e := el.Value.(*memoryEntry)
c.bytes += int64(len(stored)) - int64(len(e.body))
e.body, e.storedAt = stored, c.now()
c.ll.MoveToFront(el)
} else {
c.items[key] = c.ll.PushFront(&memoryEntry{key: key, body: stored, storedAt: c.now()})
c.bytes += int64(len(stored))
}
for c.bytes > c.maxBytes {
back := c.ll.Back()
if back == nil {
break
}
e := c.ll.Remove(back).(*memoryEntry)
delete(c.items, e.key)
c.bytes -= int64(len(e.body))
}
return nil
}
func (c *memoryCache) Stats() CacheStats {
c.mu.Lock()
defer c.mu.Unlock()
st := CacheStats{Backend: "memory", Entries: len(c.items), Bytes: c.bytes}
now := c.now()
for el := c.ll.Front(); el != nil; el = el.Next() {
if now.Sub(el.Value.(*memoryEntry).storedAt) >= c.ttl {
st.StaleEntries++
}
}
return st
}
// flightGroup collapses concurrent identical builds so N simultaneous requests
// for one key cause one upstream fan-out.
type flightGroup struct {
mu sync.Mutex
calls map[string]*flightCall
}
type flightCall struct {
wg sync.WaitGroup
resp cachedResponse
err error
}
// Do returns fn's result and whether this caller shared another's in-flight run.
func (g *flightGroup) Do(key string, fn func() (cachedResponse, error)) (cachedResponse, error, bool) {
g.mu.Lock()
if g.calls == nil {
g.calls = make(map[string]*flightCall)
}
if c, ok := g.calls[key]; ok {
g.mu.Unlock()
c.wg.Wait()
return c.resp, c.err, true
}
c := &flightCall{}
c.wg.Add(1)
g.calls[key] = c
g.mu.Unlock()
defer func() {
c.wg.Done()
g.mu.Lock()
delete(g.calls, key)
g.mu.Unlock()
}()
c.resp, c.err = fn()
return c.resp, c.err, false
}
// staleTracker records stale fallbacks for /healthz. serving flips back to false
// as soon as a response is served from a live fan-out or a fresh entry.
type staleTracker struct {
mu sync.Mutex
serving bool
served uint64
last time.Time
}
func (t *staleTracker) markStale(now time.Time) {
t.mu.Lock()
defer t.mu.Unlock()
t.serving = true
t.served++
t.last = now
}
func (t *staleTracker) markFresh() {
t.mu.Lock()
defer t.mu.Unlock()
t.serving = false
}
func (t *staleTracker) snapshot() (serving bool, served uint64, last time.Time) {
t.mu.Lock()
defer t.mu.Unlock()
return t.serving, t.served, t.last
}