Files
pdbmux/server.go
T
unkin-agent a4a29866e1
ci/woodpecker/pr/build Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/pre-commit Pipeline was successful
Override the source fact on every query shape
- drop upstream facts of the configured name whenever the feature is enabled,
  independent of the per-query injection gate, and log the drop once per request
- walk the whole AST for a nested extract and skip injection when one is found
  outside an in subquery
- skip the environment scan on /facts when nothing is injected
- document the override rule and that PQL-syntax queries never get the fact
2026-09-05 21:31:50 +10:00

450 lines
12 KiB
Go

package main
import (
"context"
"encoding/json"
"fmt"
"io"
"log"
"net/http"
"net/url"
"strconv"
"strings"
"sync"
"time"
)
const (
factsPath = "/pdb/query/v4/facts"
nodesPath = "/pdb/query/v4/nodes"
resourcesPath = "/pdb/query/v4/resources"
reportsPath = "/pdb/query/v4/reports"
eventsPath = "/pdb/query/v4/events"
eventCountsPath = "/pdb/query/v4/event-counts"
aggregateEventCountsPath = "/pdb/query/v4/aggregate-event-counts"
queryV4 = "/pdb/query/v4/"
// PuppetDB only sends this when the request carries include_total=true.
recordsHeader = "X-Records"
)
type backendResult struct {
name string
records []record
total int // upstream X-Records count, or -1 when the backend sent none
err error
}
type Server struct {
cfg Config
client *http.Client
log *log.Logger
// freshness cache (freshness merge only).
mu sync.Mutex
freshData freshness
freshAt time.Time
}
func NewServer(cfg Config, logger *log.Logger) *Server {
return &Server{
cfg: cfg,
client: &http.Client{Timeout: cfg.Timeout},
log: logger,
}
}
func (s *Server) Handler() http.Handler {
mux := http.NewServeMux()
mux.HandleFunc("/healthz", s.handleHealth)
mux.HandleFunc("/pdb/query/v4/", s.handleQuery)
mux.HandleFunc(metaVersionPath, s.handleMetaVersion)
mux.HandleFunc(metaServerTimePath, s.handleMetaServerTime)
mux.HandleFunc(metricsPrefix, s.handleMetrics)
return mux
}
func (s *Server) handleQuery(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodGet {
http.Error(w, "only GET is supported", http.StatusMethodNotAllowed)
return
}
switch r.URL.Path {
case nodesPath:
s.serveNodes(w, r)
case resourcesPath:
s.serveResources(w, r)
case factsPath:
s.serveMerged(w, r, factsPath, s.mergeFactsResponse(r))
case reportsPath:
s.serveReports(w, r)
case eventsPath:
s.serveUnion(w, r, eventsPath, rawKey)
case eventCountsPath, aggregateEventCountsPath:
s.serveSummed(w, r, r.URL.Path, inferredColumns)
default:
if isReportSubResource(r.URL.Path) {
s.serveFirstHolder(w, r)
return
}
s.proxyUnmerged(w, r)
}
}
// Matches /pdb/query/v4/reports/<hash>/{events,logs,metrics}, whose data lives in exactly one backend.
func isReportSubResource(path string) bool {
rest, ok := strings.CutPrefix(path, reportsPath+"/")
if !ok {
return false
}
hash, sub, ok := strings.Cut(rest, "/")
if !ok || hash == "" {
return false
}
switch sub {
case "events", "logs", "metrics":
return true
}
return false
}
func (s *Server) serveMerged(w http.ResponseWriter, r *http.Request, path string, merge func([]backendResult) []json.RawMessage) {
alive, ok := s.aliveResults(w, r, path, queryParams(r.URL.Query().Get("query")))
if !ok {
return
}
writeJSON(w, merge(alive))
}
// Reports and events are immutable history, so both backends' records belong in the merged view.
func (s *Server) serveUnion(w http.ResponseWriter, r *http.Request, path string, key func(record) (string, bool)) {
in := r.URL.Query()
page, err := parsePaging(in)
if err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
alive, ok := s.aliveResults(w, r, path, page.upstreamParams(in))
if !ok {
return
}
merged := mergeUnion(alive, key)
sortRecords(merged, page.order)
if page.wantTotal {
if total := sumTotals(alive); total >= 0 {
w.Header().Set(recordsHeader, strconv.Itoa(total))
}
}
writeJSON(w, page.apply(merged))
}
// A count row carries no certname, so the certname-keyed merge would collapse every backend's count into one backend's; aggregates take the summing path instead.
func (s *Server) serveNodes(w http.ResponseWriter, r *http.Request) {
if spec := parseAggregate(r.URL.Query().Get("query")); spec != nil {
s.serveSummed(w, r, nodesPath, spec.columns)
return
}
s.serveMerged(w, r, nodesPath, s.mergeNodesResponse(r))
}
// Only aggregates merge: a resource record has no cross-backend identity to dedupe on, so a plain query stays on the pass-through path.
func (s *Server) serveResources(w http.ResponseWriter, r *http.Request) {
if spec := parseAggregate(r.URL.Query().Get("query")); spec != nil {
s.serveSummed(w, r, resourcesPath, spec.columns)
return
}
s.proxyUnmerged(w, r)
}
// An `extract` query with a `function` column returns synthetic aggregate rows that carry no identity, so they are summed rather than unioned.
func (s *Server) serveReports(w http.ResponseWriter, r *http.Request) {
if spec := parseAggregate(r.URL.Query().Get("query")); spec != nil {
s.serveSummed(w, r, reportsPath, spec.columns)
return
}
s.serveUnion(w, r, reportsPath, reportKey)
}
// Merged rows are fewer than the backends' combined records, so include_total reports the merged count rather than a sum of X-Records.
func (s *Server) serveSummed(w http.ResponseWriter, r *http.Request, path string, columns func(map[string]json.RawMessage) ([]string, []string)) {
in := r.URL.Query()
page, err := parsePaging(in)
if err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
alive, ok := s.aliveResults(w, r, path, page.upstreamParams(in))
if !ok {
return
}
merged := sumRows(alive, columns)
sortRecords(merged, page.order)
if page.wantTotal {
w.Header().Set(recordsHeader, strconv.Itoa(len(merged)))
}
writeJSON(w, page.apply(merged))
}
// A backend without the report answers 404, indistinguishable from a failure, so every backend is consulted before serving empty.
func (s *Server) serveFirstHolder(w http.ResponseWriter, r *http.Request) {
results := s.fanOut(r.Context(), r.URL.Path, r.URL.Query())
var alive []backendResult
for _, res := range results {
if res.err != nil {
s.log.Printf("info: backend %q has no %s: %v", res.name, r.URL.Path, res.err)
continue
}
alive = append(alive, res)
}
if len(alive) == 0 {
http.Error(w, "no backend holds this report", http.StatusNotFound)
return
}
for _, res := range alive {
if len(res.records) > 0 {
writeJSON(w, rawRecords(res.records))
return
}
}
writeJSON(w, nil)
}
// Writes a 502 and returns ok=false only when every backend failed.
func (s *Server) aliveResults(w http.ResponseWriter, r *http.Request, path string, params url.Values) ([]backendResult, bool) {
results := s.fanOut(r.Context(), path, params)
var alive []backendResult
for _, res := range results {
if res.err != nil {
s.log.Printf("warning: backend %q failed for %s: %v", res.name, path, res.err)
continue
}
alive = append(alive, res)
}
if len(alive) == 0 {
http.Error(w, "all backends failed", http.StatusBadGateway)
return nil, false
}
return alive, true
}
func queryParams(query string) url.Values {
if query == "" {
return nil
}
return url.Values{"query": []string{query}}
}
func rawRecords(recs []record) []json.RawMessage {
out := make([]json.RawMessage, 0, len(recs))
for _, rec := range recs {
out = append(out, rec.Raw)
}
return out
}
func (s *Server) mergeNodesResponse(r *http.Request) func([]backendResult) []json.RawMessage {
inject := s.newSourceInjector(r.URL.Query().Get("query"), false)
return func(results []backendResult) []json.RawMessage {
return mergeNodes(results, inject)
}
}
func (s *Server) mergeFactsResponse(r *http.Request) func([]backendResult) []json.RawMessage {
inject := s.newSourceInjector(r.URL.Query().Get("query"), true)
return func(results []backendResult) []json.RawMessage {
var merged []json.RawMessage
if s.cfg.Merge == mergeStatic {
merged = mergeFacts(results, nil, inject)
} else {
fresh := s.freshnessMap(context.Background(), results)
merged = mergeFacts(results, func(cn string) string { return fresh[cn] }, inject)
}
inject.logSuppressed(s.log)
return merged
}
}
// Queries /nodes unfiltered rather than reusing the request's results, because a /facts query's certname set can differ.
func (s *Server) freshnessMap(ctx context.Context, _ []backendResult) freshness {
s.mu.Lock()
if s.freshData != nil && time.Since(s.freshAt) < s.cfg.FreshnessTTL {
f := s.freshData
s.mu.Unlock()
return f
}
s.mu.Unlock()
nodeResults := s.fanOut(ctx, nodesPath, nil)
var alive []backendResult
for _, res := range nodeResults {
if res.err != nil {
s.log.Printf("warning: freshness /nodes query to %q failed: %v", res.name, res.err)
continue
}
alive = append(alive, res)
}
f := buildFreshness(alive)
s.mu.Lock()
s.freshData = f
s.freshAt = time.Now()
s.mu.Unlock()
return f
}
// Returns one result per backend, in config order.
func (s *Server) fanOut(ctx context.Context, path string, params url.Values) []backendResult {
results := make([]backendResult, len(s.cfg.Backends))
var wg sync.WaitGroup
for i, b := range s.cfg.Backends {
wg.Add(1)
go func(i int, b Backend) {
defer wg.Done()
recs, total, err := s.queryBackend(ctx, b, path, params)
results[i] = backendResult{name: b.Name, records: recs, total: total, err: err}
}(i, b)
}
wg.Wait()
return results
}
// The returned count is the upstream X-Records value, or -1 when the backend sent none.
func (s *Server) queryBackend(ctx context.Context, b Backend, path string, params url.Values) ([]record, int, error) {
target := strings.TrimRight(b.URL, "/") + path
req, err := http.NewRequestWithContext(ctx, http.MethodGet, target, nil)
if err != nil {
return nil, -1, err
}
if len(params) > 0 {
req.URL.RawQuery = params.Encode()
}
resp, err := s.client.Do(req)
if err != nil {
return nil, -1, err
}
defer func() { _ = resp.Body.Close() }()
body, err := io.ReadAll(resp.Body)
if err != nil {
return nil, -1, err
}
if resp.StatusCode != http.StatusOK {
return nil, -1, fmt.Errorf("HTTP %d: %s", resp.StatusCode, strings.TrimSpace(string(body)))
}
total := -1
if n, err := strconv.Atoi(resp.Header.Get(recordsHeader)); err == nil && n >= 0 {
total = n
}
recs, err := decodeRecords(body)
return recs, total, err
}
// The record shape is unknown, so a union would be guesswork: the first 2xx wins and the first error response is replayed when none succeeds.
func (s *Server) proxyUnmerged(w http.ResponseWriter, r *http.Request) {
var fallback *bufferedResponse
for _, b := range s.cfg.Backends {
resp, err := s.passThrough(r, b)
if err != nil {
s.log.Printf("warning: backend %q pass-through failed for %s: %v", b.Name, r.URL.Path, err)
continue
}
if resp.StatusCode >= 200 && resp.StatusCode < 300 {
setContentType(w, resp.Header.Get("Content-Type"))
w.WriteHeader(resp.StatusCode)
_, _ = io.Copy(w, resp.Body)
_ = resp.Body.Close()
return
}
body, _ := io.ReadAll(resp.Body)
_ = resp.Body.Close()
if fallback == nil {
fallback = &bufferedResponse{
status: resp.StatusCode,
contentType: resp.Header.Get("Content-Type"),
body: body,
}
}
}
if fallback == nil {
http.Error(w, "all backends failed", http.StatusBadGateway)
return
}
setContentType(w, fallback.contentType)
w.WriteHeader(fallback.status)
_, _ = w.Write(fallback.body)
}
type bufferedResponse struct {
status int
contentType string
body []byte
}
func (s *Server) passThrough(r *http.Request, b Backend) (*http.Response, error) {
target := strings.TrimRight(b.URL, "/") + r.URL.Path
if r.URL.RawQuery != "" {
target += "?" + r.URL.RawQuery
}
req, err := http.NewRequestWithContext(r.Context(), http.MethodGet, target, nil)
if err != nil {
return nil, err
}
return s.client.Do(req)
}
func setContentType(w http.ResponseWriter, contentType string) {
if contentType != "" {
w.Header().Set("Content-Type", contentType)
}
}
type healthReport struct {
Status string `json:"status"`
Backends map[string]string `json:"backends"` // name -> "ok" | error text
}
func (s *Server) handleHealth(w http.ResponseWriter, r *http.Request) {
probe := `["=","certname","pdbmux-healthz-probe"]`
results := s.fanOut(r.Context(), nodesPath, queryParams(probe))
report := healthReport{Backends: map[string]string{}}
healthy := 0
for _, res := range results {
if res.err != nil {
report.Backends[res.name] = res.err.Error()
continue
}
report.Backends[res.name] = "ok"
healthy++
}
switch {
case healthy == len(results):
report.Status = "ok"
case healthy > 0:
report.Status = "degraded"
default:
report.Status = "down"
}
w.Header().Set("Content-Type", "application/json")
if healthy == 0 {
w.WriteHeader(http.StatusServiceUnavailable)
}
enc := json.NewEncoder(w)
enc.SetIndent("", " ")
_ = enc.Encode(report)
}
func writeJSON(w http.ResponseWriter, recs []json.RawMessage) {
w.Header().Set("Content-Type", "application/json")
if recs == nil {
recs = []json.RawMessage{}
}
_ = json.NewEncoder(w).Encode(recs)
}