Files
knox/internal/cmd/gossip.go
T
david 876d2aa45f feat: Prometheus metrics endpoint for knox nodes
Refs #2

- /metrics served on a dedicated port (KNOX_METRICS_ADDR, default
  localhost:8932) via prometheus/client_golang, with Go runtime +
  process collectors
- DB-derived gauges refreshed per scrape: observations by source,
  last-24h observations, entries, projects, sessions, pending
  reflections, threads by status, peers, observations by origin node,
  knowledge vector (max hcl per node)
- live gossip counters (pulls/pushes, observations pulled/pushed,
  errors) incremented during the anti-entropy sweep; Run accepts an
  optional metrics handle (nil for one-shot CLI)
- knox_node_info{node_id,name} for scrape identification
- internal/metrics package + db MetricsSnapshot; tests for snapshot,
  scrape output, and counter increments
2026-08-29 06:06:49 -07:00

157 lines
4.2 KiB
Go

package cmd
import (
"fmt"
"github.com/spf13/cobra"
"github.com/david/knox/internal/db"
"github.com/david/knox/internal/watch"
)
// NewGossipCmd exposes peer status/diff for the gossip protocol.
func NewGossipCmd(kdb *db.KnoxDB) *cobra.Command {
cmd := &cobra.Command{
Use: "gossip",
Short: "Inspect peer-to-peer observation sync",
}
cmd.AddCommand(
&cobra.Command{
Use: "status",
Short: "Show known peers and knowledge vectors",
RunE: func(c *cobra.Command, args []string) error {
peers, err := kdb.ListPeers()
if err != nil {
return err
}
vector, err := kdb.KnowledgeVector()
if err != nil {
return err
}
fmt.Printf("node_id: %s\n", kdb.NodeID())
fmt.Printf("peers (static: %d configured):\n", len(watch.PeerAddrs()))
for _, p := range peers {
fmt.Printf(" %-24s %-28s last=%s vector=%d\n", p.PeerID, p.Addr, p.LastHandshake, p.Cursor)
}
if len(peers) == 0 {
fmt.Println(" (none — set KNOX_PEERS to sync with other nodes)")
}
fmt.Println("knowledge vector (node_id -> max hcl):")
for nid, hcl := range vector {
if nid == kdb.NodeID() {
continue
}
fmt.Printf(" %-24s -> %d\n", nid, hcl)
}
return nil
},
},
&cobra.Command{
Use: "diff <peer-url>",
Short: "Show observation/thread divergence with a peer",
Args: cobra.ExactArgs(1),
RunE: func(c *cobra.Command, args []string) error {
return gossipDiff(kdb, args[0])
},
},
&cobra.Command{
Use: "sync",
Short: "Run one anti-entropy sweep against configured peers",
RunE: func(c *cobra.Command, args []string) error {
peers := watch.PeerAddrs()
if len(peers) == 0 {
return fmt.Errorf("no peers configured (set KNOX_PEERS)")
}
watch.Run(kdb, nil, peers)
created, linked, err := watch.Reconcile(kdb)
if err != nil {
return err
}
fmt.Printf("sync done: %d threads created, %d observations linked\n", created, linked)
return nil
},
},
)
return cmd
}
// gossipDiff compares this node's observation log + auto-threads with a peer's
// via /v1/diff. Never writes; it is the preview for what a sync would adopt.
func gossipDiff(kdb *db.KnoxDB, peerAddr string) error {
c := &watch.Client{Addr: peerAddr}
remote, err := c.Diff()
if err != nil {
return err
}
local, err := kdb.DistinctFingerprints()
if err != nil {
return err
}
remoteFP := make(map[string]bool, len(remote.Fingerprints))
for _, f := range remote.Fingerprints {
remoteFP[f] = true
}
var peerOnly, localOnly []string
for f := range remoteFP {
if !local[f] {
peerOnly = append(peerOnly, f)
}
}
for f := range local {
if !remoteFP[f] {
localOnly = append(localOnly, f)
}
}
fmt.Printf("peer: %s (%s)\n", remote.Name, remote.NodeID)
fmt.Printf("this node: %s\n", kdb.NodeID())
fmt.Printf("fingerprints: peer=%d this=%d\n", len(remoteFP), len(local))
fmt.Printf(" peer-only (would pull): %d\n", len(peerOnly))
for _, f := range peerOnly[:min(10, len(peerOnly))] {
fmt.Printf(" %s\n", f)
}
fmt.Printf(" local-only (would lose): %d\n", len(localOnly))
for _, f := range localOnly[:min(10, len(localOnly))] {
fmt.Printf(" %s\n", f)
}
// Tombstone divergence on auto-threaded threads.
localThreads, err := kdb.ThreadStatusByCluster()
if err != nil {
return err
}
remoteThreads := remote.ThreadStatus
var resolvedPeer, revokedLocal []string
for k, st := range remoteThreads {
if st == "resolved" {
if ls, ok := localThreads[k]; !ok || ls != "resolved" {
resolvedPeer = append(resolvedPeer, k)
}
}
}
for k, st := range localThreads {
if st == "resolved" {
if rs, ok := remoteThreads[k]; !ok || rs != "resolved" {
revokedLocal = append(revokedLocal, k)
}
}
}
if len(resolvedPeer) > 0 {
fmt.Printf("threads resolved on peer but not here (tombstone to adopt): %d\n", len(resolvedPeer))
}
if len(revokedLocal) > 0 {
fmt.Printf("threads resolved here but not on peer (would resurrect on sync): %d\n", len(revokedLocal))
}
if len(peerOnly) == 0 && len(localOnly) == 0 && len(resolvedPeer) == 0 && len(revokedLocal) == 0 {
fmt.Println("in sync.")
}
return nil
}
func min(a, b int) int {
if a < b {
return a
}
return b
}