From 30d13aa86986d10b9fbc01a6bac3d7b41f768f6d Mon Sep 17 00:00:00 2001
From: mlsmaycon <mlsmaycon@gmail.com>
Date: Sun, 26 Jul 2026 17:42:21 +0000
Subject: [PATCH] proxy: allow overriding tunnel-cache TTL via env var

The tunnel-peer validation cache (peer -> user/groups from ValidateTunnelPeer)
memoizes positive results for a fixed 5 minutes, so an authorization change
(e.g. a revoked peer) can take up to 5 minutes to take effect on the proxy.

Add NB_PROXY_TUNNEL_CACHE_TTL to override the default at construction. The
value is a Go duration string (e.g. "30s", "2m"); unset, unparseable, or
non-positive values keep the 300s default and log a warning. Operators who
need faster propagation can lower it (trading more ValidateTunnelPeer RPCs for
freshness).
---
 proxy/internal/auth/tunnel_cache.go      | 39 +++++++++++++++++++++---
 proxy/internal/auth/tunnel_cache_test.go | 29 ++++++++++++++++++
 2 files changed, 63 insertions(+), 5 deletions(-)

diff --git a/proxy/internal/auth/tunnel_cache.go b/proxy/internal/auth/tunnel_cache.go
index 10b671d82..185c53c62 100644
--- a/proxy/internal/auth/tunnel_cache.go
+++ b/proxy/internal/auth/tunnel_cache.go
@@ -3,20 +3,30 @@ package auth
 import (
 	"context"
 	"net/netip"
+	"os"
+	"strings"
 	"sync"
 	"time"
 
+	log "github.com/sirupsen/logrus"
 	"golang.org/x/sync/singleflight"
 
 	"github.com/netbirdio/netbird/proxy/internal/types"
 	"github.com/netbirdio/netbird/shared/management/proto"
 )
 
-// tunnelCacheTTL caps how long a positive ValidateTunnelPeer result is
-// reused before re-fetching from management. 5 minutes balances freshness
-// against management load on busy mesh networks.
+// tunnelCacheTTL is the default cap on how long a positive ValidateTunnelPeer
+// result is reused before re-fetching from management. 5 minutes balances
+// freshness against management load on busy mesh networks. Override it with
+// envTunnelCacheTTL when an account needs authorization changes to take effect
+// sooner (at the cost of more ValidateTunnelPeer RPCs).
 const tunnelCacheTTL = 300 * time.Second
 
+// envTunnelCacheTTL overrides tunnelCacheTTL. The value is a Go duration string
+// (e.g. "30s", "2m"); an unset, unparseable, or non-positive value keeps the
+// default.
+const envTunnelCacheTTL = "NB_PROXY_TUNNEL_CACHE_TTL"
+
 // tunnelCachePerAccount caps the number of cached identities per account.
 // Bounded eviction avoids memory growth in pathological cases (huge peer
 // roster, brief request bursts) while staying generous for normal use.
@@ -60,16 +70,35 @@ type accountBucket struct {
 	order []tunnelCacheKey
 }
 
-// newTunnelValidationCache constructs a cache with default TTL and bounds.
+// newTunnelValidationCache constructs a cache with the configured TTL
+// (envTunnelCacheTTL override or default) and default bounds.
 func newTunnelValidationCache() *tunnelValidationCache {
 	return &tunnelValidationCache{
 		entries: make(map[types.AccountID]*accountBucket),
-		ttl:     tunnelCacheTTL,
+		ttl:     tunnelCacheTTLFromEnv(),
 		maxSize: tunnelCachePerAccount,
 		now:     time.Now,
 	}
 }
 
+// tunnelCacheTTLFromEnv returns the tunnel-cache TTL, honoring the
+// envTunnelCacheTTL override. The override must be a positive Go duration
+// string (e.g. "30s", "2m"); anything unset, unparseable, or non-positive
+// falls back to tunnelCacheTTL.
+func tunnelCacheTTLFromEnv() time.Duration {
+	raw := strings.TrimSpace(os.Getenv(envTunnelCacheTTL))
+	if raw == "" {
+		return tunnelCacheTTL
+	}
+	d, err := time.ParseDuration(raw)
+	if err != nil || d <= 0 {
+		log.Warnf("ignoring invalid %s=%q (want a positive Go duration like 30s or 2m); using default %s",
+			envTunnelCacheTTL, raw, tunnelCacheTTL)
+		return tunnelCacheTTL
+	}
+	return d
+}
+
 // get returns a cached response for the key, or nil when missing or
 // expired. Expired entries are evicted lazily on read.
 func (c *tunnelValidationCache) get(key tunnelCacheKey) *proto.ValidateTunnelPeerResponse {
diff --git a/proxy/internal/auth/tunnel_cache_test.go b/proxy/internal/auth/tunnel_cache_test.go
index 1a63dc107..d663b91e7 100644
--- a/proxy/internal/auth/tunnel_cache_test.go
+++ b/proxy/internal/auth/tunnel_cache_test.go
@@ -169,3 +169,32 @@ func TestTunnelCache_BoundedSizeEvictsOldest(t *testing.T) {
 	assert.NotNil(t, cache.get(keys[1]), "second-newest must remain cached")
 	assert.NotNil(t, cache.get(keys[2]), "newest must remain cached")
 }
+
+func TestTunnelCacheTTLFromEnv(t *testing.T) {
+	t.Run("unset uses default", func(t *testing.T) {
+		t.Setenv(envTunnelCacheTTL, "")
+		assert.Equal(t, tunnelCacheTTL, tunnelCacheTTLFromEnv())
+	})
+	t.Run("valid duration overrides", func(t *testing.T) {
+		t.Setenv(envTunnelCacheTTL, "45s")
+		assert.Equal(t, 45*time.Second, tunnelCacheTTLFromEnv())
+	})
+	t.Run("whitespace trimmed", func(t *testing.T) {
+		t.Setenv(envTunnelCacheTTL, "  2m ")
+		assert.Equal(t, 2*time.Minute, tunnelCacheTTLFromEnv())
+	})
+	t.Run("unparseable uses default", func(t *testing.T) {
+		t.Setenv(envTunnelCacheTTL, "nonsense")
+		assert.Equal(t, tunnelCacheTTL, tunnelCacheTTLFromEnv())
+	})
+	t.Run("non-positive uses default", func(t *testing.T) {
+		t.Setenv(envTunnelCacheTTL, "0s")
+		assert.Equal(t, tunnelCacheTTL, tunnelCacheTTLFromEnv())
+		t.Setenv(envTunnelCacheTTL, "-30s")
+		assert.Equal(t, tunnelCacheTTL, tunnelCacheTTLFromEnv())
+	})
+	t.Run("constructor honors override", func(t *testing.T) {
+		t.Setenv(envTunnelCacheTTL, "90s")
+		assert.Equal(t, 90*time.Second, newTunnelValidationCache().ttl)
+	})
+}