From 6a29ee16716913396b7c9a7a9d48d8da7c398e36 Mon Sep 17 00:00:00 2001
From: mayor <graham@mcintire.me>
Date: Fri, 6 Feb 2026 12:30:52 -0600
Subject: [PATCH] fix: Split agent polling queries to isolate SNMP failures

Changed from one large WALK query with all OIDs to separate WALK queries
per table type. This prevents a failure in one unsupported table (like ARP
on a device that doesn't support it) from killing the entire polling
operation.

Before: Single WALK with neighbor + ARP + MAC + IP + HOST-RESOURCES OIDs
After: Separate WALKs for each table type

This makes polling more resilient - if a device doesn't support ARP tables
or HOST-RESOURCES-MIB, those WALKs will fail individually while neighbors,
MAC tables, and IP addresses can still succeed.

Fixes agent errors where a single SNMP receive error was killing the
entire poller thread and failing all subsequent operations with
'Poller thread died'.
---
 lib/towerops_web/channels/agent_channel.ex | 101 ++++++++++++---------
 1 file changed, 58 insertions(+), 43 deletions(-)

diff --git a/lib/towerops_web/channels/agent_channel.ex b/lib/towerops_web/channels/agent_channel.ex
index f60bb357..7c23b3cc 100644
--- a/lib/towerops_web/channels/agent_channel.ex
+++ b/lib/towerops_web/channels/agent_channel.ex
@@ -711,54 +711,69 @@ defmodule ToweropsWeb.AgentChannel do
         ]
       end)
 
-    # Neighbor discovery OIDs
-    neighbor_oids = [
-      # LLDP
-      "1.0.8802.1.1.2.1.4.1.1",
-      # Cisco CDP
-      "1.3.6.1.4.1.9.9.23"
-    ]
-
-    # ARP table OIDs
-    arp_oids = [
-      # IP-MIB ipNetToMediaTable (IPv4 ARP)
-      "1.3.6.1.2.1.4.22",
-      # IP-MIB ipNetToPhysicalTable (RFC 4293 - unified IPv4/IPv6)
-      "1.3.6.1.2.1.4.35"
-    ]
-
-    # MAC address table OIDs
-    mac_oids = [
-      # BRIDGE-MIB dot1dTpFdbTable
-      "1.3.6.1.2.1.17.4.3"
-    ]
-
-    # IP address OIDs (for polling changes)
-    ip_address_oids = [
-      # IP-MIB ipAddrTable (IPv4)
-      "1.3.6.1.2.1.4.20",
-      # IP-MIB ipAddressTable (IPv6)
-      "1.3.6.1.2.1.4.34"
-    ]
-
-    # HOST-RESOURCES-MIB for processors and storage
-    host_resources_oids = [
-      # hrProcessorTable
-      "1.3.6.1.2.1.25.3.3",
-      # hrStorageTable
-      "1.3.6.1.2.1.25.2.3"
-    ]
-
-    [
+    # Build separate WALK queries to isolate failures
+    # If one table doesn't exist, others can still succeed
+    base_queries = [
       %SnmpQuery{
         query_type: :GET,
         oids: sensor_oids ++ interface_oids
-      },
-      %SnmpQuery{
-        query_type: :WALK,
-        oids: neighbor_oids ++ arp_oids ++ mac_oids ++ ip_address_oids ++ host_resources_oids
       }
     ]
+
+    # Neighbor discovery (LLDP/CDP) - separate query
+    neighbor_query = %SnmpQuery{
+      query_type: :WALK,
+      oids: [
+        # LLDP
+        "1.0.8802.1.1.2.1.4.1.1",
+        # Cisco CDP
+        "1.3.6.1.4.1.9.9.23"
+      ]
+    }
+
+    # ARP table - separate query (may not be supported on all devices)
+    arp_query = %SnmpQuery{
+      query_type: :WALK,
+      oids: [
+        # IP-MIB ipNetToMediaTable (IPv4 ARP)
+        "1.3.6.1.2.1.4.22",
+        # IP-MIB ipNetToPhysicalTable (RFC 4293 - unified IPv4/IPv6)
+        "1.3.6.1.2.1.4.35"
+      ]
+    }
+
+    # MAC address table - separate query (only on switches)
+    mac_query = %SnmpQuery{
+      query_type: :WALK,
+      oids: [
+        # BRIDGE-MIB dot1dTpFdbTable
+        "1.3.6.1.2.1.17.4.3"
+      ]
+    }
+
+    # IP address tables - separate query
+    ip_query = %SnmpQuery{
+      query_type: :WALK,
+      oids: [
+        # IP-MIB ipAddrTable (IPv4)
+        "1.3.6.1.2.1.4.20",
+        # IP-MIB ipAddressTable (IPv6)
+        "1.3.6.1.2.1.4.34"
+      ]
+    }
+
+    # HOST-RESOURCES-MIB - separate query (may not be supported)
+    host_resources_query = %SnmpQuery{
+      query_type: :WALK,
+      oids: [
+        # hrProcessorTable
+        "1.3.6.1.2.1.25.3.3",
+        # hrStorageTable
+        "1.3.6.1.2.1.25.2.3"
+      ]
+    }
+
+    base_queries ++ [neighbor_query, arp_query, mac_query, ip_query, host_resources_query]
   end
 
   defp build_mikrotik_job(device) do