Nginx module: use first not private IP address as remote_ip

A common customization to the nginx logs is to add the contents of the X-Forwarded-For header in front of the remote IPs. This typically results in a list of remote IPs. This adds a new field `remote_ip_list` which is an array, and uses a Painless script to automatically select the first non-private IP for the `remote_ip` field, which is the field on which GeoIP is applied. Fixes #4322.
elastic · May 31, 2017 · 9011ed7 · 9011ed7
1 parent 812f374
commit 9011ed7
Show file tree

Hide file tree

Showing 8 changed files with 428 additions and 113 deletions.
diff --git a/filebeat/docs/fields.asciidoc b/filebeat/docs/fields.asciidoc
@@ -233,6 +233,22 @@ type: geo_point
 The longitude and latitude.
 
 
+[float]
+=== apache2.access.geoip.region_name
+
+type: keyword
+
+The region name.
+
+
+[float]
+=== apache2.access.geoip.city_name
+
+type: keyword
+
+The city name.
+
+
 [float]
 == error Fields
 
@@ -953,12 +969,20 @@ Contains fields for the Nginx access logs.
 
 
 
+[float]
+=== nginx.access.remote_ip_list
+
+type: array
+
+An array of remote IP addresses. It is a list because it is common to include, besides the client IP address, IP addresses from headers like `X-Forwarded-For`. See also the `remote_ip` field.
+
+
 [float]
 === nginx.access.remote_ip
 
 type: keyword
 
-Client IP address.
+Client IP address. The first public IP address from the `remote_ip_list` array. If no public IP addresses are present, this field contains the first private IP address from the `remote_ip_list` array.
 
 
 [float]
@@ -1141,6 +1165,22 @@ type: geo_point
 The longitude and latitude.
 
 
+[float]
+=== nginx.access.geoip.region_name
+
+type: keyword
+
+The region name.
+
+
+[float]
+=== nginx.access.geoip.city_name
+
+type: keyword
+
+The city name.
+
+
 [float]
 == error Fields
 

diff --git a/filebeat/module/apache2/access/_meta/fields.yml b/filebeat/module/apache2/access/_meta/fields.yml
@@ -104,4 +104,12 @@
           type: geo_point
           description: >
             The longitude and latitude.
+        - name: region_name
+          type: keyword
+          description: >
+            The region name.
+        - name: city_name
+          type: keyword
+          description: >
+            The city name.
 
diff --git a/filebeat/module/nginx/access/_meta/fields.yml b/filebeat/module/nginx/access/_meta/fields.yml
@@ -3,10 +3,17 @@
   description: >
     Contains fields for the Nginx access logs.
   fields:
+    - name: remote_ip_list
+      type: array
+      description: >
+        An array of remote IP addresses. It is a list because it is common to include, besides the client
+        IP address, IP addresses from headers like `X-Forwarded-For`. See also the `remote_ip` field.
     - name: remote_ip
       type: keyword
       description: >
-        Client IP address.
+        Client IP address. The first public IP address from the `remote_ip_list` array. If no public IP
+        addresses are present, this field contains the first private IP address from the `remote_ip_list`
+        array.
     - name: user_name
       type: keyword
       description: >
@@ -104,4 +111,12 @@
           type: geo_point
           description: >
             The longitude and latitude.
+        - name: region_name
+          type: keyword
+          description: >
+            The region name.
+        - name: city_name
+          type: keyword
+          description: >
+            The city name.
 
diff --git a/filebeat/module/nginx/access/ingest/default.json b/filebeat/module/nginx/access/ingest/default.json
@@ -4,11 +4,24 @@
     "grok": {
       "field": "message",
       "patterns":[
-        "%{IPORHOST:nginx.access.remote_ip}(,\\s%{IPORHOST})* - %{DATA:nginx.access.user_name} \\[%{HTTPDATE:nginx.access.time}\\] \"%{WORD:nginx.access.method} %{DATA:nginx.access.url} HTTP/%{NUMBER:nginx.access.http_version}\" %{NUMBER:nginx.access.response_code} %{NUMBER:nginx.access.body_sent.bytes} \"%{DATA:nginx.access.referrer}\" \"%{DATA:nginx.access.agent}\""
+        "\"?%{IP_LIST:nginx.access.remote_ip_list} - %{DATA:nginx.access.user_name} \\[%{HTTPDATE:nginx.access.time}\\] \"%{WORD:nginx.access.method} %{DATA:nginx.access.url} HTTP/%{NUMBER:nginx.access.http_version}\" %{NUMBER:nginx.access.response_code} %{NUMBER:nginx.access.body_sent.bytes} \"%{DATA:nginx.access.referrer}\" \"%{DATA:nginx.access.agent}\""
         ],
+      "pattern_definitions": {
+        "IP_LIST": "%{IP}(\"?,?\\s*%{IP})*"
+      },
       "ignore_missing": true
     }
-  },{
+  }, {
+    "split": {
+      "field": "nginx.access.remote_ip_list",
+      "separator": "\"?,?\\s+"
+    }
+  }, {
+    "script": {
+      "lang": "painless",
+      "inline": "boolean isPrivate(def ip) { try { StringTokenizer tok = new StringTokenizer(ip, '.'); int firstByte = Integer.parseInt(tok.nextToken());       int secondByte = Integer.parseInt(tok.nextToken());       if (firstByte == 10) {         return true;       }       if (firstByte == 192 && secondByte == 168) {         return true;       }       if (firstByte == 172 && secondByte >= 16 && secondByte <= 31) {         return true;       }       if (firstByte == 127) {         return true;       }       return false;     } catch (Exception e) {       return false;     }   }   def found = false;   for (def item : ctx.nginx.access.remote_ip_list) {     if (!isPrivate(item)) {       ctx.nginx.access.remote_ip = item;       found = true;       break;     }   }   if (!found) {     ctx.nginx.access.remote_ip = ctx.nginx.access.remote_ip_list[0];   }"
+      }
+  }, {
     "remove":{
       "field": "message"
     }

diff --git a/filebeat/module/nginx/access/test/test.log b/filebeat/module/nginx/access/test/test.log
@@ -1,2 +1,6 @@
 10.0.0.2, 10.0.0.1, 127.0.0.1 - - [07/Dec/2016:11:05:07 +0100] "GET /ocelot HTTP/1.1" 200 571 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:49.0) Gecko/20100101 Firefox/49.0"
 172.17.0.1 - - [29/May/2017:19:02:48 +0000] "GET /stringpatch HTTP/1.1" 404 612 "-" "Mozilla/5.0 (Windows NT 6.1; rv:15.0) Gecko/20120716 Firefox/15.0a2" "-"
+10.0.0.2, 10.0.0.1, 85.181.35.98 - - [07/Dec/2016:11:05:07 +0100] "GET /ocelot HTTP/1.1" 200 571 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:49.0) Gecko/20100101 Firefox/49.0"
+85.181.35.98 - - [07/Dec/2016:11:05:07 +0100] "GET /ocelot HTTP/1.1" 200 571 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:49.0) Gecko/20100101 Firefox/49.0"
+"10.5.102.222, 199.96.1.1, 204.246.1.1" 10.2.1.185 - - [22/Jan/2016:13:18:29 +0000] "GET /assets/xxxx?q=100 HTTP/1.1" 200 25507 "-" "Amazon CloudFront"
+2a03:0000:10ff:f00f:0000:0000:0:8000, 10.225.192.17 10.2.2.121 - - [30/Dec/2016:06:47:09 +0000] "GET /test.html HTTP/1.1" 404 8571 "-" "Mozilla/5.0 (compatible; Facebot 1.0; https://developers.facebook.com/docs/sharing/webmasters/crawler)"