Finally, I got working ELK stack to get some logs from a remote server. However, I would like to customize the output of the logs. Is there a way to remove some fields which I am highlighting in yellow:
I tried to remove them from _source including remove_field in the logstash.conf:
input {
beats {
port => 5044
ssl => true
ssl_certificate => "/..."
ssl_key => "/..logstash.key"
}
}
filter {
grok {
match => {
"message" => "%{SYSLOGTIMESTAMP:syslog_timestamp} %{SYSLOGHOST:syslog_hostname} %{DATA:syslog_program}(?:\[%{POSINT:syslog_pid}\])?: %{GREEDYDATA:syslog_message}"
}
remove_field => [ "tags", "prospector.type", "host.architecture", "host.containerized", "host.id", "host.os.platform", "host.os.family" ]
}
}
output {
elasticsearch {
hosts => "localhost:9200"
index => "%{[#metadata][beat]}-%{+YYYY.MM.dd}"
}
}
Do you know how can I get rid of the yellow fields in _source for the logs coming from filebeat?
Update of logstash.conf based on Leandro comments:
input {
beats {
port => 5044
ssl => true
ssl_certificate => ".../logstash.crt"
ssl_key => ".../logstash.key"
}
}
filter {
grok {
match => {
"message" => "%{SYSLOGTIMESTAMP:syslog_timestamp} %{SYSLOGHOST:syslog_hostname} %{DATA:syslog_program}(?:\[%{POSINT:syslog_pid}\])?: %{GREEDYDATA:syslog_message}"
}
remove_field => [ "tags","[prospector][type]","[host][architecture]", "[host][containerized]", "[host][id]", "[host][os][platform]", "[host][os][family]", "[beat][hostname]", "[beat][name]", "[beat][version], "[offset]", "[input][type]", "[meta][cloud][provider]", "[meta][cloud][machine_type]", "[meta][cloud][instance_id]"]
}
}
output {
elasticsearch {
hosts => "localhost:9200"
index => "%{[#metadata][beat]}-%{+YYYY.MM.dd}"
}
}
In logs:
019-02-27T17:03:41.637-0800 DEBUG [input] file/states.go:68 New state added for /logs/api.log
2019-02-27T17:03:41.637-0800 DEBUG [registrar] registrar/registrar.go:315 Registrar state updates processed. Count: 1
2019-02-27T17:03:41.637-0800 DEBUG [registrar] registrar/registrar.go:400 Write registry file: /filebeat/registry
2019-02-27T17:03:41.637-0800 INFO log/harvester.go:255 Harvester started for file: /logs/api.log
2019-02-27T17:03:41.647-0800 DEBUG [publish] pipeline/processor.go:308 Publish event: {
"#timestamp": "2019-02-28T01:03:41.647Z",
"#metadata": {
"beat": "filebeat",
"type": "doc",
"version": "6.6.0"
},
"log": {
"file": {
"path": "/logs/api.log"
}
},
"input": {
"type": "log"
},
"host": {
"name": "tomcat",
"os": {
"family": "redhat",
"name": "CentOS Linux",
"codename": "Core",
"platform": "centos",
"version": "7 (Core)"
},
"id": "6aaed308aa5a419f880c5e45eea65414",
"containerized": true,
"architecture": "x86_64"
},
"meta": {
"cloud": {
"region": "CanadaCentral",
"provider": "az",
"instance_id": "6452bcf4-7f5d-4fc3-9f8e-5ea57f00724b",
"instance_name": "tomcat",
"machine_type": "Standard_D8s_v3"
}
},
"message": "2018-09-14 20:23:37 INFO ContextLoader:272 - Root WebApplicationContext: initialization started",
"source": "/logs/api.log",
"offset": 0,
"prospector": {
"type": "log"
},
"beat": {
"hostname": "tomcat",
"version": "6.6.0",
"name": "tomcat"
}
}
Thanks
Some of those fields are nested fields, the way to access them in a Logstash filter is using the [field][subfield] notation.
Your remove_field shoud be something like this:
remove_field => ["tags","[host][architecture]","[meta][cloud][provider]"]
But I don't think you can remove the #version field.
UPDATE:
Using the event example from your Filebeat log I simulated a pipeline and got a _grokparsefailure, to remove the fields even when the grok fails you need to use the remove_field inside a mutate filter:
filter {
grok {
your grok
}
mutate {
remove_field => ["[prospector]","[host][architecture]", "[host][containerized]", "[host][id]", "[host][os][platform]", "[host][os][family]", "[beat]", "[offset]", "[input]", "[meta]"]
}
}
Don't remove the tags field until you have fixed your groks.
The logstash output on that example is:
{
"source": "/logs/api.log",
"tags": [
"_grokparsefailure"
],
"#timestamp": "2019-02-28T01:03:41.647Z",
"message": "2018-09-14 20:23:37 INFO ContextLoader:272 - Root WebApplicationContext: initialization started",
"log": {
"file": {
"path": "/logs/api.log"
}
},
"#version": "1",
"host": {
"os": {
"codename": "Core",
"version": "7 (Core)",
"name": "CentOS Linux"
},
"name": "tomcat"
}
}
Related
I know this has been asked before but I still cannot get it working on my deployment. I am using the latest versions (8.4) of both Elasticsearch and Logstash. I want to add an index template that will load in the Logstash configuration file. Here is my output section of the Logstash configuration:
output {
elasticsearch {
hosts => ["https://192.168.1.214:9200"]
ssl => true
cacert => "/etc/logstash/certs/http_ca.crt"
user => ""
password => ""
index => "apache_elk_example"
template => "/etc/logstash/conf.d/apache_template.json"
template_name => "apache_elk_example"
template_overwrite => true
}
stdout { codec => rubydebug }
}
Here is my apache_template.json
{
"template": "apache_elk_example",
"settings": {
"index.refresh_interval": "5s"
},
"mappings": {
"_default_": {
"dynamic_templates": [
{
"message_field": {
"mapping": {
"index": "analyzed",
"omit_norms": true,
"type": "string"
},
"match_mapping_type": "string",
"match": "message"
}
},
{
"string_fields": {
"mapping": {
"index": "analyzed",
"omit_norms": true,
"type": "string",
"fields": {
"raw": {
"index": "not_analyzed",
"ignore_above": 256,
"type": "string"
}
}
},
"match_mapping_type": "string",
"match": "*"
}
}
],
"properties": {
"ip_address": {
"type": "keyword"
},
"#version": {
"index": "not_analyzed",
"type": "string"
}
},
"_all": {
"enabled": true
}
}
}
}
I will eventually add more to this but I am struggling just getting any template to load. Thanks for reading.
Logstash is receiving a docs JSON object which contains various types of docs.
{
"docs": [
{
"_id": "project:A",
"_rev": "project:1",
"name": "secret",
"children": ["item:A"]
},
{
"_id": "item:A",
"_rev": "item:1",
"name": "secret"
}
]
}
I want each doc with an _id starting with project to include matching children. The end result should be:
{
"docs": [
{
"_id": "project:A",
"_rev": "project:1",
"name": "secret",
"children": [{
"_id": "item:A",
"_rev": "item:1",
"name": "secret"
}]
},
]
}
How can I achieve this?
Here is my conf file. I aven't been able to figure out how to solve this:
input {
file {
path => ["/home/logstash/logstash-testdata.json"]
sincedb_path => "/dev/null"
start_position => "beginning"
}
}
filter {
json {
source => "message"
}
// ... ???
}
output {
elasticsearch {
hosts => ["localhost:9200"]
}
stdout {
codec => rubydebug
}
}
When attempting to parse JSON data with Logstash, it seems to fail the parse and my JSON doesn't get sent to ES as expected. Any suggestions would be great. Attempting to log failed Wordpress logins, but having no luck with the parsing of the JSON.
Currently using Logstash 6.4.2 on FreeBSD 11.
Example log file. File has nothing else but this data.
{
"username": "billy",
"password": "gfdgdfdfg4",
"time": "2019-02-03 00:39:11",
"agent": "Mozilla\/5.0 (X11; Ubuntu; Linux x86_64; rv:62.0) Gecko\/20100101 Firefox\/62.0",
"ip": "11.11.11.11"
}
Template
{
"index_patterns": ["wpbadlogin*"],
"settings": {
"number_of_shards": 1,
"number_of_replicas" : 0,
"index.refresh_interval": "60s"
},
"mappings": {
"_default_": {
"properties": {
"host": {
"type": "text"
},
"username": {
"type": "text"
},
"password": {
"type": "text"
},
"agent": {
"type": "text"
},
"ip": {
"type": "ip"
}
},
"_all": {
"enabled": false
}
}
}
}
Logstash config
input {
file {
type => "json"
codec => "json"
sincedb_path => "/dev/null"
path => "/var/log/lighttpd/badlogin.txt"
start_position => "beginning"#
tags => ["wpbadlogin"]
}
}
#filter { }
output {
stdout {
codec => rubydebug
}
elasticsearch {
hosts => ["10.0.5.30:9200"]
template => "/usr/local/etc/logstash/templates/wpbadlogin.json"
template_name => "wpbadlogin"
template_overwrite => true
index => "wpbadlogin"
}
}
Error: https://pastebin.com/raw/KWEYGkLn
Hi i am trying to setup ELK server for log management . My logstash service is running fine .I am receiving logs from other machine but logstash pipeline is not able to send data to elastic search
When i look at the logstash .log file it shows this error
I am not able to identify the error in my configuration file
:message=>"Error: Expected one of #, input, filter, output at line 34, column 1 (byte 855) after ", :level=>:error}
my logstash/conf.d
input {
beats {
port => 5044
ssl => true
ssl_certificate => "/etc/pki/tls/certs/logstash-forwarder.crt"
ssl_key => "/etc/pki/tls/private/logstash-forwarder.key"
}
}
filter {
if [type] == "syslog" {
grok {
match => { "message" => "%{SYSLOGTIMESTAMP:syslog_timestamp} %{SYSLOGHOST:syslog_hostname} %{DATA:syslog_program}(?:\[%{POSINT:syslog_pid}\])?: %{GREEDYDATA:syslog_message}" }
add_field => [ "received_at", "%{#timestamp}" ]
add_field => [ "received_from", "%{host}" ]
}
syslog_pri { }
date {
match => [ "syslog_timestamp", "MMM d HH:mm:ss", "MMM dd HH:mm:ss" ]
}
}
}
output {
elasticsearch {
hosts => ["localhost:9200"]
sniffing => true
manage_template => false
index => "%{[#metadata][beat]}-%{+YYYY.MM.dd}"
document_type => "%{[#metadata][type]}"
}
}
{
"mappings": {
"_default_": {
"_all": {
"enabled": true,
"norms": {
"enabled": false
}
},
"dynamic_templates": [
{
"template1": {
"mapping": {
"doc_values": true,
"ignore_above": 1024,
"index": "not_analyzed",
"type": "{dynamic_type}"
},
"match": "*"
}
}
],
"properties": {
"#timestamp": {
"type": "date"
},
"message": {
"type": "string",
"index": "analyzed"
},
"offset": {
"type": "long",
"doc_values": "true"
},
"geoip" : {
"type" : "object",
"dynamic": true,
"properties" : {
"location" : { "type" : "geo_point" }
}
}
}
}
},
"settings": {
"index.refresh_interval": "5s"
},
"template": "filebeat-*"
}
This error happens when there are files in /etc/logstash/conf.d directory which logstash can not parse. Remove them and see if this helps. In my case, I had the same error when reports.xml file was presented in conf.d directory.
I'm new in this ELK stuff. I've been trying to create visualizations using this stack, but I'm not able to use fields such as verb, response, request, etc, I'm only able to select a few available fields:
However, in the Discover section I'm perfectly able to work with those fields. Here is a sample of one of my query results:
(I'm using Kibana 4.4.2, filebeat forwarding to logstash 2.2.3)
{
"_index": "filebeat-2016.04.12",
"_type": "apache_log",
"_id": "AVQMoRFwO5HM5nz1lmXf",
"_score": null,
"_source": {
"message": "187.142.15.173 - - [12/Apr/2016:16:39:23 -0600] \"GET /v1.0/person/297312123/client/1132347/profile HTTP/1.1\" 200 2051 \"-\" \"Android CEX 2.2.0\"",
"#version": "1",
"#timestamp": "2016-04-12T22:39:27.064Z",
"beat": {
"hostname": "myhost",
"name": "myhost"
},
"count": 1,
"fields": null,
"input_type": "log",
"offset": 30034512,
"source": "/var/log/httpd/access_log",
"type": "apache_log",
"host": "myhost",
"tags": [
"beats_input_codec_plain_applied"
],
"clientip": "187.142.15.173",
"ident": "-",
"auth": "-",
"timestamp": "12/Apr/2016:16:39:23 -0600",
"verb": "GET",
"request": "/v1.0/person/297312123/client/1132347/profile",
"httpversion": "1.1",
"response": "200",
"bytes": "2051",
"referrer": "\"-\"",
"agent": "\"Android CEX 2.2.0\"",
},
"fields": {
"#timestamp": [
1460500767064
]
},
"sort": [
1460500767064
]
}
What could posibly be wrong with this?
Here is my config file:
filter {
if [type] == "syslog" {
grok {
match => { "message" =>
"%{SYSLOGTIMESTAMP:syslog_timestamp} %{SYSLOGHOST:syslog_hostname} %{DATA:syslog_program}(?:\[%{POSINT:syslog_pid}\])?: %{GREEDYDATA:syslog_message}"
}
add_field => [ "received_at", "%{#timestamp}" ]
add_field => [ "received_from", "%{host}" ]
}
syslog_pri { }
date {
match => [ "syslog_timestamp", "MMM d HH:mm:ss", "MMM dd HH:mm:ss" ]
}
}
if [type] == "apache_log" {
grok {
# match => [ "message", "%{COMBINEDAPACHELOG}" ]
# match => { "message" => "%{COMBINEDAPACHELOG}" }
# add_field => [ "received_at", "%{#timestamp}" ]
# add_field => [ "received_from", "%{host}" ]
match => [ "message", "%{COMBINEDAPACHELOG}" ]
}
#syslog_pri { }
#date {
# match => [ "syslog_timestamp", "MMM d HH:mm:ss", "MMM dd HH:mm:ss" ]
#}
}
}
Thanks in advance!
My first thought would be the kibana field cache. Go to Settings->Indexes, select your index, and click the orange Reload button.