I'm running logstash 6.5.4 in a docker container with the following conf file:
input {
redis {
host => "${REDIS_0_HOST}"
port => "${REDIS_0_PORT}"
data_type => "list"
key => "logstash"
}
}
input {
redis {
host => "${REDIS_1_HOST}"
port => "${REDIS_1_PORT}"
data_type => "list"
key => "logstash"
}
}
filter {
# if we were successful parsing a message from the raw log, let's dive deeper into the message and assign more fields
if [message] {
# catch gelatin lib output on startup in containers and drop them
if "20500017" in [message] { drop { } }
if "2050001c" in [message] { drop { } }
# remove trailing whitespace from message field
mutate {
strip => ["message"]
}
# handle message repeated X times messages
grok {
match => ["message", "message repeated %{NUMBER:repeat_count} times: \[ %{GREEDYDATA:message}\]"]
overwrite => [ "message" ]
tag_on_failure => [ ]
}
# handle message fields that already have structured json content
if [program] == "austin-perf" {
json {
source => "message"
remove_field => ["message"]
}
} else {
grok {
break_on_match => true
patterns_dir => ["/usr/share/logstash/config/patterns"]
match => [
"message", "%{OBLOG_REVIVE_DATE}",
"message", "%{OBLOG_REVIVE}",
"message", "%{OBLOG_DATE}",
"message", "%{OBLOG}",
"message", "%{WORD}, \[%{TIMESTAMP_ISO8601} #%{NUMBER}\] ?%{WORD:level} -- : %{GREEDYDATA:kvpairs}", # ruby app logs
"message", "%{USERNAME:level}: ?%{PATH:file} %{NUMBER:line_num} %{GREEDYDATA:kvpairs}",
"message", "%{USERNAME:level}: ?%{GREEDYDATA:kvpairs}",
"message", "%{URIPATH:file}:%{POSINT:line_num}" #ruby app exceptions
]
}
if "\." not in [kvpairs] {
kv {
source => "kvpairs"
include_keys => [
"pulse_git_events",
"pulse_trending_count",
"pulse_news_count",
"kafka_records",
"repeat_count",
"used_memory",
"new_kafka_articles",
"wcs_training_time",
"rokerbot_event",
"health_check",
"rokerbot_bot_utterance",
"rokerbot_user_utterance",
"Date_Conn_Time",
"Date_Query_Time",
"Date_Parse_Time",
"News_Conn_Time",
"News_Query_Time",
"NEWS_FAIL_TIME",
"writing_image",
"timed_app",
"ran_for",
"app_name",
"klocker_app_name",
"memory_used",
"cpu_usage",
"rss_mem",
"vms_mem",
"shared_mem",
"uss_mem",
"pss_mem",
"text_mem",
"data_mem",
"total_gpu_mem",
"used_gpu_mem",
"free_gpu_mem"
]
}
}
prune {
blacklist_names => ["%{URI}"]
}
}
if [file] and [line_num] {
mutate {
add_field => {
"test_unique" => "%{file}:%{line_num}"
}
}
}
}
mutate {
convert => {
"pulse_git_events" => "integer"
"pulse_trending_count" => "integer"
"pulse_news_count" => "integer"
"kafka_records" => "integer"
"repeat_count" => "integer"
"used_memory" => "integer"
"new_kafka_articles" => "integer"
"wcs_training_time" => "integer"
"ran_for" => "integer"
"Date_Conn_Time" => "integer"
"Date_Query_Time" => "integer"
"Date_Parse_Time" => "integer"
"News_Conn_Time" => "integer"
"News_Query_Time" => "integer"
"NEWS_FAIL_TIME" => "integer"
"memory_used" => "integer"
"cpu_usage" => "double"
"rss_mem" => "integer"
"vms_mem" => "integer"
"shared_mem" => "integer"
"uss_mem" => "integer"
"pss_mem" => "integer"
"text_mem" => "integer"
"data_mem" => "integer"
"total_gpu_mem" => "integer"
"used_gpu_mem" => "integer"
"free_gpu_mem" => "integer"
}
lowercase => "level"
remove_field => [ "timestamp", "kvpairs", "type", "_type" ]
add_field => {
"time" => "%{+HHmmssZ}"
"weekday" => "%{+EEE}"
}
}
}
output {
elasticsearch {
hosts => ["${ES_DATA_0}","${ES_DATA_1}"]
index => "logstash-%{+YYYY.MM.dd}"
}
}