メモ：ALBのログをAthenaで見る

About

ALBのログをAthenaで見たかったので

データベースの作成

CREATE EXTERNAL TABLE IF NOT EXISTS alb_logs (
    type string,
    time string,
    elb string,
    client_ip string,
    client_port int,
    target_ip string,
    target_port int,
    request_processing_time double,
    target_processing_time double,
    response_processing_time double,
    elb_status_code string,
    target_status_code string,
    received_bytes bigint,
    sent_bytes bigint,
    request_verb string,
    request_url string,
    request_proto string,
    user_agent string,
    ssl_cipher string,
    ssl_protocol string,
    target_group_arn string,
    trace_id string,
    domain_name string,
    chosen_cert_arn string,
    matched_rule_priority string,
    request_creation_time string,
    actions_executed string,
    redirect_url string,
    new_field string
    )
    ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
    WITH SERDEPROPERTIES (
    'serialization.format' = '1',
    'input.regex' = 
'([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*):([0-9]*) ([^ ]*)[:-]([0-9]*) ([-.0-9]*) ([-.0-9]*) ([-.0-9]*) (|[-0-9]*) (-|[-0-9]*) ([-0-9]*) ([-0-9]*) \"([^ ]*) ([^ ]*) (- |[^ ]*)\" \"([^\"]*)\" ([A-Z0-9-]+) ([A-Za-z0-9.-]*) ([^ ]*) \"([^\"]*)\" \"([^\"]*)\" \"([^\"]*)\" ([-.0-9]*) ([^ ]*) \"([^\"]*)\"($| \"[^ ]*\")(.*)')
    LOCATION 's3://your-alb-logs-directory/AWSLogs/<ACCOUNT-ID>/elasticloadbalancing/region';

特定時間のリクエストを分析する

SELECT request_verb,
         domain_name,
         count(*) as count
FROM 
    (SELECT from_iso8601_timestamp(time) AS request_time,
         *
    FROM "default"."alb_logs")
WHERE request_time
    BETWEEN date_parse('2018-10-11 11:00:00', '%Y-%m-%d %H:%i:%S')
        AND date_parse('2018-10-11 23:00:00', '%Y-%m-%d %H:%i:%S')
GROUP BY  request_verb,domain_name
order by domain_name