feat: split ClickHouse into dual configurable databases (ja4_logs / ja4_processing)

Architecture:
- ja4_logs: raw log ingestion (http_logs_raw, http_logs, mv_http_logs)
- ja4_processing: analytics, aggregation, ML, dictionaries, audit

Configuration (env vars):
- CLICKHOUSE_DB_LOGS (default: ja4_logs)
- CLICKHOUSE_DB_PROCESSING (default: ja4_processing)

Changes:
- SQL migrations (10 files): all mabase_prod refs → ja4_logs or ja4_processing
  with correct cross-database references (MVs, views, dicts)
- deploy_schema.sh: substitutes DB names from env vars at deploy time
- Python shared settings: added CLICKHOUSE_DB_LOGS + CLICKHOUSE_DB_PROCESSING
- Dashboard routes (19 files): replaced ~80 hardcoded mabase_prod refs
  with settings.CLICKHOUSE_DB_LOGS / settings.CLICKHOUSE_DB_PROCESSING
- Bot-detector: DB → CLICKHOUSE_DB_PROCESSING, fetch_rules.py configurable
- Correlator: DSN example updated to ja4_logs
- Docker-compose + .env files: new env vars with defaults
- All documentation updated (14 markdown files)

All tests pass: sentinel 10/10, correlator 67.1%, bot-detector 11, dashboard 20, ja4_common 18

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
toto
2026-04-07 19:10:35 +02:00
parent b6391afbeb
commit 9f3e0621e5
46 changed files with 638 additions and 549 deletions

View File

@ -7,8 +7,8 @@
-- Bot reputation dictionaries (in-RAM for fast lookup)
-- CSV files must be placed at: /var/lib/clickhouse/user_files/
-- -----------------------------------------------------------------------------
DROP DICTIONARY IF EXISTS mabase_prod.dict_bot_ip;
CREATE DICTIONARY mabase_prod.dict_bot_ip
DROP DICTIONARY IF EXISTS ja4_processing.dict_bot_ip;
CREATE DICTIONARY ja4_processing.dict_bot_ip
(
prefix String,
bot_name String
@ -18,8 +18,8 @@ SOURCE(FILE(path '/var/lib/clickhouse/user_files/bot_ip.csv' format 'CSV'))
LAYOUT(IP_TRIE())
LIFETIME(MIN 300 MAX 300);
DROP DICTIONARY IF EXISTS mabase_prod.dict_bot_ja4;
CREATE DICTIONARY mabase_prod.dict_bot_ja4
DROP DICTIONARY IF EXISTS ja4_processing.dict_bot_ja4;
CREATE DICTIONARY ja4_processing.dict_bot_ja4
(
ja4 String,
bot_name String
@ -29,8 +29,8 @@ SOURCE(FILE(path '/var/lib/clickhouse/user_files/bot_ja4.csv' format 'CSV'))
LAYOUT(COMPLEX_KEY_HASHED())
LIFETIME(MIN 300 MAX 300);
DROP DICTIONARY IF EXISTS mabase_prod.dict_asn_reputation;
CREATE DICTIONARY mabase_prod.dict_asn_reputation
DROP DICTIONARY IF EXISTS ja4_processing.dict_asn_reputation;
CREATE DICTIONARY ja4_processing.dict_asn_reputation
(
src_asn UInt64,
label String
@ -44,7 +44,7 @@ LIFETIME(MIN 300 MAX 300);
-- -----------------------------------------------------------------------------
-- agg_host_ip_ja4_1h — behavioral aggregation (L4/L5/L7)
-- -----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS mabase_prod.agg_host_ip_ja4_1h
CREATE TABLE IF NOT EXISTS ja4_processing.agg_host_ip_ja4_1h
(
window_start DateTime,
src_ip IPv6, ja4 String, host String, src_asn UInt32,
@ -107,10 +107,10 @@ ORDER BY (window_start, src_ip, ja4, host);
-- -----------------------------------------------------------------------------
-- mv_agg_host_ip_ja4_1h — feeds agg_host_ip_ja4_1h from http_logs
-- -----------------------------------------------------------------------------
DROP VIEW IF EXISTS mabase_prod.mv_agg_host_ip_ja4_1h;
DROP VIEW IF EXISTS ja4_processing.mv_agg_host_ip_ja4_1h;
CREATE MATERIALIZED VIEW mabase_prod.mv_agg_host_ip_ja4_1h
TO mabase_prod.agg_host_ip_ja4_1h AS
CREATE MATERIALIZED VIEW ja4_processing.mv_agg_host_ip_ja4_1h
TO ja4_processing.agg_host_ip_ja4_1h AS
SELECT
toStartOfHour(src.time) AS window_start,
toIPv6(src.src_ip) AS src_ip, src.ja4, src.host, src.src_asn,
@ -151,14 +151,14 @@ SELECT
sum(toUInt64(src.correlated)) AS count_correlated,
sum(IF(length(src.header_accept_encoding) = 0, 1, 0)) AS count_no_accept_enc,
sum(IF(src.scheme = 'http', 1, 0)) AS count_http_scheme
FROM mabase_prod.http_logs AS src
FROM ja4_logs.http_logs AS src
GROUP BY window_start, src_ip, ja4, host, src_asn;
-- -----------------------------------------------------------------------------
-- agg_header_fingerprint_1h — header fingerprint aggregation (L7)
-- -----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS mabase_prod.agg_header_fingerprint_1h
CREATE TABLE IF NOT EXISTS ja4_processing.agg_header_fingerprint_1h
(
window_start DateTime,
src_ip IPv6,
@ -175,10 +175,10 @@ CREATE TABLE IF NOT EXISTS mabase_prod.agg_header_fingerprint_1h
ENGINE = AggregatingMergeTree()
ORDER BY (window_start, src_ip);
DROP VIEW IF EXISTS mabase_prod.mv_agg_header_fingerprint_1h;
DROP VIEW IF EXISTS ja4_processing.mv_agg_header_fingerprint_1h;
CREATE MATERIALIZED VIEW mabase_prod.mv_agg_header_fingerprint_1h
TO mabase_prod.agg_header_fingerprint_1h AS
CREATE MATERIALIZED VIEW ja4_processing.mv_agg_header_fingerprint_1h
TO ja4_processing.agg_header_fingerprint_1h AS
SELECT
toStartOfHour(src.time) AS window_start,
toIPv6(src.src_ip) AS src_ip,
@ -191,5 +191,5 @@ SELECT
max(toUInt8(if((position(src.header_user_agent, 'Windows') > 0 AND position(src.header_sec_ch_ua_platform, 'Windows') == 0) OR (position(src.header_user_agent, 'iPhone') > 0 AND position(src.header_sec_ch_ua_platform, 'iOS') == 0), 1, 0))) AS ua_ch_mismatch,
any(src.header_sec_fetch_mode) AS sec_fetch_mode,
any(src.header_sec_fetch_dest) AS sec_fetch_dest
FROM mabase_prod.http_logs AS src
FROM ja4_logs.http_logs AS src
GROUP BY window_start, src.src_ip;