From 3f15f225f47a7bf2e177c29251d75bf61b544f66 Mon Sep 17 00:00:00 2001 From: Kaushik Narayan R Date: Thu, 28 Nov 2024 22:11:32 -0700 Subject: [PATCH] load geoip data from csv --- .../data/preprocessed_configs/config.xml | 61 ------------------- clickhouse/dml/test_seed_traffic.sql | 36 ----------- clickhouse/docker-compose.yaml | 5 +- .../main/03_insert_geoip_csv.sql | 3 + preprocessing/geoip.csv | 2 +- 5 files changed, 7 insertions(+), 100 deletions(-) delete mode 100644 clickhouse/clickhouse_data/data/preprocessed_configs/config.xml delete mode 100644 clickhouse/dml/test_seed_traffic.sql create mode 100644 clickhouse/node-entrypoints/main/03_insert_geoip_csv.sql diff --git a/clickhouse/clickhouse_data/data/preprocessed_configs/config.xml b/clickhouse/clickhouse_data/data/preprocessed_configs/config.xml deleted file mode 100644 index 08de94b..0000000 --- a/clickhouse/clickhouse_data/data/preprocessed_configs/config.xml +++ /dev/null @@ -1,61 +0,0 @@ - - - - - trace - /var/log/clickhouse-keeper/clickhouse-keeper.log - /var/log/clickhouse-keeper/clickhouse-keeper.err.log - 1000M - 3 - - :: - - /var/lib/clickhouse/data/ - /var/lib/clickhouse/tmp/ - /var/lib/clickhouse/user_files/ - /var/lib/clickhouse/format_schemas/ - - - 9181 - 2 - /var/lib/clickhouse/coordination/log - /var/lib/clickhouse/coordination/snapshots - - 10000 - 30000 - trace - - - - 1 - clickhouse-keeper1 - 9234 - - - 2 - clickhouse-keeper2 - 9234 - - - 3 - clickhouse-keeper3 - 9234 - - - - - - - 0.0.0.0 - 1 - - - diff --git a/clickhouse/dml/test_seed_traffic.sql b/clickhouse/dml/test_seed_traffic.sql deleted file mode 100644 index 2399221..0000000 --- a/clickhouse/dml/test_seed_traffic.sql +++ /dev/null @@ -1,36 +0,0 @@ -INSERT INTO - traffic_records_all -VALUES - ( - '1698728400.40122', - 'UDP', - '142.12.217.111', - '163.213.146.100', - 443, - 47104, - 74 - ) ( - '1698728400.401217', - 'UDP', - '45.144.255.42', - '131.174.60.217', - 51820, - 63998, - 42 - ) ( - '1698728400.401218', - 'TCP', - '152.199.153.111', - '202.215.192.69', - 80, - 65305, - 66 - ) ( - '1698728400.401219', - 'UDP', - '45.144.255.42', - '131.174.60.217', - 51820, - 63998, - 42 - ) \ No newline at end of file diff --git a/clickhouse/docker-compose.yaml b/clickhouse/docker-compose.yaml index d0fd34e..dac8f4b 100644 --- a/clickhouse/docker-compose.yaml +++ b/clickhouse/docker-compose.yaml @@ -59,7 +59,8 @@ services: container_name: clickhouse-server1 volumes: - ../clickhouse/node1-config/:/etc/clickhouse-server/config.d/ - - ../clickhouse/ddl/main:/docker-entrypoint-initdb.d + - ../clickhouse/node-entrypoints/main:/docker-entrypoint-initdb.d + - ../preprocessing/geoip.csv:/tmp/seedData/csv/ip_region_map.csv - clickhouse_server1_data:/var/lib/clickhouse - clickhouse_server1_TTL:/clickhouse_data/server1 networks: @@ -98,7 +99,7 @@ services: container_name: clickhouse-server2 volumes: - ../clickhouse/node2-config/:/etc/clickhouse-server/config.d/ - - ../clickhouse/ddl/common:/docker-entrypoint-initdb.d + - ../clickhouse/node-entrypoints/common:/docker-entrypoint-initdb.d - clickhouse_server2_data:/var/lib/clickhouse - clickhouse_server2_TTL:/clickhouse_data/server2 networks: diff --git a/clickhouse/node-entrypoints/main/03_insert_geoip_csv.sql b/clickhouse/node-entrypoints/main/03_insert_geoip_csv.sql new file mode 100644 index 0000000..9a1ea5c --- /dev/null +++ b/clickhouse/node-entrypoints/main/03_insert_geoip_csv.sql @@ -0,0 +1,3 @@ +INSERT INTO ip_region_map +FROM INFILE '/tmp/seedData/csv/ip_region_map.csv' +FORMAT CSVWithNames; \ No newline at end of file diff --git a/preprocessing/geoip.csv b/preprocessing/geoip.csv index db087c0..305b5d4 100644 --- a/preprocessing/geoip.csv +++ b/preprocessing/geoip.csv @@ -1,4 +1,4 @@ -ip_range_start,ip_range_end,country +ip_range_start,ip_range_end,region 0.0.0.0,0.255.255.255,- 1.0.0.0,1.0.0.255,Australia 1.0.1.0,1.0.3.255,China