kafka ch integration done

This commit is contained in:
2024-11-27 16:24:14 -07:00
parent 6fb0ff4b4c
commit 75bca2d704
8 changed files with 87 additions and 37 deletions

View File

@@ -0,0 +1,28 @@
-- local table creation
CREATE TABLE traffic_records (
time_stamp DateTime64 (6, 'Japan') CODEC (Delta, ZSTD),
l4_protocol Enum8 ('TCP' = 1, 'UDP' = 2),
src_ip IPv4,
dst_ip IPv4,
src_port UInt16 CODEC (ZSTD),
dst_port UInt16 CODEC (ZSTD),
pkt_len UInt16 CODEC (ZSTD),
INDEX port_idx src_port TYPE bloom_filter GRANULARITY 10
) ENGINE = ReplicatedMergeTree(
'/clickhouse/tables/{shard}/traffic_records',
'{replica}'
)
ORDER BY time_stamp
TTL toDateTime(time_stamp) + INTERVAL 15 DAY TO VOLUME 'cold_vol'
SETTINGS storage_policy = 'hot_cold';
CREATE TABLE ip_region_map (
ip_range_start IPv4,
ip_range_end IPv4,
region LowCardinality(String),
INDEX region_idx region TYPE bloom_filter
) ENGINE = ReplicatedMergeTree(
'/clickhouse/tables/{shard}/ip_region_map',
'{replica}'
)
ORDER BY ip_range_start;

View File

@@ -0,0 +1,3 @@
CREATE TABLE traffic_records_all
AS traffic_records
ENGINE = Distributed ('{cluster}', 'default', 'traffic_records');

View File

@@ -0,0 +1,22 @@
CREATE TABLE traffic_records_kafka_queue (
time Float64,
l4_proto String,
src_addr String,
dst_addr String,
src_port UInt16,
dst_port UInt16,
pkt_len UInt32
) ENGINE = Kafka() SETTINGS kafka_broker_list = 'kafka:9092',
kafka_topic_list = 'traffic_records_stream',
kafka_group_name = 'clickhouse_consumer',
kafka_format = 'JSONEachRow',
kafka_num_consumers = 1;
CREATE MATERIALIZED VIEW traffic_records_kafka_view TO traffic_records_all AS
SELECT time AS time_stamp,
l4_proto AS l4_protocol,
src_addr AS src_ip,
dst_addr AS dst_ip,
src_port,
dst_port,
pkt_len
FROM traffic_records_kafka_queue;