Kafka および ClickHouse で Vector を使用する

cat /opt/data/github/github_all_columns.ndjson | kcat -b <host>:<port> -X security.protocol=sasl_ssl -X sasl.mechanisms=PLAIN -X sasl.username=<username> -X sasl.password=<password> -t github

CREATE TABLE github
(
    file_time DateTime,
    event_type Enum('CommitCommentEvent' = 1, 'CreateEvent' = 2, 'DeleteEvent' = 3, 'ForkEvent' = 4,
                    'GollumEvent' = 5, 'IssueCommentEvent' = 6, 'IssuesEvent' = 7, 'MemberEvent' = 8, 'PublicEvent' = 9, 'PullRequestEvent' = 10, 'PullRequestReviewCommentEvent' = 11, 'PushEvent' = 12, 'ReleaseEvent' = 13, 'SponsorshipEvent' = 14, 'WatchEvent' = 15, 'GistEvent' = 16, 'FollowEvent' = 17, 'DownloadEvent' = 18, 'PullRequestReviewEvent' = 19, 'ForkApplyEvent' = 20, 'Event' = 21, 'TeamAddEvent' = 22),
    actor_login LowCardinality(String),
    repo_name LowCardinality(String),
    created_at DateTime,
    updated_at DateTime,
    action Enum('none' = 0, 'created' = 1, 'added' = 2, 'edited' = 3, 'deleted' = 4, 'opened' = 5, 'closed' = 6, 'reopened' = 7, 'assigned' = 8, 'unassigned' = 9, 'labeled' = 10, 'unlabeled' = 11, 'review_requested' = 12, 'review_request_removed' = 13, 'synchronize' = 14, 'started' = 15, 'published' = 16, 'update' = 17, 'create' = 18, 'fork' = 19, 'merged' = 20),
    comment_id UInt64,
    path String,
    ref LowCardinality(String),
    ref_type Enum('none' = 0, 'branch' = 1, 'tag' = 2, 'repository' = 3, 'unknown' = 4),
    creator_user_login LowCardinality(String),
    number UInt32,
    title String,
    labels Array(LowCardinality(String)),
    state Enum('none' = 0, 'open' = 1, 'closed' = 2),
    assignee LowCardinality(String),
    assignees Array(LowCardinality(String)),
    closed_at DateTime,
    merged_at DateTime,
    merge_commit_sha String,
    requested_reviewers Array(LowCardinality(String)),
    merged_by LowCardinality(String),
    review_comments UInt32,
    member_login LowCardinality(String)
) ENGINE = MergeTree ORDER BY (event_type, repo_name, created_at);

[sources.github]
type = "kafka"
auto_offset_reset = "smallest"
bootstrap_servers = "<kafka_host>:<kafka_port>"
group_id = "vector"
topics = [ "github" ]
tls.enabled = true
sasl.enabled = true
sasl.mechanism = "PLAIN"
sasl.username = "<username>"
sasl.password = "<password>"
decoding.codec = "json"

[sinks.clickhouse]
type = "clickhouse"
inputs = ["github"]
endpoint = "http://localhost:8123"
database = "default"
table = "github"
skip_unknown_fields = true
auth.strategy = "basic"
auth.user = "username"
auth.password = "password"
buffer.max_events = 10000
batch.timeout_secs = 1

vector --config ./kafka.toml

SELECT count() AS count FROM github;