feat: implement multitenancy with tenant isolation + environment support
Adds configurable tenant ID (CAMELEER_TENANT_ID env var, default: "default") and environment as a first-class concept. Each server instance serves one tenant with multiple environments. Changes across 36 files: - TenantProperties config bean for tenant ID injection - AgentInfo: added environmentId field - AgentRegistrationRequest: added environmentId field - All 9 ClickHouse stores: inject tenant ID, replace hardcoded "default" constant, add environment to writes/reads - ChunkAccumulator: configurable tenant ID + environment resolver - MergedExecution/ProcessorBatch/BufferedLogEntry: added environment - ClickHouse init.sql: added environment column to all tables, updated ORDER BY (tenant→time→env→app), added tenant_id to usage_events, updated all MV GROUP BY clauses - Controllers: pass environmentId through registration/auto-heal - K8s deploy: added CAMELEER_TENANT_ID env var - All tests updated for new signatures Closes #123 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
hsiegeln
@@ -6,6 +6,7 @@
|
||||
CREATE TABLE IF NOT EXISTS agent_metrics (
|
||||
tenant_id LowCardinality(String) DEFAULT 'default',
|
||||
collected_at DateTime64(3),
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
instance_id LowCardinality(String),
|
||||
metric_name LowCardinality(String),
|
||||
metric_value Float64,
|
||||
@@ -14,7 +15,7 @@ CREATE TABLE IF NOT EXISTS agent_metrics (
|
||||
)
|
||||
ENGINE = MergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(collected_at))
|
||||
ORDER BY (tenant_id, instance_id, metric_name, collected_at)
|
||||
ORDER BY (tenant_id, collected_at, environment, instance_id, metric_name)
|
||||
TTL toDateTime(collected_at) + INTERVAL 365 DAY DELETE
|
||||
SETTINGS index_granularity = 8192;
|
||||
|
||||
@@ -28,6 +29,7 @@ CREATE TABLE IF NOT EXISTS executions (
|
||||
route_id LowCardinality(String),
|
||||
instance_id LowCardinality(String),
|
||||
application_id LowCardinality(String),
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
status LowCardinality(String),
|
||||
correlation_id String DEFAULT '',
|
||||
exchange_id String DEFAULT '',
|
||||
@@ -68,7 +70,7 @@ CREATE TABLE IF NOT EXISTS executions (
|
||||
)
|
||||
ENGINE = ReplacingMergeTree(_version)
|
||||
PARTITION BY (tenant_id, toYYYYMM(start_time))
|
||||
ORDER BY (tenant_id, start_time, application_id, route_id, execution_id)
|
||||
ORDER BY (tenant_id, start_time, environment, application_id, route_id, execution_id)
|
||||
TTL toDateTime(start_time) + INTERVAL 365 DAY DELETE
|
||||
SETTINGS index_granularity = 8192;
|
||||
|
||||
@@ -85,6 +87,7 @@ CREATE TABLE IF NOT EXISTS processor_executions (
|
||||
start_time DateTime64(3),
|
||||
route_id LowCardinality(String),
|
||||
application_id LowCardinality(String),
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
iteration Nullable(Int32),
|
||||
iteration_size Nullable(Int32),
|
||||
status LowCardinality(String),
|
||||
@@ -116,7 +119,7 @@ CREATE TABLE IF NOT EXISTS processor_executions (
|
||||
)
|
||||
ENGINE = MergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(start_time))
|
||||
ORDER BY (tenant_id, start_time, application_id, route_id, execution_id, seq)
|
||||
ORDER BY (tenant_id, start_time, environment, application_id, route_id, execution_id, seq)
|
||||
TTL toDateTime(start_time) + INTERVAL 365 DAY DELETE
|
||||
SETTINGS index_granularity = 8192;
|
||||
|
||||
@@ -127,6 +130,7 @@ SETTINGS index_granularity = 8192;
|
||||
CREATE TABLE IF NOT EXISTS stats_1m_all (
|
||||
tenant_id LowCardinality(String),
|
||||
bucket DateTime,
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
total_count AggregateFunction(count),
|
||||
failed_count AggregateFunction(countIf, UInt8),
|
||||
running_count AggregateFunction(countIf, UInt8),
|
||||
@@ -136,13 +140,14 @@ CREATE TABLE IF NOT EXISTS stats_1m_all (
|
||||
)
|
||||
ENGINE = AggregatingMergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(bucket))
|
||||
ORDER BY (tenant_id, bucket)
|
||||
ORDER BY (tenant_id, bucket, environment)
|
||||
TTL bucket + INTERVAL 365 DAY DELETE;
|
||||
|
||||
CREATE MATERIALIZED VIEW IF NOT EXISTS stats_1m_all_mv TO stats_1m_all AS
|
||||
SELECT
|
||||
tenant_id,
|
||||
toStartOfMinute(start_time) AS bucket,
|
||||
environment,
|
||||
countState() AS total_count,
|
||||
countIfState(status = 'FAILED') AS failed_count,
|
||||
countIfState(status = 'RUNNING') AS running_count,
|
||||
@@ -150,7 +155,7 @@ SELECT
|
||||
maxState(duration_ms) AS duration_max,
|
||||
quantileState(0.99)(duration_ms) AS p99_duration
|
||||
FROM executions
|
||||
GROUP BY tenant_id, bucket;
|
||||
GROUP BY tenant_id, bucket, environment;
|
||||
|
||||
-- stats_1m_app (per-application)
|
||||
|
||||
@@ -158,6 +163,7 @@ CREATE TABLE IF NOT EXISTS stats_1m_app (
|
||||
tenant_id LowCardinality(String),
|
||||
application_id LowCardinality(String),
|
||||
bucket DateTime,
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
total_count AggregateFunction(count),
|
||||
failed_count AggregateFunction(countIf, UInt8),
|
||||
running_count AggregateFunction(countIf, UInt8),
|
||||
@@ -167,7 +173,7 @@ CREATE TABLE IF NOT EXISTS stats_1m_app (
|
||||
)
|
||||
ENGINE = AggregatingMergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(bucket))
|
||||
ORDER BY (tenant_id, application_id, bucket)
|
||||
ORDER BY (tenant_id, bucket, environment, application_id)
|
||||
TTL bucket + INTERVAL 365 DAY DELETE;
|
||||
|
||||
CREATE MATERIALIZED VIEW IF NOT EXISTS stats_1m_app_mv TO stats_1m_app AS
|
||||
@@ -175,6 +181,7 @@ SELECT
|
||||
tenant_id,
|
||||
application_id,
|
||||
toStartOfMinute(start_time) AS bucket,
|
||||
environment,
|
||||
countState() AS total_count,
|
||||
countIfState(status = 'FAILED') AS failed_count,
|
||||
countIfState(status = 'RUNNING') AS running_count,
|
||||
@@ -182,7 +189,7 @@ SELECT
|
||||
maxState(duration_ms) AS duration_max,
|
||||
quantileState(0.99)(duration_ms) AS p99_duration
|
||||
FROM executions
|
||||
GROUP BY tenant_id, application_id, bucket;
|
||||
GROUP BY tenant_id, application_id, bucket, environment;
|
||||
|
||||
-- stats_1m_route (per-route)
|
||||
|
||||
@@ -191,6 +198,7 @@ CREATE TABLE IF NOT EXISTS stats_1m_route (
|
||||
application_id LowCardinality(String),
|
||||
route_id LowCardinality(String),
|
||||
bucket DateTime,
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
total_count AggregateFunction(count),
|
||||
failed_count AggregateFunction(countIf, UInt8),
|
||||
running_count AggregateFunction(countIf, UInt8),
|
||||
@@ -200,7 +208,7 @@ CREATE TABLE IF NOT EXISTS stats_1m_route (
|
||||
)
|
||||
ENGINE = AggregatingMergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(bucket))
|
||||
ORDER BY (tenant_id, application_id, route_id, bucket)
|
||||
ORDER BY (tenant_id, bucket, environment, application_id, route_id)
|
||||
TTL bucket + INTERVAL 365 DAY DELETE;
|
||||
|
||||
CREATE MATERIALIZED VIEW IF NOT EXISTS stats_1m_route_mv TO stats_1m_route AS
|
||||
@@ -209,6 +217,7 @@ SELECT
|
||||
application_id,
|
||||
route_id,
|
||||
toStartOfMinute(start_time) AS bucket,
|
||||
environment,
|
||||
countState() AS total_count,
|
||||
countIfState(status = 'FAILED') AS failed_count,
|
||||
countIfState(status = 'RUNNING') AS running_count,
|
||||
@@ -216,7 +225,7 @@ SELECT
|
||||
maxState(duration_ms) AS duration_max,
|
||||
quantileState(0.99)(duration_ms) AS p99_duration
|
||||
FROM executions
|
||||
GROUP BY tenant_id, application_id, route_id, bucket;
|
||||
GROUP BY tenant_id, application_id, route_id, bucket, environment;
|
||||
|
||||
-- stats_1m_processor (per-processor-type)
|
||||
|
||||
@@ -225,6 +234,7 @@ CREATE TABLE IF NOT EXISTS stats_1m_processor (
|
||||
application_id LowCardinality(String),
|
||||
processor_type LowCardinality(String),
|
||||
bucket DateTime,
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
total_count AggregateFunction(count),
|
||||
failed_count AggregateFunction(countIf, UInt8),
|
||||
duration_sum AggregateFunction(sum, Nullable(Int64)),
|
||||
@@ -233,7 +243,7 @@ CREATE TABLE IF NOT EXISTS stats_1m_processor (
|
||||
)
|
||||
ENGINE = AggregatingMergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(bucket))
|
||||
ORDER BY (tenant_id, application_id, processor_type, bucket)
|
||||
ORDER BY (tenant_id, bucket, environment, application_id, processor_type)
|
||||
TTL bucket + INTERVAL 365 DAY DELETE;
|
||||
|
||||
CREATE MATERIALIZED VIEW IF NOT EXISTS stats_1m_processor_mv TO stats_1m_processor AS
|
||||
@@ -242,13 +252,14 @@ SELECT
|
||||
application_id,
|
||||
processor_type,
|
||||
toStartOfMinute(start_time) AS bucket,
|
||||
environment,
|
||||
countState() AS total_count,
|
||||
countIfState(status = 'FAILED') AS failed_count,
|
||||
sumState(duration_ms) AS duration_sum,
|
||||
maxState(duration_ms) AS duration_max,
|
||||
quantileState(0.99)(duration_ms) AS p99_duration
|
||||
FROM processor_executions
|
||||
GROUP BY tenant_id, application_id, processor_type, bucket;
|
||||
GROUP BY tenant_id, application_id, processor_type, bucket, environment;
|
||||
|
||||
-- stats_1m_processor_detail (per-processor-id)
|
||||
|
||||
@@ -259,6 +270,7 @@ CREATE TABLE IF NOT EXISTS stats_1m_processor_detail (
|
||||
processor_id String,
|
||||
processor_type LowCardinality(String),
|
||||
bucket DateTime,
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
total_count AggregateFunction(count),
|
||||
failed_count AggregateFunction(countIf, UInt8),
|
||||
duration_sum AggregateFunction(sum, Nullable(Int64)),
|
||||
@@ -267,7 +279,7 @@ CREATE TABLE IF NOT EXISTS stats_1m_processor_detail (
|
||||
)
|
||||
ENGINE = AggregatingMergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(bucket))
|
||||
ORDER BY (tenant_id, application_id, route_id, processor_id, processor_type, bucket)
|
||||
ORDER BY (tenant_id, bucket, environment, application_id, route_id, processor_id, processor_type)
|
||||
TTL bucket + INTERVAL 365 DAY DELETE;
|
||||
|
||||
CREATE MATERIALIZED VIEW IF NOT EXISTS stats_1m_processor_detail_mv TO stats_1m_processor_detail AS
|
||||
@@ -278,13 +290,14 @@ SELECT
|
||||
processor_id,
|
||||
processor_type,
|
||||
toStartOfMinute(start_time) AS bucket,
|
||||
environment,
|
||||
countState() AS total_count,
|
||||
countIfState(status = 'FAILED') AS failed_count,
|
||||
sumState(duration_ms) AS duration_sum,
|
||||
maxState(duration_ms) AS duration_max,
|
||||
quantileState(0.99)(duration_ms) AS p99_duration
|
||||
FROM processor_executions
|
||||
GROUP BY tenant_id, application_id, route_id, processor_id, processor_type, bucket;
|
||||
GROUP BY tenant_id, application_id, route_id, processor_id, processor_type, bucket, environment;
|
||||
|
||||
-- ── Route Diagrams ──────────────────────────────────────────────────────
|
||||
|
||||
@@ -294,11 +307,12 @@ CREATE TABLE IF NOT EXISTS route_diagrams (
|
||||
route_id LowCardinality(String),
|
||||
instance_id LowCardinality(String),
|
||||
application_id LowCardinality(String),
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
definition String,
|
||||
created_at DateTime64(3) DEFAULT now64(3)
|
||||
)
|
||||
ENGINE = ReplacingMergeTree(created_at)
|
||||
ORDER BY (tenant_id, content_hash)
|
||||
ORDER BY (tenant_id, environment, route_id, instance_id, content_hash)
|
||||
SETTINGS index_granularity = 8192;
|
||||
|
||||
-- ── Agent Events ────────────────────────────────────────────────────────
|
||||
@@ -306,6 +320,7 @@ SETTINGS index_granularity = 8192;
|
||||
CREATE TABLE IF NOT EXISTS agent_events (
|
||||
tenant_id LowCardinality(String) DEFAULT 'default',
|
||||
timestamp DateTime64(3) DEFAULT now64(3),
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
instance_id LowCardinality(String),
|
||||
application_id LowCardinality(String),
|
||||
event_type LowCardinality(String),
|
||||
@@ -313,7 +328,7 @@ CREATE TABLE IF NOT EXISTS agent_events (
|
||||
)
|
||||
ENGINE = MergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(timestamp))
|
||||
ORDER BY (tenant_id, application_id, instance_id, timestamp)
|
||||
ORDER BY (tenant_id, timestamp, environment, instance_id)
|
||||
TTL toDateTime(timestamp) + INTERVAL 365 DAY DELETE;
|
||||
|
||||
-- ── Logs ────────────────────────────────────────────────────────────────
|
||||
@@ -321,6 +336,7 @@ TTL toDateTime(timestamp) + INTERVAL 365 DAY DELETE;
|
||||
CREATE TABLE IF NOT EXISTS logs (
|
||||
tenant_id LowCardinality(String) DEFAULT 'default',
|
||||
timestamp DateTime64(3),
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
application LowCardinality(String),
|
||||
instance_id LowCardinality(String),
|
||||
level LowCardinality(String),
|
||||
@@ -337,14 +353,16 @@ CREATE TABLE IF NOT EXISTS logs (
|
||||
)
|
||||
ENGINE = MergeTree()
|
||||
PARTITION BY (tenant_id, toYYYYMM(timestamp))
|
||||
ORDER BY (tenant_id, application, timestamp)
|
||||
ORDER BY (tenant_id, timestamp, environment, application, instance_id)
|
||||
TTL toDateTime(timestamp) + INTERVAL 365 DAY DELETE
|
||||
SETTINGS index_granularity = 8192;
|
||||
|
||||
-- ── Usage Events ────────────────────────────────────────────────────────
|
||||
|
||||
CREATE TABLE IF NOT EXISTS usage_events (
|
||||
tenant_id LowCardinality(String) DEFAULT 'default',
|
||||
timestamp DateTime64(3) DEFAULT now64(3),
|
||||
environment LowCardinality(String) DEFAULT 'default',
|
||||
username LowCardinality(String),
|
||||
method LowCardinality(String),
|
||||
path String,
|
||||
@@ -354,5 +372,5 @@ CREATE TABLE IF NOT EXISTS usage_events (
|
||||
query_params String DEFAULT ''
|
||||
)
|
||||
ENGINE = MergeTree()
|
||||
ORDER BY (username, timestamp)
|
||||
ORDER BY (tenant_id, timestamp, environment, username, normalized)
|
||||
TTL toDateTime(timestamp) + INTERVAL 90 DAY;
|
||||
|
||||
Reference in New Issue
Block a user