[exporter/clickhouse] Add create_schema option to config

.chloggen/clickhouse-add-create-schema-option.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: clickhouseexporter
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "Add `create_schema` option to ClickHouse exporter"
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [32282]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext: The new create_schema option allows disabling default DDL to let the user manage their own schema.
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: []

exporter/clickhouseexporter/README.md

@@ -279,10 +279,11 @@ Connection options:
 
 - `username` (default = ): The authentication username.
 - `password` (default = ): The authentication password.
+- `connection_params` (default = {}). Params is the extra connection parameters with map format.
 - `ttl_days` (default = 0): **Deprecated: Use 'ttl' instead.**  The data time-to-live in days, 0 means no ttl.
 - `ttl` (default = 0): The data time-to-live example 30m, 48h. Also, 0 means no ttl.
 - `database` (default = otel): The database name.
-- `connection_params` (default = {}). Params is the extra connection parameters with map format.
+- `create_schema` (default = true): When set to true, will run DDL to create the database and tables. (See [schema management](#schema-management))
 
 ClickHouse tables:
 
@@ -321,6 +322,19 @@ Processing:
 The exporter supports TLS. To enable TLS, you need to specify the `secure=true` query parameter in the `endpoint` URL or
 use the `https` scheme.
 
+## Schema management
+
+By default the exporter will create the database and tables under the names defined in the config. This is fine for simple deployments, but for production workloads, it is recommended that you manage your own schema by setting `create_schema` to `false` in the config.
+This prevents each exporter process from racing to create the database and tables, and makes it easier to upgrade the exporter in the future.
+
+In this mode, the only SQL sent to your server will be for `INSERT` statements.
+
+The default DDL used by the exporter can be found in `example/default_ddl`.
+Be sure to customize the indexes, TTL, and partitioning to fit your deployment.
+Column names and types must be the same to preserve compatibility with the exporter's `INSERT` statements.
+As long as the column names/types match the `INSERT` statement, you can create whatever kind of table you want.
+See [ClickHouse's LogHouse](https://clickhouse.com/blog/building-a-logging-platform-with-clickhouse-and-saving-millions-over-datadog#schema) as an example of this flexibility.
+
 ## Example
 
 This example shows how to configure the exporter to send data to a ClickHouse server.
@@ -339,6 +353,7 @@ exporters:
     endpoint: tcp://127.0.0.1:9000?dial_timeout=10s&compress=lz4
     database: otel
     ttl: 72h
+    create_schema: true
     logs_table_name: otel_logs
     traces_table_name: otel_traces
     metrics_table_name: otel_metrics

exporter/clickhouseexporter/config.go

@@ -47,6 +47,8 @@ type Config struct {
 	TableEngine TableEngine `mapstructure:"table_engine"`
 	// ClusterName if set will append `ON CLUSTER` with the provided name when creating tables.
 	ClusterName string `mapstructure:"cluster_name"`
+	// CreateSchema if set to true will run the DDL for creating the database and tables. default is true.
+	CreateSchema *bool `mapstructure:"create_schema"`
 }
 
 // TableEngine defines the ENGINE string value when creating the table.
@@ -147,6 +149,15 @@ func (cfg *Config) buildDB(database string) (*sql.DB, error) {
 	return conn, nil
 }
 
+// ShouldCreateSchema returns true if the exporter should run the DDL for creating database/tables.
+func (cfg *Config) ShouldCreateSchema() bool {
+	if cfg.CreateSchema == nil {
+		return true // default to true
+	}
+
+	return *cfg.CreateSchema
+}
+
 // TableEngineString generates the ENGINE string.
 func (cfg *Config) TableEngineString() string {
 	engine := cfg.TableEngine.Name

exporter/clickhouseexporter/config_test.go

@@ -33,6 +33,7 @@ func TestLoadConfig(t *testing.T) {
 	defaultCfg := createDefaultConfig()
 	defaultCfg.(*Config).Endpoint = defaultEndpoint
 
+	createSchema := true
 	storageID := component.MustNewIDWithName("file_storage", "clickhouse")
 
 	tests := []struct {
@@ -55,6 +56,7 @@ func TestLoadConfig(t *testing.T) {
 				LogsTableName:    "otel_logs",
 				TracesTableName:  "otel_traces",
 				MetricsTableName: "otel_metrics",
+				CreateSchema:     &createSchema,
 				TimeoutSettings: exporterhelper.TimeoutSettings{
 					Timeout: 5 * time.Second,
 				},
@@ -275,6 +277,48 @@ func TestConfig_buildDSN(t *testing.T) {
 	}
 }
 
+func TestShouldCreateSchema(t *testing.T) {
+	t.Parallel()
+
+	createSchemaTrue := true
+	createSchemaFalse := false
+
+	caseDefault := createDefaultConfig().(*Config)
+	caseCreateSchemaTrue := createDefaultConfig().(*Config)
+	caseCreateSchemaTrue.CreateSchema = &createSchemaTrue
+	caseCreateSchemaFalse := createDefaultConfig().(*Config)
+	caseCreateSchemaFalse.CreateSchema = &createSchemaFalse
+
+	tests := []struct {
+		name     string
+		input    *Config
+		expected bool
+	}{
+		{
+			name:     "default",
+			input:    caseDefault,
+			expected: true,
+		},
+		{
+			name:     "true",
+			input:    caseCreateSchemaTrue,
+			expected: true,
+		},
+		{
+			name:     "false",
+			input:    caseCreateSchemaFalse,
+			expected: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(fmt.Sprintf("ShouldCreateSchema case %s", tt.name), func(t *testing.T) {
+			assert.NoError(t, component.ValidateConfig(tt))
+			assert.Equal(t, tt.expected, tt.input.ShouldCreateSchema())
+		})
+	}
+}
+
 func TestTableEngineConfigParsing(t *testing.T) {
 	t.Parallel()
 	cm, err := confmaptest.LoadConf(filepath.Join("testdata", "config.yaml"))

exporter/clickhouseexporter/example/default_ddl/database.sql

@@ -0,0 +1,3 @@
+-- Default database DDL (uses "default" by default, but this is example for non-default database)
+
+CREATE DATABASE IF NOT EXISTS otel;

exporter/clickhouseexporter/example/default_ddl/histogram_metrics.sql

@@ -0,0 +1,42 @@
+-- Default Histogram metrics table DDL
+
+CREATE TABLE IF NOT EXISTS otel_metrics_histogram (
+    ResourceAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+    ResourceSchemaUrl String CODEC(ZSTD(1)),
+    ScopeName String CODEC(ZSTD(1)),
+    ScopeVersion String CODEC(ZSTD(1)),
+    ScopeAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+    ScopeDroppedAttrCount UInt32 CODEC(ZSTD(1)),
+    ScopeSchemaUrl String CODEC(ZSTD(1)),
+    ServiceName LowCardinality(String) CODEC(ZSTD(1)),
+    MetricName String CODEC(ZSTD(1)),
+    MetricDescription String CODEC(ZSTD(1)),
+    MetricUnit String CODEC(ZSTD(1)),
+    Attributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+	StartTimeUnix DateTime64(9) CODEC(Delta, ZSTD(1)),
+	TimeUnix DateTime64(9) CODEC(Delta, ZSTD(1)),
+    Count UInt64 CODEC(Delta, ZSTD(1)),
+    Sum Float64 CODEC(ZSTD(1)),
+    BucketCounts Array(UInt64) CODEC(ZSTD(1)),
+    ExplicitBounds Array(Float64) CODEC(ZSTD(1)),
+	Exemplars Nested (
+		FilteredAttributes Map(LowCardinality(String), String),
+		TimeUnix DateTime64(9),
+		Value Float64,
+		SpanId String,
+		TraceId String
+    ) CODEC(ZSTD(1)),
+    Flags UInt32 CODEC(ZSTD(1)),
+    Min Float64 CODEC(ZSTD(1)),
+    Max Float64 CODEC(ZSTD(1)),
+	INDEX idx_res_attr_key mapKeys(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_res_attr_value mapValues(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_scope_attr_key mapKeys(ScopeAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_scope_attr_value mapValues(ScopeAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_attr_key mapKeys(Attributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_attr_value mapValues(Attributes) TYPE bloom_filter(0.01) GRANULARITY 1
+) ENGINE = MergeTree()
+TTL toDateTime("TimeUnix") + toIntervalDay(180)
+PARTITION BY toDate(TimeUnix)
+ORDER BY (ServiceName, MetricName, Attributes, toUnixTimestamp64Nano(TimeUnix))
+SETTINGS index_granularity=8192, ttl_only_drop_parts = 1;

exporter/clickhouseexporter/example/default_ddl/logs.sql

@@ -0,0 +1,31 @@
+-- Default Logs table DDL
+
+CREATE TABLE IF NOT EXISTS otel_logs (
+	Timestamp DateTime64(9) CODEC(Delta, ZSTD(1)),
+	TraceId String CODEC(ZSTD(1)),
+	SpanId String CODEC(ZSTD(1)),
+	TraceFlags UInt32 CODEC(ZSTD(1)),
+	SeverityText LowCardinality(String) CODEC(ZSTD(1)),
+	SeverityNumber Int32 CODEC(ZSTD(1)),
+	ServiceName LowCardinality(String) CODEC(ZSTD(1)),
+	Body String CODEC(ZSTD(1)),
+	ResourceSchemaUrl String CODEC(ZSTD(1)),
+	ResourceAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+	ScopeSchemaUrl String CODEC(ZSTD(1)),
+	ScopeName String CODEC(ZSTD(1)),
+	ScopeVersion String CODEC(ZSTD(1)),
+	ScopeAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+	LogAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+	INDEX idx_trace_id TraceId TYPE bloom_filter(0.001) GRANULARITY 1,
+	INDEX idx_res_attr_key mapKeys(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_res_attr_value mapValues(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_scope_attr_key mapKeys(ScopeAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_scope_attr_value mapValues(ScopeAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_log_attr_key mapKeys(LogAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_log_attr_value mapValues(LogAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_body Body TYPE tokenbf_v1(32768, 3, 0) GRANULARITY 1
+) ENGINE = MergeTree()
+TTL toDateTime("Timestamp") + toIntervalDay(180)
+PARTITION BY toDate(Timestamp)
+ORDER BY (ServiceName, SeverityText, toUnixTimestamp(Timestamp), TraceId)
+SETTINGS index_granularity=8192, ttl_only_drop_parts = 1;

exporter/clickhouseexporter/example/default_ddl/sum_metrics.sql

@@ -0,0 +1,39 @@
+-- Default Sum metrics table DDL
+
+CREATE TABLE IF NOT EXISTS otel_metrics_sum (
+    ResourceAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+    ResourceSchemaUrl String CODEC(ZSTD(1)),
+    ScopeName String CODEC(ZSTD(1)),
+    ScopeVersion String CODEC(ZSTD(1)),
+    ScopeAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+    ScopeDroppedAttrCount UInt32 CODEC(ZSTD(1)),
+    ScopeSchemaUrl String CODEC(ZSTD(1)),
+    ServiceName LowCardinality(String) CODEC(ZSTD(1)),
+    MetricName String CODEC(ZSTD(1)),
+    MetricDescription String CODEC(ZSTD(1)),
+    MetricUnit String CODEC(ZSTD(1)),
+    Attributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+	StartTimeUnix DateTime64(9) CODEC(Delta, ZSTD(1)),
+	TimeUnix DateTime64(9) CODEC(Delta, ZSTD(1)),
+	Value Float64 CODEC(ZSTD(1)),
+	Flags UInt32  CODEC(ZSTD(1)),
+    Exemplars Nested (
+		FilteredAttributes Map(LowCardinality(String), String),
+		TimeUnix DateTime64(9),
+		Value Float64,
+		SpanId String,
+		TraceId String
+    ) CODEC(ZSTD(1)),
+    AggTemp Int32 CODEC(ZSTD(1)),
+	IsMonotonic Boolean CODEC(Delta, ZSTD(1)),
+	INDEX idx_res_attr_key mapKeys(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_res_attr_value mapValues(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_scope_attr_key mapKeys(ScopeAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_scope_attr_value mapValues(ScopeAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_attr_key mapKeys(Attributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_attr_value mapValues(Attributes) TYPE bloom_filter(0.01) GRANULARITY 1
+) ENGINE = MergeTree()
+TTL toDateTime("TimeUnix") + toIntervalDay(180)
+PARTITION BY toDate(TimeUnix)
+ORDER BY (ServiceName, MetricName, Attributes, toUnixTimestamp64Nano(TimeUnix))
+SETTINGS index_granularity=8192, ttl_only_drop_parts = 1;

exporter/clickhouseexporter/example/default_ddl/summary_metrics.sql

@@ -0,0 +1,35 @@
+-- Default Summary metrics DDL
+
+CREATE TABLE IF NOT EXISTS otel_metrics_summary (
+    ResourceAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+    ResourceSchemaUrl String CODEC(ZSTD(1)),
+    ScopeName String CODEC(ZSTD(1)),
+    ScopeVersion String CODEC(ZSTD(1)),
+    ScopeAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+    ScopeDroppedAttrCount UInt32 CODEC(ZSTD(1)),
+    ScopeSchemaUrl String CODEC(ZSTD(1)),
+    ServiceName LowCardinality(String) CODEC(ZSTD(1)),
+    MetricName String CODEC(ZSTD(1)),
+    MetricDescription String CODEC(ZSTD(1)),
+    MetricUnit String CODEC(ZSTD(1)),
+    Attributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+	StartTimeUnix DateTime64(9) CODEC(Delta, ZSTD(1)),
+	TimeUnix DateTime64(9) CODEC(Delta, ZSTD(1)),
+    Count UInt64 CODEC(Delta, ZSTD(1)),
+    Sum Float64 CODEC(ZSTD(1)),
+    ValueAtQuantiles Nested(
+		Quantile Float64,
+		Value Float64
+	) CODEC(ZSTD(1)),
+    Flags UInt32  CODEC(ZSTD(1)),
+	INDEX idx_res_attr_key mapKeys(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_res_attr_value mapValues(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_scope_attr_key mapKeys(ScopeAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_scope_attr_value mapValues(ScopeAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_attr_key mapKeys(Attributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+	INDEX idx_attr_value mapValues(Attributes) TYPE bloom_filter(0.01) GRANULARITY 1
+) ENGINE = MergeTree()
+TTL toDateTime("TimeUnix") + toIntervalDay(180)
+PARTITION BY toDate(TimeUnix)
+ORDER BY (ServiceName, MetricName, Attributes, toUnixTimestamp64Nano(TimeUnix))
+SETTINGS index_granularity=8192, ttl_only_drop_parts = 1;

exporter/clickhouseexporter/example/default_ddl/traces.sql

@@ -0,0 +1,40 @@
+-- Default Trace table DDL
+
+CREATE TABLE IF NOT EXISTS otel_traces (
+     Timestamp DateTime64(9) CODEC(Delta, ZSTD(1)),
+     TraceId String CODEC(ZSTD(1)),
+     SpanId String CODEC(ZSTD(1)),
+     ParentSpanId String CODEC(ZSTD(1)),
+     TraceState String CODEC(ZSTD(1)),
+     SpanName LowCardinality(String) CODEC(ZSTD(1)),
+     SpanKind LowCardinality(String) CODEC(ZSTD(1)),
+     ServiceName LowCardinality(String) CODEC(ZSTD(1)),
+     ResourceAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+     ScopeName String CODEC(ZSTD(1)),
+     ScopeVersion String CODEC(ZSTD(1)),
+     SpanAttributes Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+     Duration Int64 CODEC(ZSTD(1)),
+     StatusCode LowCardinality(String) CODEC(ZSTD(1)),
+     StatusMessage String CODEC(ZSTD(1)),
+     Events Nested (
+         Timestamp DateTime64(9),
+         Name LowCardinality(String),
+         Attributes Map(LowCardinality(String), String)
+     ) CODEC(ZSTD(1)),
+     Links Nested (
+         TraceId String,
+         SpanId String,
+         TraceState String,
+         Attributes Map(LowCardinality(String), String)
+     ) CODEC(ZSTD(1)),
+     INDEX idx_trace_id TraceId TYPE bloom_filter(0.001) GRANULARITY 1,
+     INDEX idx_res_attr_key mapKeys(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+     INDEX idx_res_attr_value mapValues(ResourceAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+     INDEX idx_span_attr_key mapKeys(SpanAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+     INDEX idx_span_attr_value mapValues(SpanAttributes) TYPE bloom_filter(0.01) GRANULARITY 1,
+     INDEX idx_duration Duration TYPE minmax GRANULARITY 1
+) ENGINE = MergeTree()
+TTL toDateTime("Timestamp") + toIntervalDay(180)
+PARTITION BY toDate(Timestamp)
+ORDER BY (ServiceName, SpanName, toUnixTimestamp(Timestamp), TraceId)
+SETTINGS index_granularity=8192, ttl_only_drop_parts = 1;

exporter/clickhouseexporter/exporter_logs.go

@@ -42,6 +42,10 @@ func newLogsExporter(logger *zap.Logger, cfg *Config) (*logsExporter, error) {
 }
 
 func (e *logsExporter) start(ctx context.Context, _ component.Host) error {
+	if !e.cfg.ShouldCreateSchema() {
+		return nil
+	}
+
 	if err := createDatabase(ctx, e.cfg); err != nil {
 		return err
 	}

exporter/clickhouseexporter/exporter_metrics.go

@@ -37,12 +37,16 @@ func newMetricsExporter(logger *zap.Logger, cfg *Config) (*metricsExporter, erro
 }
 
 func (e *metricsExporter) start(ctx context.Context, _ component.Host) error {
+	internal.SetLogger(e.logger)
+
+	if !e.cfg.ShouldCreateSchema() {
+		return nil
+	}
+
 	if err := createDatabase(ctx, e.cfg); err != nil {
 		return err
 	}
 
-	internal.SetLogger(e.logger)
-
 	ttlExpr := generateTTLExpr(e.cfg.TTLDays, e.cfg.TTL, "TimeUnix")
 	return internal.NewMetricsTable(ctx, e.cfg.MetricsTableName, e.cfg.ClusterString(), e.cfg.TableEngineString(), ttlExpr, e.client)
 }

exporter/clickhouseexporter/exporter_traces.go

@@ -42,6 +42,10 @@ func newTracesExporter(logger *zap.Logger, cfg *Config) (*tracesExporter, error)
 }
 
 func (e *tracesExporter) start(ctx context.Context, _ component.Host) error {
+	if !e.cfg.ShouldCreateSchema() {
+		return nil
+	}
+
 	if err := createDatabase(ctx, e.cfg); err != nil {
 		return err
 	}