mirror of
https://github.com/GreptimeTeam/greptimedb.git
synced 2026-10-17 17:32:30 +00:00
LFCandshuiyisong
456babbd18
feat(catalog): declare information-schema table scopes (#9504)
* feat(catalog): declare information-schema table scopes
* chore: rename cluster to global
* fix: update sqlness result
* refactor(catalog): require information-schema table scopes
---------
(cherry picked from commit 2df33380a7)
Signed-off-by: shuiyisong <xixing.sys@gmail.com>
Co-authored-by: shuiyisong <113876041+shuiyisong@users.noreply.github.com>
370 lines
18 KiB
Plaintext
370 lines
18 KiB
Plaintext
DESC TABLE information_schema.table_semantics;
|
|
|
|
+---------------------+--------+-----+------+---------+---------------+
|
|
| Column | Type | Key | Null | Default | Semantic Type |
|
|
+---------------------+--------+-----+------+---------+---------------+
|
|
| table_catalog | String | | NO | | FIELD |
|
|
| table_schema | String | | NO | | FIELD |
|
|
| table_name | String | | NO | | FIELD |
|
|
| table_id | UInt32 | | NO | | FIELD |
|
|
| signal_type | String | | YES | | FIELD |
|
|
| source | String | | YES | | FIELD |
|
|
| source_version | String | | YES | | FIELD |
|
|
| pipeline | String | | YES | | FIELD |
|
|
| metadata_quality | String | | YES | | FIELD |
|
|
| semantic_options | String | | YES | | FIELD |
|
|
| entity_declarations | String | | YES | | FIELD |
|
|
+---------------------+--------+-----+------+---------+---------------+
|
|
|
|
CREATE TABLE metrics_tagged (
|
|
ts TIMESTAMP TIME INDEX,
|
|
val DOUBLE,
|
|
)
|
|
WITH (
|
|
'greptime.semantic.signal_type' = 'metric',
|
|
'greptime.semantic.source' = 'opentelemetry',
|
|
'greptime.semantic.source_version' = '2.0',
|
|
'greptime.semantic.pipeline' = 'greptime_metric_v1',
|
|
'greptime.semantic.metric.metadata_quality' = 'declared',
|
|
'greptime.semantic.metric.type' = 'counter',
|
|
'greptime.semantic.metric.unit' = 'By'
|
|
);
|
|
|
|
Affected Rows: 0
|
|
|
|
CREATE TABLE traces_tagged (
|
|
ts TIMESTAMP TIME INDEX,
|
|
span_name STRING,
|
|
)
|
|
WITH (
|
|
'greptime.semantic.signal_type' = 'trace',
|
|
'greptime.semantic.source' = 'opentelemetry',
|
|
'greptime.semantic.trace.conventions' = 'https://opentelemetry.io/schemas/1.27.0'
|
|
);
|
|
|
|
Affected Rows: 0
|
|
|
|
-- A table with no semantic options must not appear in the view.
|
|
CREATE TABLE plain_table (
|
|
ts TIMESTAMP TIME INDEX,
|
|
val DOUBLE,
|
|
);
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_schema, table_name, signal_type, source, source_version, pipeline, metadata_quality, semantic_options
|
|
FROM information_schema.table_semantics
|
|
WHERE table_schema = 'public'
|
|
ORDER BY table_name;
|
|
|
|
+--------------+----------------+-------------+---------------+----------------+--------------------+------------------+-----------------------------------------------------------------+
|
|
| table_schema | table_name | signal_type | source | source_version | pipeline | metadata_quality | semantic_options |
|
|
+--------------+----------------+-------------+---------------+----------------+--------------------+------------------+-----------------------------------------------------------------+
|
|
| public | metrics_tagged | metric | opentelemetry | 2.0 | greptime_metric_v1 | declared | {"metric.type":"counter","metric.unit":"By"} |
|
|
| public | traces_tagged | trace | opentelemetry | | | | {"trace.conventions":"https://opentelemetry.io/schemas/1.27.0"} |
|
|
+--------------+----------------+-------------+---------------+----------------+--------------------+------------------+-----------------------------------------------------------------+
|
|
|
|
-- System table scope is exposed without changing the view's columns.
|
|
SELECT table_name, semantic_options
|
|
FROM information_schema.table_semantics
|
|
WHERE table_schema = 'information_schema'
|
|
AND table_name IN ('build_info', 'partitions', 'process_list', 'table_semantics')
|
|
ORDER BY table_name;
|
|
|
|
+-----------------+---------------------------+
|
|
| table_name | semantic_options |
|
|
+-----------------+---------------------------+
|
|
| build_info | {"table_scope":"global"} |
|
|
| partitions | {"table_scope":"catalog"} |
|
|
| process_list | {"table_scope":"global"} |
|
|
| table_semantics | {"table_scope":"catalog"} |
|
|
+-----------------+---------------------------+
|
|
|
|
-- Predicate pushdown on a promoted column.
|
|
SELECT table_name, signal_type
|
|
FROM information_schema.table_semantics
|
|
WHERE signal_type = 'metric'
|
|
ORDER BY table_name;
|
|
|
|
+----------------+-------------+
|
|
| table_name | signal_type |
|
|
+----------------+-------------+
|
|
| metrics_tagged | metric |
|
|
+----------------+-------------+
|
|
|
|
DROP TABLE metrics_tagged;
|
|
|
|
Affected Rows: 0
|
|
|
|
DROP TABLE traces_tagged;
|
|
|
|
Affected Rows: 0
|
|
|
|
DROP TABLE plain_table;
|
|
|
|
Affected Rows: 0
|
|
|
|
-- ALTER TABLE manages semantic declarations on existing tables: SET appears in
|
|
-- the view, UNSET disappears from it.
|
|
CREATE TABLE altered_semantics (
|
|
ts TIMESTAMP TIME INDEX,
|
|
svc STRING,
|
|
payload BINARY,
|
|
val DOUBLE,
|
|
);
|
|
|
|
Affected Rows: 0
|
|
|
|
ALTER TABLE altered_semantics SET 'greptime.semantic.signal_type' = 'metric', 'greptime.semantic.entity.service.id' = 'svc';
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, signal_type, semantic_options
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'altered_semantics';
|
|
|
|
+-------------------+-------------+-----------------------------+
|
|
| table_name | signal_type | semantic_options |
|
|
+-------------------+-------------+-----------------------------+
|
|
| altered_semantics | metric | {"entity.service.id":"svc"} |
|
|
+-------------------+-------------+-----------------------------+
|
|
|
|
-- Semantic options never share a statement with regular table options.
|
|
ALTER TABLE altered_semantics SET 'greptime.semantic.source' = 'prometheus', 'ttl' = '7d';
|
|
|
|
Error: 1004(InvalidArguments), Invalid table option request: `greptime.semantic.*` options must be altered separately from other table options
|
|
|
|
-- Unknown semantic keys are rejected on SET.
|
|
ALTER TABLE altered_semantics SET 'greptime.semantic.nonsense' = 'x';
|
|
|
|
Error: 1004(InvalidArguments), Invalid alter table(altered_semantics) request: unknown semantic option `greptime.semantic.nonsense`
|
|
|
|
-- Values outside the key's domain are rejected.
|
|
ALTER TABLE altered_semantics SET 'greptime.semantic.signal_type' = 'garbage';
|
|
|
|
Error: 1004(InvalidArguments), Invalid alter table(altered_semantics) request: invalid value `garbage` for semantic option `greptime.semantic.signal_type`
|
|
|
|
-- Entity columns must exist.
|
|
ALTER TABLE altered_semantics SET 'greptime.semantic.entity.host.id' = 'no_such_column';
|
|
|
|
Error: 4002(TableColumnNotFound), Column no_such_column not exists in table altered_semantics
|
|
|
|
-- Entity columns must render as strings.
|
|
ALTER TABLE altered_semantics SET 'greptime.semantic.entity.host.id' = 'payload';
|
|
|
|
Error: 1004(InvalidArguments), Invalid alter table(altered_semantics) request: entity column `payload` (option `greptime.semantic.entity.host.id`) has type `Binary`, which cannot render as a string
|
|
|
|
ALTER TABLE altered_semantics UNSET 'greptime.semantic.entity.service.id';
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, signal_type, semantic_options
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'altered_semantics';
|
|
|
|
+-------------------+-------------+------------------+
|
|
| table_name | signal_type | semantic_options |
|
|
+-------------------+-------------+------------------+
|
|
| altered_semantics | metric | |
|
|
+-------------------+-------------+------------------+
|
|
|
|
DROP TABLE altered_semantics;
|
|
|
|
Affected Rows: 0
|
|
|
|
-- Logical metric tables take the same metadata-only path.
|
|
CREATE TABLE phy_sem (ts TIMESTAMP TIME INDEX, val DOUBLE) engine=metric with ("physical_metric_table" = "");
|
|
|
|
Affected Rows: 0
|
|
|
|
CREATE TABLE logical_sem (ts TIMESTAMP TIME INDEX, val DOUBLE, host STRING PRIMARY KEY) engine=metric with ("on_physical_table" = "phy_sem");
|
|
|
|
Affected Rows: 0
|
|
|
|
ALTER TABLE logical_sem SET 'greptime.semantic.signal_type' = 'metric', 'greptime.semantic.entity.host.id' = 'host';
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, signal_type, semantic_options
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'logical_sem';
|
|
|
|
+-------------+-------------+---------------------------+
|
|
| table_name | signal_type | semantic_options |
|
|
+-------------+-------------+---------------------------+
|
|
| logical_sem | metric | {"entity.host.id":"host"} |
|
|
+-------------+-------------+---------------------------+
|
|
|
|
-- Regular options still cannot be altered on logical tables.
|
|
ALTER TABLE logical_sem SET 'ttl' = '7d';
|
|
|
|
Error: 1004(InvalidArguments), Alter logical tables invalid arguments: Only support add columns operation
|
|
|
|
ALTER TABLE logical_sem UNSET 'greptime.semantic.entity.host.id';
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, signal_type, semantic_options
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'logical_sem';
|
|
|
|
+-------------+-------------+------------------+
|
|
| table_name | signal_type | semantic_options |
|
|
+-------------+-------------+------------------+
|
|
| logical_sem | metric | |
|
|
+-------------+-------------+------------------+
|
|
|
|
DROP TABLE logical_sem;
|
|
|
|
Affected Rows: 0
|
|
|
|
DROP TABLE phy_sem;
|
|
|
|
Affected Rows: 0
|
|
|
|
-- entity_declarations reports what a table actually contributes to the graph,
|
|
-- including the declarations the built-in conventions derive. A whitelisted
|
|
-- OTel descriptor table declares its entities without any entity option, and
|
|
-- the generic container records the identity it yields to.
|
|
CREATE TABLE greptime_otel_resource_info (
|
|
greptime_timestamp TIMESTAMP TIME INDEX,
|
|
greptime_value DOUBLE,
|
|
"job" STRING,
|
|
"instance" STRING,
|
|
"service.name" STRING,
|
|
"host.id" STRING,
|
|
"container.id" STRING,
|
|
"container.name" STRING,
|
|
"k8s.pod.uid" STRING,
|
|
"k8s.pod.name" STRING,
|
|
"k8s.container.name" STRING,
|
|
PRIMARY KEY ("job", "instance", "service.name", "host.id", "container.id", "container.name", "k8s.pod.uid", "k8s.pod.name", "k8s.container.name")
|
|
)
|
|
WITH (
|
|
'greptime.semantic.signal_type' = 'metric',
|
|
'greptime.semantic.source' = 'opentelemetry',
|
|
'greptime.semantic.metric.type' = 'info'
|
|
);
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, entity_declarations
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'greptime_otel_resource_info';
|
|
|
|
+-----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
| table_name | entity_declarations |
|
|
+-----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
| greptime_otel_resource_info | [{"entity_type":"container","origin":"convention","id":["container.id"],"superseded_by":["k8s.pod.uid","k8s.container.name"],"descriptive":["container.name"]},{"entity_type":"host","origin":"convention","id":["host.id"]},{"entity_type":"k8s.container","origin":"convention","id":["k8s.pod.uid","k8s.container.name"],"descriptive":["container.id","container.name"]},{"entity_type":"k8s.pod","origin":"convention","id":["k8s.pod.uid"],"descriptive":["k8s.pod.name"]},{"entity_type":"service","origin":"convention","id":["job"],"descriptive":["service.name"]},{"entity_type":"service.instance","origin":"convention","id":["job","instance"]}] |
|
|
+-----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
|
|
-- The same table under the wrong source stamp derives nothing: the column is
|
|
-- empty and `source` names the reason.
|
|
CREATE TABLE kube_pod_info (
|
|
greptime_timestamp TIMESTAMP TIME INDEX,
|
|
greptime_value DOUBLE,
|
|
"namespace" STRING,
|
|
"pod" STRING,
|
|
"uid" STRING,
|
|
"node" STRING,
|
|
PRIMARY KEY ("namespace", "pod", "uid", "node")
|
|
)
|
|
WITH (
|
|
'greptime.semantic.signal_type' = 'metric',
|
|
'greptime.semantic.source' = 'influxdb'
|
|
);
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, source, entity_declarations
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'kube_pod_info';
|
|
|
|
+---------------+----------+---------------------+
|
|
| table_name | source | entity_declarations |
|
|
+---------------+----------+---------------------+
|
|
| kube_pod_info | influxdb | |
|
|
+---------------+----------+---------------------+
|
|
|
|
ALTER TABLE kube_pod_info SET 'greptime.semantic.source' = 'prometheus';
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, source, entity_declarations
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'kube_pod_info';
|
|
|
|
+---------------+------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
| table_name | source | entity_declarations |
|
|
+---------------+------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
| kube_pod_info | prometheus | [{"entity_type":"k8s.node","origin":"convention","id":["node"]},{"entity_type":"k8s.pod","origin":"convention","id":["uid"],"descriptive":["namespace","pod","node"]}] |
|
|
+---------------+------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
|
|
DROP TABLE greptime_otel_resource_info;
|
|
|
|
Affected Rows: 0
|
|
|
|
DROP TABLE kube_pod_info;
|
|
|
|
Affected Rows: 0
|
|
|
|
-- A missing id column drops that entity alone: without `uid` there is no
|
|
-- k8s.pod, and the k8s.node next to it still lands.
|
|
CREATE TABLE kube_pod_info (
|
|
greptime_timestamp TIMESTAMP TIME INDEX,
|
|
greptime_value DOUBLE,
|
|
"namespace" STRING,
|
|
"pod" STRING,
|
|
"node" STRING,
|
|
PRIMARY KEY ("namespace", "pod", "node")
|
|
)
|
|
WITH (
|
|
'greptime.semantic.signal_type' = 'metric',
|
|
'greptime.semantic.source' = 'prometheus'
|
|
);
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, entity_declarations
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'kube_pod_info';
|
|
|
|
+---------------+------------------------------------------------------------------+
|
|
| table_name | entity_declarations |
|
|
+---------------+------------------------------------------------------------------+
|
|
| kube_pod_info | [{"entity_type":"k8s.node","origin":"convention","id":["node"]}] |
|
|
+---------------+------------------------------------------------------------------+
|
|
|
|
DROP TABLE kube_pod_info;
|
|
|
|
Affected Rows: 0
|
|
|
|
-- A trace table carries no semantic option at all, yet the conventions derive
|
|
-- its entities: it must still be visible here, or the view cannot answer why
|
|
-- it is in the graph.
|
|
CREATE TABLE traces_untagged (
|
|
"timestamp" TIMESTAMP(9) TIME INDEX,
|
|
trace_id STRING,
|
|
span_id STRING,
|
|
service_name STRING,
|
|
"resource_attributes.host.id" STRING,
|
|
PRIMARY KEY (service_name)
|
|
) WITH ('table_data_model' = 'greptime_trace_v1', 'append_mode' = 'true');
|
|
|
|
Affected Rows: 0
|
|
|
|
SELECT table_name, signal_type, semantic_options, entity_declarations
|
|
FROM information_schema.table_semantics
|
|
WHERE table_name = 'traces_untagged';
|
|
|
|
+-----------------+-------------+------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
| table_name | signal_type | semantic_options | entity_declarations |
|
|
+-----------------+-------------+------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
| traces_untagged | | | [{"entity_type":"host","origin":"convention","id":["resource_attributes.host.id"]},{"entity_type":"service","origin":"convention","id":["service_name"]}] |
|
|
+-----------------+-------------+------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------+
|
|
|
|
DROP TABLE traces_untagged;
|
|
|
|
Affected Rows: 0
|
|
|