Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat(meta): Create distributions meta tables #5748

Merged
merged 6 commits into from
Apr 25, 2024
Merged

feat(meta): Create distributions meta tables #5748

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
7544baf
feat(meta): Create distributions meta tables
evanh Apr 10, 2024
4cdaee8
fix storage set
evanh Apr 10, 2024
46622a1
merge
evanh Apr 18, 2024
6526374
Merge branch 'master' into evanh/feat/distributions-meta-tables
evanh Apr 23, 2024
fc5b757
use 0045
evanh Apr 23, 2024
215284f
merge
evanh Apr 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions snuba/migrations/group_loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -325,6 +325,7 @@ def get_migrations(self) -> Sequence[str]:
"0033_counters_meta_tag_values_table",
"0034_counters_meta_tag_values_table_mv",
"0035_recreate_counters_meta_tag_value_table_mv",
"0036_distributions_meta_tables",
]


Expand Down
182 changes: 182 additions & 0 deletions snuba/snuba_migrations/generic_metrics/0036_distributions_meta_tables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,182 @@
from typing import Sequence

from snuba.clickhouse.columns import AggregateFunction, Column, DateTime, String, UInt
from snuba.clusters.storage_sets import StorageSetKey
from snuba.migrations import migration, operations, table_engines
from snuba.migrations.columns import MigrationModifiers as Modifiers
from snuba.migrations.operations import OperationTarget
from snuba.utils.schemas import Float


class Migration(migration.ClickhouseNodeMigration):
blocking = False
granularity = "8192"
meta_view_name = "generic_metric_distributions_meta_mv"
meta_local_table_name = "generic_metric_distributions_meta_local"
meta_dist_table_name = "generic_metric_distributions_meta_dist"
meta_table_columns: Sequence[Column[Modifiers]] = [
Column("org_id", UInt(64)),
Column("project_id", UInt(64)),
Column("use_case_id", String(Modifiers(low_cardinality=True))),
Column("metric_id", UInt(64)),
Column("tag_key", UInt(64)),
Column("timestamp", DateTime(modifiers=Modifiers(codecs=["DoubleDelta"]))),
Column("retention_days", UInt(16)),
Column("count", AggregateFunction("sum", [Float(64)])),
]

tag_value_view_name = "generic_metric_distributions_meta_tag_values_mv"
tag_value_local_table_name = "generic_metric_distributions_meta_tag_values_local"
tag_value_dist_table_name = "generic_metric_distributions_meta_tag_values_dist"
tag_value_table_columns: Sequence[Column[Modifiers]] = [
Column("project_id", UInt(64)),
Column("metric_id", UInt(64)),
Column("tag_key", UInt(64)),
Column("tag_value", String()),
Column("timestamp", DateTime(modifiers=Modifiers(codecs=["DoubleDelta"]))),
Column("retention_days", UInt(16)),
Column("count", AggregateFunction("sum", [Float(64)])),
]

storage_set_key = StorageSetKey.GENERIC_METRICS_DISTRIBUTIONS

def forwards_ops(self) -> Sequence[operations.SqlOperation]:
return [
operations.CreateTable(
storage_set=self.storage_set_key,
table_name=self.meta_local_table_name,
engine=table_engines.AggregatingMergeTree(
storage_set=self.storage_set_key,
order_by="(org_id, project_id, use_case_id, metric_id, tag_key, timestamp)",
primary_key="(org_id, project_id, use_case_id, metric_id, tag_key, timestamp)",
partition_by="(retention_days, toMonday(timestamp))",
settings={"index_granularity": self.granularity},
ttl="timestamp + toIntervalDay(retention_days)",
),
columns=self.meta_table_columns,
target=OperationTarget.LOCAL,
),
operations.CreateTable(
storage_set=self.storage_set_key,
table_name=self.meta_dist_table_name,
engine=table_engines.Distributed(
local_table_name=self.meta_local_table_name, sharding_key=None
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

dist table name?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This setting is telling the Distributed engine which local table to use as the storage node. You can see table_name above has the dist table in it.

),
columns=self.meta_table_columns,
target=OperationTarget.DISTRIBUTED,
),
operations.CreateMaterializedView(
storage_set=self.storage_set_key,
view_name=self.meta_view_name,
columns=self.meta_table_columns,
destination_table_name=self.meta_local_table_name,
target=OperationTarget.LOCAL,
query="""
SELECT
org_id,
project_id,
use_case_id,
metric_id,
tag_key,
toStartOfWeek(timestamp) as timestamp,
retention_days,
sumState(count_value) as count
FROM generic_metric_distributions_raw_local
ARRAY JOIN tags.key AS tag_key
WHERE record_meta = 1
GROUP BY
org_id,
project_id,
use_case_id,
metric_id,
tag_key,
timestamp,
retention_days
""",
),
operations.CreateTable(
storage_set=self.storage_set_key,
table_name=self.tag_value_local_table_name,
engine=table_engines.AggregatingMergeTree(
storage_set=self.storage_set_key,
order_by="(project_id, metric_id, tag_key, tag_value, timestamp)",
primary_key="(project_id, metric_id, tag_key, tag_value, timestamp)",
partition_by="(retention_days, toMonday(timestamp))",
settings={"index_granularity": self.granularity},
ttl="timestamp + toIntervalDay(retention_days)",
),
columns=self.tag_value_table_columns,
target=OperationTarget.LOCAL,
),
operations.CreateTable(
storage_set=self.storage_set_key,
table_name=self.tag_value_dist_table_name,
engine=table_engines.Distributed(
local_table_name=self.tag_value_local_table_name, sharding_key=None
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

dist table name?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

See above.

),
columns=self.tag_value_table_columns,
target=OperationTarget.DISTRIBUTED,
),
operations.CreateMaterializedView(
storage_set=self.storage_set_key,
view_name=self.tag_value_view_name,
columns=self.tag_value_table_columns,
destination_table_name=self.tag_value_local_table_name,
target=OperationTarget.LOCAL,
query="""
SELECT
project_id,
metric_id,
tag_key,
tag_value,
toStartOfWeek(timestamp) as timestamp,
retention_days,
sumState(count_value) as count
FROM generic_metric_distributions_raw_local
ARRAY JOIN
tags.key AS tag_key, tags.raw_value AS tag_value
WHERE record_meta = 1
GROUP BY
project_id,
metric_id,
tag_key,
tag_value,
timestamp,
retention_days
""",
),
]

def backwards_ops(self) -> Sequence[operations.SqlOperation]:
return [
operations.DropTable(
storage_set=self.storage_set_key,
table_name=self.tag_value_view_name,
target=OperationTarget.LOCAL,
),
operations.DropTable(
storage_set=self.storage_set_key,
table_name=self.tag_value_dist_table_name,
target=OperationTarget.DISTRIBUTED,
),
operations.DropTable(
storage_set=self.storage_set_key,
table_name=self.tag_value_local_table_name,
target=OperationTarget.LOCAL,
),
operations.DropTable(
storage_set=self.storage_set_key,
table_name=self.meta_view_name,
target=OperationTarget.LOCAL,
),
operations.DropTable(
storage_set=self.storage_set_key,
table_name=self.meta_dist_table_name,
target=OperationTarget.DISTRIBUTED,
),
operations.DropTable(
storage_set=self.storage_set_key,
table_name=self.meta_local_table_name,
target=OperationTarget.LOCAL,
),
]
Loading