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(ingest/databricks): report unique query count from usage #11576

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
+14 −1
Open

feat(ingest/databricks): report unique query count from usage #11576

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f21a846
feat(ingest/databricks): report unique query count from usage
mayurinehate Oct 9, 2024
dbe76f8
Merge branch 'master' into databricks_usage_unique_queries
mayurinehate Oct 10, 2024
88aa990
Merge branch 'master' into databricks_usage_unique_queries
mayurinehate Oct 15, 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
3 changes: 3 additions & 0 deletions metadata-ingestion/src/datahub/ingestion/source/unity/report.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,10 @@
class UnityCatalogUsagePerfReport(Report):
get_queries_timer: PerfTimer = field(default_factory=PerfTimer)
sql_parsing_timer: PerfTimer = field(default_factory=PerfTimer)
spark_sql_parsing_timer: PerfTimer = field(default_factory=PerfTimer)
aggregator_add_event_timer: PerfTimer = field(default_factory=PerfTimer)
gen_operation_timer: PerfTimer = field(default_factory=PerfTimer)
query_fingerprinting_timer: PerfTimer = field(default_factory=PerfTimer)


@dataclass
Expand All @@ -32,6 +34,7 @@ class UnityCatalogReport(IngestionStageReport, ProfilingSqlReport):
num_external_upstreams_unsupported: int = 0

num_queries: int = 0
num_unique_queries: int = 0
num_queries_dropped_parse_failure: int = 0
num_queries_missing_table: int = 0 # Can be due to pattern filter
num_queries_duplicate_table: int = 0
Expand Down
12 changes: 11 additions & 1 deletion metadata-ingestion/src/datahub/ingestion/source/unity/usage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
from datahub.ingestion.source.unity.report import UnityCatalogReport
from datahub.ingestion.source.usage.usage_common import UsageAggregator
from datahub.metadata.schema_classes import OperationClass
from datahub.sql_parsing.sqlglot_utils import get_query_fingerprint

logger = logging.getLogger(__name__)

Expand Down Expand Up @@ -76,6 +77,7 @@ def _get_workunits_internal(
self, table_refs: Set[TableReference]
) -> Iterable[MetadataWorkUnit]:
table_map = defaultdict(list)
query_hashes = set()
for ref in table_refs:
table_map[ref.table].append(ref)
table_map[f"{ref.schema}.{ref.table}"].append(ref)
Expand All @@ -85,6 +87,12 @@ def _get_workunits_internal(
for query in self._get_queries():
self.report.num_queries += 1
with current_timer.pause():
with self.report.usage_perf_report.query_fingerprinting_timer:
query_hashes.add(
get_query_fingerprint(
query.query_text, "databricks", fast=True
)
)
table_info = self._parse_query(query, table_map)
if table_info is not None:
if self.config.include_operational_stats:
Expand All @@ -100,6 +108,7 @@ def _get_workunits_internal(
user=query.user_name,
fields=[],
)
self.report.num_unique_queries = len(query_hashes)

if not self.report.num_queries:
logger.warning("No queries found in the given time range.")
Expand Down Expand Up @@ -166,7 +175,8 @@ def _parse_query(
with self.report.usage_perf_report.sql_parsing_timer:
table_info = self._parse_query_via_lineage_runner(query.query_text)
if table_info is None and query.statement_type == QueryStatementType.SELECT:
table_info = self._parse_query_via_spark_sql_plan(query.query_text)
with self.report.usage_perf_report.spark_sql_parsing_timer:
table_info = self._parse_query_via_spark_sql_plan(query.query_text)

if table_info is None:
self.report.num_queries_dropped_parse_failure += 1
Expand Down
Loading