Skip to content

bugfix: refactor generation of spark_history_url #44

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

Merged
mwc360 merged 2 commits into from
Sep 4, 2025
Merged

bugfix: refactor generation of spark_history_url #44

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9c2570a
Refactor spark_history_url construction with parsed values
mwc360 Sep 4, 2025
cdbd950
Bump version from 0.9.0 to 0.9.1
mwc360 Sep 4, 2025
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
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

[project]
name = "lakebench"
version = "0.9.0"
version = "0.9.1"
authors = [
{ name="Miles Cole" },
]
Expand Down
19 changes: 17 additions & 2 deletions src/lakebench/engines/fabric_spark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
from .spark import Spark
from typing import Optional
from decimal import Decimal
import re
from urllib.parse import urlparse, parse_qs

try:
from IPython.core.getipython import get_ipython
Expand Down Expand Up @@ -39,8 +41,19 @@ def __init__(
self.cost_per_vcore_hour = cost_per_vcore_hour or getattr(self, '_FABRIC_USD_COST_PER_VCORE_HOUR', None)
self.cost_per_hour = self.get_total_cores() * self.cost_per_vcore_hour

url = self.spark.sparkContext.uiWebUrl
# Parse webUrl string
parsed = urlparse(url)
query = parse_qs(parsed.query)
artifact_id = query.get("artifactId", [None])[0]
# Regex for GUIDs
guid_pattern = re.compile(r"[0-9a-fA-F-]{36}")
guids = guid_pattern.findall(url)
tenant_id = guids[0] # after /sparkui/
activity_id = guids[2] # after /activities/

self.extended_engine_metadata.update({
'spark_history_url': f"https://{self.spark_configs['spark.trident.pbienv'].lower()}.powerbi.com/workloads/de-ds/sparkmonitor/{self.spark_configs['spark.hadoop.trident.artifact.id']}/{self.spark_configs['spark.hadoop.trident.activity.id']}?ctid={self.spark_configs['spark.hadoop.trident.tenant.id']}",
'spark_history_url': f"https://{self.spark_configs['spark.trident.pbienv'].lower()}.powerbi.com/workloads/de-ds/sparkmonitor/{artifact_id}/{activity_id}?ctid={tenant_id}",
'cost_per_hour': Decimal(self.cost_per_hour).quantize(Decimal('0.0000')),
'capacity_id': self.capacity_id
})
Expand All @@ -60,6 +73,8 @@ def __init__(
'spark.microsoft.delta.stats.injection.enabled',
'spark.microsoft.delta.snapshot.driverMode.enabled',
'spark.microsoft.delta.stats.collect.extended.property.setAtTableCreation',
'spark.microsoft.delta.targetFileSize.adaptive.enabled',
'spark.sql.parquet.compression.codec',
'spark.app.id',
'spark.cluster.name'
]}
Expand All @@ -72,4 +87,4 @@ def __init__(
# Enable auto stats collection
self.spark.conf.set("spark.microsoft.delta.stats.collect.extended", "true")
self.spark.conf.set("spark.microsoft.delta.stats.injection.enabled", "true")
self.spark.conf.set("spark.microsoft.delta.stats.collect.extended.property.setAtTableCreation", "true")
self.spark.conf.set("spark.microsoft.delta.stats.collect.extended.property.setAtTableCreation", "true")