Skip to content

Scope shared TestDataflowRunner staging directory by UTC date #41258

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

Draft
damccorm wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

Scope shared TestDataflowRunner staging directory by UTC date #41258

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
b7809c2
Re-stage Dataflow packages older than 1 day in PackageUtil
damccorm Nov 13, 2026
66f1bd7
Merge remote-tracking branch 'upstream/master' into fix/dataflow-pack…
damccorm Nov 13, 2026
524a9ee
Scope shared TestDataflowRunner staging directory by UTC date instead…
damccorm Nov 13, 2026
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
21 changes: 19 additions & 2 deletions ...loud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/TestDataflowRunner.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,8 @@
import java.io.File;
import java.io.IOException;
import java.math.BigDecimal;
import java.time.LocalDate;
import java.time.ZoneOffset;
import java.util.List;
import java.util.Map;
import java.util.concurrent.Callable;
Expand Down Expand Up @@ -70,6 +72,10 @@
})
public class TestDataflowRunner extends PipelineRunner<DataflowPipelineJob> {
private static final String TENTATIVE_COUNTER = "tentative";

@VisibleForTesting
static final String DAILY_STAGING_DIR = "staging-" + LocalDate.now(ZoneOffset.UTC);

static final String MAX_CONCURRENT_STANDALONE_JOBS_PROPERTY =
"beam.dataflow.maxConcurrentStandaloneJobs";
private static final int DEFAULT_MAX_CONCURRENT_STANDALONE_JOBS = 12;
Expand Down Expand Up @@ -148,9 +154,20 @@ public static TestDataflowRunner fromOptions(PipelineOptions options) {
dataflowOptions.setTempLocation(tempLocation);
String defaultPerJobStagingLocation =
FileSystems.matchNewDirectory(tempLocation, "staging").toString();
if (defaultPerJobStagingLocation.equals(dataflowOptions.getStagingLocation())) {
String unversionedSharedStagingLocation =
FileSystems.matchNewDirectory(dataflowOptions.getTempRoot(), "staging").toString();
String rawStagingLocation = dataflowOptions.getStagingLocation();
String configuredStagingLocation =
rawStagingLocation != null
? FileSystems.matchNewDirectory(rawStagingLocation).toString()
: null;
// Scope shared test staging directories by UTC date so tests running on the same day reuse
// staged JARs without referencing objects near the 7-day GCS lifecycle deletion threshold.
if (defaultPerJobStagingLocation.equals(configuredStagingLocation)
|| unversionedSharedStagingLocation.equals(configuredStagingLocation)) {
dataflowOptions.setStagingLocation(
FileSystems.matchNewDirectory(dataflowOptions.getTempRoot(), "staging").toString());
FileSystems.matchNewDirectory(dataflowOptions.getTempRoot(), DAILY_STAGING_DIR)
.toString());
}

return new TestDataflowRunner(
Expand Down
14 changes: 13 additions & 1 deletion ...-dataflow-java/src/test/java/org/apache/beam/runners/dataflow/TestDataflowRunnerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,19 @@ public void testFromOptionsUsesSharedStagingLocationUnderTempRoot() {
TestDataflowRunner.fromOptions(options);
assertEquals("gs://test/test-job-1/output/results", options.getTempLocation());
assertEquals("gs://test/test-job-1/output/results", options.getGcpTempLocation());
assertEquals("gs://test/staging/", options.getStagingLocation());
assertEquals(
"gs://test/" + TestDataflowRunner.DAILY_STAGING_DIR + "/", options.getStagingLocation());
}

@Test
public void testFromOptionsScopesUnversionedTempRootStagingLocationByDate() {
options.setJobName("test-job-unversioned-staging");
options.setStagingLocation("gs://test/staging");
TestDataflowRunner.fromOptions(options);
assertEquals(
"gs://test/test-job-unversioned-staging/output/results", options.getTempLocation());
assertEquals(
"gs://test/" + TestDataflowRunner.DAILY_STAGING_DIR + "/", options.getStagingLocation());
}

@Test
Expand Down
Loading