Skip to content

Add disk size as Dataflow Job Configuration #841

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
feast-ci-bot merged 1 commit into from
Jun 30, 2020
Merged

Add disk size as Dataflow Job Configuration #841

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 4 additions & 0 deletions core/src/main/java/feast/core/job/dataflow/DataflowRunnerConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ public DataflowRunnerConfig(DataflowRunnerConfigOptions runnerConfigOptions) {
this.tempLocation = runnerConfigOptions.getTempLocation();
this.maxNumWorkers = runnerConfigOptions.getMaxNumWorkers();
this.deadLetterTableSpec = runnerConfigOptions.getDeadLetterTableSpec();
this.diskSizeGb = runnerConfigOptions.getDiskSizeGb();
this.labels = runnerConfigOptions.getLabelsMap();
validate();
}
Expand Down Expand Up @@ -85,6 +86,9 @@ public DataflowRunnerConfig(DataflowRunnerConfigOptions runnerConfigOptions) {
/* BigQuery table specification, e.g. PROJECT_ID:DATASET_ID.PROJECT_ID */
public String deadLetterTableSpec;

/* Disk size to use on each remote Compute Engine worker instance */
public Integer diskSizeGb;

public Map<String, String> labels;

/** Validates Dataflow runner configuration options */
Expand Down
38 changes: 38 additions & 0 deletions core/src/test/java/feast/core/job/dataflow/DataflowRunnerConfigTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ public void shouldConvertToPipelineArgs() throws IllegalAccessException {
.setUsePublicIps(false)
.setWorkerMachineType("n1-standard-1")
.setDeadLetterTableSpec("project_id:dataset_id.table_id")
.setDiskSizeGb(100)
.putLabels("key", "value")
.build();

Expand All @@ -60,9 +61,46 @@ public void shouldConvertToPipelineArgs() throws IllegalAccessException {
"--usePublicIps=false",
"--workerMachineType=n1-standard-1",
"--deadLetterTableSpec=project_id:dataset_id.table_id",
"--diskSizeGb=100",
"--labels={\"key\":\"value\"}")
.toArray(String[]::new);
assertThat(args.size(), equalTo(expectedArgs.length));
assertThat(args, containsInAnyOrder(expectedArgs));
}

@Test
public void shouldIgnoreOptionalArguments() throws IllegalAccessException {
DataflowRunnerConfigOptions opts =
DataflowRunnerConfigOptions.newBuilder()
.setProject("my-project")
.setRegion("asia-east1")
.setZone("asia-east1-a")
.setTempLocation("gs://bucket/tempLocation")
.setNetwork("default")
.setSubnetwork("regions/asia-east1/subnetworks/mysubnetwork")
.setMaxNumWorkers(1)
.setAutoscalingAlgorithm("THROUGHPUT_BASED")
.setUsePublicIps(false)
.setWorkerMachineType("n1-standard-1")
.build();

DataflowRunnerConfig dataflowRunnerConfig = new DataflowRunnerConfig(opts);
List<String> args = Lists.newArrayList(dataflowRunnerConfig.toArgs());
String[] expectedArgs =
Arrays.asList(
"--project=my-project",
"--region=asia-east1",
"--zone=asia-east1-a",
"--tempLocation=gs://bucket/tempLocation",
"--network=default",
"--subnetwork=regions/asia-east1/subnetworks/mysubnetwork",
"--maxNumWorkers=1",
"--autoscalingAlgorithm=THROUGHPUT_BASED",
"--usePublicIps=false",
"--workerMachineType=n1-standard-1",
"--labels={}")
.toArray(String[]::new);
assertThat(args.size(), equalTo(expectedArgs.length));
assertThat(args, containsInAnyOrder(expectedArgs));
}
}
4 changes: 4 additions & 0 deletions protos/feast/core/Runner.proto
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,4 +77,8 @@ message DataflowRunnerConfigOptions {

/* Labels to apply to the dataflow job */
map<string, string> labels = 13;

/* Disk size to use on each remote Compute Engine worker instance */
int32 diskSizeGb = 14;

}