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.

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

Add autotuning_config and cohort fields for Dataproc batch #20410

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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 .changelog/12357.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
```release-note:enhancement
dataproc: added `autotuning_config` and `cohort` fields to `google_dataproc_batch`
```
95 changes: 95 additions & 0 deletions google/services/dataproc/resource_dataproc_batch.go
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@ import (

"github.com/hashicorp/terraform-provider-google/google/tpgresource"
transport_tpg "github.com/hashicorp/terraform-provider-google/google/transport"
"github.com/hashicorp/terraform-provider-google/google/verify"
)

/*
Expand Down Expand Up @@ -285,6 +286,34 @@ Supported file types: .py, .egg, and .zip.`,
MaxItems: 1,
Elem: &schema.Resource{
Schema: map[string]*schema.Schema{
"autotuning_config": {
Type: schema.TypeList,
Optional: true,
ForceNew: true,
Description: `Optional. Autotuning configuration of the workload.`,
MaxItems: 1,
Elem: &schema.Resource{
Schema: map[string]*schema.Schema{
"scenarios": {
Type: schema.TypeList,
Optional: true,
ForceNew: true,
Description: `Optional. Scenarios for which tunings are applied. Possible values: ["SCALING", "BROADCAST_HASH_JOIN", "MEMORY"]`,
Elem: &schema.Schema{
Type: schema.TypeString,
ValidateFunc: verify.ValidateEnum([]string{"SCALING", "BROADCAST_HASH_JOIN", "MEMORY"}),
},
RequiredWith: []string{"runtime_config.0.cohort"},
},
},
},
},
"cohort": {
Type: schema.TypeString,
Optional: true,
ForceNew: true,
Description: `Optional. Cohort identifier. Identifies families of the workloads having the same shape, e.g. daily ETL jobs.`,
},
"container_image": {
Type: schema.TypeString,
Optional: true,
Expand Down Expand Up @@ -1132,6 +1161,10 @@ func flattenDataprocBatchRuntimeConfig(v interface{}, d *schema.ResourceData, co
flattenDataprocBatchRuntimeConfigProperties(original["properties"], d, config)
transformed["effective_properties"] =
flattenDataprocBatchRuntimeConfigEffectiveProperties(original["effective_properties"], d, config)
transformed["autotuning_config"] =
flattenDataprocBatchRuntimeConfigAutotuningConfig(original["autotuningConfig"], d, config)
transformed["cohort"] =
flattenDataprocBatchRuntimeConfigCohort(original["cohort"], d, config)
return []interface{}{transformed}
}
func flattenDataprocBatchRuntimeConfigVersion(v interface{}, d *schema.ResourceData, config *transport_tpg.Config) interface{} {
Expand All @@ -1150,6 +1183,27 @@ func flattenDataprocBatchRuntimeConfigEffectiveProperties(v interface{}, d *sche
return v
}

func flattenDataprocBatchRuntimeConfigAutotuningConfig(v interface{}, d *schema.ResourceData, config *transport_tpg.Config) interface{} {
if v == nil {
return nil
}
original := v.(map[string]interface{})
if len(original) == 0 {
return nil
}
transformed := make(map[string]interface{})
transformed["scenarios"] =
flattenDataprocBatchRuntimeConfigAutotuningConfigScenarios(original["scenarios"], d, config)
return []interface{}{transformed}
}
func flattenDataprocBatchRuntimeConfigAutotuningConfigScenarios(v interface{}, d *schema.ResourceData, config *transport_tpg.Config) interface{} {
return v
}

func flattenDataprocBatchRuntimeConfigCohort(v interface{}, d *schema.ResourceData, config *transport_tpg.Config) interface{} {
return v
}

func flattenDataprocBatchEnvironmentConfig(v interface{}, d *schema.ResourceData, config *transport_tpg.Config) interface{} {
if v == nil {
return nil
Expand Down Expand Up @@ -1501,6 +1555,20 @@ func expandDataprocBatchRuntimeConfig(v interface{}, d tpgresource.TerraformReso
transformed["effective_properties"] = transformedEffectiveProperties
}

transformedAutotuningConfig, err := expandDataprocBatchRuntimeConfigAutotuningConfig(original["autotuning_config"], d, config)
if err != nil {
return nil, err
} else if val := reflect.ValueOf(transformedAutotuningConfig); val.IsValid() && !tpgresource.IsEmptyValue(val) {
transformed["autotuningConfig"] = transformedAutotuningConfig
}

transformedCohort, err := expandDataprocBatchRuntimeConfigCohort(original["cohort"], d, config)
if err != nil {
return nil, err
} else if val := reflect.ValueOf(transformedCohort); val.IsValid() && !tpgresource.IsEmptyValue(val) {
transformed["cohort"] = transformedCohort
}

return transformed, nil
}

Expand Down Expand Up @@ -1534,6 +1602,33 @@ func expandDataprocBatchRuntimeConfigEffectiveProperties(v interface{}, d tpgres
return m, nil
}

func expandDataprocBatchRuntimeConfigAutotuningConfig(v interface{}, d tpgresource.TerraformResourceData, config *transport_tpg.Config) (interface{}, error) {
l := v.([]interface{})
if len(l) == 0 || l[0] == nil {
return nil, nil
}
raw := l[0]
original := raw.(map[string]interface{})
transformed := make(map[string]interface{})

transformedScenarios, err := expandDataprocBatchRuntimeConfigAutotuningConfigScenarios(original["scenarios"], d, config)
if err != nil {
return nil, err
} else if val := reflect.ValueOf(transformedScenarios); val.IsValid() && !tpgresource.IsEmptyValue(val) {
transformed["scenarios"] = transformedScenarios
}

return transformed, nil
}

func expandDataprocBatchRuntimeConfigAutotuningConfigScenarios(v interface{}, d tpgresource.TerraformResourceData, config *transport_tpg.Config) (interface{}, error) {
return v, nil
}

func expandDataprocBatchRuntimeConfigCohort(v interface{}, d tpgresource.TerraformResourceData, config *transport_tpg.Config) (interface{}, error) {
return v, nil
}

func expandDataprocBatchEnvironmentConfig(v interface{}, d tpgresource.TerraformResourceData, config *transport_tpg.Config) (interface{}, error) {
l := v.([]interface{})
if len(l) == 0 || l[0] == nil {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -406,6 +406,67 @@ resource "google_dataproc_batch" "example_batch_sparkr" {
`, context)
}

func TestAccDataprocBatch_dataprocBatchAutotuningExample(t *testing.T) {
t.Parallel()

context := map[string]interface{}{
"project_name": envvar.GetTestProjectFromEnv(),
"prevent_destroy": false,
"subnetwork_name": acctest.BootstrapSubnetWithFirewallForDataprocBatches(t, "dataproc-autotuning-test-network", "dataproc-autotuning-test-subnetwork"),
"random_suffix": acctest.RandString(t, 10),
}

acctest.VcrTest(t, resource.TestCase{
PreCheck: func() { acctest.AccTestPreCheck(t) },
ProtoV5ProviderFactories: acctest.ProtoV5ProviderFactories(t),
CheckDestroy: testAccCheckDataprocBatchDestroyProducer(t),
Steps: []resource.TestStep{
{
Config: testAccDataprocBatch_dataprocBatchAutotuningExample(context),
},
{
ResourceName: "google_dataproc_batch.example_batch_autotuning",
ImportState: true,
ImportStateVerify: true,
ImportStateVerifyIgnore: []string{"batch_id", "labels", "location", "runtime_config.0.properties", "terraform_labels"},
},
},
})
}

func testAccDataprocBatch_dataprocBatchAutotuningExample(context map[string]interface{}) string {
return acctest.Nprintf(`
resource "google_dataproc_batch" "example_batch_autotuning" {

batch_id = "tf-test-batch%{random_suffix}"
location = "us-central1"
labels = {"batch_test": "terraform"}

runtime_config {
version = "2.2"
properties = { "spark.dynamicAllocation.enabled": "false", "spark.executor.instances": "2" }
cohort = "tf-dataproc-batch-example"
autotuning_config {
scenarios = ["SCALING", "MEMORY"]
}
}

environment_config {
execution_config {
subnetwork_uri = "%{subnetwork_name}"
ttl = "3600s"
}
}

spark_batch {
main_class = "org.apache.spark.examples.SparkPi"
args = ["10"]
jar_file_uris = ["file:///usr/lib/spark/examples/jars/spark-examples.jar"]
}
}
`, context)
}

func testAccCheckDataprocBatchDestroyProducer(t *testing.T) func(s *terraform.State) error {
return func(s *terraform.State) error {
for name, rs := range s.RootModule().Resources {
Expand Down
50 changes: 50 additions & 0 deletions website/docs/r/dataproc_batch.html.markdown
Original file line number Diff line number Diff line change
Expand Up @@ -266,6 +266,39 @@ resource "google_dataproc_batch" "example_batch_sparkr" {
}
}
```
## Example Usage - Dataproc Batch Autotuning


```hcl
resource "google_dataproc_batch" "example_batch_autotuning" {

batch_id = "tf-test-batch%{random_suffix}"
location = "us-central1"
labels = {"batch_test": "terraform"}

runtime_config {
version = "2.2"
properties = { "spark.dynamicAllocation.enabled": "false", "spark.executor.instances": "2" }
cohort = "tf-dataproc-batch-example"
autotuning_config {
scenarios = ["SCALING", "MEMORY"]
}
}

environment_config {
execution_config {
subnetwork_uri = "default"
ttl = "3600s"
}
}

spark_batch {
main_class = "org.apache.spark.examples.SparkPi"
args = ["10"]
jar_file_uris = ["file:///usr/lib/spark/examples/jars/spark-examples.jar"]
}
}
```

## Argument Reference

Expand Down Expand Up @@ -344,6 +377,23 @@ The following arguments are supported:
(Output)
A mapping of property names to values, which are used to configure workload execution.

* `autotuning_config` -
(Optional)
Optional. Autotuning configuration of the workload.
Structure is [documented below](#nested_autotuning_config).

* `cohort` -
(Optional)
Optional. Cohort identifier. Identifies families of the workloads having the same shape, e.g. daily ETL jobs.


<a name="nested_autotuning_config"></a>The `autotuning_config` block supports:

* `scenarios` -
(Optional)
Optional. Scenarios for which tunings are applied.
Each value may be one of: `SCALING`, `BROADCAST_HASH_JOIN`, `MEMORY`.

<a name="nested_environment_config"></a>The `environment_config` block supports:

* `execution_config` -
Expand Down