databricks-cli/bundle/libraries/upload_test.go

339 lines
11 KiB
Go
Raw Normal View History

package libraries
import (
"context"
"path/filepath"
"testing"
"github.com/databricks/cli/bundle"
"github.com/databricks/cli/bundle/config"
"github.com/databricks/cli/bundle/config/resources"
mockfiler "github.com/databricks/cli/internal/mocks/libs/filer"
"github.com/databricks/cli/internal/testutil"
"github.com/databricks/cli/libs/filer"
Add DABs support for Unity Catalog volumes (#1762) ## Changes This PR adds support for UC volumes to DABs. ### Can I use a UC volume managed by DABs in `artifact_path`? Yes, but we require the volume to exist before being referenced in `artifact_path`. Otherwise you'll see an error that the volume does not exist. For this case, this PR also adds a warning if we detect that the UC volume is defined in the DAB itself, which informs the user to deploy the UC volume in a separate deployment first before using it in `artifact_path`. We cannot create the UC volume and then upload the artifacts to it in the same `bundle deploy` because `bundle deploy` always uploads the artifacts to `artifact_path` before materializing any resources defined in the bundle. Supporting this in a single deployment requires us to migrate away from our dependency on the Databricks Terraform provider to manage the CRUD lifecycle of DABs resources. ### Why do we not support `preset.name_prefix` for UC volumes? UC volumes will not have a `dev_shreyas_goenka` prefix added in `mode: development`. Configuring `presets.name_prefix` will be a no-op for UC volumes. We have decided not to support prefixing for UC resources. This is because: 1. UC provides its own namespace hierarchy that is independent of DABs. 2. Users can always manually use `${workspace.current_user.short_name}` to configure the prefixes manually. Customers often manually set up a UC hierarchy for dev and prod, including a schema or catalog per developer. Thus, it's often unnecessary for us to add prefixing in `mode: development` by default for UC resources. In retrospect, supporting prefixing for UC schemas and registered models was a mistake and will be removed in a future release of DABs. ## Tests Unit, integration test, and manually. ### Manual Testing cases: 1. UC volume does not exist: ``` ➜ bundle-playground git:(master) ✗ cli bundle deploy Error: failed to fetch metadata for the UC volume /Volumes/main/caps/my_volume that is configured in the artifact_path: Not Found ``` 2. UC Volume does not exist, but is defined in the DAB ``` ➜ bundle-playground git:(master) ✗ cli bundle deploy Error: failed to fetch metadata for the UC volume /Volumes/main/caps/managed_by_dab that is configured in the artifact_path: Not Found Warning: You might be using a UC volume in your artifact_path that is managed by this bundle but which has not been deployed yet. Please deploy the UC volume in a separate bundle deploy before using it in the artifact_path. at resources.volumes.bar in databricks.yml:24:7 ``` --------- Co-authored-by: Pieter Noordhuis <pieter.noordhuis@databricks.com>
2024-12-02 21:18:07 +00:00
sdkconfig "github.com/databricks/databricks-sdk-go/config"
"github.com/databricks/databricks-sdk-go/experimental/mocks"
"github.com/databricks/databricks-sdk-go/service/compute"
"github.com/databricks/databricks-sdk-go/service/jobs"
"github.com/stretchr/testify/mock"
"github.com/stretchr/testify/require"
)
func TestArtifactUploadForWorkspace(t *testing.T) {
tmpDir := t.TempDir()
whlFolder := filepath.Join(tmpDir, "whl")
testutil.Touch(t, whlFolder, "source.whl")
whlLocalPath := filepath.Join(whlFolder, "source.whl")
b := &bundle.Bundle{
SyncRootPath: tmpDir,
Config: config.Root{
Workspace: config.Workspace{
ArtifactPath: "/foo/bar/artifacts",
},
Artifacts: config.Artifacts{
"whl": {
Type: config.ArtifactPythonWheel,
Files: []config.ArtifactFile{
{Source: whlLocalPath},
},
},
},
Resources: config.Resources{
Jobs: map[string]*resources.Job{
"job": {
JobSettings: &jobs.JobSettings{
Tasks: []jobs.Task{
{
Libraries: []compute.Library{
{
Whl: filepath.Join("whl", "*.whl"),
},
{
Whl: "/Workspace/Users/foo@bar.com/mywheel.whl",
},
},
},
{
ForEachTask: &jobs.ForEachTask{
Task: jobs.Task{
Libraries: []compute.Library{
{
Whl: filepath.Join("whl", "*.whl"),
},
{
Whl: "/Workspace/Users/foo@bar.com/mywheel.whl",
},
},
},
},
},
},
Environments: []jobs.JobEnvironment{
{
Spec: &compute.Environment{
Dependencies: []string{
filepath.Join("whl", "source.whl"),
"/Workspace/Users/foo@bar.com/mywheel.whl",
},
},
},
},
},
},
},
},
},
}
mockFiler := mockfiler.NewMockFiler(t)
mockFiler.EXPECT().Write(
mock.Anything,
filepath.Join("source.whl"),
mock.AnythingOfType("*os.File"),
filer.OverwriteIfExists,
filer.CreateParentDirectories,
).Return(nil)
diags := bundle.Apply(context.Background(), b, bundle.Seq(ExpandGlobReferences(), UploadWithClient(mockFiler)))
require.NoError(t, diags.Error())
// Test that libraries path is updated
require.Equal(t, "/Workspace/foo/bar/artifacts/.internal/source.whl", b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries[0].Whl)
require.Equal(t, "/Workspace/Users/foo@bar.com/mywheel.whl", b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries[1].Whl)
require.Equal(t, "/Workspace/foo/bar/artifacts/.internal/source.whl", b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies[0])
require.Equal(t, "/Workspace/Users/foo@bar.com/mywheel.whl", b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies[1])
require.Equal(t, "/Workspace/foo/bar/artifacts/.internal/source.whl", b.Config.Resources.Jobs["job"].JobSettings.Tasks[1].ForEachTask.Task.Libraries[0].Whl)
require.Equal(t, "/Workspace/Users/foo@bar.com/mywheel.whl", b.Config.Resources.Jobs["job"].JobSettings.Tasks[1].ForEachTask.Task.Libraries[1].Whl)
}
func TestArtifactUploadForVolumes(t *testing.T) {
tmpDir := t.TempDir()
whlFolder := filepath.Join(tmpDir, "whl")
testutil.Touch(t, whlFolder, "source.whl")
whlLocalPath := filepath.Join(whlFolder, "source.whl")
b := &bundle.Bundle{
SyncRootPath: tmpDir,
Config: config.Root{
Workspace: config.Workspace{
ArtifactPath: "/Volumes/foo/bar/artifacts",
},
Artifacts: config.Artifacts{
"whl": {
Type: config.ArtifactPythonWheel,
Files: []config.ArtifactFile{
{Source: whlLocalPath},
},
},
},
Resources: config.Resources{
Jobs: map[string]*resources.Job{
"job": {
JobSettings: &jobs.JobSettings{
Tasks: []jobs.Task{
{
Libraries: []compute.Library{
{
Whl: filepath.Join("whl", "*.whl"),
},
{
Whl: "/Volumes/some/path/mywheel.whl",
},
},
},
{
ForEachTask: &jobs.ForEachTask{
Task: jobs.Task{
Libraries: []compute.Library{
{
Whl: filepath.Join("whl", "*.whl"),
},
{
Whl: "/Volumes/some/path/mywheel.whl",
},
},
},
},
},
},
Environments: []jobs.JobEnvironment{
{
Spec: &compute.Environment{
Dependencies: []string{
filepath.Join("whl", "source.whl"),
"/Volumes/some/path/mywheel.whl",
},
},
},
},
},
},
},
},
},
}
mockFiler := mockfiler.NewMockFiler(t)
mockFiler.EXPECT().Write(
mock.Anything,
filepath.Join("source.whl"),
mock.AnythingOfType("*os.File"),
filer.OverwriteIfExists,
filer.CreateParentDirectories,
).Return(nil)
Add DABs support for Unity Catalog volumes (#1762) ## Changes This PR adds support for UC volumes to DABs. ### Can I use a UC volume managed by DABs in `artifact_path`? Yes, but we require the volume to exist before being referenced in `artifact_path`. Otherwise you'll see an error that the volume does not exist. For this case, this PR also adds a warning if we detect that the UC volume is defined in the DAB itself, which informs the user to deploy the UC volume in a separate deployment first before using it in `artifact_path`. We cannot create the UC volume and then upload the artifacts to it in the same `bundle deploy` because `bundle deploy` always uploads the artifacts to `artifact_path` before materializing any resources defined in the bundle. Supporting this in a single deployment requires us to migrate away from our dependency on the Databricks Terraform provider to manage the CRUD lifecycle of DABs resources. ### Why do we not support `preset.name_prefix` for UC volumes? UC volumes will not have a `dev_shreyas_goenka` prefix added in `mode: development`. Configuring `presets.name_prefix` will be a no-op for UC volumes. We have decided not to support prefixing for UC resources. This is because: 1. UC provides its own namespace hierarchy that is independent of DABs. 2. Users can always manually use `${workspace.current_user.short_name}` to configure the prefixes manually. Customers often manually set up a UC hierarchy for dev and prod, including a schema or catalog per developer. Thus, it's often unnecessary for us to add prefixing in `mode: development` by default for UC resources. In retrospect, supporting prefixing for UC schemas and registered models was a mistake and will be removed in a future release of DABs. ## Tests Unit, integration test, and manually. ### Manual Testing cases: 1. UC volume does not exist: ``` ➜ bundle-playground git:(master) ✗ cli bundle deploy Error: failed to fetch metadata for the UC volume /Volumes/main/caps/my_volume that is configured in the artifact_path: Not Found ``` 2. UC Volume does not exist, but is defined in the DAB ``` ➜ bundle-playground git:(master) ✗ cli bundle deploy Error: failed to fetch metadata for the UC volume /Volumes/main/caps/managed_by_dab that is configured in the artifact_path: Not Found Warning: You might be using a UC volume in your artifact_path that is managed by this bundle but which has not been deployed yet. Please deploy the UC volume in a separate bundle deploy before using it in the artifact_path. at resources.volumes.bar in databricks.yml:24:7 ``` --------- Co-authored-by: Pieter Noordhuis <pieter.noordhuis@databricks.com>
2024-12-02 21:18:07 +00:00
m := mocks.NewMockWorkspaceClient(t)
m.WorkspaceClient.Config = &sdkconfig.Config{}
m.GetMockFilesAPI().EXPECT().GetDirectoryMetadataByDirectoryPath(mock.Anything, "/Volumes/foo/bar/artifacts").Return(nil)
b.SetWorkpaceClient(m.WorkspaceClient)
diags := bundle.Apply(context.Background(), b, bundle.Seq(ExpandGlobReferences(), UploadWithClient(mockFiler)))
require.NoError(t, diags.Error())
// Test that libraries path is updated
require.Equal(t, "/Volumes/foo/bar/artifacts/.internal/source.whl", b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries[0].Whl)
require.Equal(t, "/Volumes/some/path/mywheel.whl", b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries[1].Whl)
require.Equal(t, "/Volumes/foo/bar/artifacts/.internal/source.whl", b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies[0])
require.Equal(t, "/Volumes/some/path/mywheel.whl", b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies[1])
require.Equal(t, "/Volumes/foo/bar/artifacts/.internal/source.whl", b.Config.Resources.Jobs["job"].JobSettings.Tasks[1].ForEachTask.Task.Libraries[0].Whl)
require.Equal(t, "/Volumes/some/path/mywheel.whl", b.Config.Resources.Jobs["job"].JobSettings.Tasks[1].ForEachTask.Task.Libraries[1].Whl)
}
func TestArtifactUploadWithNoLibraryReference(t *testing.T) {
tmpDir := t.TempDir()
whlFolder := filepath.Join(tmpDir, "whl")
testutil.Touch(t, whlFolder, "source.whl")
whlLocalPath := filepath.Join(whlFolder, "source.whl")
b := &bundle.Bundle{
SyncRootPath: tmpDir,
Config: config.Root{
Workspace: config.Workspace{
ArtifactPath: "/Workspace/foo/bar/artifacts",
},
Artifacts: config.Artifacts{
"whl": {
Type: config.ArtifactPythonWheel,
Files: []config.ArtifactFile{
{Source: whlLocalPath},
},
},
},
},
}
mockFiler := mockfiler.NewMockFiler(t)
mockFiler.EXPECT().Write(
mock.Anything,
filepath.Join("source.whl"),
mock.AnythingOfType("*os.File"),
filer.OverwriteIfExists,
filer.CreateParentDirectories,
).Return(nil)
diags := bundle.Apply(context.Background(), b, bundle.Seq(ExpandGlobReferences(), UploadWithClient(mockFiler)))
require.NoError(t, diags.Error())
require.Equal(t, "/Workspace/foo/bar/artifacts/.internal/source.whl", b.Config.Artifacts["whl"].Files[0].RemotePath)
}
func TestUploadMultipleLibraries(t *testing.T) {
tmpDir := t.TempDir()
whlFolder := filepath.Join(tmpDir, "whl")
testutil.Touch(t, whlFolder, "source1.whl")
testutil.Touch(t, whlFolder, "source2.whl")
testutil.Touch(t, whlFolder, "source3.whl")
testutil.Touch(t, whlFolder, "source4.whl")
b := &bundle.Bundle{
SyncRootPath: tmpDir,
Config: config.Root{
Workspace: config.Workspace{
ArtifactPath: "/foo/bar/artifacts",
},
Resources: config.Resources{
Jobs: map[string]*resources.Job{
"job": {
JobSettings: &jobs.JobSettings{
Tasks: []jobs.Task{
{
Libraries: []compute.Library{
{
Whl: filepath.Join("whl", "*.whl"),
},
{
Whl: "/Workspace/Users/foo@bar.com/mywheel.whl",
},
},
},
},
Environments: []jobs.JobEnvironment{
{
Spec: &compute.Environment{
Dependencies: []string{
filepath.Join("whl", "*.whl"),
"/Workspace/Users/foo@bar.com/mywheel.whl",
},
},
},
},
},
},
},
},
},
}
mockFiler := mockfiler.NewMockFiler(t)
mockFiler.EXPECT().Write(
mock.Anything,
filepath.Join("source1.whl"),
mock.AnythingOfType("*os.File"),
filer.OverwriteIfExists,
filer.CreateParentDirectories,
).Return(nil).Once()
mockFiler.EXPECT().Write(
mock.Anything,
filepath.Join("source2.whl"),
mock.AnythingOfType("*os.File"),
filer.OverwriteIfExists,
filer.CreateParentDirectories,
).Return(nil).Once()
mockFiler.EXPECT().Write(
mock.Anything,
filepath.Join("source3.whl"),
mock.AnythingOfType("*os.File"),
filer.OverwriteIfExists,
filer.CreateParentDirectories,
).Return(nil).Once()
mockFiler.EXPECT().Write(
mock.Anything,
filepath.Join("source4.whl"),
mock.AnythingOfType("*os.File"),
filer.OverwriteIfExists,
filer.CreateParentDirectories,
).Return(nil).Once()
diags := bundle.Apply(context.Background(), b, bundle.Seq(ExpandGlobReferences(), UploadWithClient(mockFiler)))
require.NoError(t, diags.Error())
// Test that libraries path is updated
require.Len(t, b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries, 5)
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries, compute.Library{Whl: "/Workspace/foo/bar/artifacts/.internal/source1.whl"})
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries, compute.Library{Whl: "/Workspace/foo/bar/artifacts/.internal/source2.whl"})
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries, compute.Library{Whl: "/Workspace/foo/bar/artifacts/.internal/source3.whl"})
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries, compute.Library{Whl: "/Workspace/foo/bar/artifacts/.internal/source4.whl"})
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Tasks[0].Libraries, compute.Library{Whl: "/Workspace/Users/foo@bar.com/mywheel.whl"})
require.Len(t, b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies, 5)
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies, "/Workspace/foo/bar/artifacts/.internal/source1.whl")
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies, "/Workspace/foo/bar/artifacts/.internal/source2.whl")
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies, "/Workspace/foo/bar/artifacts/.internal/source3.whl")
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies, "/Workspace/foo/bar/artifacts/.internal/source4.whl")
require.Contains(t, b.Config.Resources.Jobs["job"].JobSettings.Environments[0].Spec.Dependencies, "/Workspace/Users/foo@bar.com/mywheel.whl")
}