Provide configuration for the optional creation of buildtreestpollard/896

Artifacts can be cached explicitly with an empty `build tree` when
built via the cli main options or user config for all or only
successful build artifacts. Default behaviour is to still create
and cache all expected buildtrees.

element.py: _cache_artifact() Check if context for cache_buildtrees
has been set to always or failure with a corresponding build
result, if not skip attempting to export the build-root. Element
types without a build-root are cached with an empty buildtree
regardless. Update _stage_sources_at() to warn the user that the
buildtree import is empty.

tests/integration: Add test to artifact.py for the optional caching
of buildtree content from bst build. Rename build-tree.py to
shellbuildtrees.py to reflect included test cases, add test for
empty buildtree warning and failure option.

NEWS: Add entry for new option.

4 files changed, 216 insertions, 14 deletions

diff --git a/NEWS b/NEWS
index 50d136886..9876210c3 100644
--- a/NEWS
+++ b/NEWS
@@ -126,6 +126,14 @@ buildstream 1.3.1
     Providing a remote will limit build's pull/push remote actions to the given
     remote specifically, ignoring those defined via user or project configuration.
 
+  o Artifacts can now be cached explicitly with an empty `build tree` when built.
+    Element types without a build-root were already cached with an empty build tree
+    directory, this can now be extended to all or successful artifacts to save on cache
+    overheads. The cli main option '--cache-buildtrees' or the user configuration cache
+    group option 'cache-buildtrees' can be set as 'always', 'failure' or 'never', with
+    the default being always. Note, as the cache-key for the artifact is independant of
+    the cached build tree input it will remain unaltered, however the availbility of the
+    build tree content may differ.
 
 =================
 buildstream 1.1.5
diff --git a/buildstream/element.py b/buildstream/element.py
index e03f1e171..a3bf59dc6 100644
--- a/buildstream/element.py
+++ b/buildstream/element.py
@@ -1457,6 +1457,9 @@ class Element(Plugin):
             elif usebuildtree:
                 artifact_base, _ = self.__extract()
                 import_dir = os.path.join(artifact_base, 'buildtree')
+                if not os.listdir(import_dir):
+                    detail = "Element type either does not expect a buildtree or it was explictily cached without one."
+                    self.warn("WARNING: {} Artifact contains an empty buildtree".format(self.name), detail=detail)
             else:
                 # No workspace or cached buildtree, stage source directly
                 for source in self.sources():
@@ -1663,6 +1666,8 @@ class Element(Plugin):
                 # No collect directory existed
                 collectvdir = None
 
+        context = self._get_context()
+
         # Create artifact directory structure
         assembledir = os.path.join(rootdir, 'artifact')
         filesdir = os.path.join(assembledir, 'files')
@@ -1680,20 +1685,30 @@ class Element(Plugin):
         if collect is not None and collectvdir is not None:
             collectvdir.export_files(filesdir, can_link=True)
 
-        try:
-            sandbox_vroot = sandbox.get_virtual_directory()
-            sandbox_build_dir = sandbox_vroot.descend(
-                self.get_variable('build-root').lstrip(os.sep).split(os.sep))
-            # Hard link files from build-root dir to buildtreedir directory
-            sandbox_build_dir.export_files(buildtreedir)
-        except VirtualDirectoryError:
-            # Directory could not be found. Pre-virtual
-            # directory behaviour was to continue silently
-            # if the directory could not be found.
-            pass
+        cache_buildtrees = context.cache_buildtrees
+        build_success = self.__build_result[0]
+
+        # cache_buildtrees defaults to 'always', as such the
+        # default behaviour is to attempt to cache them. If only
+        # caching failed artifact buildtrees, then query the build
+        # result. Element types without a build-root dir will be cached
+        # with an empty buildtreedir regardless of this configuration.
+
+        if cache_buildtrees == 'always' or (cache_buildtrees == 'failure' and not build_success):
+            try:
+                sandbox_vroot = sandbox.get_virtual_directory()
+                sandbox_build_dir = sandbox_vroot.descend(
+                    self.get_variable('build-root').lstrip(os.sep).split(os.sep))
+                # Hard link files from build-root dir to buildtreedir directory
+                sandbox_build_dir.export_files(buildtreedir)
+            except VirtualDirectoryError:
+                # Directory could not be found. Pre-virtual
+                # directory behaviour was to continue silently
+                # if the directory could not be found.
+                pass
 
         # Copy build log
-        log_filename = self._get_context().get_log_filename()
+        log_filename = context.get_log_filename()
         self._build_log_path = os.path.join(logsdir, 'build.log')
         if log_filename:
             shutil.copyfile(log_filename, self._build_log_path)
@@ -1834,7 +1849,7 @@ class Element(Plugin):
             return True
 
         # Do not push elements that aren't cached, or that are cached with a dangling buildtree
-        # artifact unless element type is expected to have an an empty buildtree directory
+        # ref unless element type is expected to have an an empty buildtree directory
         if not self._cached_buildtree():
             return True
 
@@ -2036,6 +2051,8 @@ class Element(Plugin):
     # Returns:
     #     (bool): True if artifact cached with buildtree, False if
     #             element not cached or missing expected buildtree.
+    #             Note this only confirms if a buildtree is present,
+    #             not its contents.
     #
     def _cached_buildtree(self):
         context = self._get_context()
diff --git a/tests/integration/artifact.py b/tests/integration/artifact.py
index 459241209..742c33455 100644
--- a/tests/integration/artifact.py
+++ b/tests/integration/artifact.py
@@ -20,9 +20,12 @@
 
 import os
 import pytest
+import shutil
 
 from buildstream.plugintestutils import cli_integration as cli
-
+from tests.testutils import create_artifact_share
+from tests.testutils.site import HAVE_SANDBOX
+from buildstream._exceptions import ErrorDomain
 
 pytestmark = pytest.mark.integration
 
@@ -66,3 +69,106 @@ def test_artifact_log(cli, tmpdir, datafiles):
     assert result.exit_code == 0
     # The artifact is cached under both a strong key and a weak key
     assert (log + log) == result.output
+
+
+# A test to capture the integration of the cachebuildtrees
+# behaviour, which by default is to include the buildtree
+# content of an element on caching.
+@pytest.mark.integration
+@pytest.mark.datafiles(DATA_DIR)
+@pytest.mark.skipif(not HAVE_SANDBOX, reason='Only available with a functioning sandbox')
+def test_cache_buildtrees(cli, tmpdir, datafiles):
+    project = os.path.join(datafiles.dirname, datafiles.basename)
+    element_name = 'autotools/amhello.bst'
+
+    # Create artifact shares for pull & push testing
+    with create_artifact_share(os.path.join(str(tmpdir), 'share1')) as share1,\
+        create_artifact_share(os.path.join(str(tmpdir), 'share2')) as share2,\
+        create_artifact_share(os.path.join(str(tmpdir), 'share3')) as share3:
+        cli.configure({
+            'artifacts': {'url': share1.repo, 'push': True},
+            'artifactdir': os.path.join(str(tmpdir), 'artifacts')
+        })
+
+        # Build autotools element with cache-buildtrees set via the
+        # cli. The artifact should be successfully pushed to the share1 remote
+        # and cached locally with an 'empty' buildtree digest, as it's not a
+        # dangling ref
+        result = cli.run(project=project, args=['--cache-buildtrees', 'never', 'build', element_name])
+        assert result.exit_code == 0
+        assert cli.get_element_state(project, element_name) == 'cached'
+        assert share1.has_artifact('test', element_name, cli.get_element_key(project, element_name))
+
+        # The extracted buildtree dir should be empty, as we set the config
+        # to not cache buildtrees
+        cache_key = cli.get_element_key(project, element_name)
+        elementdigest = share1.has_artifact('test', element_name, cache_key)
+        buildtreedir = os.path.join(str(tmpdir), 'artifacts', 'extract', 'test', 'autotools-amhello',
+                                    elementdigest.hash, 'buildtree')
+        assert os.path.isdir(buildtreedir)
+        assert not os.listdir(buildtreedir)
+
+        # Delete the local cached artifacts, and assert the when pulled with --pull-buildtrees
+        # that is was cached in share1 as expected with an empty buildtree dir
+        shutil.rmtree(os.path.join(str(tmpdir), 'artifacts'))
+        assert cli.get_element_state(project, element_name) != 'cached'
+        result = cli.run(project=project, args=['--pull-buildtrees', 'artifact', 'pull', element_name])
+        assert element_name in result.get_pulled_elements()
+        assert os.path.isdir(buildtreedir)
+        assert not os.listdir(buildtreedir)
+        shutil.rmtree(os.path.join(str(tmpdir), 'artifacts'))
+
+        # Assert that the default behaviour of pull to not include buildtrees on the artifact
+        # in share1 which was purposely cached with an empty one behaves as expected. As such the
+        # pulled artifact will have a dangling ref for the buildtree dir, regardless of content,
+        # leading to no buildtreedir being extracted
+        result = cli.run(project=project, args=['artifact', 'pull', element_name])
+        assert element_name in result.get_pulled_elements()
+        assert not os.path.isdir(buildtreedir)
+        shutil.rmtree(os.path.join(str(tmpdir), 'artifacts'))
+
+        # Repeat building the artifacts, this time with the default behaviour of caching buildtrees,
+        # as such the buildtree dir should not be empty
+        cli.configure({
+            'artifacts': {'url': share2.repo, 'push': True},
+            'artifactdir': os.path.join(str(tmpdir), 'artifacts')
+        })
+        result = cli.run(project=project, args=['build', element_name])
+        assert result.exit_code == 0
+        assert cli.get_element_state(project, element_name) == 'cached'
+        assert share2.has_artifact('test', element_name, cli.get_element_key(project, element_name))
+
+        # Cache key will be the same however the digest hash will have changed as expected, so reconstruct paths
+        elementdigest = share2.has_artifact('test', element_name, cache_key)
+        buildtreedir = os.path.join(str(tmpdir), 'artifacts', 'extract', 'test', 'autotools-amhello',
+                                    elementdigest.hash, 'buildtree')
+        assert os.path.isdir(buildtreedir)
+        assert os.listdir(buildtreedir) is not None
+
+        # Delete the local cached artifacts, and assert that when pulled with --pull-buildtrees
+        # that it was cached in share2 as expected with a populated buildtree dir
+        shutil.rmtree(os.path.join(str(tmpdir), 'artifacts'))
+        assert cli.get_element_state(project, element_name) != 'cached'
+        result = cli.run(project=project, args=['--pull-buildtrees', 'artifact', 'pull', element_name])
+        assert element_name in result.get_pulled_elements()
+        assert os.path.isdir(buildtreedir)
+        assert os.listdir(buildtreedir) is not None
+        shutil.rmtree(os.path.join(str(tmpdir), 'artifacts'))
+
+        # Clarify that the user config option for cache-buildtrees works as the cli
+        # main option does. Point to share3 which does not have the artifacts cached to force
+        # a build
+        cli.configure({
+            'artifacts': {'url': share3.repo, 'push': True},
+            'artifactdir': os.path.join(str(tmpdir), 'artifacts'),
+            'cache': {'cache-buildtrees': 'never'}
+        })
+        result = cli.run(project=project, args=['build', element_name])
+        assert result.exit_code == 0
+        assert cli.get_element_state(project, element_name) == 'cached'
+        cache_key = cli.get_element_key(project, element_name)
+        elementdigest = share3.has_artifact('test', element_name, cache_key)
+        buildtreedir = os.path.join(str(tmpdir), 'artifacts', 'extract', 'test', 'autotools-amhello',
+                                    elementdigest.hash, 'buildtree')
+        assert os.path.isdir(buildtreedir)
+        assert not os.listdir(buildtreedir)
diff --git a/tests/integration/build-tree.py b/tests/integration/shellbuildtrees.py
index 98bb5b1e8..4d9d24e26 100644
--- a/tests/integration/build-tree.py
+++ b/tests/integration/shellbuildtrees.py
@@ -54,6 +54,29 @@ def test_buildtree_staged_forced_true(cli_integration, tmpdir, datafiles):
 
 @pytest.mark.datafiles(DATA_DIR)
 @pytest.mark.skipif(not HAVE_SANDBOX, reason='Only available with a functioning sandbox')
+def test_buildtree_staged_warn_empty_cached(cli_integration, tmpdir, datafiles):
+    # Test that if we stage a cached and empty buildtree, we warn the user.
+    project = os.path.join(datafiles.dirname, datafiles.basename)
+    element_name = 'build-shell/buildtree.bst'
+
+    # Switch to a temp artifact cache dir to ensure the artifact is rebuilt,
+    # caching an empty buildtree
+    cli_integration.configure({
+        'artifactdir': os.path.join(os.path.join(str(tmpdir), 'artifacts'))
+    })
+
+    res = cli_integration.run(project=project, args=['--cache-buildtrees', 'never', 'build', element_name])
+    res.assert_success()
+
+    res = cli_integration.run(project=project, args=[
+        'shell', '--build', '--use-buildtree', 'always', element_name, '--', 'cat', 'test'
+    ])
+    res.assert_shell_error()
+    assert "Artifact contains an empty buildtree" in res.stderr
+
+
+@pytest.mark.datafiles(DATA_DIR)
+@pytest.mark.skipif(not HAVE_SANDBOX, reason='Only available with a functioning sandbox')
 def test_buildtree_staged_if_available(cli_integration, tmpdir, datafiles):
     # Test that a build tree can be correctly detected.
     project = os.path.join(datafiles.dirname, datafiles.basename)
@@ -106,6 +129,54 @@ def test_buildtree_from_failure(cli_integration, tmpdir, datafiles):
     assert 'Hi' in res.output
 
 
+@pytest.mark.datafiles(DATA_DIR)
+@pytest.mark.skipif(not HAVE_SANDBOX, reason='Only available with a functioning sandbox')
+def test_buildtree_from_failure_option_never(cli_integration, tmpdir, datafiles):
+
+    project = os.path.join(datafiles.dirname, datafiles.basename)
+    element_name = 'build-shell/buildtree-fail.bst'
+
+    # Switch to a temp artifact cache dir to ensure the artifact is rebuilt,
+    # caching an empty buildtree
+    cli_integration.configure({
+        'artifactdir': os.path.join(os.path.join(str(tmpdir), 'artifacts'))
+    })
+
+    res = cli_integration.run(project=project, args=['--cache-buildtrees', 'never', 'build', element_name])
+    res.assert_main_error(ErrorDomain.STREAM, None)
+
+    res = cli_integration.run(project=project, args=[
+        'shell', '--build', element_name, '--use-buildtree', 'always', '--', 'cat', 'test'
+    ])
+    res.assert_shell_error()
+    assert "Artifact contains an empty buildtree" in res.stderr
+
+
+@pytest.mark.datafiles(DATA_DIR)
+@pytest.mark.skipif(not HAVE_SANDBOX, reason='Only available with a functioning sandbox')
+def test_buildtree_from_failure_option_failure(cli_integration, tmpdir, datafiles):
+
+    project = os.path.join(datafiles.dirname, datafiles.basename)
+    element_name = 'build-shell/buildtree-fail.bst'
+
+    # build with  --cache-buildtrees set to 'failure', behaviour should match
+    # default behaviour (which is always) as the buildtree will explicitly have been
+    # cached with content.
+    cli_integration.configure({
+        'artifactdir': os.path.join(os.path.join(str(tmpdir), 'artifacts'))
+    })
+
+    res = cli_integration.run(project=project, args=['--cache-buildtrees', 'failure', 'build', element_name])
+    res.assert_main_error(ErrorDomain.STREAM, None)
+
+    res = cli_integration.run(project=project, args=[
+        'shell', '--build', element_name, '--use-buildtree', 'always', '--', 'cat', 'test'
+    ])
+    res.assert_success()
+    assert "WARNING: using a buildtree from a failed build" in res.stderr
+    assert 'Hi' in res.output
+
+
 # Check that build shells work when pulled from a remote cache
 # This is to roughly simulate remote execution
 @pytest.mark.datafiles(DATA_DIR)