siggen: Improve runtaskdeps data to fix sstate debugging

The runtaskdep data in siginfo files was written out with full paths to
the bb files, matching bitbake's internal "unique key" ID for recipes/tasks.
When originally implemented this made sense.

Over time, the main use for the data in siginfo files has become to match
against other siginfo files to debug changes of hash calcuations. The
recipename data is not useful for this as the siginfo filenames use PN
instead which can often be derived from the recipe filename but not always.

It is time to throw away the 'tid' data format and switch over the use a
hybrid PN form which includes the multiconfig. That can be easily stripped
off in the find_siginfo code in oe-core.

The other purpose of having a sortable dependency ID is retained and the
multiconfig needs to be included to allow the taskhashes to be processed
and calculated correctly. PN is meant to be unique between recipes, only
one would ever be built so using PN in this location is fine.

The one risk of this change is there isn't any compatibility to the old
format. I'm not convinced we should spend time complicating the code
with it. This change will change the taskhashes everywhere so the only
mixing of old and new siginfo files will be either through hash equivalence
or through users using the tool against old and new info files manually
which will give some weird output but it should be clear they're in
different formats as there would be large paths from the old files not
present in the new ones.

We have options to add backwards compatibility if some issue is found
to need that.

Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

2 files changed, 31 insertions, 118 deletions

diff --git a/lib/bb/siggen.py b/lib/bb/siggen.py
index c4ff9d8de..d0a555654 100644
--- a/lib/bb/siggen.py
+++ b/lib/bb/siggen.py
@@ -182,6 +182,11 @@ class SignatureGenerator(object):
     def exit(self):
         return
 
+def build_pnid(mc, pn, taskname):
+    if mc:
+        return "mc:" + mc + ":" + pn + ":" + taskname
+    return pn + ":" + taskname
+
 class SignatureGeneratorBasic(SignatureGenerator):
     """
     """
@@ -309,15 +314,19 @@ class SignatureGeneratorBasic(SignatureGenerator):
         recipename = dataCaches[mc].pkg_fn[mcfn]
 
         self.tidtopn[tid] = recipename
+        # save hashfn for deps into siginfo?
+        for dep in deps:
+            (depmc, _, deptask, depmcfn) = bb.runqueue.split_tid_mcfn(dep)
+            dep_pn = dataCaches[depmc].pkg_fn[depmcfn]
 
-        for dep in sorted(deps, key=clean_basepath):
-            (depmc, _, _, depmcfn) = bb.runqueue.split_tid_mcfn(dep)
-            depname = dataCaches[depmc].pkg_fn[depmcfn]
-            if not self.rundep_check(mcfn, recipename, task, dep, depname, dataCaches):
+            if not self.rundep_check(mcfn, recipename, task, dep, dep_pn, dataCaches):
                 continue
+
             if dep not in self.taskhash:
                 bb.fatal("%s is not in taskhash, caller isn't calling in dependency order?" % dep)
-            self.runtaskdeps[tid].append(dep)
+
+            dep_pnid = build_pnid(depmc, dep_pn, deptask)
+            self.runtaskdeps[tid].append((dep_pnid, dep))
 
         if task in dataCaches[mc].file_checksums[mcfn]:
             if self.checksum_cache:
@@ -348,8 +357,8 @@ class SignatureGeneratorBasic(SignatureGenerator):
     def get_taskhash(self, tid, deps, dataCaches):
 
         data = self.basehash[tid]
-        for dep in self.runtaskdeps[tid]:
-            data += self.get_unihash(dep)
+        for dep in sorted(self.runtaskdeps[tid]):
+            data += self.get_unihash(dep[1])
 
         for (f, cs) in self.file_checksum_values[tid]:
             if cs:
@@ -414,7 +423,7 @@ class SignatureGeneratorBasic(SignatureGenerator):
             data['varvals'][dep] = self.datacaches[mc].siggen_varvals[mcfn][dep]
 
         if runtime and tid in self.taskhash:
-            data['runtaskdeps'] = self.runtaskdeps[tid]
+            data['runtaskdeps'] = [dep[0] for dep in sorted(self.runtaskdeps[tid])]
             data['file_checksum_values'] = []
             for f,cs in self.file_checksum_values[tid]:
                 if "/./" in f:
@@ -422,8 +431,8 @@ class SignatureGeneratorBasic(SignatureGenerator):
                 else:
                     data['file_checksum_values'].append((os.path.basename(f), cs))
             data['runtaskhashes'] = {}
-            for dep in data['runtaskdeps']:
-                data['runtaskhashes'][dep] = self.get_unihash(dep)
+            for dep in self.runtaskdeps[tid]:
+                data['runtaskhashes'][dep[0]] = self.get_unihash(dep[1])
             data['taskhash'] = self.taskhash[tid]
             data['unihash'] = self.get_unihash(tid)
 
@@ -793,39 +802,6 @@ def list_inline_diff(oldlist, newlist, colors=None):
             ret.append(item)
     return '[%s]' % (', '.join(ret))
 
-def clean_basepath(basepath):
-    basepath, dir, recipe_task = basepath.rsplit("/", 2)
-    cleaned = dir + '/' + recipe_task
-
-    if basepath[0] == '/':
-        return cleaned
-
-    if basepath.startswith("mc:") and basepath.count(':') >= 2:
-        mc, mc_name, basepath = basepath.split(":", 2)
-        mc_suffix = ':mc:' + mc_name
-    else:
-        mc_suffix = ''
-
-    # mc stuff now removed from basepath. Whatever was next, if present will be the first
-    # suffix. ':/', recipe path start, marks the end of this. Something like
-    # 'virtual:a[:b[:c]]:/path...' (b and c being optional)
-    if basepath[0] != '/':
-        cleaned += ':' + basepath.split(':/', 1)[0]
-
-    return cleaned + mc_suffix
-
-def clean_basepaths(a):
-    b = {}
-    for x in a:
-        b[clean_basepath(x)] = a[x]
-    return b
-
-def clean_basepaths_list(a):
-    b = []
-    for x in a:
-        b.append(clean_basepath(x))
-    return b
-
 # Handled renamed fields
 def handle_renames(data):
     if 'basewhitelist' in data:
@@ -994,11 +970,11 @@ def compare_sigfiles(a, b, recursecb=None, color=False, collapsed=False):
                 a = a_data['runtaskdeps'][idx]
                 b = b_data['runtaskdeps'][idx]
                 if a_data['runtaskhashes'][a] != b_data['runtaskhashes'][b] and not collapsed:
-                    changed.append("%s with hash %s\n changed to\n%s with hash %s" % (clean_basepath(a), a_data['runtaskhashes'][a], clean_basepath(b), b_data['runtaskhashes'][b]))
+                    changed.append("%s with hash %s\n changed to\n%s with hash %s" % (a, a_data['runtaskhashes'][a], b, b_data['runtaskhashes'][b]))
 
         if changed:
-            clean_a = clean_basepaths_list(a_data['runtaskdeps'])
-            clean_b = clean_basepaths_list(b_data['runtaskdeps'])
+            clean_a = a_data['runtaskdeps']
+            clean_b = b_data['runtaskdeps']
             if clean_a != clean_b:
                 output.append(color_format("{color_title}runtaskdeps changed:{color_default}\n%s") % list_inline_diff(clean_a, clean_b, colors))
             else:
@@ -1007,8 +983,8 @@ def compare_sigfiles(a, b, recursecb=None, color=False, collapsed=False):
 
 
     if 'runtaskhashes' in a_data and 'runtaskhashes' in b_data:
-        a = clean_basepaths(a_data['runtaskhashes'])
-        b = clean_basepaths(b_data['runtaskhashes'])
+        a = a_data['runtaskhashes']
+        b = b_data['runtaskhashes']
         changed, added, removed = dict_diff(a, b)
         if added:
             for dep in sorted(added):
diff --git a/lib/bb/tests/siggen.py b/lib/bb/tests/siggen.py
index c21ab4e4f..0dc67e6cc 100644
--- a/lib/bb/tests/siggen.py
+++ b/lib/bb/tests/siggen.py
@@ -17,75 +17,12 @@ import bb.siggen
 
 class SiggenTest(unittest.TestCase):
 
-    def test_clean_basepath_simple_target_basepath(self):
-        basepath = '/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask'
-        expected_cleaned = 'helloworld/helloworld_1.2.3.bb:do_sometask'
+    def test_build_pnid(self):
+        tests = {
+            ('', 'helloworld', 'do_sometask') : 'helloworld:do_sometask',
+            ('XX', 'helloworld', 'do_sometask') : 'mc:XX:helloworld:do_sometask',
+        }
 
-        actual_cleaned = bb.siggen.clean_basepath(basepath)
+        for t in tests:
+            self.assertEqual(bb.siggen.build_pnid(*t), tests[t])
 
-        self.assertEqual(actual_cleaned, expected_cleaned)
-
-    def test_clean_basepath_basic_virtual_basepath(self):
-        basepath = 'virtual:something:/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask'
-        expected_cleaned = 'helloworld/helloworld_1.2.3.bb:do_sometask:virtual:something'
-
-        actual_cleaned = bb.siggen.clean_basepath(basepath)
-
-        self.assertEqual(actual_cleaned, expected_cleaned)
-
-    def test_clean_basepath_mc_basepath(self):
-        basepath = 'mc:somemachine:/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask'
-        expected_cleaned = 'helloworld/helloworld_1.2.3.bb:do_sometask:mc:somemachine'
-
-        actual_cleaned = bb.siggen.clean_basepath(basepath)
-
-        self.assertEqual(actual_cleaned, expected_cleaned)
-
-    def test_clean_basepath_virtual_long_prefix_basepath(self):
-        basepath = 'virtual:something:A:B:C:/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask'
-        expected_cleaned = 'helloworld/helloworld_1.2.3.bb:do_sometask:virtual:something:A:B:C'
-
-        actual_cleaned = bb.siggen.clean_basepath(basepath)
-
-        self.assertEqual(actual_cleaned, expected_cleaned)
-
-    def test_clean_basepath_mc_virtual_basepath(self):
-        basepath = 'mc:somemachine:virtual:something:/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask'
-        expected_cleaned = 'helloworld/helloworld_1.2.3.bb:do_sometask:virtual:something:mc:somemachine'
-
-        actual_cleaned = bb.siggen.clean_basepath(basepath)
-
-        self.assertEqual(actual_cleaned, expected_cleaned)
-
-    def test_clean_basepath_mc_virtual_long_prefix_basepath(self):
-        basepath = 'mc:X:virtual:something:C:B:A:/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask'
-        expected_cleaned = 'helloworld/helloworld_1.2.3.bb:do_sometask:virtual:something:C:B:A:mc:X'
-
-        actual_cleaned = bb.siggen.clean_basepath(basepath)
-
-        self.assertEqual(actual_cleaned, expected_cleaned)
-
-
-    # def test_clean_basepath_performance(self):
-    #     input_basepaths = [
-    #         'mc:X:/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask',
-    #         'mc:X:virtual:something:C:B:A:/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask',
-    #         'virtual:something:C:B:A:/different/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask',
-    #         'virtual:something:A:/full/path/to/poky/meta/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask',
-    #         '/this/is/most/common/input/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask',
-    #         '/and/should/be/tested/with/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask',
-    #         '/more/weight/recipes-whatever/helloworld/helloworld_1.2.3.bb:do_sometask',
-    #     ]
-
-    #     time_start = time.time()
-
-    #     i = 2000000
-    #     while i >= 0:
-    #         for basepath in input_basepaths:
-    #             bb.siggen.clean_basepath(basepath)
-    #         i -= 1
-
-    #     elapsed = time.time() - time_start
-    #     print('{} ({}s)'.format(self.id(), round(elapsed, 3)))
-
-    #     self.assertTrue(False)