bitbake: bitbake: siggen/runqueue: Switch to using RECIPE_SIGGEN_INFO feature for signature dumping

Now that we have cache support for the taskdep/gendep/lookupcache data,
we can switch to use that cooker feature and skip the secondary reparse to
write the sig files. This does make the initial parse longer but means the
secondary one isn't needed.

At present parsing with the larger cache isn't optimal but we have plans
in place which will make this faster than the current reparse code being
removed here.

(Bitbake rev: 5951b5b56449855bc2a30146af65eb287a35fcef)

(Bitbake rev: 1252e5bce51ae912ecff9dcc354a371786ff2c72)

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

3 files changed, 37 insertions, 33 deletions

diff --git a/bitbake/lib/bb/main.py b/bitbake/lib/bb/main.py
index f1ea7859da..ed3e1ede61 100755
--- a/bitbake/lib/bb/main.py
+++ b/bitbake/lib/bb/main.py
@@ -395,6 +395,11 @@ def setup_bitbake(configParams, extrafeatures=None):
         # In status only mode there are no logs and no UI
         logger.addHandler(handler)
 
+    if configParams.dump_signatures:
+        if extrafeatures is None:
+            extrafeatures = []
+        extrafeatures.append(bb.cooker.CookerFeatures.RECIPE_SIGGEN_INFO)
+
     if configParams.server_only:
         featureset = []
         ui_module = None
diff --git a/bitbake/lib/bb/runqueue.py b/bitbake/lib/bb/runqueue.py
index 991aa94f67..61cb9f4c95 100644
--- a/bitbake/lib/bb/runqueue.py
+++ b/bitbake/lib/bb/runqueue.py
@@ -1608,28 +1608,28 @@ class RunQueue:
         else:
             self.rqexe.finish()
 
-    def rq_dump_sigfn(self, fn, options):
-        mc = bb.runqueue.mc_from_tid(fn)
-        the_data = self.cooker.databuilder.parseRecipe(fn, self.cooker.collections[mc].get_file_appends(fn))
-        siggen = bb.parse.siggen
-        dataCaches = self.rqdata.dataCaches
-        siggen.dump_sigfn(fn, dataCaches, options)
+    def _rq_dump_sigtid(self, tids):
+        for tid in tids:
+            (mc, fn, taskname, taskfn) = split_tid_mcfn(tid)
+            dataCaches = self.rqdata.dataCaches
+            bb.parse.siggen.dump_sigtask(taskfn, taskname, dataCaches[mc].stamp[taskfn], True)
 
     def dump_signatures(self, options):
-        fns = set()
-        bb.note("Reparsing files to collect dependency data")
+        if bb.cooker.CookerFeatures.RECIPE_SIGGEN_INFO not in self.cooker.featureset:
+            bb.fatal("The dump signatures functionality needs the RECIPE_SIGGEN_INFO feature enabled")
 
-        for tid in self.rqdata.runtaskentries:
-            fn = fn_from_tid(tid)
-            fns.add(fn)
+        bb.note("Writing task signature files")
 
         max_process = int(self.cfgData.getVar("BB_NUMBER_PARSE_THREADS") or os.cpu_count() or 1)
+        def chunkify(l, n):
+            return [l[i::n] for i in range(n)]
+        tids = chunkify(list(self.rqdata.runtaskentries), max_process)
         # We cannot use the real multiprocessing.Pool easily due to some local data
         # that can't be pickled. This is a cheap multi-process solution.
         launched = []
-        while fns:
+        while tids:
             if len(launched) < max_process:
-                p = Process(target=self.rq_dump_sigfn, args=(fns.pop(), options))
+                p = Process(target=self._rq_dump_sigtid, args=(tids.pop(), ))
                 p.start()
                 launched.append(p)
             for q in launched:
diff --git a/bitbake/lib/bb/siggen.py b/bitbake/lib/bb/siggen.py
index e57f1ffe69..6b73843c67 100644
--- a/bitbake/lib/bb/siggen.py
+++ b/bitbake/lib/bb/siggen.py
@@ -335,8 +335,8 @@ class SignatureGeneratorBasic(SignatureGenerator):
         self.unihash_cache.copyfile(targetdir)
 
     def dump_sigtask(self, fn, task, stampbase, runtime):
-
         tid = fn + ":" + task
+        mc = bb.runqueue.mc_from_tid(fn)
         referencestamp = stampbase
         if isinstance(runtime, str) and runtime.startswith("customfile"):
             sigfile = stampbase
@@ -353,16 +353,27 @@ class SignatureGeneratorBasic(SignatureGenerator):
         data['task'] = task
         data['basehash_ignore_vars'] = self.basehash_ignore_vars
         data['taskhash_ignore_tasks'] = self.taskhash_ignore_tasks
-        data['taskdeps'] = self.taskdeps[fn][task]
+        if hasattr(self, "datacaches"):
+            data['taskdeps'] = self.datacaches[mc].siggen_taskdeps[fn][task]
+        else:
+            data['taskdeps'] = self.taskdeps[fn][task]
         data['basehash'] = self.basehash[tid]
         data['gendeps'] = {}
         data['varvals'] = {}
-        data['varvals'][task] = self.lookupcache[fn][task]
-        for dep in self.taskdeps[fn][task]:
-            if dep in self.basehash_ignore_vars:
-                continue
-            data['gendeps'][dep] = self.gendeps[fn][dep]
-            data['varvals'][dep] = self.lookupcache[fn][dep]
+        if hasattr(self, "datacaches"):
+            data['varvals'][task] = self.datacaches[mc].siggen_varvals[fn][task]
+            for dep in self.datacaches[mc].siggen_taskdeps[fn][task]:
+                if dep in self.basehash_ignore_vars:
+                   continue
+                data['gendeps'][dep] = self.datacaches[mc].siggen_gendeps[fn][dep]
+                data['varvals'][dep] = self.datacaches[mc].siggen_varvals[fn][dep]
+        else:
+            data['varvals'][task] = self.lookupcache[fn][task]
+            for dep in self.taskdeps[fn][task]:
+                if dep in self.basehash_ignore_vars:
+                    continue
+                data['gendeps'][dep] = self.gendeps[fn][dep]
+                data['varvals'][dep] = self.lookupcache[fn][dep]
 
         if runtime and tid in self.taskhash:
             data['runtaskdeps'] = self.runtaskdeps[tid]
@@ -409,18 +420,6 @@ class SignatureGeneratorBasic(SignatureGenerator):
                 pass
             raise err
 
-    def dump_sigfn(self, fn, dataCaches, options):
-        if fn in self.taskdeps:
-            for task in self.taskdeps[fn]:
-                tid = fn + ":" + task
-                mc = bb.runqueue.mc_from_tid(tid)
-                if tid not in self.taskhash:
-                    continue
-                if dataCaches[mc].basetaskhash[tid] != self.basehash[tid]:
-                    bb.error("Bitbake's cached basehash does not match the one we just generated (%s)!" % tid)
-                    bb.error("The mismatched hashes were %s and %s" % (dataCaches[mc].basetaskhash[tid], self.basehash[tid]))
-                self.dump_sigtask(fn, task, dataCaches[mc].stamp[fn], True)
-
 class SignatureGeneratorBasicHash(SignatureGeneratorBasic):
     name = "basichash"